Bump versions.

Fix for #120 
(ProceedQuestion got an unexpected keyword argument 'log_viewer_unique_name')

MANIFEST.in

@@ -0,0 +1 @@
+include DESCRIPTION.rst

calibre-plugin/__init__.py

@@ -4,18 +4,24 @@ from __future__ import (unicode_literals, division, absolute_import,
                         print_function)
 
 __license__   = 'GPL v3'
-__copyright__ = '2015, Jim Miller'
+__copyright__ = '2016, Jim Miller'
 __docformat__ = 'restructuredtext en'
 
-import sys
+import sys, os
 if sys.version_info >= (2, 7):
     import logging
     logger = logging.getLogger(__name__)
     loghandler=logging.StreamHandler()
-    loghandler.setFormatter(logging.Formatter("FFF:%(levelname)s:%(filename)s(%(lineno)d):%(message)s"))
+    loghandler.setFormatter(logging.Formatter("FFF: %(levelname)s: %(asctime)s: %(filename)s(%(lineno)d): %(message)s"))
     logger.addHandler(loghandler)
-    loghandler.setLevel(logging.DEBUG)
-    logger.setLevel(logging.DEBUG)
+
+    from calibre.constants import DEBUG
+    if os.environ.get('CALIBRE_WORKER', None) is not None or DEBUG:
+        loghandler.setLevel(logging.DEBUG)
+        logger.setLevel(logging.DEBUG)
+    else:
+        loghandler.setLevel(logging.CRITICAL)
+        logger.setLevel(logging.CRITICAL)
 
 # pulls in translation files for _() strings
 try:
@@ -42,7 +48,7 @@ class FanFicFareBase(InterfaceActionBase):
     description         = _('UI plugin to download FanFiction stories from various sites.')
     supported_platforms = ['windows', 'osx', 'linux']
     author              = 'Jim Miller'
-    version             = (2, 2, 7)
+    version             = (2, 3, 4)
     minimum_calibre_version = (1, 48, 0)
 
     #: This field defines the GUI plugin class that contains all the code

calibre-plugin/basicinihighlighter.py

@@ -1,5 +1,5 @@
-#!/usr/bin/env python
-# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+# -*- coding: utf-8 -*-
+
 from __future__ import (unicode_literals, division,
                         print_function)
 

calibre-plugin/common_utils.py

@@ -1,5 +1,5 @@
-#!/usr/bin/env python
-# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+# -*- coding: utf-8 -*-
+
 from __future__ import (unicode_literals, division, absolute_import,
                         print_function)
 

calibre-plugin/config.py

@@ -1,16 +1,16 @@
-#!/usr/bin/env python
-# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+# -*- coding: utf-8 -*-
+
 from __future__ import (unicode_literals, division, absolute_import,
                         print_function)
 
 __license__   = 'GPL v3'
-__copyright__ = '2015, Jim Miller'
+__copyright__ = '2016, Jim Miller'
 __docformat__ = 'restructuredtext en'
 
 import logging
 logger = logging.getLogger(__name__)
 
-import traceback, copy, threading
+import traceback, copy, threading, re
 from collections import OrderedDict
 
 try:
@@ -81,15 +81,15 @@ no_trans = { 'pini':'personal.ini',
 STD_COLS_SKIP = ['size','cover','news','ondevice','path','series_sort','sort']
 
 from calibre_plugins.fanficfare_plugin.prefs \
-    import (prefs, PREFS_NAMESPACE, updatecalcover_order, calcover_save_options,
-            gencalcover_order, SAVE_YES, SAVE_NO)
+    import (prefs, PREFS_NAMESPACE, prefs_save_options, updatecalcover_order,
+            gencalcover_order, do_wordcount_order, SAVE_YES, SAVE_NO)
 
 from calibre_plugins.fanficfare_plugin.dialogs \
     import (UPDATE, UPDATEALWAYS, collision_order, save_collisions, RejectListDialog,
             EditTextDialog, IniTextDialog, RejectUrlEntry)
     
 from calibre_plugins.fanficfare_plugin.fanficfare.adapters \
-    import getConfigSections
+    import getSiteSections
 
 from calibre_plugins.fanficfare_plugin.common_utils \
     import ( KeyboardConfigDialog, PrefsViewerDialog )
@@ -243,6 +243,7 @@ class ConfigWidget(QWidget):
         prefs['fileform'] = unicode(self.basic_tab.fileform.currentText())
         prefs['collision'] = save_collisions[unicode(self.basic_tab.collision.currentText())]
         prefs['updatemeta'] = self.basic_tab.updatemeta.isChecked()
+        prefs['bgmeta'] = self.basic_tab.bgmeta.isChecked()
         prefs['updateepubcover'] = self.basic_tab.updateepubcover.isChecked()
         prefs['keeptags'] = self.basic_tab.keeptags.isChecked()
         prefs['suppressauthorsort'] = self.basic_tab.suppressauthorsort.isChecked()
@@ -259,6 +260,8 @@ class ConfigWidget(QWidget):
         prefs['checkforseriesurlid'] = self.basic_tab.checkforseriesurlid.isChecked()
         prefs['checkforurlchange'] = self.basic_tab.checkforurlchange.isChecked()
         prefs['injectseries'] = self.basic_tab.injectseries.isChecked()
+        prefs['matchtitleauth'] = self.basic_tab.matchtitleauth.isChecked()
+        prefs['do_wordcount'] = prefs_save_options[unicode(self.basic_tab.do_wordcount.currentText())]
         prefs['smarten_punctuation'] = self.basic_tab.smarten_punctuation.isChecked()
         prefs['reject_always'] = self.basic_tab.reject_always.isChecked()
 
@@ -271,6 +274,7 @@ class ConfigWidget(QWidget):
             prefs['addtolists'] = self.readinglist_tab.addtolists.isChecked()
             prefs['addtoreadlists'] = self.readinglist_tab.addtoreadlists.isChecked()
             prefs['addtolistsonread'] = self.readinglist_tab.addtolistsonread.isChecked()
+            prefs['autounnew'] = self.readinglist_tab.autounnew.isChecked()
 
         # personal.ini
         ini = self.personalini_tab.personalini
@@ -280,11 +284,13 @@ class ConfigWidget(QWidget):
             # if they've removed everything, reset to default.
             prefs['personal.ini'] = get_resources('plugin-example.ini')
 
+        prefs['cal_cols_pass_in'] = self.personalini_tab.cal_cols_pass_in.isChecked()
+            
         # Covers tab
-        prefs['updatecalcover'] = calcover_save_options[unicode(self.calibrecover_tab.updatecalcover.currentText())]
+        prefs['updatecalcover'] = prefs_save_options[unicode(self.calibrecover_tab.updatecalcover.currentText())]
         # for backward compatibility:
         prefs['updatecover'] = prefs['updatecalcover'] == SAVE_YES
-        prefs['gencalcover'] = calcover_save_options[unicode(self.calibrecover_tab.gencalcover.currentText())]
+        prefs['gencalcover'] = prefs_save_options[unicode(self.calibrecover_tab.gencalcover.currentText())]
         prefs['calibre_gen_cover'] = self.calibrecover_tab.calibre_gen_cover.isChecked()
         prefs['plugin_gen_cover'] = self.calibrecover_tab.plugin_gen_cover.isChecked()
         prefs['gcnewonly'] = self.calibrecover_tab.gcnewonly.isChecked()
@@ -321,9 +327,12 @@ class ConfigWidget(QWidget):
             colsnewonly[col] = checkbox.isChecked()
         prefs['std_cols_newonly'] = colsnewonly
 
+        prefs['set_author_url'] =self.std_columns_tab.set_author_url.isChecked()
+
         # Custom Columns tab
         # error column
         prefs['errorcol'] = unicode(convert_qvariant(self.cust_columns_tab.errorcol.itemData(self.cust_columns_tab.errorcol.currentIndex())))
+        prefs['save_all_errors'] = self.cust_columns_tab.save_all_errors.isChecked()
 
         # metadata column
         prefs['savemetacol'] = unicode(convert_qvariant(self.cust_columns_tab.savemetacol.itemData(self.cust_columns_tab.savemetacol.currentIndex())))
@@ -344,13 +353,14 @@ class ConfigWidget(QWidget):
         
         prefs['allow_custcol_from_ini'] = self.cust_columns_tab.allow_custcol_from_ini.isChecked()
 
-        prefs['imapserver'] = unicode(self.imap_tab.imapserver.text())
-        prefs['imapuser'] = unicode(self.imap_tab.imapuser.text())
-        prefs['imappass'] = unicode(self.imap_tab.imappass.text())
-        prefs['imapfolder'] = unicode(self.imap_tab.imapfolder.text())
+        prefs['imapserver'] = unicode(self.imap_tab.imapserver.text()).strip()
+        prefs['imapuser'] = unicode(self.imap_tab.imapuser.text()).strip()
+        prefs['imappass'] = unicode(self.imap_tab.imappass.text()).strip()
+        prefs['imapfolder'] = unicode(self.imap_tab.imapfolder.text()).strip()
         prefs['imapmarkread'] = self.imap_tab.imapmarkread.isChecked()
         prefs['imapsessionpass'] = self.imap_tab.imapsessionpass.isChecked()
         prefs['auto_reject_from_email'] = self.imap_tab.auto_reject_from_email.isChecked()
+        prefs['download_from_email_immediately'] = self.imap_tab.download_from_email_immediately.isChecked()
         
         prefs.save_to_db()
 
@@ -423,6 +433,12 @@ class BasicTab(QWidget):
         self.updateepubcover.setToolTip(_("On each download, FanFicFare offers an option to update the book cover image <i>inside</i> the EPUB from the web site when the EPUB is updated.<br />This sets whether that will default to on or off."))
         self.updateepubcover.setChecked(prefs['updateepubcover'])
         horz.addWidget(self.updateepubcover)
+        
+        self.bgmeta = QCheckBox(_('Default Background Metadata?'),self)
+        self.bgmeta.setToolTip(_("On each download, FanFicFare offers an option to Collect Metadata from sites in a Background process.<br />This returns control to you quicker while updating, but you won't be asked for username/passwords or if you are an adult--stories that need those will just fail.<br />Only available for Update/Overwrite of existing books in case URL given isn't canonical or matches to existing book by Title/Author."))
+        self.bgmeta.setChecked(prefs['bgmeta'])
+        horz.addWidget(self.bgmeta)
+
         self.l.addLayout(horz)
 
         cali_gb = groupbox = QGroupBox(_("Updating Calibre Options"))
@@ -450,7 +466,7 @@ class BasicTab(QWidget):
         self.l.addWidget(self.suppresstitlesort)
 
         self.checkforseriesurlid = QCheckBox(_("Check for existing Series Anthology books?"),self)
-        self.checkforseriesurlid.setToolTip(_("Check for existings Series Anthology books using each new story's series URL before downloading.\nOffer to skip downloading if a Series Anthology is found."))
+        self.checkforseriesurlid.setToolTip(_("Check for existings Series Anthology books using each new story's series URL before downloading.\nOffer to skip downloading if a Series Anthology is found.\nDoesn't work when Collect Metadata in Background is selected."))
         self.checkforseriesurlid.setChecked(prefs['checkforseriesurlid'])
         self.l.addWidget(self.checkforseriesurlid)
 
@@ -464,6 +480,10 @@ class BasicTab(QWidget):
         self.lookforurlinhtml.setChecked(prefs['lookforurlinhtml'])
         self.l.addWidget(self.lookforurlinhtml)
 
+        proc_gb = groupbox = QGroupBox(_("Post Processing Options"))
+        self.l = QVBoxLayout()
+        groupbox.setLayout(self.l)
+
         self.mark = QCheckBox(_("Mark added/updated books when finished?"),self)
         self.mark.setToolTip(_("Mark added/updated books when finished.  Use with option below.\nYou can also manually search for 'marked:fff_success'.\n'marked:fff_failed' is also available, or search 'marked:fff' for both."))
         self.mark.setChecked(prefs['mark'])
@@ -479,6 +499,24 @@ class BasicTab(QWidget):
         self.smarten_punctuation.setChecked(prefs['smarten_punctuation'])
         self.l.addWidget(self.smarten_punctuation)
 
+        
+        tooltip = _("Calculate Word Counts using Calibre internal methods.\n"
+                    "Many sites include Word Count, but many do not.\n"
+                    "This will count the words in each book and include it as if it came from the site.")
+        horz = QHBoxLayout()
+        label = QLabel(_('Calculate Word Count:'))
+        label.setToolTip(tooltip)
+        horz.addWidget(label)
+        self.do_wordcount = QComboBox(self)
+        for i in do_wordcount_order:
+            self.do_wordcount.addItem(i)
+        self.do_wordcount.setCurrentIndex(self.do_wordcount.findText(prefs_save_options[prefs['do_wordcount']]))
+        self.do_wordcount.setToolTip(tooltip)
+        label.setBuddy(self.do_wordcount)
+        horz.addWidget(self.do_wordcount)
+        self.l.addLayout(horz)
+
+        
         self.autoconvert = QCheckBox(_("Automatically Convert new/update books?"),self)
         self.autoconvert.setToolTip(_("Automatically call calibre's Convert for new/update books.\nConverts to the current output format as chosen in calibre's\nPreferences->Behavior settings."))
         self.autoconvert.setChecked(prefs['autoconvert'])
@@ -517,6 +555,11 @@ class BasicTab(QWidget):
         self.injectseries.setChecked(prefs['injectseries'])
         self.l.addWidget(self.injectseries)
 
+        self.matchtitleauth = QCheckBox(_("Search by Title/Author(s) for If Story Already Exists?"),self)
+        self.matchtitleauth.setToolTip(_("When checking <i>If Story Already Exists</i> FanFicFare will first match by URL Identifier.  But if not found, it can also search existing books by Title and Author(s)."))
+        self.matchtitleauth.setChecked(prefs['matchtitleauth'])
+        self.l.addWidget(self.matchtitleauth)
+
         rej_gb = groupbox = QGroupBox(_("Reject List"))
         self.l = QVBoxLayout()
         groupbox.setLayout(self.l)
@@ -545,14 +588,17 @@ class BasicTab(QWidget):
 
         horz = QHBoxLayout()
 
-        horz.addWidget(cali_gb)
+        vertleft = QVBoxLayout()
+        vertleft.addWidget(cali_gb)
+        vertleft.addWidget(proc_gb)
 
-        vert = QVBoxLayout()
-        vert.addWidget(gui_gb)
-        vert.addWidget(misc_gb)
-        vert.addWidget(rej_gb)
+        vertright = QVBoxLayout()
+        vertright.addWidget(gui_gb)
+        vertright.addWidget(misc_gb)
+        vertright.addWidget(rej_gb)
         
-        horz.addLayout(vert)
+        horz.addLayout(vertleft)
+        horz.addLayout(vertright)
         
         topl.addLayout(horz)
         topl.insertStretch(-1)
@@ -620,48 +666,94 @@ class PersonalIniTab(QWidget):
         label = QLabel(_('These settings provide more detailed control over what metadata will be displayed inside the ebook as well as let you set %(isa)s and %(u)s/%(p)s for different sites.')%no_trans)
         label.setWordWrap(True)
         self.l.addWidget(label)
-#        self.l.addSpacing(5)
-
-        label = QLabel(_("FanFicFare now includes find, color coding, and error checking for personal.ini editing.  Red generally indicates errors."))
-        label.setWordWrap(True)
-        self.l.addWidget(label)
-        
-        # self.label = QLabel('personal.ini:')
-        # self.l.addWidget(self.label)
-
-        # self.ini = QTextEdit(self)
-        # try:
-        #     self.ini.setFont(QFont("Courier",
-        #                            self.plugin_action.gui.font().pointSize()+1))
-        # except Exception as e:
-        #     logger.error("Couldn't get font: %s"%e)
-        # self.ini.setLineWrapMode(QTextEdit.NoWrap)
-        # self.ini.setText(prefs['personal.ini'])
-        # self.l.addWidget(self.ini)
+        self.l.addSpacing(5)
 
         self.personalini = prefs['personal.ini']
 
+        groupbox = QGroupBox(_("personal.ini"))
+        vert = QVBoxLayout()
+        groupbox.setLayout(vert)
+        self.l.addWidget(groupbox)
+
+        horz = QHBoxLayout()
+        vert.addLayout(horz)        
         self.ini_button = QPushButton(_('Edit personal.ini'), self)
         #self.ini_button.setToolTip(_("Edit personal.ini file."))
         self.ini_button.clicked.connect(self.add_ini_button)
-        self.l.addWidget(self.ini_button)
+        horz.addWidget(self.ini_button)
         
+        label = QLabel(_("FanFicFare now includes find, color coding, and error checking for personal.ini editing.  Red generally indicates errors."))
+        label.setWordWrap(True)
+        horz.addWidget(label)
+        
+        vert.addSpacing(5)
+
+        horz = QHBoxLayout()
+        vert.addLayout(horz)
+        self.ini_button = QPushButton(_('View "Safe" personal.ini'), self)
+        #self.ini_button.setToolTip(_("Edit personal.ini file."))
+        self.ini_button.clicked.connect(self.safe_ini_button)
+        horz.addWidget(self.ini_button)
+        
+        label = QLabel(_("View your personal.ini with usernames and passwords removed.  For safely sharing your personal.ini settings with others."))
+        label.setWordWrap(True)
+        horz.addWidget(label)
+        
+        self.l.addSpacing(5)
+        
+        groupbox = QGroupBox(_("defaults.ini"))
+        horz = QHBoxLayout()
+        groupbox.setLayout(horz)
+        self.l.addWidget(groupbox)
+        
+        view_label = _("View all of the plugin's configurable settings\nand their default settings.")
+        self.defaults = QPushButton(_('View Defaults')+' (plugin-defaults.ini)', self)
+        self.defaults.setToolTip(view_label)
+        self.defaults.clicked.connect(self.show_defaults)
+        horz.addWidget(self.defaults)
+
+        label = QLabel(view_label)
+        label.setWordWrap(True)
+        horz.addWidget(label)
+        
+        self.l.addSpacing(5)
+
+        groupbox = QGroupBox(_("Calibre Columns"))
+        vert = QVBoxLayout()
+        groupbox.setLayout(vert)
+        self.l.addWidget(groupbox)
+
+        horz = QHBoxLayout()
+        vert.addLayout(horz)
+        pass_label = _("If checked, when updating/overwriting an existing book, FanFicFare will have the Calibre Columns available to use in replace_metadata, title_page, etc.<br>Click the button below to see the Calibre Column namess.")%no_trans
+        self.cal_cols_pass_in = QCheckBox(_('Pass Calibre Columns into FanFicFare on Update/Overwrite')%no_trans,self)
+        self.cal_cols_pass_in.setToolTip(pass_label)
+        self.cal_cols_pass_in.setChecked(prefs['cal_cols_pass_in'])
+        horz.addWidget(self.cal_cols_pass_in)
+        
+        label = QLabel(pass_label)
+        label.setWordWrap(True)
+        horz.addWidget(label)
+
+        vert.addSpacing(5)
+        
+        horz = QHBoxLayout()
+        vert.addLayout(horz)
+        col_label = _("FanFicFare can pass the Calibre Columns into the download/update process.<br>This will show you the columns available by name.")
+        self.showcalcols = QPushButton(_('Show Calibre Column Names'), self)
+        self.showcalcols.setToolTip(col_label)
+        self.showcalcols.clicked.connect(self.show_showcalcols)
+        horz.addWidget(self.showcalcols)
+
+        label = QLabel(col_label)
+        label.setWordWrap(True)
+        horz.addWidget(label)
+
         label = QLabel(_("Changes will only be saved if you click 'OK' to leave Customize FanFicFare."))
         label.setWordWrap(True)
         self.l.addWidget(label)
-        
-        self.defaults = QPushButton(_('View Defaults')+' (plugin-defaults.ini)', self)
-        self.defaults.setToolTip(_("View all of the plugin's configurable settings\nand their default settings."))
-        self.defaults.clicked.connect(self.show_defaults)
-        self.l.addWidget(self.defaults)
-
-        self.showcalcols = QPushButton(_('Show Calibre Column Names'), self)
-        self.showcalcols.setToolTip(_("FanFicFare passes the Calibre columns into the download/update process.  This will show you the columns available by name."))
-        self.showcalcols.clicked.connect(self.show_showcalcols)
-        self.l.addWidget(self.showcalcols)
 
         self.l.insertStretch(-1)
-        # let edit box fill the space.
         
     def show_defaults(self):
         IniTextDialog(self,
@@ -673,6 +765,18 @@ class PersonalIniTab(QWidget):
                        read_only=True,
                        save_size_name='fff:defaults.ini').exec_()
         
+    def safe_ini_button(self):
+        personalini = re.sub(r'((username|password) *[=:]).*$',r'\1XXXXXXXX',self.personalini,flags=re.MULTILINE)
+        
+        d = EditTextDialog(self,
+                           personalini,
+                           icon=self.windowIcon(),
+                           title=_("View 'Safe' personal.ini"),
+                           label=_("View your personal.ini with usernames and passwords removed.  For safely sharing your personal.ini settings with others."),
+                           save_size_name='fff:safe personal.ini',
+                           read_only=True)
+        d.exec_()
+        
     def add_ini_button(self):
         d = IniTextDialog(self,
                            self.personalini,
@@ -766,6 +870,11 @@ class ReadingListTab(QWidget):
         self.addtolistsonread.setChecked(prefs['addtolistsonread'])
         self.l.addWidget(self.addtolistsonread)
             
+        self.autounnew = QCheckBox(_('Automatically run Remove "New" Chapter Marks when marking books "Read".'),self)
+        self.autounnew.setToolTip(_('Menu option to remove from "To Read" lists will also remove "(new)" chapter marks created by personal.ini <i>mark_new_chapters</i> setting.'))
+        self.autounnew.setChecked(prefs['autounnew'])
+        self.l.addWidget(self.autounnew)
+            
         self.l.insertStretch(-1)
         
 class CalibreCoverTab(QWidget):
@@ -811,11 +920,11 @@ class CalibreCoverTab(QWidget):
             self.updatecalcover.addItem(i)
         # back compat.  If has own value, use.
         if prefs['updatecalcover']:
-            self.updatecalcover.setCurrentIndex(self.updatecalcover.findText(calcover_save_options[prefs['updatecalcover']]))
+            self.updatecalcover.setCurrentIndex(self.updatecalcover.findText(prefs_save_options[prefs['updatecalcover']]))
         elif prefs['updatecover']: # doesn't have own val, set YES if old value set.
-            self.updatecalcover.setCurrentIndex(self.updatecalcover.findText(calcover_save_options[SAVE_YES]))
+            self.updatecalcover.setCurrentIndex(self.updatecalcover.findText(prefs_save_options[SAVE_YES]))
         else: # doesn't have own value, old value not set, NO.
-            self.updatecalcover.setCurrentIndex(self.updatecalcover.findText(calcover_save_options[SAVE_NO]))
+            self.updatecalcover.setCurrentIndex(self.updatecalcover.findText(prefs_save_options[SAVE_NO]))
         self.updatecalcover.setToolTip(tooltip)
         label.setBuddy(self.updatecalcover)
         horz.addWidget(self.updatecalcover)
@@ -833,11 +942,11 @@ class CalibreCoverTab(QWidget):
             self.gencalcover.addItem(i)
         # back compat.  If has own value, use.
         # if prefs['gencalcover']:
-        self.gencalcover.setCurrentIndex(self.gencalcover.findText(calcover_save_options[prefs['gencalcover']]))
+        self.gencalcover.setCurrentIndex(self.gencalcover.findText(prefs_save_options[prefs['gencalcover']]))
         # elif prefs['gencover']: # doesn't have own val, set YES if old value set.
-        #     self.gencalcover.setCurrentIndex(self.gencalcover.findText(calcover_save_options[SAVE_YES]))
+        #     self.gencalcover.setCurrentIndex(self.gencalcover.findText(prefs_save_options[SAVE_YES]))
         # else: # doesn't have own value, old value not set, NO.
-        #     self.gencalcover.setCurrentIndex(self.gencalcover.findText(calcover_save_options[SAVE_NO]))
+        #     self.gencalcover.setCurrentIndex(self.gencalcover.findText(prefs_save_options[SAVE_NO]))
             
         self.gencalcover.setToolTip(tooltip)
         label.setBuddy(self.gencalcover)
@@ -913,7 +1022,7 @@ class CalibreCoverTab(QWidget):
         
         self.gc_dropdowns = {}
 
-        sitelist = getConfigSections()
+        sitelist = getSiteSections()
         sitelist.sort()
         sitelist.insert(0,_("Default"))
         for site in sitelist:
@@ -961,7 +1070,7 @@ class CalibreCoverTab(QWidget):
 
         ## First, cover gen on/off 
         for e in self.gencov_elements:
-            e.setEnabled(calcover_save_options[unicode(self.gencalcover.currentText())] != SAVE_NO)
+            e.setEnabled(prefs_save_options[unicode(self.gencalcover.currentText())] != SAVE_NO)
 
         # next, disable plugin settings when using calibre gen cov.
         if not self.plugin_gen_cover.isChecked():
@@ -1223,7 +1332,6 @@ class CustomColumnsTab(QWidget):
         self.allow_custcol_from_ini.setChecked(prefs['allow_custcol_from_ini'])
         self.l.addWidget(self.allow_custcol_from_ini)
         
-        self.l.addSpacing(5)
         label = QLabel(_("Special column:"))
         label.setWordWrap(True)
         self.l.addWidget(label)
@@ -1233,6 +1341,7 @@ class CustomColumnsTab(QWidget):
         tooltip=_("When an update or overwrite of an existing story fails, record the reason in this column.\n(Text and Long Text columns only.)")
         label.setToolTip(tooltip)
         horz.addWidget(label)
+
         self.errorcol = QComboBox(self)
         self.errorcol.setToolTip(tooltip)
         self.errorcol.addItem('','none')
@@ -1241,6 +1350,15 @@ class CustomColumnsTab(QWidget):
                 self.errorcol.addItem(column['name'],key)
         self.errorcol.setCurrentIndex(self.errorcol.findData(prefs['errorcol']))
         horz.addWidget(self.errorcol)
+        
+        self.save_all_errors = QCheckBox(_('Save All Errors'),self)
+        self.save_all_errors.setToolTip(_('If unchecked, these errors will not be saved:%s')%(
+                '\n'+
+                '\n'.join((_("Not Overwriting, web site is not newer."),
+                           _("Already contains %d chapters.").replace('%d','X')))))
+        self.save_all_errors.setChecked(prefs['save_all_errors'])
+        horz.addWidget(self.save_all_errors)
+        
         self.l.addLayout(horz)
         
         horz = QHBoxLayout()
@@ -1256,6 +1374,10 @@ class CustomColumnsTab(QWidget):
                 self.savemetacol.addItem(column['name'],key)
         self.savemetacol.setCurrentIndex(self.savemetacol.findData(prefs['savemetacol']))
         horz.addWidget(self.savemetacol)
+
+        label = QLabel('')
+        horz.addWidget(label) # empty spacer for alignment with error column line.
+        
         self.l.addLayout(horz)
 
         #print("prefs['custom_cols'] %s"%prefs['custom_cols'])
@@ -1305,6 +1427,17 @@ class StandardColumnsTab(QWidget):
             horz.addWidget(newonlycheck)
             
             self.l.addLayout(horz)
+            
+        self.l.addSpacing(5)
+        label = QLabel(_("Other Standard Column Options"))
+        label.setWordWrap(True)
+        self.l.addWidget(label)
+        self.l.addSpacing(5)
+
+        self.set_author_url = QCheckBox(_('Set Calibre Author URL'),self)
+        self.set_author_url.setToolTip(_("Set Calibre Author URL to Author's URL on story site."))
+        self.set_author_url.setChecked(prefs['set_author_url'])
+        self.l.addWidget(self.set_author_url)
         
         self.l.insertStretch(-1)
 
@@ -1383,6 +1516,12 @@ class ImapTab(QWidget):
         self.l.addWidget(self.auto_reject_from_email,row,0,1,-1)
         row+=1
         
+        self.download_from_email_immediately = QCheckBox(_('Download from Email Immediately'),self)
+        self.download_from_email_immediately.setToolTip(_('If checked, FanFicFare will start downloading story URLs from emails immediately.<br>Otherwise the usual Download from URLs dialog will appear.'))
+        self.download_from_email_immediately.setChecked(prefs['download_from_email_immediately'])
+        self.l.addWidget(self.download_from_email_immediately,row,0,1,-1)
+        row+=1
+        
         label = QLabel(_("<b>It's safest if you create a separate email account that you use only "
                          "for your story update notices.  FanFicFare and calibre cannot guarantee that "
                          "malicious code cannot get your email password once you've entered it. "

calibre-plugin/dialogs.py

@@ -1,10 +1,10 @@
-#!/usr/bin/env python
-# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+# -*- coding: utf-8 -*-
+
 from __future__ import (unicode_literals, division,
                         print_function)
 
 __license__   = 'GPL v3'
-__copyright__ = '2015, Jim Miller'
+__copyright__ = '2016, Jim Miller'
 __docformat__ = 'restructuredtext en'
 
 import traceback, re
@@ -21,19 +21,19 @@ from datetime import datetime
 try:
     from PyQt5 import QtWidgets as QtGui
     from PyQt5 import QtCore
-    from PyQt5.Qt import (QDialog, QTableWidget, QVBoxLayout, QHBoxLayout, QGridLayout,
-                          QPushButton, QFont, QLabel, QCheckBox, QIcon, QLineEdit,
-                          QComboBox, QProgressDialog, QTimer, QDialogButtonBox,
-                          QPixmap, Qt, QAbstractItemView, QTextEdit, pyqtSignal,
-                          QGroupBox, QFrame, QTextBrowser, QSize, QAction)
+    from PyQt5.Qt import (QDialog, QWidget, QTableWidget, QVBoxLayout, QHBoxLayout,
+                          QGridLayout, QPushButton, QFont, QLabel, QCheckBox, QIcon,
+                          QLineEdit, QComboBox, QProgressDialog, QTimer, QDialogButtonBox,
+                          QScrollArea, QPixmap, Qt, QAbstractItemView, QTextEdit,
+                          pyqtSignal, QGroupBox, QFrame, QTextBrowser, QSize, QAction)
 except ImportError as e:
     from PyQt4 import QtGui
     from PyQt4 import QtCore
-    from PyQt4.Qt import (QDialog, QTableWidget, QVBoxLayout, QHBoxLayout, QGridLayout,
-                          QPushButton, QFont, QLabel, QCheckBox, QIcon, QLineEdit,
-                          QComboBox, QProgressDialog, QTimer, QDialogButtonBox,
-                          QPixmap, Qt, QAbstractItemView, QTextEdit, pyqtSignal,
-                          QGroupBox, QFrame, QTextBrowser, QSize, QAction)
+    from PyQt4.Qt import (QDialog, QWidget, QTableWidget, QVBoxLayout, QHBoxLayout,
+                          QGridLayout, QPushButton, QFont, QLabel, QCheckBox, QIcon,
+                          QLineEdit, QComboBox, QProgressDialog, QTimer, QDialogButtonBox,
+                          QScrollArea, QPixmap, Qt, QAbstractItemView, QTextEdit,
+                          pyqtSignal, QGroupBox, QFrame, QTextBrowser, QSize, QAction)
 
 try:
     from calibre.gui2 import QVariant
@@ -73,61 +73,37 @@ from calibre_plugins.fanficfare_plugin.fanficfare.configurable \
 
 from inihighlighter import IniHighlighter
 
-SKIP=_('Skip')
-ADDNEW=_('Add New Book')
-UPDATE=_('Update EPUB if New Chapters')
-UPDATEALWAYS=_('Update EPUB Always')
-OVERWRITE=_('Overwrite if Newer')
-OVERWRITEALWAYS=_('Overwrite Always')
-CALIBREONLY=_('Update Calibre Metadata from Web Site')
-CALIBREONLYSAVECOL=_('Update Calibre Metadata from Saved Metadata Column')
-collision_order=[SKIP,
-                 ADDNEW,
-                 UPDATE,
-                 UPDATEALWAYS,
-                 OVERWRITE,
-                 OVERWRITEALWAYS,
-                 CALIBREONLY,
-                 CALIBREONLYSAVECOL,]
-
-# best idea I've had for how to deal with config/pref saving the
-# collision name in english.
-SAVE_SKIP='Skip'
-SAVE_ADDNEW='Add New Book'
-SAVE_UPDATE='Update EPUB if New Chapters'
-SAVE_UPDATEALWAYS='Update EPUB Always'
-SAVE_OVERWRITE='Overwrite if Newer'
-SAVE_OVERWRITEALWAYS='Overwrite Always'
-SAVE_CALIBREONLY='Update Calibre Metadata Only'
-SAVE_CALIBREONLYSAVECOL='Update Calibre Metadata Only(Saved Column)'
-save_collisions={
-    SKIP:SAVE_SKIP,
-    ADDNEW:SAVE_ADDNEW,
-    UPDATE:SAVE_UPDATE,
-    UPDATEALWAYS:SAVE_UPDATEALWAYS,
-    OVERWRITE:SAVE_OVERWRITE,
-    OVERWRITEALWAYS:SAVE_OVERWRITEALWAYS,
-    CALIBREONLY:SAVE_CALIBREONLY,
-    SAVE_SKIP:SKIP,
-    SAVE_ADDNEW:ADDNEW,
-    SAVE_UPDATE:UPDATE,
-    SAVE_UPDATEALWAYS:UPDATEALWAYS,
-    SAVE_OVERWRITE:OVERWRITE,
-    SAVE_OVERWRITEALWAYS:OVERWRITEALWAYS,
-    SAVE_CALIBREONLY:CALIBREONLY,
-    SAVE_CALIBREONLYSAVECOL:CALIBREONLYSAVECOL,
-    }
-    
-anthology_collision_order=[UPDATE,
-                           UPDATEALWAYS,
-                           OVERWRITEALWAYS]
+## moved to prefs.py so they can be included in jobs.py.
+from calibre_plugins.fanficfare_plugin.prefs import \
+    ( SAVE_YES,
+      SAVE_YES_UNLESS_SITE,
+      SKIP,
+      ADDNEW,
+      UPDATE,
+      UPDATEALWAYS,
+      OVERWRITE,
+      OVERWRITEALWAYS,
+      CALIBREONLY,
+      CALIBREONLYSAVECOL,
+      collision_order,
+      SAVE_SKIP,
+      SAVE_ADDNEW,
+      SAVE_UPDATE,
+      SAVE_UPDATEALWAYS,
+      SAVE_OVERWRITE,
+      SAVE_OVERWRITEALWAYS,
+      SAVE_CALIBREONLY,
+      SAVE_CALIBREONLYSAVECOL,
+      save_collisions,
+      anthology_collision_order,
+      )
 
 gpstyle='QGroupBox {border:0; padding-top:10px; padding-bottom:0px; margin-bottom:0px;}' #  background-color:red;
 
 class RejectUrlEntry:
 
     matchpat=re.compile(r"^(?P<url>[^,]+?)(,(?P<fullnote>(((?P<title>.+?) by (?P<auth>.+?)( - (?P<note>.+))?)|.*)))?$")
-    
+
     def __init__(self,url_or_line,note=None,title=None,auth=None,
                  addreasontext=None,fromline=False,book_id=None):
 
@@ -151,7 +127,7 @@ class RejectUrlEntry:
                 self.note=note
                 self.title=title
                 self.auth=auth
-        
+
         if not self.note:
             if addreasontext:
                 self.note = addreasontext
@@ -160,14 +136,14 @@ class RejectUrlEntry:
         else:
             if addreasontext:
                 self.note = self.note + ' - ' + addreasontext
-                
+
         self.url = getNormalStoryURL(self.url)
         self.valid = self.url != None
-                
+
     def to_line(self):
         # always 'url,'
         return self.url+","+self.fullnote()
-        
+
     def fullnote(self):
         retval = ""
         if self.title and self.auth:
@@ -175,16 +151,17 @@ class RejectUrlEntry:
             retval = retval + "%s by %s"%(self.title,self.auth)
             if self.note:
                 retval = retval + " - "
-                
+
         if self.note:
             retval = retval + self.note
-            
+
         return retval
 
 class NotGoingToDownload(Exception):
-    def __init__(self,error,icon='dialog_error.png'):
+    def __init__(self,error,icon='dialog_error.png',showerror=True):
         self.error=error
         self.icon=icon
+        self.showerror=showerror
 
     def __str__(self):
         return self.error
@@ -222,7 +199,7 @@ class DroppableQTextEdit(QTextEdit):
             self.append("\n".join(urllist))
             return None
         return QTextEdit.dropEvent(self,event)
-        
+
     def canInsertFromMimeData(self, source):
         if source.hasUrls():
             return True
@@ -234,7 +211,7 @@ class DroppableQTextEdit(QTextEdit):
             self.append(source.text())
         else:
             return QTextEdit.insertFromMimeData(self, source)
-                            
+
 class AddNewDialog(SizePersistedDialog):
 
     go_signal = pyqtSignal(object, object, object, object)
@@ -242,7 +219,7 @@ class AddNewDialog(SizePersistedDialog):
     def __init__(self, gui, prefs, icon):
         SizePersistedDialog.__init__(self, gui, 'fff:add new dialog')
         self.prefs = prefs
-        
+
         self.setMinimumWidth(300)
         self.l = QVBoxLayout()
         self.setLayout(self.l)
@@ -258,7 +235,8 @@ class AddNewDialog(SizePersistedDialog):
         self.l.addWidget(self.url)
 
         self.merge = self.newmerge = False
-        
+        self.extraoptions = {}
+
         # elements to hide when doing merge.
         self.mergehide = []
         # elements to show again when doing *update* merge
@@ -281,11 +259,11 @@ class AddNewDialog(SizePersistedDialog):
 
         self.gbf.setVisible(False)
         self.groupbox.toggled.connect(self.gbf.setVisible)
-        
+
         horz = QHBoxLayout()
         label = QLabel(_('Output &Format:'))
         self.mergehide.append(label)
-        
+
         self.fileform = QComboBox(self)
         self.fileform.addItem('epub')
         self.fileform.addItem('mobi')
@@ -293,7 +271,7 @@ class AddNewDialog(SizePersistedDialog):
         self.fileform.addItem('txt')
         self.fileform.setToolTip(_('Choose output format to create.  May set default from plugin configuration.'))
         self.fileform.activated.connect(self.set_collisions)
-        
+
         horz.addWidget(label)
         label.setBuddy(self.fileform)
         horz.addWidget(self.fileform)
@@ -331,15 +309,27 @@ class AddNewDialog(SizePersistedDialog):
         self.updateepubcover.setChecked(self.prefs['updateepubcover'])
         horz.addWidget(self.updateepubcover)
         self.mergehide.append(self.updateepubcover)
-        
+
         self.gbl.addLayout(horz)
 
+        ## bgmeta not used with Add New because of stories that change
+        ## story URL and for title/author collision matching.
+        # horz = QHBoxLayout()
+        # self.bgmeta = QCheckBox(_('Background Metadata?'),self)
+        # self.bgmeta.setToolTip(_("Collect Metadata from sites in a Background process.<br />This returns control to you quicker while updating, but you won't be asked for username/passwords or if you are an adult--stories that need those will just fail."))
+        # self.bgmeta.setChecked(self.prefs['bgmeta'])
+        # horz.addWidget(self.bgmeta)
+        # self.mergehide.append(self.bgmeta)
+        # self.mergeupdateshow.append(self.bgmeta)
+
+        # self.gbl.addLayout(horz)
+
         self.button_box = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel)
         self.button_box.accepted.connect(self.ok_clicked)
         self.button_box.rejected.connect(self.reject)
         self.l.addWidget(self.button_box)
 
-    # invoke the 
+    # invoke the
     def ok_clicked(self):
         self.dialog_closing(None) # save persistent size.
         self.hide()
@@ -375,7 +365,7 @@ class AddNewDialog(SizePersistedDialog):
         self.extrapayload = extrapayload
 
         self.groupbox.setVisible(not(self.merge and self.newmerge))
-        
+
         if self.merge:
             self.toplabel.setText(_('Story URLs for anthology, one per line:'))
             self.url.setToolTip(_('URLs for stories to include in the anthology, one per line.\nWill take URLs from clipboard, but only valid URLs.'))
@@ -397,7 +387,7 @@ class AddNewDialog(SizePersistedDialog):
         # Need to re-able after hiding/showing
         self.setAcceptDrops(True)
         self.url.setFocus()
-            
+
         if self.prefs['adddialogstaysontop']:
             QDialog.setWindowFlags ( self, Qt.Dialog | Qt.WindowStaysOnTopHint )
         else:
@@ -414,18 +404,19 @@ class AddNewDialog(SizePersistedDialog):
         i = self.collision.findText(save_collisions[self.prefs['collision']])
         if i > -1:
             self.collision.setCurrentIndex(i)
-            
+
         self.updatemeta.setChecked(self.prefs['updatemeta'])
-            
+        # self.bgmeta.setChecked(self.prefs['bgmeta'])
+
         if not self.merge:
             self.updateepubcover.setChecked(self.prefs['updateepubcover'])
-                
+
         self.url.setText(url_list_text)
         if url_list_text:
             self.button_box.button(QDialogButtonBox.Ok).setFocus()
         # restore saved size.
         self.resize_dialog()
-        
+
         if show: # so anthology update can be modal still.
             self.show()
         #self.resize(self.sizeHint())
@@ -446,27 +437,29 @@ class AddNewDialog(SizePersistedDialog):
 
         for o in order:
             self.collision.addItem(o)
-            
+
         i = self.collision.findText(prev)
         if i > -1:
             self.collision.setCurrentIndex(i)
-        
+
     def get_fff_options(self):
         retval =  {
             'fileform': unicode(self.fileform.currentText()),
             'collision': unicode(self.collision.currentText()),
             'updatemeta': self.updatemeta.isChecked(),
+            'bgmeta': False, # self.bgmeta.isChecked(),
             'updateepubcover': self.updateepubcover.isChecked(),
-            'smarten_punctuation':self.prefs['smarten_punctuation']
-                }
-        
+            'smarten_punctuation':self.prefs['smarten_punctuation'],
+            'do_wordcount':self.prefs['do_wordcount'],
+            }
+
         if self.merge:
             retval['fileform']=='epub'
             retval['updateepubcover']=True
             if self.newmerge:
                 retval['updatemeta']=True
                 retval['collision']=ADDNEW
-            
+
         return dict(retval.items() + self.extraoptions.items() )
 
     def get_urlstext(self):
@@ -476,21 +469,21 @@ class AddNewDialog(SizePersistedDialog):
 class FakeLineEdit():
     def __init__(self):
         pass
-    
+
     def text(self):
         pass
-    
+
 class CollectURLDialog(SizePersistedDialog):
     '''
     Collect single url for get urls.
     '''
-    def __init__(self, gui, title, url_text, anthology=False, indiv=True): 
+    def __init__(self, gui, title, url_text, anthology=False, indiv=True):
         SizePersistedDialog.__init__(self, gui, 'fff:get story urls')
         self.status=False
         self.anthology=False
 
         self.setMinimumWidth(300)
-        
+
         self.l = QVBoxLayout()
         self.setLayout(self.l)
 
@@ -560,16 +553,16 @@ class UserPassDialog(QDialog):
         else:
             self.setWindowTitle(_('User/Password'))
             self.l.addWidget(QLabel(_("%s requires you to login to download this story.")%site),0,0,1,2)
-        
+
             self.l.addWidget(QLabel(_("User:")),1,0)
             self.user = QLineEdit(self)
             self.l.addWidget(self.user,1,1)
-   
+
         self.l.addWidget(QLabel(_("Password:")),2,0)
         self.passwd = QLineEdit(self)
         self.passwd.setEchoMode(QLineEdit.Password)
         self.l.addWidget(self.passwd,2,1)
-   
+
         self.ok_button = QPushButton(_('OK'), self)
         self.ok_button.clicked.connect(self.ok)
         self.l.addWidget(self.ok_button,3,0)
@@ -588,14 +581,34 @@ class UserPassDialog(QDialog):
         self.status=False
         self.hide()
 
-class LoopProgressDialog(QProgressDialog):
+def LoopProgressDialog(gui,
+                       book_list,
+                       foreach_function,
+                       finish_function,
+                       init_label=_("Fetching metadata for stories..."),
+                       win_title=_("Downloading metadata for stories"),
+                       status_prefix=_("Fetched metadata for")):
+    ld = _LoopProgressDialog(gui,
+                             book_list,
+                             foreach_function,
+                             init_label,
+                             win_title,
+                             status_prefix)
+    
+    # Mac OS X gets upset if the finish_function is called from inside
+    # the real _LoopProgressDialog class.
+    
+    # reflect old behavior.
+    if not ld.wasCanceled():
+        finish_function(book_list)
+        
+class _LoopProgressDialog(QProgressDialog):
     '''
     ProgressDialog displayed while fetching metadata for each story.
     '''
     def __init__(self, gui,
                  book_list,
                  foreach_function,
-                 finish_function,
                  init_label=_("Fetching metadata for stories..."),
                  win_title=_("Downloading metadata for stories"),
                  status_prefix=_("Fetched metadata for")):
@@ -606,7 +619,6 @@ class LoopProgressDialog(QProgressDialog):
         self.setMinimumWidth(500)
         self.book_list = book_list
         self.foreach_function = foreach_function
-        self.finish_function = finish_function
         self.status_prefix = status_prefix
         self.i = 0
         self.start_time = datetime.now()
@@ -615,6 +627,9 @@ class LoopProgressDialog(QProgressDialog):
         from calibre_plugins.fanficfare_plugin.prefs import prefs
         self.show_est_time = prefs['show_est_time']
 
+        self.setLabelText('%s %d / %d' % (self.status_prefix, self.i, len(self.book_list)))
+        self.setValue(self.i)
+
         ## self.do_loop does QTimer.singleShot on self.do_loop also.
         ## A weird way to do a loop, but that was the example I had.
         QTimer.singleShot(0, self.do_loop)
@@ -641,21 +656,22 @@ class LoopProgressDialog(QProgressDialog):
             ## collision spec passed into getadapter by partial from fff_plugin
             ## no retval only if it exists, but collision is SKIP
             self.foreach_function(book)
-            
+
         except NotGoingToDownload as d:
+            book['status']=_('Skipped')
             book['good']=False
+            book['showerror']=d.showerror
             book['comment']=unicode(d)
             book['icon'] = d.icon
 
         except Exception as e:
             book['good']=False
             book['comment']=unicode(e)
-            logger.error("Exception: %s:%s"%(book,unicode(e)))
-            traceback.print_exc()
-            
+            logger.error("Exception: %s:%s"%(book,unicode(e)),exc_info=True)
+
         self.updateStatus()
         self.i += 1
-            
+
         if self.i >= len(self.book_list) or self.wasCanceled():
             return self.do_when_finished()
         else:
@@ -663,8 +679,6 @@ class LoopProgressDialog(QProgressDialog):
 
     def do_when_finished(self):
         self.hide()
-        # Queues a job to process these books in the background.
-        self.finish_function(self.book_list)
 
 def time_duration_format(seconds):
     """
@@ -746,7 +760,7 @@ class UpdateExistingDialog(SizePersistedDialog):
         self.prefs = prefs
         self.setWindowTitle(header)
         self.setWindowIcon(icon)
-        
+
         layout = QVBoxLayout(self)
         self.setLayout(layout)
         title_layout = ImageTitleLayout(self, 'images/icon.png',
@@ -783,15 +797,18 @@ class UpdateExistingDialog(SizePersistedDialog):
         gbl = QVBoxLayout()
         gbl.addWidget(gbf)
         groupbox.setLayout(gbl)
-        gbl = QHBoxLayout()
+        gbl = QVBoxLayout()
         gbf.setLayout(gbl)
         options_layout.addWidget(groupbox)
 
         gbf.setVisible(False)
         groupbox.toggled.connect(gbf.setVisible)
+
+        horz = QHBoxLayout()
+        gbl.addLayout(horz)
         
         label = QLabel(_('Output &Format:'))
-        gbl.addWidget(label)
+        horz.addWidget(label)
         self.fileform = QComboBox(self)
         self.fileform.addItem('epub')
         self.fileform.addItem('mobi')
@@ -801,10 +818,10 @@ class UpdateExistingDialog(SizePersistedDialog):
         self.fileform.setToolTip(_('Choose output format to create.  May set default from plugin configuration.'))
         self.fileform.activated.connect(self.set_collisions)
         label.setBuddy(self.fileform)
-        gbl.addWidget(self.fileform)
-        
+        horz.addWidget(self.fileform)
+
         label = QLabel(_('Update Mode:'))
-        gbl.addWidget(label)
+        horz.addWidget(label)
         self.collision = QComboBox(self)
         self.collision.setToolTip(_("What sort of update to perform.  May set default from plugin configuration."))
         # add collision options
@@ -813,27 +830,33 @@ class UpdateExistingDialog(SizePersistedDialog):
         if i > -1:
             self.collision.setCurrentIndex(i)
         label.setBuddy(self.collision)
-        gbl.addWidget(self.collision)
+        horz.addWidget(self.collision)
 
+        horz = QHBoxLayout()
+        gbl.addLayout(horz)
+        
         self.updatemeta = QCheckBox(_('Update Calibre &Metadata?'),self)
         self.updatemeta.setToolTip(_("Update metadata for existing stories in Calibre from web site?\n(Columns set to 'New Only' in the column tabs will only be set for new books.)"))
         self.updatemeta.setChecked(self.prefs['updatemeta'])
-        gbl.addWidget(self.updatemeta)
-                
+        horz.addWidget(self.updatemeta)
+
         self.updateepubcover = QCheckBox(_('Update EPUB Cover?'),self)
         self.updateepubcover.setToolTip(_('Update book cover image from site or defaults (if found) <i>inside</i> the EPUB when EPUB is updated.'))
         self.updateepubcover.setChecked(self.prefs['updateepubcover'])
-        gbl.addWidget(self.updateepubcover)
+        horz.addWidget(self.updateepubcover)
 
+        self.bgmeta = QCheckBox(_('Background Metadata?'),self)
+        self.bgmeta.setToolTip(_("Collect Metadata from sites in a Background process.<br />This returns control to you quicker while updating, but you won't be asked for username/passwords or if you are an adult--stories that need those will just fail."))
+        self.bgmeta.setChecked(self.prefs['bgmeta'])
+        horz.addWidget(self.bgmeta)
 
-        
         button_box = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel)
         button_box.accepted.connect(self.accept)
         button_box.rejected.connect(self.reject)
         options_layout.addWidget(button_box)
-        
+
         layout.addLayout(options_layout)
-        
+
         # Cause our dialog size to be restored from prefs or created on first usage
         self.resize_dialog()
         self.books_table.populate_table(books)
@@ -849,14 +872,14 @@ class UpdateExistingDialog(SizePersistedDialog):
             order.remove(UPDATEALWAYS)
         if self.prefs['savemetacol'] == '':
             order.remove(CALIBREONLYSAVECOL)
-            
+
         for o in order:
             self.collision.addItem(o)
-            
+
         i = self.collision.findText(prev)
         if i > -1:
             self.collision.setCurrentIndex(i)
-        
+
     def remove_from_list(self):
         self.books_table.remove_selected_rows()
 
@@ -868,8 +891,10 @@ class UpdateExistingDialog(SizePersistedDialog):
             'fileform': unicode(self.fileform.currentText()),
             'collision': unicode(self.collision.currentText()),
             'updatemeta': self.updatemeta.isChecked(),
+            'bgmeta': self.bgmeta.isChecked(),
             'updateepubcover': self.updateepubcover.isChecked(),
-            'smarten_punctuation':self.prefs['smarten_punctuation']
+            'smarten_punctuation':self.prefs['smarten_punctuation'],
+            'do_wordcount':self.prefs['do_wordcount'],
             }
 
 class StoryListTableWidget(QTableWidget):
@@ -923,16 +948,16 @@ class StoryListTableWidget(QTableWidget):
         status_cell = IconWidgetItem(None,icon,val)
         status_cell.setData(Qt.UserRole, val)
         self.setItem(row, 0, status_cell)
-        
+
         title_cell = ReadOnlyTableWidgetItem(book['title'])
         title_cell.setData(Qt.UserRole, row)
         self.setItem(row, 1, title_cell)
-        
+
         self.setItem(row, 2, AuthorTableWidgetItem(", ".join(book['author']), ", ".join(book['author_sort'])))
-        
+
         url_cell = ReadOnlyTableWidgetItem(book['url'])
         self.setItem(row, 3, url_cell)
-        
+
         comment_cell = ReadOnlyTableWidgetItem(book['comment'])
         self.setItem(row, 4, comment_cell)
 
@@ -1010,9 +1035,9 @@ class RejectListTableWidget(QTableWidget):
         self.setItem(row, 0, url_cell)
         self.setItem(row, 1, ReadOnlyTableWidgetItem(rej.title))
         self.setItem(row, 2, ReadOnlyTableWidgetItem(rej.auth))
-        
+
         note_cell = EditWithComplete(self,sort_func=lambda x:1)
-        
+
         items = [rej.note]+self.rejectreasons
         note_cell.update_items_cache(items)
         note_cell.show_initial_value(rej.note)
@@ -1020,7 +1045,7 @@ class RejectListTableWidget(QTableWidget):
         note_cell.setToolTip(_('Select or Edit Reject Note.'))
         self.setCellWidget(row, 3, note_cell)
         note_cell.setCursorPosition(0)
-        
+
     def remove_selected_rows(self):
         self.setFocus()
         rows = self.selectionModel().selectedRows()
@@ -1052,10 +1077,10 @@ class RejectListDialog(SizePersistedDialog):
                  show_all_reasons=True,
                  save_size_name='fff:reject list dialog'):
         SizePersistedDialog.__init__(self, gui, save_size_name)
-      
+
         self.setWindowTitle(header)
         self.setWindowIcon(get_icon(icon))
-      
+
         layout = QVBoxLayout(self)
         self.setLayout(layout)
         title_layout = ImageTitleLayout(self, icon, header,
@@ -1071,7 +1096,7 @@ class RejectListDialog(SizePersistedDialog):
         rejects_layout.addLayout(button_layout)
         spacerItem = QtGui.QSpacerItem(20, 40, QtGui.QSizePolicy.Minimum, QtGui.QSizePolicy.Expanding)
         button_layout.addItem(spacerItem)
-        
+
         self.remove_button = QtGui.QToolButton(self)
         self.remove_button.setToolTip(_('Remove selected URLs from the list'))
         self.remove_button.setIcon(get_icon('list_remove.png'))
@@ -1083,13 +1108,13 @@ class RejectListDialog(SizePersistedDialog):
 
         if show_all_reasons:
             self.reason_edit = EditWithComplete(self,sort_func=lambda x:1)
-            
+
             items = ['']+rejectreasons
             self.reason_edit.update_items_cache(items)
             self.reason_edit.show_initial_value('')
             self.reason_edit.set_separator(None)
             self.reason_edit.setToolTip(_("This will be added to whatever note you've set for each URL above."))
-            
+
             horz = QHBoxLayout()
             label = QLabel(_("Add this reason to all URLs added:"))
             label.setToolTip(_("This will be added to whatever note you've set for each URL above."))
@@ -1098,7 +1123,7 @@ class RejectListDialog(SizePersistedDialog):
             self.reason_edit.setCursorPosition(0)
             horz.insertStretch(-1)
             layout.addLayout(horz)
-                    
+
         options_layout = QHBoxLayout()
 
         if show_delete:
@@ -1106,14 +1131,14 @@ class RejectListDialog(SizePersistedDialog):
             self.deletebooks.setToolTip(_("Delete the selected books after adding them to the Rejected URLs list."))
             self.deletebooks.setChecked(True)
             options_layout.addWidget(self.deletebooks)
-        
+
         button_box = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel)
         button_box.accepted.connect(self.accept)
         button_box.rejected.connect(self.reject)
         options_layout.addWidget(button_box)
-      
+
         layout.addLayout(options_layout)
-      
+
         # Cause our dialog size to be restored from prefs or created on first usage
         self.resize_dialog()
         self.rejects_table.populate_table(reject_list)
@@ -1146,7 +1171,7 @@ class RejectListDialog(SizePersistedDialog):
         except:
             # doesn't have self.reason_edit when editing existing list.
             return None
-    
+
     def get_deletebooks(self):
         return self.deletebooks.isChecked()
 
@@ -1168,7 +1193,7 @@ class EditTextDialog(SizePersistedDialog):
         if icon:
             self.setWindowIcon(icon)
         self.l.addWidget(self.label)
-        
+
         self.textedit = QTextEdit(self)
         self.textedit.setLineWrapMode(QTextEdit.NoWrap)
         self.textedit.setReadOnly(read_only)
@@ -1181,13 +1206,13 @@ class EditTextDialog(SizePersistedDialog):
 
         if rejectreasons or reasonslabel:
             self.reason_edit = EditWithComplete(self,sort_func=lambda x:1)
-            
+
             items = ['']+rejectreasons
             self.reason_edit.update_items_cache(items)
             self.reason_edit.show_initial_value('')
             self.reason_edit.set_separator(None)
             self.reason_edit.setToolTip(reasonslabel)
-            
+
             if reasonslabel:
                 horz = QHBoxLayout()
                 label = QLabel(reasonslabel)
@@ -1198,12 +1223,12 @@ class EditTextDialog(SizePersistedDialog):
             else:
                 self.l.addWidget(self.reason_edit)
             self.reason_edit.setCursorPosition(0)
-            
+
         button_box = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel)
         button_box.accepted.connect(self.accept)
         button_box.rejected.connect(self.reject)
         self.l.addWidget(button_box)
-        
+
         # Cause our dialog size to be restored from prefs or created on first usage
         self.resize_dialog()
 
@@ -1212,7 +1237,7 @@ class EditTextDialog(SizePersistedDialog):
 
     def get_reason_text(self):
         return unicode(self.reason_edit.currentText()).strip()
-    
+
 class IniTextDialog(SizePersistedDialog):
 
     def __init__(self, parent, text,
@@ -1222,9 +1247,9 @@ class IniTextDialog(SizePersistedDialog):
                  save_size_name='fff:ini text dialog',
                  ):
         SizePersistedDialog.__init__(self, parent, save_size_name)
-        
+
         self.keys=dict()
-        
+
         self.l = QVBoxLayout()
         self.setLayout(self.l)
         self.label = QLabel(label)
@@ -1233,7 +1258,7 @@ class IniTextDialog(SizePersistedDialog):
         if icon:
             self.setWindowIcon(icon)
         self.l.addWidget(self.label)
-        
+
         self.textedit = QTextEdit(self)
 
         highlighter = IniHighlighter(self.textedit,
@@ -1242,7 +1267,7 @@ class IniTextDialog(SizePersistedDialog):
                                      entries=get_valid_entries(),
                                      entry_keywords=get_valid_entry_keywords(),
                                      )
-        
+
         self.textedit.setLineWrapMode(QTextEdit.NoWrap)
         try:
             self.textedit.setFont(QFont("Courier",
@@ -1260,41 +1285,41 @@ class IniTextDialog(SizePersistedDialog):
         if use_find:
 
             findtooltip=_('Search for string in edit box.')
-            
+
             horz = QHBoxLayout()
             label = QLabel(_('Find:'))
 
             label.setToolTip(findtooltip)
-                
+
             # Button to search the document for something
             self.findButton = QtGui.QPushButton(_('Find'),self)
             self.findButton.clicked.connect(self.find)
             self.findButton.setToolTip(findtooltip)
-        
+
             # The field into which to type the query
             self.findField = QLineEdit(self)
             self.findField.setToolTip(findtooltip)
             self.findField.returnPressed.connect(self.findButton.setFocus)
-            
+
             # Case Sensitivity option
             self.caseSens = QtGui.QCheckBox(_('Case sensitive'),self)
             self.caseSens.setToolTip(_("Search for case sensitive string; don't treat Harry, HARRY and harry all the same."))
-            
+
             horz.addWidget(label)
             horz.addWidget(self.findField)
             horz.addWidget(self.findButton)
             horz.addWidget(self.caseSens)
-            
+
             self.l.addLayout(horz)
 
             self.addCtrlKeyPress(QtCore.Qt.Key_F,self.findFocus)
             self.addCtrlKeyPress(QtCore.Qt.Key_G,self.find)
-        
+
         button_box = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel)
         button_box.accepted.connect(self.accept)
         button_box.rejected.connect(self.reject)
         self.l.addWidget(button_box)
-        
+
         # Cause our dialog size to be restored from prefs or created on first usage
         self.resize_dialog()
 
@@ -1310,9 +1335,9 @@ class IniTextDialog(SizePersistedDialog):
                         _('Go back to fix errors?'),
                         errors)
             retry = d.exec_() == d.Accepted
-            
+
             # print("retry:%s"%retry)
-        
+
         if retry:
             lineno=d.get_lineno()
             if lineno:
@@ -1334,19 +1359,19 @@ class IniTextDialog(SizePersistedDialog):
             return func()
         else:
             return SizePersistedDialog.keyPressEvent(self, event)
-    
+
     def get_plain_text(self):
         return unicode(self.textedit.toPlainText())
 
     def findFocus(self):
         # print("findFocus called")
         self.findField.setFocus()
-        self.findField.selectAll()        
-        
+        self.findField.selectAll()
+
     def find(self):
 
         #print("find self.lastStart:%s"%self.lastStart)
-        
+
         # Grab the parent's text
         text = self.textedit.toPlainText()
 
@@ -1361,7 +1386,7 @@ class IniTextDialog(SizePersistedDialog):
         # last starting position
         self.lastStart = text.find(query,self.lastStart + 1)
         # If the find() method didn't return -1 (not found)
-        
+
         if self.lastStart >= 0:
             end = self.lastStart + len(query)
             self.moveCursor(self.lastStart,end)
@@ -1369,7 +1394,7 @@ class IniTextDialog(SizePersistedDialog):
             # Make the next search start from the begining again
             self.lastStart = 0
             self.textedit.moveCursor(self.textedit.textCursor().Start)
-                    
+
     def moveCursor(self,start,end):
 
         # We retrieve the QTextCursor object from the parent's QTextEdit
@@ -1386,7 +1411,7 @@ class IniTextDialog(SizePersistedDialog):
         self.textedit.setTextCursor(cursor)
 
     def select_line(self,lineno):
-        
+
         # We retrieve the QTextCursor object from the parent's QTextEdit
         cursor = self.textedit.textCursor()
 
@@ -1412,8 +1437,8 @@ class ViewLog(SizePersistedDialog):
 
     def get_lineno(self):
         return self.lineno
-        
-    def __init__(self, parent, title, errors, 
+
+    def __init__(self, parent, title, errors,
                  save_size_name='fff:view log dialog',):
         SizePersistedDialog.__init__(self, parent,save_size_name)
         self.l = l = QVBoxLayout()
@@ -1425,25 +1450,36 @@ class ViewLog(SizePersistedDialog):
 
         self.lineno = None
 
+        scrollable = QScrollArea()
+        scrollcontent = QWidget()
+        scrollable.setWidget(scrollcontent)
+        scrollable.setWidgetResizable(True)
+        self.l.addWidget(scrollable)
+
+        self.sl = QVBoxLayout()
+        scrollcontent.setLayout(self.sl)
+
         ## error = (lineno, msg)
         for (lineno, error_msg) in errors:
             # print('adding label for error:%s: %s'%(lineno, error_msg))
+            if len(error_msg) > 200:
+                error_msg=error_msg[:200]+" ..."
             label = QLabel('%s: %s'%(lineno, error_msg))
             label.setWordWrap(True)
             label.setStyleSheet("QLabel { margin-left: 2em; color : blue; } QLabel:hover { color: red; }");
             label.setToolTip(_('Click to go to line %s')%lineno)
             label.mouseReleaseEvent = partial(self.label_clicked, lineno=lineno)
-            self.l.addWidget(label)
-        
+            self.sl.addWidget(label)
+
         # html='<p>'+'</p><p>'.join([ '(lineno: %s) %s'%e for e in errors ])+'</p>'
-        
+
         # self.tb = QTextBrowser(self)
         # self.tb.setFont(QFont("Courier",
         #                       parent.font().pointSize()+1))
         # self.tb.setHtml(html)
         # l.addWidget(self.tb)
 
-        self.l.insertStretch(-1)
+        self.sl.insertStretch(-1)
 
         horz = QHBoxLayout()
 
@@ -1454,13 +1490,13 @@ class ViewLog(SizePersistedDialog):
         saveanyway = QPushButton(_('Save Anyway'), self)
         saveanyway.clicked.connect(self.reject)
         horz.addWidget(saveanyway)
-        
+
         l.addLayout(horz)
         self.setModal(False)
         self.setWindowTitle(title)
         self.setWindowIcon(QIcon(I('debug.png')))
         #self.show()
-        
+
         # Cause our dialog size to be restored from prefs or created on first usage
         self.resize_dialog()
 
@@ -1481,7 +1517,7 @@ class EmailPassDialog(QDialog):
 
         self.setWindowTitle(_('Password'))
         self.l.addWidget(QLabel(_("Enter Email Password for %s:")%user),0,0,1,2)
-   
+
         # self.l.addWidget(QLabel(_("Password:")),1,0)
         self.passwd = QLineEdit(self)
         self.passwd.setEchoMode(QLineEdit.Password)

calibre-plugin/fff_util.py

@@ -1,5 +1,5 @@
-#!/usr/bin/env python
-# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+# -*- coding: utf-8 -*-
+
 from __future__ import (unicode_literals, division, absolute_import,
                         print_function)
 
@@ -23,12 +23,12 @@ def get_fff_personalini():
 def get_fff_config(url,fileform="epub",personalini=None):
     if not personalini:
         personalini = get_fff_personalini()
-    site='unknown'
+    sections=['unknown']
     try:
-        site = adapters.getConfigSectionFor(url)
+        sections = adapters.getConfigSectionsFor(url)
     except Exception as e:
-        logger.debug("Failed trying to get ini config for url(%s): %s, using section [%s] instead"%(url,e,site))
-    configuration = Configuration(site,fileform)
+        logger.debug("Failed trying to get ini config for url(%s): %s, using section %s instead"%(url,e,sections))
+    configuration = Configuration(sections,fileform)
     configuration.readfp(StringIO(get_resources("plugin-defaults.ini")))
     configuration.readfp(StringIO(personalini))
 

calibre-plugin/inihighlighter.py

@@ -1,10 +1,10 @@
-#!/usr/bin/env python
-# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+# -*- coding: utf-8 -*-
+
 from __future__ import (unicode_literals, division,
                         print_function)
 
 __license__   = 'GPL v3'
-__copyright__ = '2015, Jim Miller'
+__copyright__ = '2016, Jim Miller'
 __docformat__ = 'restructuredtext en'
 
 import re
@@ -68,6 +68,10 @@ class IniHighlighter(QSyntaxHighlighter):
         self.teststoryRule = HighlightingRule( r"^\[teststory:([0-9]+|defaults)\]", Qt.darkCyan, blocknum=3 )
         self.highlightingRules.append( self.teststoryRule )
 
+        # storyUrl sections
+        self.storyUrlRule = HighlightingRule( r"^\[https?://.*\]", Qt.darkMagenta, blocknum=4 )
+        self.highlightingRules.append( self.storyUrlRule )
+
         # NOT comments -- but can be custom columns, so don't flag.
         #self.highlightingRules.append( HighlightingRule( r"(?<!^)#[^\n]*" , Qt.red ) )
         
@@ -96,6 +100,10 @@ class IniHighlighter(QSyntaxHighlighter):
             if blocknum == 3:
                 self.setFormat( 0, len(text), self.teststoryRule.highlight )
             
+            # storyUrl section rules:
+            if blocknum == 4:
+                self.setFormat( 0, len(text), self.storyUrlRule.highlight )
+            
         self.setCurrentBlockState( blocknum )
 
 class HighlightingRule():

calibre-plugin/jobs.py

@@ -1,21 +1,33 @@
-#!/usr/bin/env python
-# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+# -*- coding: utf-8 -*-
+
 from __future__ import (unicode_literals, division, absolute_import,
                         print_function)
 
 __license__   = 'GPL v3'
-__copyright__ = '2015, Jim Miller, 2011, Grant Drake <grant.drake@gmail.com>'
+__copyright__ = '2016, Jim Miller, 2011, Grant Drake <grant.drake@gmail.com>'
 __docformat__ = 'restructuredtext en'
 
 import logging
 logger = logging.getLogger(__name__)
 
-import time, traceback
+import traceback
+from datetime import time
 from StringIO import StringIO
     
 from calibre.utils.ipc.server import Server
 from calibre.utils.ipc.job import ParallelJob
 from calibre.constants import numeric_version as calibre_version
+from calibre.utils.date import local_tz
+from calibre.library.comments import sanitize_comments_html
+
+from calibre_plugins.fanficfare_plugin.wordcount import get_word_count
+from calibre_plugins.fanficfare_plugin.prefs import (SAVE_YES, SAVE_YES_UNLESS_SITE)
+
+# pulls in translation files for _() strings
+try:
+    load_translations()
+except NameError:
+    pass # load_translations() added in calibre 1.9
 
 # ------------------------------------------------------------------------------
 #
@@ -23,8 +35,11 @@ from calibre.constants import numeric_version as calibre_version
 #
 # ------------------------------------------------------------------------------
 
-def do_download_worker(book_list, options,
-                       cpus, notification=lambda x,y:x):
+def do_download_worker(book_list,
+                       options,
+                       cpus,
+                       merge=False,
+                       notification=lambda x,y:x):
     '''
     Master job, to launch child jobs to extract ISBN for a set of books
     This is run as a worker job in the background to keep the UI more
@@ -44,7 +59,7 @@ def do_download_worker(book_list, options,
             total += 1
             args = ['calibre_plugins.fanficfare_plugin.jobs',
                     'do_download_for_worker',
-                    (book,options)]
+                    (book,options,merge)]
             job = ParallelJob('arbitrary_n',
                               "url:(%s) id:(%s)"%(book['url'],book['calibre_id']),
                               done=None,
@@ -73,16 +88,22 @@ def do_download_worker(book_list, options,
         book_list.append(job.result)
         book_id = job._book['calibre_id']
         count = count + 1
-        notification(float(count)/total, '%d of %d stories finished downloading'%(count,total))
+        notification(float(count)/total, _('%d of %d stories finished downloading')%(count,total))
         # Add this job's output to the current log
         logger.info('Logfile for book ID %s (%s)'%(book_id, job._book['title']))
         logger.info(job.details)
 
         if count >= total:
-            logger.info("\n"+_("Successful:")+"\n%s\n"%("\n".join([book['url'] for book in 
-                                                      filter(lambda x: x['good'], book_list) ] ) ) )
-            logger.info("\n"+_("Unsuccessful:")+"\n%s\n"%("\n".join([book['url'] for book in 
-                                                        filter(lambda x: not x['good'], book_list) ] ) ) )
+            ## ordering first by good vs bad, then by listorder.
+            good_list = filter(lambda x : x['good'], book_list)
+            bad_list = filter(lambda x : not x['good'], book_list)
+            good_list = sorted(good_list,key=lambda x : x['listorder'])
+            bad_list = sorted(bad_list,key=lambda x : x['listorder'])
+            
+            logger.info("\n"+_("Download Results:")+"\n%s\n"%("\n".join([ "%(url)s %(comment)s" % book for book in good_list+bad_list])))
+            
+            logger.info("\n"+_("Successful:")+"\n%s\n"%("\n".join([book['url'] for book in good_list])))
+            logger.info("\n"+_("Unsuccessful:")+"\n%s\n"%("\n".join([book['url'] for book in bad_list])))
             break
 
     server.close()
@@ -90,7 +111,7 @@ def do_download_worker(book_list, options,
     # return the book list as the job result
     return book_list
 
-def do_download_for_worker(book,options,notification=lambda x,y:x):
+def do_download_for_worker(book,options,merge,notification=lambda x,y:x):
     '''
     Child job, to download story when run as a worker job
     '''
@@ -136,7 +157,7 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
             adapter.setChaptersRange(book['begin'],book['end'])
             
             adapter.load_cookiejar(options['cookiejarfile'])
-            logger.debug("cookiejar:%s"%adapter.cookiejar)
+            #logger.debug("cookiejar:%s"%adapter.cookiejar)
             adapter.set_pagecache(options['pagecache'])
             
             story = adapter.getStoryMetadataOnly()
@@ -147,6 +168,26 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
             if 'version' in options:
                 story.setMetadata('version',options['version'])
                 
+            book['title'] = story.getMetadata("title", removeallentities=True)
+            book['author_sort'] = book['author'] = story.getList("author", removeallentities=True)
+            book['publisher'] = story.getMetadata("site")
+            book['url'] = story.getMetadata("storyUrl")
+            book['tags'] = story.getSubjectTags(removeallentities=True)
+            if story.getMetadata("description"):
+                book['comments'] = sanitize_comments_html(story.getMetadata("description"))
+            else:
+                book['comments']=''
+            book['series'] = story.getMetadata("series", removeallentities=True)
+    
+            if story.getMetadataRaw('datePublished'):
+                book['pubdate'] = story.getMetadataRaw('datePublished').replace(tzinfo=local_tz)
+            if story.getMetadataRaw('dateUpdated'):
+                book['updatedate'] = story.getMetadataRaw('dateUpdated').replace(tzinfo=local_tz)
+            if story.getMetadataRaw('dateCreated'):
+                book['timestamp'] = story.getMetadataRaw('dateCreated').replace(tzinfo=local_tz)
+            else:
+                book['timestamp'] = None # need *something* there for calibre.
+                
             writer = writers.getWriter(options['fileform'],configuration,adapter)
     
             outfile = book['outfile']
@@ -154,9 +195,10 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
             ## No need to download at all.  Shouldn't ever get down here.
             if options['collision'] in (CALIBREONLY, CALIBREONLYSAVECOL):
                 logger.info("Skipping CALIBREONLY 'update' down inside worker--this shouldn't be happening...")
-                book['comment'] = 'Metadata collected.'
+                book['comment'] = _('Metadata collected.')
                 book['all_metadata'] = story.getAllMetadata(removeallentities=True)
-                book['savemetacol'] = story.dump_html_metadata()
+                if options['savemetacol'] != '':
+                    book['savemetacol'] = story.dump_html_metadata()
                 
             ## checks were done earlier, it's new or not dup or newer--just write it.
             elif options['collision'] in (ADDNEW, SKIP, OVERWRITE, OVERWRITEALWAYS) or \
@@ -164,19 +206,31 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
     
                 # preserve logfile even on overwrite.
                 if 'epub_for_update' in book:
-                    
                     adapter.logfile = get_update_data(book['epub_for_update'])[6]
                     # change the existing entries id to notid so
                     # write_epub writes a whole new set to indicate overwrite.
                     if adapter.logfile:
                         adapter.logfile = adapter.logfile.replace("span id","span notid")
+
+                if options['collision'] == OVERWRITE and 'fileupdated' in book:
+                    lastupdated=story.getMetadataRaw('dateUpdated')
+                    fileupdated=book['fileupdated']
+
+                    # updated doesn't have time (or is midnight), use dates only.
+                    # updated does have time, use full timestamps.
+                    if (lastupdated.time() == time.min and fileupdated.date() > lastupdated.date()) or \
+                            (lastupdated.time() != time.min and fileupdated > lastupdated):
+                        raise NotGoingToDownload(_("Not Overwriting, web site is not newer."),'edit-undo.png',showerror=False)
+
                 
                 logger.info("write to %s"%outfile)
                 inject_cal_cols(book,story,configuration)
                 writer.writeStory(outfilename=outfile, forceOverwrite=True)
-                book['comment'] = 'Download %s completed, %s chapters.'%(options['fileform'],story.getMetadata("numChapters"))
+                
+                book['comment'] = _('Download %s completed, %s chapters.')%(options['fileform'],story.getMetadata("numChapters"))
                 book['all_metadata'] = story.getAllMetadata(removeallentities=True)
-                book['savemetacol'] = story.dump_html_metadata()
+                if options['savemetacol'] != '':
+                    book['savemetacol'] = story.dump_html_metadata()
                 
             ## checks were done earlier, just update it.
             elif 'epub_for_update' in book and options['collision'] in (UPDATE, UPDATEALWAYS):
@@ -190,21 +244,27 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
                  adapter.oldimgs,
                  adapter.oldcover,
                  adapter.calibrebookmark,
-                 adapter.logfile) = get_update_data(book['epub_for_update'])[0:7]
+                 adapter.logfile,
+                 adapter.oldchaptersmap,
+                 adapter.oldchaptersdata) = get_update_data(book['epub_for_update'])[0:9]
     
                 # dup handling from fff_plugin needed for anthology updates.
                 if options['collision'] == UPDATE:
                     if chaptercount == urlchaptercount:
-                        book['comment']=_("Already contains %d chapters.  Reuse as is.")%chaptercount
-                        book['all_metadata'] = story.getAllMetadata(removeallentities=True)
-                        book['savemetacol'] = story.dump_html_metadata()
-                        book['outfile'] = book['epub_for_update'] # for anthology merge ops.
-                        return book
-    
-                # dup handling from fff_plugin needed for anthology updates.
-                if chaptercount > urlchaptercount:
-                    raise NotGoingToDownload(_("Existing epub contains %d chapters, web site only has %d. Use Overwrite to force update.") % (chaptercount,urlchaptercount),'dialog_error.png')
-    
+                        if merge:
+                            book['comment']=_("Already contains %d chapters.  Reuse as is.")%chaptercount
+                            book['all_metadata'] = story.getAllMetadata(removeallentities=True)
+                            if options['savemetacol'] != '':
+                                book['savemetacol'] = story.dump_html_metadata()
+                            book['outfile'] = book['epub_for_update'] # for anthology merge ops.
+                            return book
+                        else: # not merge,
+                            raise NotGoingToDownload(_("Already contains %d chapters.")%chaptercount,'edit-undo.png',showerror=False)
+                    elif chaptercount > urlchaptercount:
+                        raise NotGoingToDownload(_("Existing epub contains %d chapters, web site only has %d. Use Overwrite to force update.") % (chaptercount,urlchaptercount),'dialog_error.png')
+                    elif chaptercount == 0:
+                        raise NotGoingToDownload(_("FanFicFare doesn't recognize chapters in existing epub, epub is probably from a different source. Use Overwrite to force update."),'dialog_error.png')
+                    
                 if not (options['collision'] == UPDATEALWAYS and chaptercount == urlchaptercount) \
                         and adapter.getConfig("do_update_hook"):
                     chaptercount = adapter.hookForUpdates(chaptercount)
@@ -218,8 +278,19 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
                 book['comment'] = _('Update %s completed, added %s chapters for %s total.')%\
                     (options['fileform'],(urlchaptercount-chaptercount),urlchaptercount)
                 book['all_metadata'] = story.getAllMetadata(removeallentities=True)
-                book['savemetacol'] = story.dump_html_metadata()
-            
+                if options['savemetacol'] != '':
+                    book['savemetacol'] = story.dump_html_metadata()
+
+            if options['do_wordcount'] == SAVE_YES or (
+                options['do_wordcount'] == SAVE_YES_UNLESS_SITE and not story.getMetadataRaw('numWords') ):
+                wordcount = get_word_count(outfile)
+                logger.info("get_word_count:%s"%wordcount)
+                story.setMetadata('numWords',wordcount)
+                writer.writeStory(outfilename=outfile, forceOverwrite=True)
+                book['all_metadata'] = story.getAllMetadata(removeallentities=True)
+                if options['savemetacol'] != '':
+                    book['savemetacol'] = story.dump_html_metadata()
+                
             if options['smarten_punctuation'] and options['fileform'] == "epub" \
                     and calibre_version >= (0, 9, 39):
                 # for smarten punc
@@ -235,11 +306,11 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
                 opts = O(**opts)
                 
                 log = Log(level=Log.DEBUG)
-                # report = []
-                polish({outfile:outfile}, opts, log, logger.info) # report.append
+                polish({outfile:outfile}, opts, log, logger.info)
             
         except NotGoingToDownload as d:
             book['good']=False
+            book['showerror']=d.showerror
             book['comment']=unicode(d)
             book['icon'] = d.icon
     
@@ -247,9 +318,8 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
             book['good']=False
             book['comment']=unicode(e)
             book['icon']='dialog_error.png'
-            book['status'] = 'Error'
-            logger.info("Exception: %s:%s"%(book,unicode(e)))
-            traceback.print_exc()
+            book['status'] = _('Error')
+            logger.info("Exception: %s:%s"%(book,unicode(e)),exc_info=True)
             
         #time.sleep(10)
     return book

calibre-plugin/plugin-defaults.ini

@@ -1,4 +1,4 @@
-# Copyright 2015 Fanficdownloader team, 2015 FanFicFare team
+# Copyright 2015 Fanficdownloader team, 2016 FanFicFare team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -163,20 +163,29 @@ connect_timeout:60.0
 ## For example, you could change Sci-Fi=>SF, remove *-Centered tags,
 ## etc.  See http://docs.python.org/library/re.html (look for re.sub)
 ## for regexp details.
+##
 ## Make sure to keep at least one space at the start of each line and
 ## to escape % to %%, if used.
+##
 ## Two, three or five part lines.  Two part effect everything.
 ## Three part effect only those key(s) lists.
 ## *Five* part lines.  Effect only when trailing conditional key=>regexp matches
 ## metakey[,metakey]=>pattern=>replacement[&&conditionalkey=>regexp]
+##
 ## Note that if metakey == conditionalkey the conditional is ignored.
 ## You can use \s in the replacement to add explicit spaces.  (The config parser
 ## tends to discard trailing spaces.)
+##
 ## replace_metadata <entry>_LIST options: FanFicFare replace_metadata lines
 ## operate on individual list items for list entries. But if you
 ## want to do a replacement on the joined string for the whole list,
 ## you can by using <entry>_LIST. Example, if you added
 ## calibre_author: calibre_author_LIST=>^(.{,100}).*$=>\1
+##
+## You can 'split' one list item into multiple list entries by using
+## \' in the replacement string.
+##
+## Examples:
 #replace_metadata:
 # genre,category=>Sci-Fi=>SF
 # Puella Magi Madoka Magica.* => Madoka
@@ -186,6 +195,8 @@ connect_timeout:60.0
 # .*-Centered=>
 # characters=>Sam W\.=>Sam Witwicky&&category=>Transformers
 # characters=>Sam W\.=>Sam Winchester&&category=>Supernatural
+# category=>Bitextual=>M/M\,F/M
+
 
 ## Include/Exclude metadata
 ##
@@ -210,7 +221,7 @@ connect_timeout:60.0
 ##
 ## This is fairly complicated, so it's documented on its own wiki
 ## page:
-## https://code.google.com/p/fanficdownloader/wiki/InExcludeMetadataFeature
+## https://github.com/JimmXinu/FanFicFare/wiki/InExcludeMetadataFeature
 
 ## Some readers don't show horizontal rule (<hr />) tags correctly.
 ## This replaces them all with a centered '* * *'.  (Note centering
@@ -255,12 +266,37 @@ keep_summary_html:true
 
 ## If set true, any style attributes on tags in the story HTML will be
 ## kept.  Useful for keeping extra colors & formatting from original.
+## DEPRECATED - use keep_html_attrs (or add_to_keep_html_attrs) instead.
 #keep_style_attr: false
 
 ## If set true, any title attributes on tags in the story HTML will be
 ## kept.  Some sites(AO3) use <a title="Translation">Foreign language</a>
+## DEPRECATED - use keep_html_attrs (or add_to_keep_html_attrs) instead.
 #keep_title_attr: false
 
+## Some attributes cause problems for EBook readers.  By default,
+## FanFicFare will remove all attributes except the ones specified
+## from all tags.  (The only exception is that <img> tags will also
+## keep src, alt and longdesc attributes.)
+## Example: To add 'style', 'title' and 'align' to the list to keep,
+## in your personal.ini [defaults] put:
+## add_to_keep_html_attrs:,style,title,align
+keep_html_attrs:href,name,class,id
+
+## Tags listed here will be replaced with <span class="tagname">.
+## For example: <u>underlined text</u> becomes
+## <span class="u">underlined text</span>
+## Note that the output_css should contain the class .u, .big, etc for
+## the spans to be useful.
+## This feature is for replacing old tags deprecated/removed in newer
+## HTML and EPUB standards.
+replace_tags_with_spans:u,big,small
+
+## If a chapter range was given, use this pattern for the book title.
+## replace_metadata and include/exclude will be applied *after* this.
+## Set to empty value to disable.
+title_chapter_range_pattern:${title} (Ch ${first}-${last})
+
 ## Don't like the numbers at the start of chapter titles on some
 ## sites?  You can use strip_chapter_numbers to strip them off.  Just
 ## want to make them all look the same?  Strip them off, then add them
@@ -283,22 +319,48 @@ add_chapter_numbers:false
 ## "1: Start" => "Start"
 ## "2, Chapter the second" => "Chapter the second"
 ## etc
-chapter_title_strip_pattern:^[0-9]+[\.: -]+
+## Leaves unchanged "1.1" or "1"
+## Note that your ToC entry(ies) may be empty if the
+## chapter_title_strip_pattern removes everything and you don't have
+## add_chapter_numbers:true.
+chapter_title_strip_pattern:^[0-9]+[\.: -]+(?=[^0-9]|$)
 
-## This version will strip all of the above *plus* remove 'Chapter 1':
+## This version remove leading numbers and 'Chapter 1':
 ## "Chapter 1" => ""
 ## "1. Chapter 1" => ""
 ## "1. Chapter 1, Bob's First Clue" => "Bob's First Clue"
 ## "Chapter 2 - Pirates Place" => "Pirates Place"
 ## etc
+## Note that your ToC entry(ies) may be empty if the
+## chapter_title_strip_pattern removes everything and you don't have
+## add_chapter_numbers:true.
 #chapter_title_strip_pattern:^([0-9]+[\.: -]+)?(Chapter *[0-9]+[\.:, -]*)?
 
-## Uses a python template substitution.  The ${index} is the 'chapter'
-## number and ${title} is the chapter title, after applying
-## chapter_title_strip_pattern.  Those are the only variables available.
-## "The Beginning" => "1. The Beginning" 
+## If true, when updating an epub that already has old chapters, new
+## chapters will be marked in the TOC and chapter header by using
+## chapter_title_new_pattern and chapter_title_addnew_pattern to set the chapter.
+mark_new_chapters:false
+
+## chapter title patterns use python template substitution.  The
+## ${index} is the 'chapter' number and ${title} is the chapter title,
+## after applying chapter_title_strip_pattern.  Those are the only
+## variables available.
+
+## The basic pattern used when not using add_chapter_numbers or
+## mark_new_chapters
+chapter_title_def_pattern:${title}
+
+## Pattern used with add_chapter_numbers, but not mark_new_chapters
 chapter_title_add_pattern:${index}. ${title}
 
+## Pattern used with mark_new_chapters, but not add_chapter_numbers
+## (new) is just text and can be changed.
+chapter_title_new_pattern:(new) ${title}
+
+## Pattern used with add_chapter_numbers and mark_new_chapters
+## (new) is just text and can be changed.
+chapter_title_addnew_pattern:${index}. (new) ${title}
+
 ## Uses a python template substitution.  The ${title} is the default
 ## title of a new anthology, <series name> in the case of a series, or
 ## the first book title otherwise.  This is only applied to new
@@ -309,12 +371,19 @@ anthology_title_pattern:${title} Anthology
 ## any anthology tags.
 anthology_tags:Anthology
 
-## Reorder ships so b/a and c/b/a become a/b and a/b/c. Only separates
-## on '/', so use replace_metadata to change separator first if
-## needed. Something like: ships=>[ ]*(/|&amp;|&)[ ]*=>/ You can use
-## ships_LIST to change the / back to something else if you want.
+## Reorder ships so b/a and c/b/a become a/b and a/b/c. '/' is no
+## longer hard coded and can be changed and added to with
+## sort_ships_splits.
 sort_ships:false
 
+## Each line indicates first a regex that should be used to split each
+## ships entry and then, after => the string to use to merge the parts
+## back together.  \s == blank space.
+## Each part will have replace_metadata with key ships_CHARS applied.
+sort_ships_splits:
+ [ ]*/[ ]*=>/
+ [ ]*&amp;[ ]*=>\s&amp;\s
+
 ## join_string_<entry> options -- FanFicFare list entries are comma
 ## separated by default. You can use this to change that. For example,
 ## if you want authors separated with ' & ' instead, use
@@ -330,6 +399,122 @@ sort_ships:false
 ## User-agent
 user_agent:FFF/2.X
 
+## Added for [base_xenforoforum], but can be used with other sites,
+## too.  Limit the 'description' to the first X *characters*
+## collected.  Character count includes HTML tags, so it can be
+## non-intuitive.
+#description_limit:1000
+
+[base_efiction]
+## At the time of writing, eFiction Base adapters allow downloading
+## the whole story in bulk using the 'Print' feature. If 'bulk_load'
+## is set to 'true', both metadata and chapters can be loaded in one
+## step
+bulk_load:true
+
+[base_xenforoforum]
+
+cover_exclusion_regexp:/styles/
+
+## I saw lots of chapters name simply '1.1' etc during testing.
+strip_chapter_numbers:false
+
+## Copy title to tagsfromtitle for parsing tags.
+add_to_extra_valid_entries:,tagsfromtitle,forumtags
+
+## '.NOREPL' tells the system to *not* apply title's
+## in/exclude/replace_metadata -- Only works on include_in_ lines.
+include_in_tagsfromtitle:title.NOREPL
+
+tagsfromtitle_label:Tags from Title
+forumtags_label:Tags from Forum
+
+## might want to do this, maybe not.  Will often include category, but
+## also often include non-category stuff.
+# include_in_category:tagsfromtitle 
+
+add_to_include_metadata_pre:
+# only keep tagsfromtitle with ( or [ in.
+ tagsfromtitle=~[\[\(]
+
+## disable chapter range in title because of tagsfromtitle processing.
+title_chapter_range_pattern:
+
+add_to_replace_metadata:
+# for QuestionableQuesting NSFW subforum.
+ tagsfromtitle=>^\[NSFW\].*?([\(\[]([^\]\)]+)[\)\]]).*?$=>NSFW,\2
+# remove anything outside () or []
+ tagsfromtitle=>^.*?([\(\[]([^\]\)]+)[\)\]]).*?$=>\2
+# remove () []
+# tagsfromtitle=>[\(\)\[\]]=>
+# change (spaces)slash(or semicolon)(spaces) to comma
+ tagsfromtitle=> *[/;] *=>,
+ tagsfromtitle=> [xX] =>,
+
+# remove [] or () blocks and leading/trailing spaces/dashes/colons
+ title=>[-: ]*[\(\[]([^\]\)]+)[\)\]][-: ]*=>
+# remove 'Thread' and the next word, usually "Thread 2", "Thread
+# four", "Thread iv", "Story Thread", etc
+ title,tagsfromtitle=>[-: ]*(Story *)?[Tt]hread [^ ]+[-: ]*=>
+
+# Normalize 'fanfiction/fanfic/fan-fiction' a little.
+ forumtags=>[Ff]an-?[Ff]ic(tion)?=>FanFiction
+
+add_to_extra_titlepage_entries:,tagsfromtitle,forumtags
+
+## XenForo tags are all lowercase everywhere that I've seen.  This
+## makes the first letter of each word uppercase.  Applied before
+## replace_metadata.
+capitalize_forumtags:true
+
+## Add both title tags and forumtags to standard (subject) tags.
+## '.SPLIT' tells the system to split by ','
+add_to_include_subject_tags:,tagsfromtitle.SPLIT,forumtags
+
+## base_xenforoforum reads Published and Updated datetimes from
+## Threadmarks if used, or from the posted & updated times of the
+## 'first' post if no threadmarks.
+datePublished_format:%%Y-%%m-%%d %%H:%%M
+dateUpdated_format:%%Y-%%m-%%d %%H:%%M
+
+## Only take the first X characters of the 'first' post to use as
+## the description.
+description_limit:500
+
+## Because base_xenforoforum adapters can pull chapter URLs from human
+## posts, the odds of errors in the chapter URLs are vastly higher.
+## You can set continue_on_chapter_error:true to continue on after
+## failing to download a chapter and instead record an error message
+## in the ebook for that chapter.
+continue_on_chapter_error:false
+
+## When given a thread URL, use threadmarks as chapter links when
+## there are at least this many threadmarks.  A number of older
+## threads have a single threadmark to an 'index' post.  Set to 1 to
+## use threadmarks whenever they exist.
+minimum_threadmarks:2
+
+## When 'first post' (or post URL) is being added as a chapter, give
+## the chapter this title.
+first_post_title:First Post
+
+## In normal operation, if given a post URL or a thread URL with less
+## than minimum_threadmarks, the given post or the first post of the
+## thread will be included as the first chapter (with chapter title
+## from first_post_title) unless that post is explicitly linked to in
+## the collected chapter list.  First post is not included when using
+## thread marks.
+##
+## If always_include_first_post:true, then the given or first post
+## will be included as above even if it is a link in the post or even
+## if threadmarks are used.  Can result in a duplicated chapter.
+always_include_first_post:false
+
+## In normal operation, forumtags will only be populated when
+## threadmarks are used for chapters (see minimum_threadmarks above).
+## When always_use_forumtags:true, always populate forumtags.
+always_use_forumtags:false
+
 ## Each output format has a section that overrides [defaults]
 [html]
 
@@ -367,6 +552,8 @@ output_css:
  .smcap    {font-variant: small-caps;}
  .u        {text-decoration: underline;}
  .bold     {font-weight: bold;}
+ .big { font-size: larger; }
+ .small { font-size: smaller; }
 
 [txt]
 ## Add URLs since there aren't links.
@@ -447,6 +634,8 @@ output_css:
  .smcap    {font-variant: small-caps;}
  .u        {text-decoration: underline;}
  .bold     {font-weight: bold;}
+ .big { font-size: larger; }
+ .small { font-size: smaller; }
 
 ## include images from img tags in the body and summary of
 ## stories.  Images will be converted to jpg for size if possible.
@@ -522,6 +711,7 @@ nook_img_fix:true
 ## URLs like: http://test1.com?sid=12345
 [test1.com]
 extratags: FanFiction,Testing
+
 # extracategories:Fafner
 # extragenres:Romance,Fluff
 # extracharacters:Reginald Smythe-Smythe,Mokona,Harry P.
@@ -578,11 +768,13 @@ extratags: FanFiction,Testing,HTML
 ## doesn't like that.  If do_update_hook is uncommented and set true,
 ## the adapter will discard all existing chapters from the newest one
 ## on when updating to enforce accurate chapters.
+## Starting July 2015, FFF stores chapter URLs in the chapter files.
+## Stories downloaded after that shouldn't need this setting anymore.
 #do_update_hook:false
 
 ## AO3 adapter defines a few extra metadata entries.
 ## If there's ever more than 4 series, add series04,series04Url etc.
-extra_valid_entries:fandoms,freeformtags,freefromtags,ao3categories,comments,kudos,hits,bookmarks,collections,series00,series01,series02,series03,series00Url,series01Url,series02Url,series03Url
+extra_valid_entries:fandoms,freeformtags,freefromtags,ao3categories,comments,kudos,hits,bookmarks,collections,byline,series00,series01,series02,series03,series00Url,series01Url,series02Url,series03Url,series00HTML,series01HTML,series02HTML,series03HTML
 fandoms_label:Fandoms
 freeformtags_label:Freeform Tags
 freefromtags_label:Freeform Tags
@@ -592,6 +784,14 @@ kudos_label:Kudos
 hits_label:Hits
 collections_label:Collections
 bookmarks_label:Bookmarks
+series00HTML_label:Series
+series01HTML_label:Additional Series
+series02HTML_label:Additional Series
+series03HTML_label:Additional Series
+
+## Assume entryUrl, apply to "<a class='%slink' href='%s'>%s</a>" to
+## make entryHTML.
+make_linkhtml_entries:series00,series01,series02,series03
 
 ## AO3 doesn't have anything it calls 'genre'.  The adapter used to be
 ## hardcoded to include the site specific metadata freeformtags &
@@ -610,7 +810,7 @@ include_in_category:fandoms
 include_in_freefromtags:freeformtags
 
 ## adds to titlepage_entries instead of replacing it.
-#extra_titlepage_entries: fandoms,freeformtags,ao3categories,comments,kudos,hits,bookmarks,series00,series01,series02,series03,series00Url,series01Url,series02Url,series03Url
+#extra_titlepage_entries: fandoms,freeformtags,ao3categories,comments,kudos,hits,bookmarks,series01HTML,series02HTML,series03HTML,byline
 
 ## adds to include_subject_tags instead of replacing it.
 #extra_subject_tags:fandoms,freeformtags,ao3categories
@@ -647,18 +847,6 @@ extracategories:The Sentinel
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
-[bdsm-geschichten.net]
-## Some sites do not require a login, but do require the user to
-## confirm they are adult for adult content.  In commandline version,
-## this should go in your personal.ini, not defaults.ini.
-#is_adult:true
-
-## This site offers no index page so we can either guess the chapter URLs
-## by dec/incrementing numbers ('guess') or walk all the chapters in the metadata
-## parsing state ('parse'). Since guessing can lead to errors for non-standard
-## story URLs, the default is to parse
-#find_chapters:guess 
-
 [bloodshedverse.com]
 ## website encoding(s) In theory, each website reports the character
 ## encoding they use for each page.  In practice, some sites report it
@@ -669,6 +857,12 @@ extracategories:The Sentinel
 ## it has +90% confidence.  'auto' is not reliable.
 website_encodings:Windows-1252,ISO-8859-1,auto
 
+## dateUpdate doesn't usually have time, but it does on
+## bloodshedverse.com.  See
+## http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+## Note that ini format requires % to be escaped as %%.
+dateUpdated_format:%%Y-%%m-%%d %%H:%%M
+
 ## Extra metadata that this adapter knows about.  See [dramione.org]
 ## for examples of how to use them.
 extra_valid_entries:warnings,reviews
@@ -698,15 +892,6 @@ strip_text_links:true
 ## Site dedicated to these categories/characters/ships
 extracategories:Blood Ties
 
-[buffynfaith.net]
-## Site dedicated to these categories/characters/ships
-extracategories:Buffy: The Vampire Slayer
-
-## Some sites also require the user to confirm they are adult for
-## adult content.  In commandline version, this should go in your
-## personal.ini, not defaults.ini.
-#is_adult:true
-
 [fanfic.castletv.net]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -760,17 +945,6 @@ extracategories:Buffy: The Vampire Slayer
 extracharacters:Buffy, Spike
 extraships:Spike/Buffy
 
-[devianthearts.com]
-## Some sites do not require a login, but do require the user to
-## confirm they are adult for adult content.  In commandline version,
-## this should go in your personal.ini, not defaults.ini.
-#is_adult:true
-
-## Virtually all eFiction Base adapters allow downloading the whole story in
-## bulk using the 'Print' feature. If 'bulk_load' is set to 'true', both
-## metadata and chapters can be loaded in one step
-bulk_load:true
-
 [dramione.org]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -951,11 +1125,6 @@ extraships:Harry Potter/Hermione Granger
 #username:YourName
 #password:yourpassword
 
-## Virtually all eFiction Base adapters allow downloading the whole story in
-## bulk using the 'Print' feature. If 'bulk_load' is set to 'true', both
-## metadata and chapters can be loaded in one step
-bulk_load:true
-
 extra_valid_entries: readings,romance
 extra_titlepage_entries: readings,romance
 readings_label: Readings
@@ -1036,35 +1205,47 @@ dislikes_label:Dislikes
 ## program can prompt you, or you can save it in config.  In
 ## commandline version, this should go in your personal.ini, not
 ## defaults.ini.
-#username:YourName
+## finestories.com has started requiring login by email rather than
+## pen name.
+#username:youremail@yourdomain.dom
 #password:yourpassword
 
-# shows size as "10 KB", not word count
-extra_valid_entries:size
+## Clear FanFiction from defaults, site is original fiction.
+extratags:
 
-# don't show twitter icon.
-cover_exclusion_regexp:/res/css/bir.png
+extra_valid_entries:size,universe,universeUrl,universeHTML,sitetags,notice,codes,score
+#extra_titlepage_entries:size,universeHTML,sitetags,notice,score
+include_in_codes:sitetags
 
-[grangerenchanted.com]
-## Some sites require login (or login for some rated stories) The
-## program can prompt you, or you can save it in config.  In
-## commandline version, this should go in your personal.ini, not
-## defaults.ini.
-#username:YourName
-#password:yourpassword
+## adds to include_subject_tags instead of replacing it.
+#extra_subject_tags:sitetags
 
-## Some sites also require the user to confirm they are adult for
-## adult content.  In commandline version, this should go in your
-## personal.ini, not defaults.ini.
-#is_adult:true
+size_label:Size
+universe_label:Universe
+universeUrl_label:Universe URL
+universeHTML_label:Universe
+sitetags_label:Site Tags
+notice_label:Notice
+score_label:Score
 
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-extracharacters:Hermione Granger
+## Assume entryUrl, apply to "<a class='%slink' href='%s'>%s</a>" to
+## make entryHTML.
+make_linkhtml_entries:universe
 
-## Extra metadata that this adapter knows about.  See [dramione.org]
-## for examples of how to use them.
-extra_valid_entries:read,reviews
+## storiesonline.net stories can be in a series or a universe, but not
+## both.  By default, universe will be populated in 'series' with
+## index=0
+universe_as_series: true
+
+## some sites include images that we don't ever want becoming the
+## cover image.  This lets you exclude them.
+cover_exclusion_regexp:/css/bir.png
+
+[forums.spacebattles.com]
+## see [base_xenforoforum]
+
+[forums.sufficientvelocity.com]
+## see [base_xenforoforum]
 
 [hlfiction.net]
 ## Site dedicated to these categories/characters/ships
@@ -1103,11 +1284,6 @@ extracategories:Glee RPF
 extracharacters:Darren Criss, Chris Colfer
 extraships:Darren Criss/Chris Colfer
 
-## Virtually all eFiction Base adapters allow downloading the whole story in
-## bulk using the 'Print' feature. If 'bulk_load' is set to 'true', both
-## metadata and chapters can be loaded in one step
-bulk_load:true
-
 [ksarchive.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Star Trek
@@ -1122,16 +1298,23 @@ crossoverfandom_label:Crossover Fandom
 extra_titlepage_entries:universe,crossoverfandom
 
 [literotica.com]
-extra_valid_entries:eroticatags
+extra_valid_entries:eroticatags,averrating
 eroticatags_label:Erotica Tags
-extra_titlepage_entries: eroticatags
+averrating_label:Average Rating
+extra_titlepage_entries:eroticatags,averrating
+
+## Extract more erotica_tags from the meta tag of each chapter
+use_meta_keywords: true
+
+## For multiple chapter stories, attempt to clean up the chapter title. This will
+## remove the story title and change "Ch. 01" to "Chapter 1", "Pt. 01" to "Part 1"
+## or just use the text. If this can't be done, the full title is used.
+clean_chapter_titles: false
+
+## Add the chapter description at the start of each chapter.
+description_in_chapter: false
 
 [lotrfanfiction.com]
-## Virtually all eFiction Base adapters allow downloading the whole story in
-## bulk using the 'Print' feature. If 'bulk_load' is set to 'true', both
-## metadata and chapters can be loaded in one step
-bulk_load:true
-
 extra_valid_entries: readings
 readings_label: Readings
 
@@ -1147,6 +1330,19 @@ extracategories:Lord of the Rings
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
 
+[mcstories.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
+## Clear FanFiction from defaults, site is original fiction.
+extratags:Erotica
+
+extra_valid_entries:eroticatags
+eroticatags_label:Erotica Tags
+extra_titlepage_entries: eroticatags
+
 [merlinfic.dtwins.co.uk]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -1185,6 +1381,12 @@ extracategories:NCIS
 extracategories:Buffy: The Vampire Slayer
 extracharacters:Willow
 
+[ninelivesarchive.com]
+## Site dedicated to these categories/characters/ships
+extracategories:The Walking Dead
+extracharacters:Carol,Daryl
+extraships:Carol/Daryl
+
 [nocturnal-light.net]
 ## Extra metadata that this adapter knows about.  See [dramione.org]
 ## for examples of how to use them.
@@ -1258,6 +1460,16 @@ extracategories:My Little Pony: Friendship is Magic
 ## Site dedicated to these categories/characters/ships
 extracategories:The Pretender
 
+[forum.questionablequesting.com]
+## see [base_xenforoforum]
+
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
 [samandjack.net]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -1282,28 +1494,6 @@ extracategories:Supernatural
 extracharacters:Sam,Dean
 extraships:Sam/Dean
 
-[scarhead.net]
-## Some sites require login (or login for some rated stories) The
-## program can prompt you, or you can save it in config.  In
-## commandline version, this should go in your personal.ini, not
-## defaults.ini.
-#username:YourName
-#password:yourpassword
-
-## Some sites also require the user to confirm they are adult for
-## adult content.  In commandline version, this should go in your
-## personal.ini, not defaults.ini.
-#is_adult:true
-
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-
-[sg1-heliopolis.com]
-## Some sites do not require a login, but do require the user to
-## confirm they are adult for adult content.  In commandline version,
-## this should go in your personal.ini, not defaults.ini.
-#is_adult:true
-
 [sheppardweir.com]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -1381,10 +1571,23 @@ extracategories:Transgender
 ## confirm they are adult for adult content.
 #is_adult:true
 
-## Virtually all eFiction Base adapters allow downloading the whole story in
-## bulk using the 'Print' feature. If 'bulk_load' is set to 'true', both
-## metadata and chapters can be loaded in one step
-bulk_load:true
+## This site has a number of additional site specific metadata
+## entries.  This is the first test case of base_efiction 'Auto
+## metadata' automatically including unrecognized metadata.  Still
+## requires entries in extra_valid_entries to be used.
+extra_valid_entries:turnedinto,featureditems,locale,motivationforchange,sexualorientation,storytheme,bodymodification,personality,storytype,typeofchange
+#add_to_titlepage_entries:,turnedinto,featureditems,locale,motivationforchange,sexualorientation,storytheme,bodymodification,personality,storytype,typeofchange
+
+turnedinto_label:Turned Into
+featureditems_label:Featured Items
+locale_label:Locale
+motivationforchange_label:Motivation for Change
+sexualorientation_label:Sexual Orientation
+storytheme_label:Story Theme
+bodymodification_label:Body Modification
+personality_label:Personality
+storytype_label:Story Type
+typeofchange_label:Type of Change
 
 [thehexfiles.net]
 ## Site dedicated to these categories/characters/ships
@@ -1405,11 +1608,6 @@ extraships:Harry Potter/Draco Malfoy
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
-## Virtually all eFiction Base adapters allow downloading the whole story in
-## bulk using the 'Print' feature. If 'bulk_load' is set to 'true', both
-## metadata and chapters can be loaded in one step
-bulk_load:true
-
 ## Site dedicated to these categories/characters/ships
 extracategories:Criminal Minds
 
@@ -1419,11 +1617,6 @@ extracategories:Criminal Minds
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
-## Virtually all eFiction Base adapters allow downloading the whole story in
-## bulk using the 'Print' feature. If 'bulk_load' is set to 'true', both
-## metadata and chapters can be loaded in one step
-bulk_load:true
-
 extra_valid_entries: readings,challenge
 extra_titlepage_entries: readings,challenge
 challenge_label: Challenge
@@ -1442,31 +1635,6 @@ readings_label: Readings
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
-[thequidditchpitch.org]
-## Some sites require login (or login for some rated stories) The
-## program can prompt you, or you can save it in config.  In
-## commandline version, this should go in your personal.ini, not
-## defaults.ini.
-#username:YourName
-#password:yourpassword
-
-## Some sites also require the user to confirm they are adult for
-## adult content.  In commandline version, this should go in your
-## personal.ini, not defaults.ini.
-#is_adult:true
-
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-
-[tokra.fandomnet.com]
-## Some sites do not require a login, but do require the user to
-## confirm they are adult for adult content.  In commandline version,
-## this should go in your personal.ini, not defaults.ini.
-#is_adult:true
-
-## Site dedicated to these categories/characters/ships
-extracategories:Stargate: SG-1
-
 [tolkienfanfiction.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Lord of the Rings
@@ -1628,6 +1796,10 @@ check_next_chapter:false
 #password:yourpassword
 
 [www.ficbook.net]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
 
 [www.fictionalley.org]
 ## Some sites do not require a login, but do require the user to
@@ -1746,6 +1918,9 @@ extracategories:Harry Potter
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
 
+extra_valid_entries:reads,reviews
+reads_label:Total Read Count
+
 [www.hpfanficarchive.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
@@ -1777,12 +1952,38 @@ extraships:InuYasha/Kagome
 ## Site dedicated to these categories/characters/ships
 extracategories:Lord of the Rings
 
-## Virtually all eFiction Base adapters allow downloading the whole story in
-## bulk using the 'Print' feature. If 'bulk_load' is set to 'true', both
-## metadata and chapters can be loaded in one step
-bulk_load:true
+[www.masseffect2.in]
+## Site dedicated to this fandom.
+extracategories: Mass Effect
+
+## Ucoz.com engine, upon which MassEffect2.in is based, imposes an unspecified limit on request frequency.
+## Reports vary from `5 requests per second' to `2 requests per second for more than 10 per minute'.
+## With default settings, a several-hours IP ban may follow, so set it higher.
+slow_down_sleep_time: 2
+
+## Whether to exclude editor signature from the bottom of chapter text.
+exclude_editor_signature: false
+
+## Stories on the site almost never have cover image, and for the stories which do,
+## this may be adjusted in `personal.ini' before downloading.
+never_make_cover: true
+
+## Titles for ratings identified by 1- or 2-letter codes from `ERATING system'
+## (`система Р.Е.Й.Т.И.Н.Г.').  MassEffect2.in and some other sites adopted it,
+## but changed titles and update them occasionally.
+rating_titles: R=RESTRICTED (16+), E=EXEMPT (18+), I=ART HOUSE, T=To every, A=IN=Иной мир, Nn=Новый мир, G=О\, Господи!
+adult_ratings: E,R
 
 [www.mediaminer.org]
+dateUpdated_format:%%Y-%%m-%%d %%H:%%M:%%S
+## Note that mediaminer doesn't give datePublished on the story's
+## index page--it's collected from the earliest uploaded chapter.  So
+## it's not available when only fetching metadata.
+datePublished_format:%%Y-%%m-%%d %%H:%%M:%%S
+
+## some sites include images that we don't ever want becoming the
+## cover image.  This lets you exclude them.
+cover_exclusion_regexp:/img/rss.png
 
 [www.midnightwhispers.ca]
 ## Some sites do not require a login, but do require the user to
@@ -1801,11 +2002,6 @@ cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
 ## Site dedicated to these categories/characters/ships
 extracategories:NCIS
 
-[www.nickandgreg.net]
-## Site dedicated to these categories/characters/ships
-extracategories:CSI
-extraships:Nick Stokes/Greg Sanders
-
 [www.phoenixsong.net]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -1825,9 +2021,18 @@ extracategories:Harry Potter
 extraships:Harry Potter/Ginny Weasley
 
 [www.potionsandsnitches.org]
+extra_valid_entries:stars,reviews,reads,takesplaces,snapeflavours,sitetags
+stars_label:Frogs
+takesplaces_label:Takes Place
+snapeflavours_label:Snape Flavour
+sitetags_label:Site Tags
+
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
 
+add_to_include_subject_tags:,takesplaces,snapeflavours,sitetags
+#add_to_extra_titlepage_entries:,stars,reviews,reads,takesplaces,snapeflavours,sitetags
+
 [www.potterfics.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
@@ -1850,6 +2055,17 @@ extracategories:Psych
 ## Site dedicated to these categories/characters/ships
 extracategories:Queer as Folk
 
+[quotev.com]
+extra_valid_entries:pages,readers,reads,favorites,searchtags,comments
+pages_label:Pages
+readers_label:Readers
+reads_label:Reads
+favorites_label:Favorites
+searchtags_label:Search Tags
+comments_label:Comments
+
+include_in_category:category,searchtags
+
 [www.restrictedsection.org]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -1945,6 +2161,28 @@ collect_series: false
 #username:YourName
 #password:yourpassword
 
+## TtH uses 'category' Buffy-Centered, Xander-Centered, etc.  If
+## centeredcat_to_characters:true, they will not be included in the
+## category list and Buffy, Xander, etc will instead be included in
+## the characters list.
+centeredcat_to_characters:true
+
+## TtH uses 'category' Pairing: Dawn, Pairing: Willow, etc, but only
+## if there's already been a -Centered category, like Xander-Centered.
+## If pairingcat_to_characters_ships:true, Pairing: Whomever will not
+## be included in the category list and Dawn, Willow, etc will instead
+## be included in the characters list *and* an entry added to the
+## ships list for Centered character / Pairing character.  IE,
+## category: Xander-Centered, Pairing: Dawn becomes characters:
+## Xander, Dawn and ships: Xander/Dawn.
+pairingcat_to_characters_ships:true
+
+## TtH uses 'category' Romance followed by a pairing 'category', such
+## as Romance > Buffy/Spike.  If romancecat_to_characters_ships:true,
+## Romance will still be added to category, but Buffy/Spike will
+## instead be added to characters Buffy, Spike and ships Buffy/Spike
+romancecat_to_characters_ships:true
+
 [www.twilightarchives.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Twilight
@@ -1964,6 +2202,9 @@ extracategories:Twilight
 collect_series: false
 
 [www.walkingtheplank.org]
+extra_valid_entries:reads
+reads_label:Read Count
+
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
 ## this should go in your personal.ini, not defaults.ini.
@@ -1993,6 +2234,80 @@ extracategories:Stargate: Atlantis
 extra_valid_entries:reviews
 reviews_label:Reviews
 
+[buffygiles.velocitygrass.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Site dedicated to these categories/characters/ships
+extracharacters:Buffy,Giles
+
+[fanfiction.lucifael.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+[www.andromeda-web.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Site dedicated to these categories/characters/ships
+extracategories:Andromeda
+
+[www.artemis-fowl.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Site dedicated to these categories/characters/ships
+extracategories:Artemis Fowl
+
+[www.naiceanilme.net]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
 [overrides]
 ## It may sometimes be useful to override all of the specific format,
 ## site and site:format sections in your private configuration.  For

calibre-plugin/prefs.py

@@ -1,10 +1,10 @@
-#!/usr/bin/env python
-# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+# -*- coding: utf-8 -*-
+
 from __future__ import (unicode_literals, division, absolute_import,
                         print_function)
 
 __license__   = 'GPL v3'
-__copyright__ = '2015, Jim Miller'
+__copyright__ = '2016, Jim Miller'
 __docformat__ = 'restructuredtext en'
 
 import logging
@@ -15,9 +15,59 @@ import copy
 from calibre.utils.config import JSONConfig
 from calibre.gui2.ui import get_gui
 
-from calibre_plugins.fanficfare_plugin.dialogs import SAVE_UPDATE
 from calibre_plugins.fanficfare_plugin.common_utils import get_library_uuid
 
+SKIP=_('Skip')
+ADDNEW=_('Add New Book')
+UPDATE=_('Update EPUB if New Chapters')
+UPDATEALWAYS=_('Update EPUB Always')
+OVERWRITE=_('Overwrite if Newer')
+OVERWRITEALWAYS=_('Overwrite Always')
+CALIBREONLY=_('Update Calibre Metadata from Web Site')
+CALIBREONLYSAVECOL=_('Update Calibre Metadata from Saved Metadata Column')
+collision_order=[SKIP,
+                 ADDNEW,
+                 UPDATE,
+                 UPDATEALWAYS,
+                 OVERWRITE,
+                 OVERWRITEALWAYS,
+                 CALIBREONLY,
+                 CALIBREONLYSAVECOL,]
+
+# best idea I've had for how to deal with config/pref saving the
+# collision name in english.
+SAVE_SKIP='Skip'
+SAVE_ADDNEW='Add New Book'
+SAVE_UPDATE='Update EPUB if New Chapters'
+SAVE_UPDATEALWAYS='Update EPUB Always'
+SAVE_OVERWRITE='Overwrite if Newer'
+SAVE_OVERWRITEALWAYS='Overwrite Always'
+SAVE_CALIBREONLY='Update Calibre Metadata Only'
+SAVE_CALIBREONLYSAVECOL='Update Calibre Metadata Only(Saved Column)'
+save_collisions={
+    SKIP:SAVE_SKIP,
+    ADDNEW:SAVE_ADDNEW,
+    UPDATE:SAVE_UPDATE,
+    UPDATEALWAYS:SAVE_UPDATEALWAYS,
+    OVERWRITE:SAVE_OVERWRITE,
+    OVERWRITEALWAYS:SAVE_OVERWRITEALWAYS,
+    CALIBREONLY:SAVE_CALIBREONLY,
+    CALIBREONLYSAVECOL:SAVE_CALIBREONLYSAVECOL,
+    SAVE_SKIP:SKIP,
+    SAVE_ADDNEW:ADDNEW,
+    SAVE_UPDATE:UPDATE,
+    SAVE_UPDATEALWAYS:UPDATEALWAYS,
+    SAVE_OVERWRITE:OVERWRITE,
+    SAVE_OVERWRITEALWAYS:OVERWRITEALWAYS,
+    SAVE_CALIBREONLY:CALIBREONLY,
+    SAVE_CALIBREONLYSAVECOL:CALIBREONLYSAVECOL,
+    }
+
+anthology_collision_order=[UPDATE,
+                           UPDATEALWAYS,
+                           OVERWRITEALWAYS]
+
+
 # Show translated strings, but save the same string in prefs so your
 # prefs are the same in different languages.
 YES=_('Yes, Always')
@@ -26,9 +76,11 @@ YES_IF_IMG=_('Yes, if EPUB has a cover image')
 SAVE_YES_IF_IMG='Yes, if img'
 YES_UNLESS_IMG=_('Yes, unless FanFicFare found a cover image')
 SAVE_YES_UNLESS_IMG='Yes, unless img'
+YES_UNLESS_SITE=_('Yes, unless found on site')
+SAVE_YES_UNLESS_SITE='Yes, unless site'
 NO=_('No')
 SAVE_NO='No'
-calcover_save_options = {
+prefs_save_options = {
     YES:SAVE_YES,
     SAVE_YES:YES,
     YES_IF_IMG:SAVE_YES_IF_IMG,
@@ -37,9 +89,12 @@ calcover_save_options = {
     SAVE_YES_UNLESS_IMG:YES_UNLESS_IMG,
     NO:SAVE_NO,
     SAVE_NO:NO,
+    YES_UNLESS_SITE:SAVE_YES_UNLESS_SITE,
+    SAVE_YES_UNLESS_SITE:YES_UNLESS_SITE,
     }
 updatecalcover_order=[YES,YES_IF_IMG,NO]
 gencalcover_order=[YES,YES_UNLESS_IMG,NO]
+do_wordcount_order=[YES,YES_UNLESS_SITE,NO]
 
 # if don't have any settings for FanFicFarePlugin, copy from
 # predecessor FanFictionDownLoaderPlugin.
@@ -51,6 +106,7 @@ PREFS_KEY_SETTINGS = 'settings'
 # take from here.
 default_prefs = {}
 default_prefs['personal.ini'] = get_resources('plugin-example.ini')
+default_prefs['cal_cols_pass_in'] = False
 default_prefs['rejecturls'] = ''
 default_prefs['rejectreasons'] = '''Sucked
 Boring
@@ -58,6 +114,7 @@ Dup from another site'''
 default_prefs['reject_always'] = False
 
 default_prefs['updatemeta'] = True
+default_prefs['bgmeta'] = False
 default_prefs['updateepubcover'] = False
 default_prefs['keeptags'] = False
 default_prefs['suppressauthorsort'] = False
@@ -75,6 +132,8 @@ default_prefs['lookforurlinhtml'] = False
 default_prefs['checkforseriesurlid'] = True
 default_prefs['checkforurlchange'] = True
 default_prefs['injectseries'] = False
+default_prefs['matchtitleauth'] = True
+default_prefs['do_wordcount'] = SAVE_YES_UNLESS_SITE
 default_prefs['smarten_punctuation'] = False
 default_prefs['show_est_time'] = False
 
@@ -83,6 +142,7 @@ default_prefs['read_lists'] = ''
 default_prefs['addtolists'] = False
 default_prefs['addtoreadlists'] = False
 default_prefs['addtolistsonread'] = False
+default_prefs['autounnew'] = False
 
 default_prefs['updatecalcover'] = None
 default_prefs['gencalcover'] = SAVE_YES
@@ -98,12 +158,14 @@ default_prefs['countpagesstats'] = []
 default_prefs['wordcountmissing'] = False
 
 default_prefs['errorcol'] = ''
+default_prefs['save_all_errors'] = True
 default_prefs['savemetacol'] = ''
 default_prefs['custom_cols'] = {}
 default_prefs['custom_cols_newonly'] = {}
 default_prefs['allow_custcol_from_ini'] = True
 
 default_prefs['std_cols_newonly'] = {}
+default_prefs['set_author_url'] = True
 
 default_prefs['imapserver'] = ''
 default_prefs['imapuser'] = ''
@@ -112,6 +174,7 @@ default_prefs['imapsessionpass'] = False
 default_prefs['imapfolder'] = 'INBOX'
 default_prefs['imapmarkread'] = True
 default_prefs['auto_reject_from_email'] = False
+default_prefs['download_from_email_immediately'] = False
 
 def set_library_config(library_config,db):
     db.prefs.set_namespaced(PREFS_NAMESPACE,

calibre-plugin/wordcount.py

@@ -0,0 +1,95 @@
+#!/usr/bin/env python
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+from __future__ import (unicode_literals, division, absolute_import,
+                        print_function)
+
+__license__ = 'GPL v3'
+__copyright__ = '2016, Jim Miller, 2011, Grant Drake <grant.drake@gmail.com>'
+__docformat__ = 'restructuredtext en'
+
+'''
+A lot of this is lifted from Count Pages plugin by Grant Drake (with
+some changes from davidfor.)
+'''
+
+import logging
+logger = logging.getLogger(__name__)
+
+import re
+
+from calibre.ebooks.oeb.iterator import EbookIterator
+
+RE_HTML_BODY = re.compile(u'<body[^>]*>(.*)</body>', re.UNICODE | re.DOTALL | re.IGNORECASE)
+RE_STRIP_MARKUP = re.compile(u'<[^>]+>', re.UNICODE)
+
+
+def get_word_count(book_path):
+    '''
+    Estimate a word count
+    '''
+    from calibre.utils.localization import get_lang
+    
+    iterator = _open_epub_file(book_path)
+
+    lang = iterator.opf.language
+    lang = get_lang() if not lang else lang
+    count = _get_epub_standard_word_count(iterator, lang)
+
+    return count
+
+def _open_epub_file(book_path, strip_html=False):
+    '''
+    Given a path to an EPUB file, read the contents into a giant block of text
+    '''
+    iterator = EbookIterator(book_path)
+    iterator.__enter__(only_input_plugin=True, run_char_count=True,
+            read_anchor_map=False)
+    return iterator
+
+def _get_epub_standard_word_count(iterator, lang='en'):
+    '''
+    This algorithm counts individual words instead of pages
+    '''
+
+    book_text = _read_epub_contents(iterator, strip_html=True)
+    
+    try:
+        from calibre.spell.break_iterator import count_words
+        wordcount = count_words(book_text, lang)
+        logger.debug('\tWord count - count_words method:%s'%wordcount)
+    except:
+        try: # The above method is new and no-one will have it as of 08/01/2016. Use an older method for a beta.
+            from calibre.spell.break_iterator import split_into_words_and_positions
+            wordcount = len(split_into_words_and_positions(book_text, lang))
+            logger.debug('\tWord count - split_into_words_and_positions method:%s'%wordcount)
+        except:
+            from calibre.utils.wordcount import get_wordcount_obj
+            wordcount = get_wordcount_obj(book_text)
+            wordcount = wordcount.words
+            logger.debug('\tWord count - old method:%s'%wordcount)
+    
+    return wordcount
+
+def _read_epub_contents(iterator, strip_html=False):
+    '''
+    Given an iterator for an ePub file, read the contents into a giant block of text
+    '''
+    book_files = []
+    for path in iterator.spine:
+        with open(path, 'rb') as f:
+            html = f.read().decode('utf-8', 'replace')
+            if strip_html:
+                html = unicode(_extract_body_text(html)).strip()
+                #print('FOUND HTML:', html)
+        book_files.append(html)
+    return ''.join(book_files)
+
+def _extract_body_text(data):
+    '''
+    Get the body text of this html content wit any html tags stripped
+    '''
+    body = RE_HTML_BODY.findall(data)
+    if body:
+        return RE_STRIP_MARKUP.sub('', body[0]).replace('.','. ')
+    return ''
+

fanficfare/__init__.py

@@ -27,7 +27,7 @@ except:
             import logging
             logger = logging.getLogger(__name__)
             loghandler=logging.StreamHandler()
-            loghandler.setFormatter(logging.Formatter("FFF:%(levelname)s:%(filename)s(%(lineno)d):%(message)s"))
+            loghandler.setFormatter(logging.Formatter("FFF: %(levelname)s: %(asctime)s: %(filename)s(%(lineno)d): %(message)s"))
             logger.addHandler(loghandler)
             loghandler.setLevel(logging.DEBUG)
             logger.setLevel(logging.DEBUG)

fanficfare/adapters/__init__.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
+# Copyright 2011 Fanficdownloader team, 2016 FanFicFare team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -49,7 +49,6 @@ import adapter_ficbooknet
 import adapter_portkeyorg
 import adapter_mugglenetcom
 import adapter_hpfandomnet
-import adapter_thequidditchpitchorg
 import adapter_nfacommunitycom
 import adapter_midnightwhispersca
 import adapter_ksarchivecom
@@ -76,7 +75,6 @@ import adapter_ncisfictionnet
 import adapter_thealphagatecom
 import adapter_fanfiktionde
 import adapter_ponyfictionarchivenet
-import adapter_sg1heliopoliscom
 import adapter_ncisficcom
 import adapter_nationallibrarynet
 import adapter_themasquenet
@@ -87,7 +85,6 @@ import adapter_hpfanficarchivecom
 import adapter_twilightarchivescom
 import adapter_nhamagicalworldsus
 import adapter_hlfictionnet
-import adapter_grangerenchantedcom
 import adapter_dracoandginnycom
 import adapter_scarvesandcoffeenet
 import adapter_thepetulantpoetesscom
@@ -104,13 +101,9 @@ import adapter_efictionestelielde
 import adapter_pommedesangcom
 import adapter_restrictedsectionorg
 import adapter_imagineeficcom
-import adapter_buffynfaithnet
 import adapter_psychficcom
-import adapter_tokrafandomnetcom
 import adapter_asr3slashzoneorg
-import adapter_nickandgregnet
 import adapter_potterheadsanonymouscom
-import adapter_scarheadnet
 import adapter_fictionpadcom
 import adapter_storiesonlinenet
 import adapter_trekiverseorg
@@ -122,7 +115,6 @@ import adapter_nocturnallightnet
 import adapter_fanfichu
 import adapter_fanfictioncsodaidokhu
 import adapter_fictionmaniatv
-import adapter_bdsmgeschichten
 import adapter_tolkienfanfiction
 import adapter_themaplebookshelf
 import adapter_fannation
@@ -132,9 +124,20 @@ import adapter_csiforensicscom
 import adapter_lotrfanfictioncom
 import adapter_fhsarchivecom
 import adapter_fanfictionjunkiesde
-import adapter_devianthearts
 import adapter_tgstorytimecom
 import adapter_itcouldhappennet
+import adapter_forumsspacebattlescom
+import adapter_forumssufficientvelocitycom
+import adapter_forumquestionablequestingcom
+import adapter_ninelivesarchivecom
+import adapter_masseffect2in
+import adapter_quotevcom
+import adapter_mcstoriescom
+import adapter_lucifaelff
+import adapter_buffygilescom
+import adapter_andromedawebcom
+import adapter_artemisfowlcom
+import adapter_naiceanilmenet
 
 ## This bit of complexity allows adapters to be added by just adding
 ## importing.  It eliminates the long if/else clauses we used to need
@@ -165,8 +168,9 @@ def getNormalStoryURL(url):
         return None
 
 def getNormalStoryURLSite(url):
+    # print("getNormalStoryURLSite:%s"%url)
     if not getNormalStoryURL.__dummyconfig:
-        getNormalStoryURL.__dummyconfig = Configuration("test1.com","EPUB")
+        getNormalStoryURL.__dummyconfig = Configuration(["test1.com"],"EPUB",lightweight=True)
     # pulling up an adapter is pretty low over-head.  If
     # it fails, it's a bad url.
     try:
@@ -194,14 +198,24 @@ def getAdapter(config,url,anyurl=False):
     # No adapter found.
     raise exceptions.UnknownSite( url, [cls.getSiteDomain() for cls in __class_list] )
 
-def getConfigSections():
+def getSiteSections():
+    # doesn't include base sections. Sections rather than site DNS because of squidge/peja
     return [cls.getConfigSection() for cls in __class_list]
 
+def getConfigSections():
+    # does include base sections.
+    sections = set()
+    for cls in __class_list:
+        sections.update(cls.getConfigSections())
+    return sections
+
 def get_bulk_load_sites():
     # for now, all eFiction Base adapters are assumed to allow bulk_load.
-    return [cls.getConfigSection().replace('www.','') for cls in
-            filter( lambda x : issubclass(x,base_efiction_adapter.BaseEfictionAdapter),
-                    __class_list)]
+    sections = set()
+    for cls in filter( lambda x : issubclass(x,base_efiction_adapter.BaseEfictionAdapter),
+                       __class_list):
+        sections.update( [ x.replace('www.','') for x in cls.getConfigSections() ] )
+    return sections
 
 def getSiteExamples():
     l=[]
@@ -209,10 +223,10 @@ def getSiteExamples():
         l.append((cls.getConfigSection(),cls.getSiteExampleURLs().split()))
     return l
 
-def getConfigSectionFor(url):
+def getConfigSectionsFor(url):
     (cls,fixedurl) = getClassFor(url)
     if cls:
-        return cls.getConfigSection()
+        return cls.getConfigSections()
 
     # No adapter found.
     raise exceptions.UnknownSite( url, [cls.getSiteDomain() for cls in __class_list] )
@@ -224,8 +238,11 @@ def getClassFor(url):
         fixedurl = "http:%s"%url
     if not fixedurl.startswith("http"):
         fixedurl = "http://%s"%url
-    ## remove any trailing '#' locations.
-    fixedurl = re.sub(r"#.*$","",fixedurl)
+        
+    ## remove any trailing '#' locations, except for #post-12345 for
+    ## XenForo
+    if not "#post-" in fixedurl:
+        fixedurl = re.sub(r"#.*$","",fixedurl)
 
     parsedUrl = up.urlparse(fixedurl)
     domain = parsedUrl.netloc.lower()

fanficfare/adapters/adapter_adastrafanficcom.py

@@ -23,7 +23,6 @@ import re
 import urllib
 import urllib2
 
-from .. import BeautifulSoup as bs
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -40,15 +39,15 @@ class AdAstraFanficComSiteAdapter(BaseSiteAdapter):
                                # iso-8859-1 (and some that claim to be
                                # utf8) are really windows-1252.
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
+
+
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
 
-            
+
     @staticmethod
     def getSiteDomain():
         return 'www.adastrafanfic.com'
@@ -66,14 +65,14 @@ class AdAstraFanficComSiteAdapter(BaseSiteAdapter):
         this and change it to True.
         '''
         return True
-    
+
     def extractChapterUrlsAndMetadata(self):
 
         if self.is_adult or self.getConfig("is_adult"):
             addurl = "&warning=5"
         else:
             addurl=""
-            
+
         url = self.url+'&index=1'+addurl
         logger.debug("URL: "+url)
 
@@ -87,19 +86,19 @@ class AdAstraFanficComSiteAdapter(BaseSiteAdapter):
 
         if "Content is only suitable for mature adults. May contain explicit language and adult themes. Equivalent of NC-17." in data:
             raise exceptions.AdultCheckRequired(self.url)
-            
+
         # problems with some stories, but only in calibre.  I suspect
         # issues with different SGML parsers in python.  This is a
         # nasty hack, but it works.
         data = data[data.index("<body"):]
-        
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
 
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',stripHTML(a))
-        
+
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
@@ -126,7 +125,7 @@ class AdAstraFanficComSiteAdapter(BaseSiteAdapter):
                 return d[k]
             except:
                 return ""
-        
+
         # <span class="label">Rated:</span> NC-17<br /> etc
         labels = soup.findAll('span',{'class':'label'})
         for labelspan in labels:
@@ -136,8 +135,8 @@ class AdAstraFanficComSiteAdapter(BaseSiteAdapter):
             if 'Summary' in label:
                 ## Everything until the next span class='label'
                 svalue = ''
-                while value and not defaultGetattr(value,'class') == 'label':
-                    svalue += str(value)
+                while value and 'label' not in defaultGetattr(value,'class'):
+                    svalue += unicode(value)
                     value = value.nextSibling
                 # sometimes poorly formated desc (<p> w/o </p>) leads
                 # to all labels being included.
@@ -185,7 +184,7 @@ class AdAstraFanficComSiteAdapter(BaseSiteAdapter):
 
             if 'Published' in label:
                 self.story.setMetadata('datePublished', makeDate(value.strip(), "%d %b %Y"))
-            
+
             if 'Updated' in label:
                 # there's a stray [ at the end.
                 #value = value[0:-1]
@@ -198,7 +197,7 @@ class AdAstraFanficComSiteAdapter(BaseSiteAdapter):
             series_url = 'http://'+self.host+'/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            seriessoup = self_make_soup(self._fetchUrl(series_url))
             storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
             i=1
             for a in storyas:
@@ -207,11 +206,11 @@ class AdAstraFanficComSiteAdapter(BaseSiteAdapter):
                     self.story.setMetadata('seriesUrl',series_url)
                     break
                 i+=1
-            
+
         except:
             # I find it hard to care if the series parsing fails
             pass
-            
+
 
     def getChapterText(self, url):
 
@@ -222,15 +221,14 @@ class AdAstraFanficComSiteAdapter(BaseSiteAdapter):
         # issues with different SGML parsers in python.  This is a
         # nasty hack, but it works.
         data = data[data.index("<body"):]
-        
-        soup = bs.BeautifulStoneSoup(data,
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
+
+        soup = self.make_soup(data)
+
         span = soup.find('div', {'id' : 'story'})
 
         if None == span:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,span)
 
 def getClass():

fanficfare/adapters/adapter_andromedawebcom.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
+# Copyright 2016 FanFicFare team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -14,6 +14,8 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 #
+# ####### Not all lables are captured. they are not formtted correctly on the 
+# #######  webpage.
 
 # Software: eFiction
 import time
@@ -22,22 +24,18 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
 from base_adapter import BaseSiteAdapter,  makeDate
 
-# This function is called by the downloader in all adapter_*.py files
-# in this dir to register the adapter class.  So it needs to be
-# updated to reflect the class below it.  That, plus getSiteDomain()
-# take care of 'Registering'.
 def getClass():
-    return TheQuidditchPitchOrgAdapter # XXX
+    return AndromedaWebComAdapter # XXX
 
 # Class name has to be unique.  Our convention is camel case the
 # sitename with Adapter at the end.  www is skipped.
-class TheQuidditchPitchOrgAdapter(BaseSiteAdapter): # XXX
+class AndromedaWebComAdapter(BaseSiteAdapter):  # XXX
 
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
@@ -50,47 +48,43 @@ class TheQuidditchPitchOrgAdapter(BaseSiteAdapter): # XXX
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
+
+
         # normalized story URL.
-        # XXX Most sites don't have the  part.  Replace all to remove it usually.
-        self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
+        # XXX Most sites don't have the /fiction part.  Replace all to remove it usually.
+        self._setURL('http://' + self.getSiteDomain() + '/fiction/viewstory.php?sid='+self.story.getMetadata('storyId'))
+
         # Each adapter needs to have a unique site abbreviation.
-        self.story.setMetadata('siteabbrev','tqdpch') # XXX
+        self.story.setMetadata('siteabbrev','awc') # XXX
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = "%m/%d/%Y" # XXX
-            
+        self.dateformat = "%d %b %Y" # XXX
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
-        return 'thequidditchpitch.org' # XXX
-
-    @classmethod
-    def getAcceptDomains(cls):
-        return ['www.thequidditchpitch.org','thequidditchpitch.org']
+        return 'www.andromeda-web.com'  # XXX
 
     @classmethod
     def getSiteExampleURLs(cls):
-        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
+        return "http://"+cls.getSiteDomain()+"/fiction/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
-        return re.escape("http://")+"(www\.)?"+re.escape(self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
+        return re.escape("http://"+self.getSiteDomain()+"/fiction/viewstory.php?sid=")+r"\d+$"
 
     ## Login seems to be reasonably standard across eFiction sites.
     def needToLoginCheck(self, data):
-        if 'Registered Users Only - Not suitable for readers under the age of legal consent in their country.' in data \
+        if 'Registered Users Only' in data \
                 or 'There is no such account on our website' in data \
                 or "That password doesn't match the one in our database" in data:
             return True
         else:
             return False
-        
+
     def performLogin(self, url):
         params = {}
 
@@ -102,13 +96,13 @@ class TheQuidditchPitchOrgAdapter(BaseSiteAdapter): # XXX
             params['password'] = self.getConfig("password")
         params['cookiecheck'] = '1'
         params['submit'] = 'Submit'
-    
+
         loginUrl = 'http://' + self.getSiteDomain() + '/user.php?action=login'
         logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
                                                               params['penname']))
-    
+
         d = self._fetchUrl(loginUrl, params)
-    
+
         if "Member Account" not in d : #Member Account
             logger.info("Failed to login to URL %s as %s" % (loginUrl,
                                                               params['penname']))
@@ -125,7 +119,7 @@ class TheQuidditchPitchOrgAdapter(BaseSiteAdapter): # XXX
             # If the title search below fails, there's a good chance
             # you need a different number.  print data at that point
             # and see what the 'click here to continue' url says.
-            addurl = "&ageconsent=ok&warning=4" # XXX
+            addurl = "&warning=2"
         else:
             addurl=""
 
@@ -147,29 +141,55 @@ class TheQuidditchPitchOrgAdapter(BaseSiteAdapter): # XXX
             self.performLogin(url)
             data = self._fetchUrl(url)
 
-        # The actual text that is used to announce you need to be an
-        # adult varies from site to site.  Again, print data before
-        # the title search to troubleshoot.
-        if ("Not suitable for readers under the age of legal consent in their country." in data \
-                or "Not suitable for readers under 16 yrs. \r\nStories may contain violence, slight nudity, and/or sexual situations." in data ) \
-                and not (self.is_adult or self.getConfig("is_adult")): # XXX 
-            raise exceptions.AdultCheckRequired(self.url)
-            
+        # Since the warning text can change by warning level, let's
+        # look for the warning pass url.  ksarchive uses
+        # &warning= -- actually, so do other sites.  Must be an
+        # eFiction book.
+
+        # fiction/viewstory.php?sid=1882&warning=4
+        # fiction/viewstory.php?sid=1654&ageconsent=ok&warning=2
+        #print data
+        m = re.search(r"'fiction/viewstory.php\?sid=10(&warning=2)'",data)
+        m = re.search(r"'fiction/viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
+        if m != None:
+            if self.is_adult or self.getConfig("is_adult"):
+                # We tried the default and still got a warning, so
+                # let's pull the warning number from the 'continue'
+                # link and reload data.
+                addurl = m.group(1)
+                # correct stupid & error in url.
+                addurl = addurl.replace("&","&")
+                url = self.url+'&index=1'+addurl
+                logger.debug("URL 2nd try: "+url)
+
+                try:
+                    data = self._fetchUrl(url)
+                except urllib2.HTTPError, e:
+                    if e.code == 404:
+                        raise exceptions.StoryDoesNotExist(self.url)
+                    else:
+                        raise e
+            else:
+                raise exceptions.AdultCheckRequired(self.url)
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
             raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
-        #print data
+        soup = self.make_soup(data)
+        # print data
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
+        pagetitle = soup.find('div',{'id':'content'})
+
         ## Title
-        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')))
+        a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+
         self.story.setMetadata('title',stripHTML(a))
-        
+
         # Find authorid and URL from... author url.
-        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
         self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
         self.story.setMetadata('author',a.string)
@@ -177,9 +197,9 @@ class TheQuidditchPitchOrgAdapter(BaseSiteAdapter): # XXX
         # Find the chapters:
         for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
             # just in case there's tags, like <i> in chapter titles.
-            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']+addurl))
+            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/fiction/'+chapter['href']+addurl))
 
-        self.story.setMetadata('numChapters',len(self.chapterUrls))
+            self.story.setMetadata('numChapters',len(self.chapterUrls))
 
         # eFiction sites don't help us out a lot with their meta data
         # formating, so it's a little ugly.
@@ -200,8 +220,8 @@ class TheQuidditchPitchOrgAdapter(BaseSiteAdapter): # XXX
             if 'Summary' in label:
                 ## Everything until the next span class='label'
                 svalue = ""
-                while not defaultGetattr(value,'class') == 'label':
-                    svalue += str(value)
+                while 'label' not in defaultGetattr(value,'class'):
+                    svalue += unicode(value)
                     value = value.nextSibling
                 self.setDescription(url,svalue)
                 #self.story.setMetadata('description',stripHTML(svalue))
@@ -214,28 +234,22 @@ class TheQuidditchPitchOrgAdapter(BaseSiteAdapter): # XXX
 
             if 'Categories' in label:
                 cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
-                catstext = [cat.string for cat in cats]
-                for cat in catstext:
+                for cat in cats:
                     self.story.addToList('category',cat.string)
 
             if 'Characters' in label:
                 chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
-                charstext = [char.string for char in chars]
-                for char in charstext:
+                for char in chars:
                     self.story.addToList('characters',char.string)
 
             if 'Genre' in label:
-                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1')) # XXX
-                genrestext = [genre.string for genre in genres]
-                self.genre = ', '.join(genrestext)
-                for genre in genrestext:
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
+                for genre in genres:
                     self.story.addToList('genre',genre.string)
 
             if 'Warnings' in label:
-                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')) # XXX
-                warningstext = [warning.string for warning in warnings]
-                self.warning = ', '.join(warningstext)
-                for warning in warningstext:
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=3'))
+                for warning in warnings:
                     self.story.addToList('warnings',warning.string)
 
             if 'Completed' in label:
@@ -246,7 +260,7 @@ class TheQuidditchPitchOrgAdapter(BaseSiteAdapter): # XXX
 
             if 'Published' in label:
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
+
             if 'Updated' in label:
                 # there's a stray [ at the end.
                 #value = value[0:-1]
@@ -254,39 +268,35 @@ class TheQuidditchPitchOrgAdapter(BaseSiteAdapter): # XXX
 
         try:
             # Find Series name from series URL.
-            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            a = soup.find('a', href=re.compile(r"fiction/viewseries.php\?seriesid=\d+"))
             series_name = a.string
             series_url = 'http://'+self.host+'/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
-            storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
+            seriessoup = self.make_soup(self._fetchUrl(series_url))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^fiction/viewstory.php\?sid=\d+$'))
             i=1
             for a in storyas:
-                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                if a['href'] == ('fiction/viewstory.php?sid='+self.story.getMetadata('storyId')):
                     self.setSeries(series_name, i)
                     self.story.setMetadata('seriesUrl',series_url)
                     break
                 i+=1
-            
+
         except:
             # I find it hard to care if the series parsing fails
             pass
-            
+        
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        soup = self.make_soup(self._fetchUrl(url))
 
-        # span?  Really?  span?  Yeah... I don't think so.
-        div = soup.find('span', {'style' : 'font-size: 100%;'})
-        div.name='div'
+        div = soup.find('div', {'class' : 'story'})
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_archiveofourownorg.py

@@ -42,35 +42,35 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
                                # Most sites that claim to be
                                # iso-8859-1 (and some that claim to be
                                # utf8) are really windows-1252.
-							   
-							   
+							
+							
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2])
-        
-        
+
+
         # get storyId from url--url validation guarantees query correct
         m = re.match(self.getSiteURLPattern(),url)
         if m:
             self.story.setMetadata('storyId',m.group('id'))
-            
+
             # normalized story URL.
             self._setURL('http://' + self.getSiteDomain() + '/works/'+self.story.getMetadata('storyId'))
         else:
             raise exceptions.InvalidStoryURL(url,
                                              self.getSiteDomain(),
                                              self.getSiteExampleURLs())
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','ao3')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%Y-%b-%d"
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -84,7 +84,7 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
         # http://archiveofourown.org/collections/Smallville_Slash_Archive/works/159770
         # Discard leading zeros from story ID numbers--AO3 doesn't use them in it's own chapter URLs.
         return r"https?://"+re.escape(self.getSiteDomain())+r"(/collections/[^/]+)?/works/0*(?P<id>\d+)"
-        
+
     ## Login
     def needToLoginCheck(self, data):
         if 'This work is only available to registered users of the Archive.' in data \
@@ -92,7 +92,7 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
             return True
         else:
             return False
-        
+
     def performLogin(self, url, data):
 
         params = {}
@@ -110,10 +110,10 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
         loginUrl = 'http://' + self.getSiteDomain() + '/user_sessions'
         logger.info("Will now login to URL (%s) as (%s)" % (loginUrl,
                                                             params['user_session[login]']))
-    
+
         d = self._postUrl(loginUrl, params)
         #logger.info(d)
-    
+
         if "Successfully logged in" not in d : #Member Account
             logger.info("Failed to login to URL %s as %s" % (loginUrl,
                                                               params['user_session[login]']))
@@ -148,7 +148,7 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
 
             if "This work could have adult content. If you proceed you have agreed that you are willing to see such content." in meta:
                 raise exceptions.AdultCheckRequired(self.url)
-            
+
         except urllib2.HTTPError, e:
             if e.code == 404:
                 raise exceptions.StoryDoesNotExist(self.url)
@@ -157,13 +157,13 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
 
         if "Sorry, we couldn&#x27;t find the work you were looking for." in data:
             raise exceptions.StoryDoesNotExist(self.url)
-            
+
         if self.needToLoginCheck(data):
             # need to log in for this one.
             self.performLogin(url,data)
             data = self._fetchUrl(url,usecache=False)
             meta = self._fetchUrl(metaurl,usecache=False)
-            
+
         # use BeautifulSoup HTML parser to make everything easier to find.
         soup = self.make_soup(data)
         for tag in soup.findAll('div',id='admin-banner'):
@@ -173,7 +173,7 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
             tag.extract()
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
         ## Title
         a = soup.find('a', href=re.compile(r"/works/\d+$"))
         self.story.setMetadata('title',stripHTML(a))
@@ -190,6 +190,10 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
                 self.story.addToList('authorUrl',a['href'])
                 self.story.addToList('author',a.text)
 
+        byline = metasoup.find('h3',{'class':'byline'})
+        if byline:
+            self.story.setMetadata('byline',stripHTML(byline))
+
         newestChapter = None
         self.newestChapterNum = None # save for comparing during update.
         # Scan all chapters to find the oldest and newest, on AO3 it's
@@ -242,7 +246,7 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
             genres = a.findAll('a',{'class':"tag"})
             for genre in genres:
                 self.story.addToList('freeformtags',genre.string)
-                
+
         a = metasoup.find('dd',{'class':"category tags"})
         if a != None:
             genres = a.findAll('a',{'class':"tag"})
@@ -255,7 +259,7 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
             chars = a.findAll('a',{'class':"tag"})
             for char in chars:
                 self.story.addToList('characters',char.string)
-                
+
         a = metasoup.find('dd',{'class':"relationship tags"})
         if a != None:
             ships = a.findAll('a',{'class':"tag"})
@@ -300,7 +304,7 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
             if 'Published' in label:
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
                 self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
-            
+
             if 'Updated' in label:
                 self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
 				
@@ -343,7 +347,7 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
             new_tag = soup.new_tag(tag)
             new_tag.string=string
             elem.append(new_tag)
-    
+
         if 'authorheadnotes' not in exclude_notes:
             headnotes = soup.find('div', {'class' : "preface group"}).find('div', {'class' : "notes module"})
             if headnotes != None:
@@ -351,14 +355,14 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
                 if headnotes != None:
                     append_tag(chapter,'b',"Author's Note:")
                     chapter.append(headnotes)
-        
+
         if 'chaptersummary' not in exclude_notes:
             chapsumm = soup.find('div', {'id' : "summary"})
             if chapsumm != None:
                 chapsumm = chapsumm.find('blockquote')
                 append_tag(chapter,'b',"Summary for the Chapter:")
                 chapter.append(chapsumm)
-                
+
         if 'chapterheadnotes' not in exclude_notes:
             chapnotes = soup.find('div', {'id' : "notes"})
             if chapnotes != None:

fanficfare/adapters/adapter_archiveskyehawkecom.py

@@ -21,7 +21,7 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -46,21 +46,21 @@ class ArchiveSkyeHawkeComAdapter(BaseSiteAdapter):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
+
+
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/story.php?no='+self.story.getMetadata('storyId'))
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','ash')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%Y-%m-%d"
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -92,23 +92,23 @@ class ArchiveSkyeHawkeComAdapter(BaseSiteAdapter):
                 raise e
 
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
         ## Title
         a = soup.find('div', {'class':"story border"}).find('span',{'class':'left'})
         title=stripHTML(a).split('"')[1]
         self.story.setMetadata('title',title)
-        
+
         # Find authorid and URL from... author url.
         author = a.find('a')
         self.story.setMetadata('authorId',author['href'].split('=')[1])
         self.story.setMetadata('authorUrl','http://'+self.host+'/'+author['href'])
         self.story.setMetadata('author',author.string)
 		
-        authorSoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
+        authorSoup = self.make_soup(self._fetchUrl(self.story.getMetadata('authorUrl')))
 		
         chapter=soup.find('select',{'name':'chapter'}).findAll('option')
 	
@@ -174,18 +174,17 @@ class ArchiveSkyeHawkeComAdapter(BaseSiteAdapter):
                 break
 	
 	
-            
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
+        soup = self.make_soup(self._fetchUrl(url))
+
         div = soup.find('div',{'class':"chapter bordersolid"}).findNext('div').findNext('div')
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_artemisfowlcom.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2013 Fanficdownloader team, 2015 FanFicFare team
+# Copyright 2016 FanFicFare team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -14,6 +14,8 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 #
+# ####### Not all lables are captured. they are not formtted correctly on the 
+# #######  webpage.
 
 # Software: eFiction
 import time
@@ -22,18 +24,18 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
 from base_adapter import BaseSiteAdapter,  makeDate
 
 def getClass():
-    return ScarHeadNetAdapter
+    return ArtemisFowlComAdapter # XXX
 
 # Class name has to be unique.  Our convention is camel case the
 # sitename with Adapter at the end.  www is skipped.
-class ScarHeadNetAdapter(BaseSiteAdapter):
+class ArtemisFowlComAdapter(BaseSiteAdapter):  # XXX
 
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
@@ -46,32 +48,33 @@ class ScarHeadNetAdapter(BaseSiteAdapter):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
+
+
         # normalized story URL.
-        self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
+        # XXX Most sites don't have the /fiction part.  Replace all to remove it usually.
+        self._setURL('http://' + self.getSiteDomain() + '/fanfiction/viewstory.php?sid='+self.story.getMetadata('storyId'))
+
         # Each adapter needs to have a unique site abbreviation.
-        self.story.setMetadata('siteabbrev','shn')
+        self.story.setMetadata('siteabbrev','afcff') # XXX
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = "%d/%m/%y"
-            
+        self.dateformat = "%d/%m/%y" # XXX
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
-        return 'scarhead.net'
+        return 'www.artemis-fowl.com'  # XXX
 
     @classmethod
     def getSiteExampleURLs(cls):
-        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
+        return "http://"+cls.getSiteDomain()+"/fanfiction/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
-        return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
+        return re.escape("http://"+self.getSiteDomain()+"/fanfiction/viewstory.php?sid=")+r"\d+$"
 
     ## Login seems to be reasonably standard across eFiction sites.
     def needToLoginCheck(self, data):
@@ -81,7 +84,7 @@ class ScarHeadNetAdapter(BaseSiteAdapter):
             return True
         else:
             return False
-        
+
     def performLogin(self, url):
         params = {}
 
@@ -93,13 +96,13 @@ class ScarHeadNetAdapter(BaseSiteAdapter):
             params['password'] = self.getConfig("password")
         params['cookiecheck'] = '1'
         params['submit'] = 'Submit'
-    
+
         loginUrl = 'http://' + self.getSiteDomain() + '/user.php?action=login'
         logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
                                                               params['penname']))
-    
+
         d = self._fetchUrl(loginUrl, params)
-    
+
         if "Member Account" not in d : #Member Account
             logger.info("Failed to login to URL %s as %s" % (loginUrl,
                                                               params['penname']))
@@ -116,7 +119,7 @@ class ScarHeadNetAdapter(BaseSiteAdapter):
             # If the title search below fails, there's a good chance
             # you need a different number.  print data at that point
             # and see what the 'click here to continue' url says.
-            addurl = "&ageconsent=ok&warning=5"
+            addurl = "&warning=5"
         else:
             addurl=""
 
@@ -137,17 +140,17 @@ class ScarHeadNetAdapter(BaseSiteAdapter):
             # need to log in for this one.
             self.performLogin(url)
             data = self._fetchUrl(url)
-            
+
         # Since the warning text can change by warning level, let's
         # look for the warning pass url.  ksarchive uses
         # &warning= -- actually, so do other sites.  Must be an
         # eFiction book.
-            
-        # viewstory.php?sid=1882&warning=4
-        # viewstory.php?sid=1654&ageconsent=ok&warning=5
+
+        # fanfiction/viewstory.php?sid=1882&warning=4
+        # fanfiction/viewstory.php?sid=1654&ageconsent=ok&warning=2
         #print data
-        #m = re.search(r"'viewstory.php\?sid=1882(&warning=4)'",data)
-        m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
+        m = re.search(r"'fanfiction/viewstory.php\?sid=10(&warning=5)'",data)
+        m = re.search(r"'fanfiction/viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
         if m != None:
             if self.is_adult or self.getConfig("is_adult"):
                 # We tried the default and still got a warning, so
@@ -165,25 +168,26 @@ class ScarHeadNetAdapter(BaseSiteAdapter):
                     if e.code == 404:
                         raise exceptions.StoryDoesNotExist(self.url)
                     else:
-                        raise e    
+                        raise e
             else:
                 raise exceptions.AdultCheckRequired(self.url)
-            
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
             raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
 
-        pagetitle = soup.find('tr',{'valign':'top'})
-        
+        pagetitle = soup.find('div',{'id':'pagetitle'})
+
         ## Title
         a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+
         self.story.setMetadata('title',stripHTML(a))
-        
+
         # Find authorid and URL from... author url.
         a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
@@ -193,108 +197,106 @@ class ScarHeadNetAdapter(BaseSiteAdapter):
         # Find the chapters:
         for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
             # just in case there's tags, like <i> in chapter titles.
-            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']+addurl))
+            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/fanfiction/'+chapter['href']+addurl))
 
-        self.story.setMetadata('numChapters',len(self.chapterUrls))
+            self.story.setMetadata('numChapters',len(self.chapterUrls))
 
         # eFiction sites don't help us out a lot with their meta data
         # formating, so it's a little ugly.
-        
-        cats = soup.findAll('a',href=re.compile(r'browse.php\?type=categories'))
-        for cat in cats:
-            if '/' == cat.string[0]:
-                self.story.addToList('ships','Harry Potter'+cat.string.split('(')[0])
-            elif 'Harry' in cat.string:
-                self.story.addToList('ships',cat.string.split('(')[0])
-            else:
-                self.story.addToList('category',cat.string)
-            if '(' in cat.string:
-                self.story.addToList('category',cat.string.split('(')[1].split(')')[0])
-            
-                
-            
 
-        chars = soup.findAll('a',href=re.compile(r'browse.php\?type=characters'))
-        for char in chars:
-            self.story.addToList('characters',char.string)
-
-        genres = soup.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2'))
-        for genre in genres:
-            self.story.addToList('genre',genre.string)
-
-        warnings = soup.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
-        for warning in warnings:
-            self.story.addToList('warnings',warning.string)
-            
-        textsoup = stripHTML(soup)
-
-        a = textsoup.split('Published: ')[1].split(' ')[0]
-        self.story.setMetadata('datePublished', makeDate(stripHTML(a), self.dateformat))
-        a = textsoup.split('Updated: ')[1].split(' ')[0]
-        self.story.setMetadata('dateUpdated', makeDate(stripHTML(a), self.dateformat))
-        a = textsoup.split('Rating: ')[1].split(' ')[0]
-        self.story.setMetadata('rating', a)
-        a = textsoup.split('Length: ')[1].split('(')[1].split(' ')[0]
-        self.story.setMetadata('numWords', a)
-        a = textsoup.split('Completed: ')[1].split(' ')[0]
-        if 'Yes' in a:
-            self.story.setMetadata('status', 'Completed')
-        else:
-            self.story.setMetadata('status', 'In-Progress')
-        #a = textsoup.split('Summary: ')[1].split('Add Story to Favorites')[0]
-        #self.setDescription(url,a)
-        
-
-        
-        a=soup.find(text=re.compile("Summary: "))
-        i=0
-        svalue = ""
-        while i == 0:
+        # utility method
+        def defaultGetattr(d,k):
             try:
-                b = str(a)
-                svalue += b.split('Summary: ')[1]
+                return d[k]
             except:
-                svalue += str(a)
-            if a.nextSibling != None:
-                a = a.nextSibling
-            else:
-                a = a.parent.nextSibling
-            if 'Disclaimer: ' in stripHTML(a):
-                i=1
-        self.setDescription(url,svalue)
+                return ""
+
+        # <span class="label">Rated:</span> NC-17<br /> etc
+        labels = soup.findAll('span',{'class':'label'})
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.string
+
+            if 'Summary' in label:
+                ## Everything until the next span class='label'
+                svalue = ""
+                while 'label' not in defaultGetattr(value,'class'):
+                    svalue += unicode(value)
+                    value = value.nextSibling
+                self.setDescription(url,svalue)
+                #self.story.setMetadata('description',stripHTML(svalue))
+
+            if 'Rated' in label:
+                self.story.setMetadata('rating', value)
+
+            if 'Word count' in label:
+                self.story.setMetadata('numWords', value)
+
+            if 'Categories' in label:
+                cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
+                for cat in cats:
+                    self.story.addToList('category',cat.string)
+
+            if 'Characters' in label:
+                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+                for char in chars:
+                    self.story.addToList('characters',char.string)
+
+            if 'Genre' in label:
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
+                for genre in genres:
+                    self.story.addToList('genre',genre.string)
+
+            if 'Warnings' in label:
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=3'))
+                for warning in warnings:
+                    self.story.addToList('warnings',warning.string)
+
+            if 'Completed' in label:
+                if 'Yes' in value:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+
+            if 'Published' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+
+            if 'Updated' in label:
+                # there's a stray [ at the end.
+                #value = value[0:-1]
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
 
         try:
             # Find Series name from series URL.
-            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            a = soup.find('a', href=re.compile(r"fanfiction/viewseries.php\?seriesid=\d+"))
             series_name = a.string
             series_url = 'http://'+self.host+'/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
-            storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
+            seriessoup = self.make_soup(self._fetchUrl(series_url))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^fanfiction/viewstory.php\?sid=\d+$'))
             i=1
             for a in storyas:
-                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                if a['href'] == ('fanfiction/viewstory.php?sid='+self.story.getMetadata('storyId')):
                     self.setSeries(series_name, i)
                     self.story.setMetadata('seriesUrl',series_url)
                     break
                 i+=1
-            
+
         except:
             # I find it hard to care if the series parsing fails
             pass
-            
+        
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
+        soup = self.make_soup(self._fetchUrl(url))
+
         div = soup.find('div', {'id' : 'story'})
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_ashwindersycophanthexcom.py

@@ -22,7 +22,7 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -46,22 +46,22 @@ class AshwinderSycophantHexComAdapter(BaseSiteAdapter):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
+
 		
-        
+
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','asph')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%m/%d/%Y"
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -77,11 +77,12 @@ class AshwinderSycophantHexComAdapter(BaseSiteAdapter):
     ## Login seems to be reasonably standard across eFiction sites.
     def needToLoginCheck(self, data):
         if 'This story contains adult content and/or themes.' in data \
-                or "That password doesn't match the one in our database" in data:
+                or "That password doesn't match the one in our database" in data \
+                or "Member Login" in data:
             return True
         else:
             return False
-        
+
     def performLogin(self, url):
         params = {}
 
@@ -95,13 +96,13 @@ class AshwinderSycophantHexComAdapter(BaseSiteAdapter):
         params['sid'] = ''
         params['intent'] = ''
         params['submit'] = 'Submit'
-    
+
         loginUrl = 'http://' + self.getSiteDomain() + '/user.php'
         logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
                                                               params['penname']))
-    
+
         d = self._fetchUrl(loginUrl, params)
-    
+
         if "Logout" not in d : #Member Account
             logger.info("Failed to login to URL %s as %s" % (loginUrl,
                                                               params['penname']))
@@ -129,29 +130,29 @@ class AshwinderSycophantHexComAdapter(BaseSiteAdapter):
             # need to log in for this one.
             self.performLogin(url)
             data = self._fetchUrl(url)
-            
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
-            
+
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
         self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
         self.story.setMetadata('author',a.string)
-        asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
+        asoup = self.make_soup(self._fetchUrl(self.story.getMetadata('authorUrl')))
 		
         try:
             # in case link points somewhere other than the first chapter
             a = soup.findAll('option')[1]['value']
             self.story.setMetadata('storyId',a.split('=',)[1])
             url = 'http://'+self.host+'/'+a
-            soup = bs.BeautifulSoup(self._fetchUrl(url))
+            soup = self.make_soup(self._fetchUrl(url))
         except:
             pass
 		
@@ -194,7 +195,7 @@ class AshwinderSycophantHexComAdapter(BaseSiteAdapter):
             val = val.nextSibling
         val = val.nextSibling
         while not defaultGetattr(val) == 'table':
-            svalue += str(val)
+            svalue += unicode(val)
             val = val.nextSibling
         self.setDescription(url,svalue)
 
@@ -230,13 +231,13 @@ class AshwinderSycophantHexComAdapter(BaseSiteAdapter):
 
             if 'Published' in label:
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
+
             if 'Updated' in label:
                 # there's a stray [ at the end.
                 #value = value[0:-1]
                 self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
 
-            
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
@@ -244,11 +245,11 @@ class AshwinderSycophantHexComAdapter(BaseSiteAdapter):
 		
         data = self._fetchUrl(url)
 
-        soup = bs.BeautifulSoup(data, selfClosingTags=('br','hr','span','center')) # some chapters seem to be hanging up on those tags, so it is safer to close them
-        
+        soup = self.make_soup(data) # some chapters seem to be hanging up on those tags, so it is safer to close them
+
         story = soup.find('div', {"align" : "left"})
 
         if None == story:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,story)

fanficfare/adapters/adapter_asr3slashzoneorg.py

@@ -22,7 +22,7 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -44,21 +44,21 @@ class Asr3SlashzoneOrgAdapter(BaseSiteAdapter):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
+
+
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/archive/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','asr3')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%d/%m/%y"
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -114,23 +114,23 @@ class Asr3SlashzoneOrgAdapter(BaseSiteAdapter):
                     if e.code == 404:
                         raise exceptions.StoryDoesNotExist(self.url)
                     else:
-                        raise e    
+                        raise e
             else:
                 raise exceptions.AdultCheckRequired(self.url)
-            
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         #print data
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',stripHTML(a))
-        
+
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
@@ -158,7 +158,7 @@ class Asr3SlashzoneOrgAdapter(BaseSiteAdapter):
         categorys = smalldiv.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
         for category in categorys:
             self.story.addToList('category',category.string)
-        
+
         chars = smalldiv.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
         for char in chars:
             self.story.addToList('characters',char.string)
@@ -191,7 +191,7 @@ class Asr3SlashzoneOrgAdapter(BaseSiteAdapter):
             series_url = 'http://'+self.host+'/archive/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            seriessoup = self.make_soup(self._fetchUrl(series_url))
             # can't use ^viewstory...$ in case of higher rated stories with javascript href.
             storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+'))
             i=1
@@ -203,25 +203,25 @@ class Asr3SlashzoneOrgAdapter(BaseSiteAdapter):
                         self.story.setMetadata('seriesUrl',series_url)
                         break
                     i+=1
-            
+
         except:
             # I find it hard to care if the series parsing fails
             pass
-            
+
         # remove 'small' leaving only summary.
         smalldiv.extract()
         self.setDescription(url,metadiv)
-        
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulSoup(self._fetchUrl(url))
-        
+        soup = self.make_soup(self._fetchUrl(url))
+
         div = soup.find('div', {'id' : 'story'})
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_bdsmgeschichten.py

@@ -1,346 +0,0 @@
-# -*- coding: utf-8 -*-
-
-# Copyright 2014 Fanficdownloader team, 2015 FanFicFare team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-#
-
-import time
-import logging
-logger = logging.getLogger(__name__)
-import re
-import urllib2
-import urlparse
-import time
-
-from .. import BeautifulSoup as bs
-from .. import exceptions as exceptions
-
-from base_adapter import BaseSiteAdapter, makeDate
-
-def _translate_date_german_english(date):
-    fullmon = {"Januar":"01",
-               "Februar":"02",
-               u"März":"03",
-               "April":"04",
-               "Mai":"05",
-               "Juni":"06",
-               "Juli":"07",
-               "August":"08",
-               "September":"09",
-               "Oktober":"10",
-               "November":"11",
-               "Dezember":"12"}
-    for (name,num) in fullmon.items():
-        date = date.replace(name,num)
-    return date
-
-_REGEX_TRAILING_DIGIT = re.compile("(\d+)$")
-_REGEX_DASH_TO_END = re.compile("-[^-]+$")
-_REGEX_CHAPTER_TITLE = re.compile(ur"""
-    \s*
-    [\u2013-]?
-    \s*
-    ([\dIVX-]+)?
-    \.?
-    \s*
-    [\[\(]?
-    \s*
-    (Teil|Kapitel|Tag)?
-    \s*
-    ([\dIVX-]+)?
-    \s*
-    [\]\)]?
-    \s*
-    $
-""", re.VERBOSE)
-_INITIAL_STEP = 5
-
-class BdsmGeschichtenAdapter(BaseSiteAdapter):
-
-    def __init__(self, config, url):
-        BaseSiteAdapter.__init__(self, config, url)
-
-        self.decode = ["utf8", "Windows-1252"]
-
-        self.story.setMetadata('siteabbrev','bdsmgesch')
-
-        # Replace possible chapter numbering
-        chapterMatch = _REGEX_TRAILING_DIGIT.search(url)
-        if chapterMatch is None:
-            self.maxChapter = 1
-        else:
-            self.maxChapter = int(chapterMatch.group(1))
-        # url = re.sub(_REGEX_TRAILING_DIGIT, "1", url)
-
-        # set storyId
-        self.story.setMetadata('storyId', re.compile(self.getSiteURLPattern()).match(url).group('storyId'))
-
-        # normalize URL
-        self._setURL('http://%s/%s' % (self.getSiteDomain(), self.story.getMetadata('storyId')))
-
-        self.dateformat = '%d. %m %Y - %H:%M'
-
-    @staticmethod
-    def getSiteDomain():
-        return 'bdsm-geschichten.net'
-
-    @classmethod
-    def getAcceptDomains(cls):
-        return ['www.bdsm-geschichten.net', 'www.bdsm-geschichten.net']
-
-    @classmethod
-    def getSiteExampleURLs(cls):
-        return "http://www.bdsm-geschichten.net/title-of-story-1 http://bdsm-geschichten.net/title-of-story-1"
-
-    def getSiteURLPattern(self):
-        return r"http://(www\.)?bdsm-geschichten.net/(?P<storyId>[a-zA-Z0-9_-]+)"
-
-    def extractChapterUrlsAndMetadata(self):
-
-        if not (self.is_adult or self.getConfig("is_adult")):
-            raise exceptions.AdultCheckRequired(self.url)
-
-        try:
-            data1 = self._fetchUrl(self.url)
-            soup = bs.BeautifulSoup(data1)
-        except urllib2.HTTPError, e:
-            if e.code == 404:
-                raise exceptions.StoryDoesNotExist(self.url)
-            else:
-                raise e
-
-        #strip comments from soup
-        [comment.extract() for comment in soup.findAll(text=lambda text:isinstance(text, bs.Comment))]
-
-        # Cache the soups so we won't have to redownload in getChapterText later
-        self.soupsCache = {}
-        self.soupsCache[self.url] = soup
-
-        # author
-        authorDiv = soup.find("div", "author-pane-line author-name")
-        authorId = authorDiv.string.strip()
-        self.story.setMetadata('authorId', authorId)
-        self.story.setMetadata('author', authorId)
-        # TODO not really true need to be loggedin for this to work or fetch userid
-        self.story.setMetadata('authorUrl','http://'+self.host+'/'+authorId)
-
-        # TODO better metadata
-        date = soup.find("div", {"class": "submitted"}).string.strip()
-        date = re.sub(" &#151;.*", "", date)
-        date = _translate_date_german_english(date)
-        self.story.setMetadata('datePublished', makeDate(date, self.dateformat))
-        title1 = soup.find("h1", {'class': 'title'}).string
-
-
-        for tagLink in soup.find("ul", "taxonomy").findAll("a"):
-            self.story.addToList('category', tagLink.string)
-
-        ## Retrieve chapter soups
-        if self.getConfig('find_chapters') == 'guess':
-            self.chapterUrls = []
-            self._find_chapters_by_guessing(title1)
-        else:
-            self._find_chapters_by_parsing(soup)
-
-        firstChapterUrl = self.chapterUrls[0][1]
-        if firstChapterUrl in self.soupsCache:
-            firstChapterSoup = self.soupsCache[firstChapterUrl]
-            h1 = firstChapterSoup.find("h1").text
-        else:
-            h1 = soup.find("h1").text
-
-        h1 = re.sub(_REGEX_CHAPTER_TITLE, "", h1)
-        self.story.setMetadata('title', h1)
-        self.story.setMetadata('numChapters', len(self.chapterUrls))
-        return
-
-    def _find_chapters_by_parsing(self, soup):
-
-        # store original soup
-        origSoup = soup
-
-        #
-        # find first chapter
-        #
-        firstLink = None
-        firstLinkDiv = soup.find("div", "field-field-erster-teil")
-        if firstLinkDiv is not None:
-            firstLink = "http://%s%s" % (self.getSiteDomain(), firstLinkDiv.findNext("a")['href'])
-            logger.debug("Found first chapter right away <%s>" % firstLink)
-            try:
-                soup = bs.BeautifulSoup(self._fetchUrl(firstLink))
-                self.soupsCache[firstLink] = soup
-                self.chapterUrls.insert(0, (soup.find("h1").text, firstLink))
-            except urllib2.HTTPError, e:
-                if e.code == 404:
-                    raise exceptions.StoryDoesNotExist(self.url)
-                else:
-                    raise exceptions.StoryDoesNotExist(firstLink)
-        else:
-            logger.debug("DIDN'T find first chapter right away")
-            # parse previous Link until first
-            while True:
-                prevLink = None
-                prevLinkDiv = soup.find("div", "field-field-vorheriger-teil")
-                if prevLinkDiv is not None:
-                    prevLink = prevLinkDiv.find("a")
-                if prevLink is None:
-                    prevLink = soup.find("a", text=re.compile("&lt;&lt;&lt;")) # <<<
-                if prevLink is None:
-                    logger.debug("Couldn't find prev part")
-                    break
-                else:
-                    logger.debug("Previous Chapter <%s>" % prevLink)
-                    if type(prevLink) != bs.Tag or prevLink.name != "a":
-                        prevLink = prevLink.findParent("a")
-                    if prevLink is None or '#' in prevLink['href']:
-                        logger.debug("Couldn't find prev part (false positive) <%s>" % prevLink)
-                        break
-                    prevLink = prevLink['href']
-                try:
-                    soup = bs.BeautifulSoup(self._fetchUrl(prevLink))
-                    self.soupsCache[prevLink] = soup
-                    prevTtitle = soup.find("h1", {'class': 'title'}).string
-                    self.chapterUrls.insert(0, (prevTtitle, prevLink))
-                except urllib2.HTTPError, e:
-                    if e.code == 404:
-                        raise exceptions.StoryDoesNotExist(nextLink)
-                    else:
-                        raise e
-                firstLink = prevLink
-
-        # if first chapter couldn't be determined, assume the URL originally
-        # passed is the first chapter
-        if firstLink is None:
-            logger.debug("Couldn't set first chapter")
-            firstLink = self.url
-            self.chapterUrls.insert(0, (soup.find("h1").text, firstLink))
-
-        # set first URL
-        logger.debug("Set first link: %s" % firstLink)
-        self._setURL(firstLink)
-        self.story.setMetadata('storyId', re.compile(self.getSiteURLPattern()).match(firstLink).group('storyId'))
-
-        #
-        # Parse next chapters
-        #
-        while True:
-            nextLink = None
-            nextLinkDiv = soup.find("div", "field-field-naechster-teil")
-            if nextLinkDiv is not None:
-                nextLink = nextLinkDiv.find("a")
-            if nextLink is None:
-                nextLink = soup.find("a", text=re.compile("&gt;&gt;&gt;"))
-            if nextLink is None:
-                nextLink = soup.find("a", text=re.compile("Fortsetzung"))
-
-            if nextLink is None:
-                logger.debug("Couldn't find next part")
-                break
-            else:
-                if type(nextLink) != bs.Tag or nextLink.name != "a":
-                    nextLink = nextLink.findParent("a")
-                if nextLink is None or '#' in nextLink['href']:
-                    logger.debug("Couldn't find next part (false positive) <%s>" % nextLink)
-                    break
-                nextLink = nextLink['href']
-
-            if not nextLink.startswith('http:'):
-                nextLink = 'http://' + self.getSiteDomain() + nextLink
-
-            for loadedChapter in self.chapterUrls:
-                if loadedChapter[0] == nextLink:
-                    logger.debug("ERROR: Repeating chapter <%s> Try to fix it" % nextLink)
-                    nextLinkMatch = _REGEX_TRAILING_DIGIT.match(nextLink)
-                    if nextLinkMatch is not None:
-                        curChap = nextLinkMatch.group(1)
-                        nextLink = re.sub(_REGEX_TRAILING_DIGIT, str(int(curChap) + 1), nextLink)
-                    else:
-                        break
-            try:
-                data = self._fetchUrl(nextLink)
-                soup = bs.BeautifulSoup(data)
-            except urllib2.HTTPError, e:
-                if e.code == 404:
-                    raise exceptions.StoryDoesNotExist(nextLink)
-                else:
-                    raise e
-            title2 = soup.find("h1", {'class': 'title'}).string
-            self.chapterUrls.append((title2, nextLink))
-            logger.debug("Grabbing next chapter URL " + nextLink)
-            self.soupsCache[nextLink] = soup
-            # [comment.extract() for comment in soup.findAll(text=lambda text:isinstance(text, bs.Comment))]
-        logger.debug("Chapters: %s" % self.chapterUrls)
-
-
-    def _find_chapters_by_guessing(self, title1):
-        step = _INITIAL_STEP
-        curMax = self.maxChapter + step
-        lastHit = True
-        while True:
-            nextChapterUrl = re.sub(_REGEX_TRAILING_DIGIT, str(curMax), self.url) 
-            if nextChapterUrl == self.url:
-                logger.debug("Unable to guess next chapter because URL doesn't end in numbers")
-                break;
-            try:
-                logger.debug("Trying chapter URL " + nextChapterUrl)
-                data = self._fetchUrl(nextChapterUrl)
-                hit = True
-            except urllib2.HTTPError, e:
-                if e.code == 404:
-                    hit = False
-                else:
-                    raise e
-            if hit:
-                logger.debug("Found chapter URL " + nextChapterUrl)
-                self.maxChapter = curMax
-                self.soupsCache[nextChapterUrl] = bs.BeautifulSoup(data)
-                if not lastHit:
-                    break
-                lastHit = curMax
-                curMax += step
-            else:
-                lastHit = False
-                curMax -= 1
-            logger.debug(curMax)
-
-        for i in xrange(1, self.maxChapter):
-            nextChapterUrl = re.sub(_REGEX_TRAILING_DIGIT, str(i), self.url)
-            nextChapterTitle = re.sub("1", str(i), title1)
-            self.chapterUrls.append((nextChapterTitle, nextChapterUrl))
-
-    def getChapterText(self, url):
-
-        if url in self.soupsCache:
-            logger.debug('Getting chapter <%s> from cache' % url)
-            soup = self.soupsCache[url]
-        else:
-            logger.debug('Downloading chapter <%s>' % url)
-            data1 = self._fetchUrl(url)
-            soup = bs.BeautifulSoup(data1)
-            #strip comments from soup
-            [comment.extract() for comment in soup.findAll(text=lambda text:isinstance(text, bs.Comment))]
-
-        # get story text
-        storyDiv1 = bs.Tag(soup, "div")
-        for para in soup.find("div", "full-node").find('div', 'content').findAll("p"):
-            storyDiv1.append(para)
-        storyDiv1.append('<br />')
-        storytext = self.utf8FromSoup(url,storyDiv1)
-
-        return storytext
-
-
-def getClass():
-    return BdsmGeschichtenAdapter

fanficfare/adapters/adapter_bloodshedversecom.py

@@ -3,7 +3,7 @@ import re
 import urllib2
 import urlparse
 
-from .. import BeautifulSoup
+from bs4 import BeautifulSoup
 from ..htmlcleanup import stripHTML
 
 from base_adapter import BaseSiteAdapter, makeDate
@@ -28,7 +28,7 @@ class BloodshedverseComAdapter(BaseSiteAdapter):
     READ_URL_TEMPLATE = BASE_URL + 'stories.php?go=read&no=%s'
 
     STARTED_DATETIME_FORMAT = '%m/%d/%Y'
-    UPDATED_DATETIME_FORMAT = '%m/%d/%Y %I:%M'
+    UPDATED_DATETIME_FORMAT = '%m/%d/%Y %I:%M %p'
 
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
@@ -51,7 +51,7 @@ class BloodshedverseComAdapter(BaseSiteAdapter):
         else:
             data = self._fetchUrl(url, parameters)
 
-        return BeautifulSoup.BeautifulSoup(data)
+        return self.make_soup(data)
 
     @staticmethod
     def getSiteDomain():
@@ -62,7 +62,7 @@ class BloodshedverseComAdapter(BaseSiteAdapter):
         return cls.READ_URL_TEMPLATE % 1234
 
     def getSiteURLPattern(self):
-        return re.escape(self.BASE_URL + 'stories.php?go=') + r'(read|chapters)\&no=\d+$'
+        return re.escape(self.BASE_URL + 'stories.php?go=') + r'(read|chapters)\&(amp;)?no=\d+$'
 
     # Override stripURLParameters so the "no" parameter won't get stripped
     @classmethod
@@ -168,14 +168,8 @@ class BloodshedverseComAdapter(BaseSiteAdapter):
                     self.story.setMetadata('datePublished', makeDate(value, self.STARTED_DATETIME_FORMAT))
 
                 elif key == 'Updated':
-                    date_string, period = value.rsplit(' ', 1)
-                    date = makeDate(date_string, self.UPDATED_DATETIME_FORMAT)
-
-                    # Rather ugly hack to work around Calibre's changing of
-                    # Python's locale setting, causing am/pm to not be properly
-                    # parsed by strptime() when using a non-english locale
-                    if period == 'pm':
-                        date += timedelta(hours=12)
+                    date = makeDate(value, self.UPDATED_DATETIME_FORMAT)
+                    # ugly %p(am/pm) hack moved into makeDate so other sites can use it.
                     self.story.setMetadata('dateUpdated', date)
 
         if self.story.getMetadata('rating') == 'NC-17' and not (self.is_adult or self.getConfig('is_adult')):

fanficfare/adapters/adapter_bloodtiesfancom.py

@@ -22,7 +22,7 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+from bs4.element import Tag
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -68,22 +68,22 @@ class BloodTiesFansComAdapter(BaseSiteAdapter): # XXX
                                # iso-8859-1 (and some that claim to be
                                # utf8) are really windows-1252.
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
+
+
         # normalized story URL.
         # XXX Most sites don't have the /fanfic part.  Replace all to remove it usually.
         self._setURL('http://' + self.getSiteDomain() + '/fiction/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','btf') # XXX
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%d %b %Y" # XXX
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -104,7 +104,7 @@ class BloodTiesFansComAdapter(BaseSiteAdapter): # XXX
             return True
         else:
             return False
-        
+
     def performLogin(self, url):
         params = {}
 
@@ -116,13 +116,13 @@ class BloodTiesFansComAdapter(BaseSiteAdapter): # XXX
             params['password'] = self.getConfig("password")
         params['cookiecheck'] = '1'
         params['submit'] = 'Submit'
-    
+
         loginUrl = 'http://' + self.getSiteDomain() + '/fiction/user.php?action=login'
         logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
                                                               params['penname']))
-    
+
         d = self._fetchUrl(loginUrl, params)
-    
+
         if "Member Account" not in d : #Member Account
             logger.info("Failed to login to URL %s as %s" % (loginUrl,
                                                               params['penname']))
@@ -160,16 +160,16 @@ class BloodTiesFansComAdapter(BaseSiteAdapter): # XXX
                 raise exceptions.StoryDoesNotExist(self.url)
             else:
                 raise e
-            
+
         # The actual text that is used to announce you need to be an
         # adult varies from site to site.  Again, print data before
         # the title search to troubleshoot.
-            
+
         # Since the warning text can change by warning level, let's
         # look for the warning pass url.  nfacommunity uses
         # &warning= -- actually, so do other sites.  Must be an
         # eFiction book.
-            
+
         # viewstory.php?sid=561&warning=4
         # viewstory.php?sid=561&warning=1
         # viewstory.php?sid=561&warning=2
@@ -193,23 +193,23 @@ class BloodTiesFansComAdapter(BaseSiteAdapter): # XXX
                     if e.code == 404:
                         raise exceptions.StoryDoesNotExist(self.url)
                     else:
-                        raise e    
+                        raise e
             else:
                 raise exceptions.AdultCheckRequired(self.url)
-            
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',stripHTML(a))
-        
+
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
@@ -243,8 +243,8 @@ class BloodTiesFansComAdapter(BaseSiteAdapter): # XXX
             if 'Summary' in label:
                 ## Everything until the next strong tag.
                 svalue = ""
-                while not isinstance(value,bs.Tag) or value.name != 'strong':
-                    svalue += str(value)
+                while not isinstance(value,Tag) or value.name != 'strong':
+                    svalue += unicode(value)
                     value = value.nextSibling
                 self.setDescription(url,svalue)
                 #self.story.setMetadata('description',stripHTML(svalue))
@@ -277,7 +277,7 @@ class BloodTiesFansComAdapter(BaseSiteAdapter): # XXX
             if 'Published' in label:
                 value=re.sub(r"\|",r"",value)
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
+
             if 'Updated' in label:
                 value=re.sub(r"\|",r"",value)
                 self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
@@ -293,7 +293,7 @@ class BloodTiesFansComAdapter(BaseSiteAdapter): # XXX
         for genre in genrestext:
             self.story.addToList('genre',genre.string)
 
-                
+
         try:
             # Find Series name from series URL.
             a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
@@ -301,7 +301,7 @@ class BloodTiesFansComAdapter(BaseSiteAdapter): # XXX
             series_url = 'http://'+self.host+'/fiction/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            seriessoup = self.make_soup(self._fetchUrl(series_url))
             storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
             i=1
             for a in storyas:
@@ -310,22 +310,21 @@ class BloodTiesFansComAdapter(BaseSiteAdapter): # XXX
                     self.story.setMetadata('seriesUrl',series_url)
                     break
                 i+=1
-            
+
         except:
             # I find it hard to care if the series parsing fails
             pass
-            
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
+        soup = self.make_soup(self._fetchUrl(url))
+
         div = soup.find('div', {'id' : 'story'})
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_buffygilescom.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2012 Fanficdownloader team, 2015 FanFicFare team
+# Copyright 2016 FanFicFare team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -22,18 +22,18 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
 from base_adapter import BaseSiteAdapter,  makeDate
 
 def getClass():
-    return SG1HeliopolisComAdapter
+    return BuffyGilesComAdapter
 
 # Class name has to be unique.  Our convention is camel case the
 # sitename with Adapter at the end.  www is skipped.
-class SG1HeliopolisComAdapter(BaseSiteAdapter):
+class BuffyGilesComAdapter(BaseSiteAdapter):
 
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
@@ -46,42 +46,68 @@ class SG1HeliopolisComAdapter(BaseSiteAdapter):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        self.section=self.parsedUrl.path.split('/',)[1]
-        
-        # normalized story URL.
-        self._setURL('http://' + self.getSiteDomain() + '/'+self.section+'/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
-        # Each adapter needs to have a unique site abbreviation.
-        self.story.setMetadata('siteabbrev','sghp')
 
-        # If all stories from the site fall into the same category,
-        # the site itself isn't likely to label them as such, so we
-        # do.  Can't use extracategories, could be Atlantis or SG-1
-        if 'atlantis' in self.section:
-            self.story.addToList("category","Stargate: Atlantis")
-        else:
-            self.story.addToList("category","Stargate: SG-1")
+
+        # normalized story URL.
+        # XXX Most sites don't have the /efiction part.  Replace all to remove it usually.
+        self._setURL('http://' + self.getSiteDomain() + '/efiction/viewstory.php?sid='+self.story.getMetadata('storyId'))
+
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','bufg')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = "%Y.%m.%d"
-            
+        self.dateformat = "%d/%m/%y"
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
-        return 'sg1-heliopolis.com'
+        return 'buffygiles.velocitygrass.com'
 
     @classmethod
     def getSiteExampleURLs(cls):
-        return "http://"+cls.getSiteDomain()+"/archive/viewstory.php?sid=1234 http://"+cls.getSiteDomain()+"/adult/viewstory.php?sid=1234 http://"+cls.getSiteDomain()+"/atlantis/viewstory.php?sid=1234"
+        return "http://"+cls.getSiteDomain()+"/efiction/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
-        return r"http://sg1-heliopolis.com/(archive|adult|atlantis)?/viewstory.php\?sid=\d+$"
+        return re.escape("http://"+self.getSiteDomain()+"/efiction/viewstory.php?sid=")+r"\d+$"
 
+    ## Login seems to be reasonably standard across eFiction sites.
+    def needToLoginCheck(self, data):
+        if 'Registered Users Only' in data \
+                or 'There is no such account on our website' in data \
+                or "That password doesn't match the one in our database" in data:
+            return True
+        else:
+            return False
+
+    def performLogin(self, url):
+        params = {}
+
+        if self.password:
+            params['penname'] = self.username
+            params['password'] = self.password
+        else:
+            params['penname'] = self.getConfig("username")
+            params['password'] = self.getConfig("password")
+        params['cookiecheck'] = '1'
+        params['submit'] = 'Submit'
+
+        loginUrl = 'http://' + self.getSiteDomain() + '/user.php?action=login'
+        logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
+                                                              params['penname']))
+
+        d = self._fetchUrl(loginUrl, params)
+
+        if "Member Account" not in d : #Member Account
+            logger.info("Failed to login to URL %s as %s" % (loginUrl,
+                                                              params['penname']))
+            raise exceptions.FailedToLogin(url,params['penname'])
+            return False
+        else:
+            return True
 
     ## Getting the chapter list and the meta data, plus 'is adult' checking.
     def extractChapterUrlsAndMetadata(self):
@@ -91,7 +117,7 @@ class SG1HeliopolisComAdapter(BaseSiteAdapter):
             # If the title search below fails, there's a good chance
             # you need a different number.  print data at that point
             # and see what the 'click here to continue' url says.
-            addurl = "&warning=4"
+            addurl = "&warning=5"
         else:
             addurl=""
 
@@ -108,7 +134,21 @@ class SG1HeliopolisComAdapter(BaseSiteAdapter):
             else:
                 raise e
 
-        m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
+        if self.needToLoginCheck(data):
+            # need to log in for this one.
+            self.performLogin(url)
+            data = self._fetchUrl(url)
+
+        # Since the warning text can change by warning level, let's
+        # look for the warning pass url.  ksarchive uses
+        # &warning= -- actually, so do other sites.  Must be an
+        # eFiction book.
+
+        # efiction/viewstory.php?sid=1882&warning=4
+        # efiction/viewstory.php?sid=1654&ageconsent=ok&warning=5
+        #print data
+        m = re.search(r"'efiction/viewstory.php\?sid=542(&warning=5)'",data)
+        m = re.search(r"'efiction/viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
         if m != None:
             if self.is_adult or self.getConfig("is_adult"):
                 # We tried the default and still got a warning, so
@@ -126,25 +166,28 @@ class SG1HeliopolisComAdapter(BaseSiteAdapter):
                     if e.code == 404:
                         raise exceptions.StoryDoesNotExist(self.url)
                     else:
-                        raise e    
+                        raise e
             else:
                 raise exceptions.AdultCheckRequired(self.url)
-            
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
             raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
+        pagetitle = soup.find('div',{'id':'pagetitle'})
+
         ## Title
-        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+
         self.story.setMetadata('title',stripHTML(a))
-        
+
         # Find authorid and URL from... author url.
-        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
         self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
         self.story.setMetadata('author',a.string)
@@ -152,9 +195,9 @@ class SG1HeliopolisComAdapter(BaseSiteAdapter):
         # Find the chapters:
         for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
             # just in case there's tags, like <i> in chapter titles.
-            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+self.section+'/'+chapter['href']+addurl))
+            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/efiction/'+chapter['href']+addurl))
 
-        self.story.setMetadata('numChapters',len(self.chapterUrls))
+            self.story.setMetadata('numChapters',len(self.chapterUrls))
 
         # eFiction sites don't help us out a lot with their meta data
         # formating, so it's a little ugly.
@@ -175,8 +218,8 @@ class SG1HeliopolisComAdapter(BaseSiteAdapter):
             if 'Summary' in label:
                 ## Everything until the next span class='label'
                 svalue = ""
-                while not defaultGetattr(value,'class') == 'label':
-                    svalue += str(value)
+                while 'label' not in defaultGetattr(value,'class'):
+                    svalue += unicode(value)
                     value = value.nextSibling
                 self.setDescription(url,svalue)
                 #self.story.setMetadata('description',stripHTML(svalue))
@@ -203,7 +246,7 @@ class SG1HeliopolisComAdapter(BaseSiteAdapter):
                     self.story.addToList('genre',genre.string)
 
             if 'Warnings' in label:
-                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2'))
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=3'))
                 for warning in warnings:
                     self.story.addToList('warnings',warning.string)
 
@@ -215,45 +258,43 @@ class SG1HeliopolisComAdapter(BaseSiteAdapter):
 
             if 'Published' in label:
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
+
             if 'Updated' in label:
+                # there's a stray [ at the end.
+                #value = value[0:-1]
                 self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
 
         try:
             # Find Series name from series URL.
-            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            a = soup.find('a', href=re.compile(r"efiction/viewseries.php\?seriesid=\d+"))
             series_name = a.string
-            series_url = 'http://'+self.host+'/'+self.section+'/'+a['href']
+            series_url = 'http://'+self.host+'/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
-            # can't use ^viewstory...$ in case of higher rated stories with javascript href.
-            storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+'))
+            seriessoup = self.make_soup(self._fetchUrl(series_url))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^efiction/viewstory.php\?sid=\d+$'))
             i=1
             for a in storyas:
-                # skip 'report this' and 'TOC' links
-                if 'contact.php' not in a['href'] and 'index' not in a['href']:
-                    if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
-                        self.setSeries(series_name, i)
-                        self.story.setMetadata('seriesUrl',series_url)
-                        break
-                    i+=1
-            
+                if a['href'] == ('efiction/viewstory.php?sid='+self.story.getMetadata('storyId')):
+                    self.setSeries(series_name, i)
+                    self.story.setMetadata('seriesUrl',series_url)
+                    break
+                i+=1
+
         except:
             # I find it hard to care if the series parsing fails
             pass
-            
+        
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
+        soup = self.make_soup(self._fetchUrl(url))
+
         div = soup.find('div', {'id' : 'story'})
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_buffynfaithnet.py

@@ -1,296 +0,0 @@
-# -*- coding: utf-8 -*-
-
-# Copyright 2013 Fanficdownloader team, 2015 FanFicFare team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-#
-
-import time
-import logging
-logger = logging.getLogger(__name__)
-import re
-import urllib2
-import cookielib as cl
-
-from .. import BeautifulSoup as bs
-from ..htmlcleanup import stripHTML
-from .. import exceptions as exceptions
-
-from base_adapter import BaseSiteAdapter,  makeDate
-
-
-# This function is called by the downloader in all adapter_*.py files
-# in this dir to register the adapter class.  So it needs to be
-# updated to reflect the class below it.  That, plus getSiteDomain()
-# take care of 'Registering'.
-def getClass():
-    return BuffyNFaithNetAdapter
-
-# Class name has to be unique.  Our convention is camel case the
-# sitename with Adapter at the end.  www is skipped.
-class BuffyNFaithNetAdapter(BaseSiteAdapter):
-
-    def __init__(self, config, url):
-        BaseSiteAdapter.__init__(self, config, url)
-        
-        self.setHeader()
-        
-        self.decode = ["Windows-1252",
-                       "utf8"] # 1252 is a superset of iso-8859-1.
-                               # Most sites that claim to be
-                               # iso-8859-1 (and some that claim to be
-                               # utf8) are really windows-1252.
-        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
-        self.password = ""
-        self.is_adult=False
-        
-        # get storyId from url--url validation guarantees query correct
-        m = re.match(self.getSiteURLPattern(),url)
-        if m:
-            self.story.setMetadata('storyId',m.group('id'))
-            
-            # normalized story URL. gets rid of chapter if there, left with ch 1 URL on this site
-            nurl = "http://"+self.getSiteDomain()+"/fanfictions/index.php?act=vie&id="+self.story.getMetadata('storyId')
-            self._setURL(nurl)
-            #argh, this mangles the ampersands I need on metadata['storyUrl']
-            #will set it this way
-            self.story.setMetadata('storyUrl',nurl,condremoveentities=False)
-        else:
-            raise exceptions.InvalidStoryURL(url,
-                                             self.getSiteDomain(),
-                                             self.getSiteExampleURLs())
-        
-        
-        # Each adapter needs to have a unique site abbreviation.
-        self.story.setMetadata('siteabbrev','bnfnet')
-
-    @staticmethod # must be @staticmethod, don't remove it.
-    def getSiteDomain():
-        # The site domain.  Does have www here, if it uses it.
-        return 'buffynfaith.net'
-
-    @classmethod
-    def stripURLParameters(cls,url):
-        "Only needs to be overriden if URL contains more than one parameter"
-        ## This adapter needs at least two parameters left on the URL, act and id
-        return re.sub(r"(\?act=(vie|ovr)&id=\d+)&.*$",r"\1",url)
-    
-    def setHeader(self):
-        "buffynfaith.net wants a Referer for images.  Used both above and below(after cookieproc added)"
-        self.opener.addheaders.append(('Referer', 'http://'+self.getSiteDomain()+'/'))
-        
-    @classmethod
-    def getSiteExampleURLs(cls):
-        return "http://"+cls.getSiteDomain()+"/fanfictions/index.php?act=vie&id=1234 http://"+cls.getSiteDomain()+"/fanfictions/index.php?act=ovr&id=1234 http://"+cls.getSiteDomain()+"/fanfictions/index.php?act=vie&id=1234&ch=2"
-
-    def getSiteURLPattern(self):
-        #http://buffynfaith.net/fanfictions/index.php?act=vie&id=963
-        #http://buffynfaith.net/fanfictions/index.php?act=vie&id=949
-        #http://buffynfaith.net/fanfictions/index.php?act=vie&id=949&ch=2
-        p = re.escape("http://"+self.getSiteDomain()+"/fanfictions/index.php?act=")+\
-            r"(vie|ovr)&id=(?P<id>\d+)(&ch=(?P<ch>\d+))?$"
-        return p
-
-    def use_pagecache(self):
-        '''
-        adapters that will work with the page cache need to implement
-        this and change it to True.
-        '''
-        return True
-    
-    def extractChapterUrlsAndMetadata(self):
-
-        dateformat = "%d %B %Y"
-        url = self.url
-        logger.debug("URL: "+url)
-        
-        #set a cookie to get past adult check
-        if self.is_adult or self.getConfig("is_adult"):
-            cookie = cl.Cookie(version=0, name='my_age', value='yes',
-                               port=None, port_specified=False,
-                               domain=self.getSiteDomain(), domain_specified=False, domain_initial_dot=False,
-                               path='/', path_specified=True,
-                               secure=False,
-                               expires=time.time()+10000,
-                               discard=False,
-                               comment=None,
-                               comment_url=None,
-                               rest={'HttpOnly': None},
-                               rfc2109=False)
-            self.cookiejar.set_cookie(cookie)
-            self.setHeader()
-
-        try:
-            data = self._fetchUrl(url)
-        except urllib2.HTTPError, e:
-            if e.code == 404:
-                raise exceptions.StoryDoesNotExist(self.url)
-            else:
-                raise e
-
-        #print data
-
-        if "ADULT CONTENT WARNING" in data: 
-            raise exceptions.AdultCheckRequired(self.url)
-
-        # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
-
-        # Now go hunting for all the meta data and the chapter list.
-        
-        #stuff in <head>: description
-        svalue = soup.head.find('meta',attrs={'name':'description'})['content']
-        #self.story.setMetadata('description',svalue)
-        self.setDescription(url,svalue)
-        
-        #useful stuff in rest of doc, all contained in this:
-        doc = soup.body.find('div', id='my_wrapper')
-        
-        #first the site category (more of a genre to me, meh) and title, in this element:
-        mt = doc.find('div',attrs={'class':'maintitle'})
-        self.story.addToList('genre',mt.findAll('a')[1].string)
-        self.story.setMetadata('title',mt.findAll('a')[1].nextSibling[len('&nbsp;&raquo;&nbsp;'):])
-        del mt
-
-        #the actual category, for me, is 'Buffy: The Vampire Slayer'
-        #self.story.addToList('category','Buffy: The Vampire Slayer')
-        #No need to do it here, it is better to set it in in plugin-defaults.ini and defaults.ini
-        
-        #then a block that sits in a table cell like so:
-        #(contains a lot of metadata)
-        mblock = doc.find('td', align='left', width = '70%').contents
-        while len(mblock) > 0:
-            i = mblock.pop(0)
-            if 'Author:' in i.string:
-                #drop empty space
-                mblock.pop(0)
-                #get author link
-                a = mblock.pop(0)
-                authre = re.escape('./index.php?act=bio&id=')+'(?P<authid>\d+)'
-                m = re.match(authre,a['href'])
-                self.story.setMetadata('author',a.string)
-                self.story.setMetadata('authorId',m.group('authid'))
-                authurl = u'http://%s/fanfictions/index.php?act=bio&id=%s' % ( self.getSiteDomain(),
-                                            self.story.getMetadata('authorId'))
-                self.story.setMetadata('authorUrl',authurl,condremoveentities=False)
-                #drop empty space
-                mblock.pop(0)
-            if 'Rating:' in i.string:
-                self.story.setMetadata('rating',mblock.pop(0).strip())
-            if 'Published:' in i.string:
-                date = mblock.pop(0).strip()
-                #get rid of 'st', 'nd', 'rd', 'th' after day number
-                date = date[0:2]+date[4:]
-                self.story.setMetadata('datePublished',makeDate(date, dateformat))
-            if 'Last Updated:' in i.string:
-                date = mblock.pop(0).strip()
-                #get rid of 'st', 'nd', 'rd', 'th' after day number
-                date = date[0:2]+date[4:]
-                self.story.setMetadata('dateUpdated',makeDate(date, dateformat))
-            if 'Genre:' in i.string:
-                genres = mblock.pop(0).strip()
-                genres = genres.split('/')
-                for genre in genres: self.story.addToList('genre',genre)
-            #end ifs
-        #end while
-
-        # Find the chapter selector 
-        select = soup.find('select', { 'name' : 'ch' } )
-         
-        if select is None:
-           # no selector found, so it's a one-chapter story.
-           #self.chapterUrls.append((self.story.getMetadata('title'),url))
-           self.chapterUrls.append((self.story.getMetadata('title'),url))
-        else:
-            allOptions = select.findAll('option')
-            for o in allOptions:
-                url = u'http://%s/fanfictions/index.php?act=vie&id=%s&ch=%s' % ( self.getSiteDomain(),
-                                            self.story.getMetadata('storyId'),
-                                            o['value'])
-                title = u"%s" % o
-                title = stripHTML(title)
-                ts = title.split(' ',1)
-                title = ts[0]+'. '+ts[1]
-                self.chapterUrls.append((title,url))
-        self.story.setMetadata('numChapters',len(self.chapterUrls))
-        
-        ## Go scrape the rest of the metadata from the author's page.
-        data = self._fetchUrl(self.story.getMetadata('authorUrl'))
-        soup = bs.BeautifulSoup(data)
-        #find the story link and its parent div
-        storya = soup.find('a',{'href':self.story.getMetadata('storyUrl')})
-        storydiv = storya.parent
-        #warnings come under a <spawn> tag. Never seen that before...
-        #appears to just be a line of freeform text, not necessarily a list
-        #optional
-        spawn = storydiv.find('spawn',{'id':'warnings'})
-        if spawn is not None:
-            warns = spawn.nextSibling.strip()
-            self.story.addToList('warnings',warns)
-        #some meta in spans - this should get all, even the ones jammed in a table
-        spans = storydiv.findAll('span')
-        for s in spans:
-            if s.string == 'Ship:':
-                list = s.nextSibling.strip().split()
-                self.story.extendList('ships',list)
-            if s.string == 'Characters:':
-                list = s.nextSibling.strip().split(',')
-                self.story.extendList('characters',list)
-            if s.string == 'Status:':
-                st = s.nextSibling.strip()
-                self.story.setMetadata('status',st)
-            if s.string == 'Words:':
-                st = s.nextSibling.strip()
-                self.story.setMetadata('numWords',st)
-
-        #reviews - is this worth having?
-        #ffnet adapter gathers it, don't know if anything else does
-        #or if it's ever going to be used!
-        a = storydiv.find('a',{'id':'bold-blue'})
-        if a:
-            revs = a.nextSibling.strip()[1:-1]
-            self.story.setMetadata('reviews',st)
-        else:
-            revs = '0'
-            self.story.setMetadata('reviews',st)
-
-    # grab the text for an individual chapter.
-    def getChapterText(self, url):
-
-        logger.debug('Getting chapter text from: %s' % url)
-
-        soup = bs.BeautifulSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
-        div = soup.find('div', {'id' : 'fanfiction'})
-        if None == div:
-            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-        
-        #remove all the unnecessary bookmark tags
-        [s.extract() for s in div('div',{'class':"tiny_box2"})]
-        
-        #is there a review link?
-        r = div.find('a',href=re.compile(re.escape("./index.php?act=irv")+".*$"))
-        if r is not None:
-        #remove the review link and its parent div
-            r.parent.extract()
-        
-        #There might also be a link to the sequel on the last chapter
-        #I'm inclined to keep it in, but the URL needs to be changed from relative to absolute
-        #Shame there isn't proper series metadata available
-        #(I couldn't find it anyway)
-        s = div.find('a',href=re.compile(re.escape("./index.php?act=ovr")+".*$"))
-        if s is not None:
-            s['href'] = 'http://'+self.getSiteDomain()+'/fanfictions'+s['href'][1:]
-
-        return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_chaossycophanthexcom.py

@@ -22,7 +22,7 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -46,22 +46,22 @@ class ChaosSycophantHexComAdapter(BaseSiteAdapter):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
+
 		
-        
+
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','csph')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%m/%d/%Y"
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -104,21 +104,21 @@ class ChaosSycophantHexComAdapter(BaseSiteAdapter):
         # the title search to troubleshoot.
         if "Age Consent Required" in data:
             raise exceptions.AdultCheckRequired(self.url)
-            
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
         ## Title
         pt = soup.find('div', {'id' : 'pagetitle'})
         a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',stripHTML(a))
-        
+
         # Find authorid and URL from... author url.
         a = pt.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
@@ -155,8 +155,8 @@ class ChaosSycophantHexComAdapter(BaseSiteAdapter):
         while value != None:
             val = value
             value = value.previousSibling
-        while not defaultGetattr(val,'class') == 'label':
-            svalue += str(val)
+        while 'label' not in defaultGetattr(val,'class'):
+            svalue += unicode(val)
             val = val.nextSibling
         self.setDescription(url,svalue)
 		
@@ -195,7 +195,7 @@ class ChaosSycophantHexComAdapter(BaseSiteAdapter):
 
             if 'Published' in label:
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value.split(' -')[0]), self.dateformat))
-            
+
             if 'Updated' in label:
                 # there's a stray [ at the end.
                 #value = value[0:-1]
@@ -208,7 +208,7 @@ class ChaosSycophantHexComAdapter(BaseSiteAdapter):
             series_url = 'http://'+self.host+'/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            seriessoup = self.make_soup(self._fetchUrl(series_url))
             storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
             i=1
             for a in storyas:
@@ -217,22 +217,21 @@ class ChaosSycophantHexComAdapter(BaseSiteAdapter):
                     self.story.setMetadata('seriesUrl',series_url)
                     break
                 i+=1
-            
+
         except:
             # I find it hard to care if the series parsing fails
             pass
-            
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
+        soup = self.make_soup(self._fetchUrl(url))
+
         div = soup.find('div', {'id' : 'story'})
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_csiforensicscom.py

@@ -21,7 +21,7 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -46,21 +46,21 @@ class CSIForensicsComAdapter(BaseSiteAdapter):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
+
+
 
         self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','csiforensics')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%d %b %Y"
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -101,24 +101,24 @@ class CSIForensicsComAdapter(BaseSiteAdapter):
         # The actual text that is used to announce you need to be an
         # adult varies from site to site.  Again, print data before
         # the title search to troubleshoot.
-        if "This story is rated NC-17, and therefore is not suitable for minors.  If you are below the age required to view such material in your locality, please return from whence you came." in data: # XXX 
+        if "This story is rated NC-17, and therefore is not suitable for minors.  If you are below the age required to view such material in your locality, please return from whence you came." in data: # XXX
             raise exceptions.AdultCheckRequired(self.url)
-            
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
         ## Title
-       
+
         pt = soup.find('div', {'id' : 'pagetitle'})
         a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',a.string)
-       
+
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
@@ -136,10 +136,10 @@ class CSIForensicsComAdapter(BaseSiteAdapter):
             self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']+addurl))
 
         self.story.setMetadata('numChapters',len(self.chapterUrls))
-        
+
         # eFiction sites don't help us out a lot with their meta data
         # formating, so it's a little ugly.
-        
+
         # utility method
         def defaultGetattr(d,k):
             try:
@@ -148,29 +148,29 @@ class CSIForensicsComAdapter(BaseSiteAdapter):
                 return ""
 
         smalldiv = soup.find('div', {'class' : 'small'})
-        
-      
+
+
         chars = smalldiv.findAll('a',href=re.compile(r'browse.php\?type=characters'))
         for char in chars:
             self.story.addToList('characters',char.string)
-            
+
         metatext = stripHTML(smalldiv)
 
         if 'Completed: Yes' in metatext:
             self.story.setMetadata('status', 'Completed')
         else:
-            self.story.setMetadata('status', 'In-Progress') 
-        
+            self.story.setMetadata('status', 'In-Progress')
+
         word=soup.find(text=re.compile("Word count:")).split(':')
         self.story.setMetadata('numWords', word[1])
 
         cats = smalldiv.findAll('a',href=re.compile(r'browse.php\?type=categories'))
         for cat in cats:
             self.story.addToList('category',cat.string)
-            
+
         warnings = smalldiv.findAll('a',href=re.compile(r'browse.php\?type=class(&)type_id=2(&)classid=\d+'))
         for warning in warnings:
-            self.story.addToList('warnings',warning.string)            
+            self.story.addToList('warnings',warning.string)
             			
         date=soup.find('div',{'class' : 'bottom'})
         pd=date.find(text=re.compile("Published:")).string.split(': ')
@@ -189,7 +189,7 @@ class CSIForensicsComAdapter(BaseSiteAdapter):
                 for genre in genres:
                     self.story.addToList('genre',genre.string)
 
-            if 'Warnings' in label:                
+            if 'Warnings' in label:
                 warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2'))
                 for warning in warnings:
                     self.story.addToList('warnings',warning.string)
@@ -201,7 +201,7 @@ class CSIForensicsComAdapter(BaseSiteAdapter):
             series_url = 'http://'+self.host+'/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            seriessoup = self.make_soup(self._fetchUrl(series_url))
             storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
             i=1
             for a in storyas:
@@ -210,28 +210,28 @@ class CSIForensicsComAdapter(BaseSiteAdapter):
                     self.story.setMetadata('seriesUrl',series_url)
                     break
                 i+=1
-            
+
         except:
             # I find it hard to care if the series parsing fails
             pass
-            
+
         smalldiv.extract()
-        
-        # Summary  
+
+        # Summary
         summary = soup.find('div', {'class' : 'content'})
-        self.setDescription(url,summary)        
-           
+        self.setDescription(url,summary)
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulSoup(self._fetchUrl(url))
-        
+        soup = self.make_soup(self._fetchUrl(url))
+
         div = soup.find('div', {'id' : 'story'})
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)
  

fanficfare/adapters/adapter_darksolaceorg.py

@@ -16,321 +16,26 @@
 #
 
 # Software: eFiction
-import time
-import logging
-logger = logging.getLogger(__name__)
-import re
-import urllib2
+from base_efiction_adapter import BaseEfictionAdapter
 
-from .. import BeautifulSoup as bs
-from ..htmlcleanup import stripHTML
-from .. import exceptions as exceptions
+class DarkSolaceOrgAdapter(BaseEfictionAdapter):
 
-from base_adapter import BaseSiteAdapter,  makeDate
+    @staticmethod
+    def getSiteDomain():
+        return 'dark-solace.org'
+
+    @classmethod
+    def getPathToArchive(self):
+        return '/elysian'
+
+    @classmethod
+    def getSiteAbbrev(self):
+        return 'dksl'
+
+    @classmethod
+    def getDateFormat(self):
+        return "%B %d, %Y"
 
 def getClass():
     return DarkSolaceOrgAdapter
 
-# Class name has to be unique.  Our convention is camel case the
-# sitename with Adapter at the end.  www is skipped.
-class DarkSolaceOrgAdapter(BaseSiteAdapter):
-
-    def __init__(self, config, url):
-        BaseSiteAdapter.__init__(self, config, url)
-
-        self.decode = ["Windows-1252",
-                       "utf8"] # 1252 is a superset of iso-8859-1.
-                               # Most sites that claim to be
-                               # iso-8859-1 (and some that claim to be
-                               # utf8) are really windows-1252.
-        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
-        self.password = ""
-        self.is_adult=False
-        
-        # get storyId from url--url validation guarantees query is only sid=1234
-        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
-        # normalized story URL.
-        self._setURL('http://' + self.getSiteDomain() + '/elysian/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
-        # Each adapter needs to have a unique site abbreviation.
-        self.story.setMetadata('siteabbrev','dksl')
-
-        # The date format will vary from site to site.
-        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = "%B %d, %Y"
-            
-    @staticmethod # must be @staticmethod, don't remove it.
-    def getSiteDomain():
-        # The site domain.  Does have www here, if it uses it.
-        return 'dark-solace.org'
-        
-    @classmethod
-    def getAcceptDomains(cls):
-        return ['www.dark-solace.org','dark-solace.org']
-
-    @classmethod
-    def getSiteExampleURLs(cls):
-        return "http://"+cls.getSiteDomain()+"/elysian/viewstory.php?sid=1234"
-
-    def getSiteURLPattern(self):
-        return re.escape("http://")+"(www\.)?"+re.escape(self.getSiteDomain()+"/elysian/viewstory.php?sid=")+r"\d+$"
-
-    ## Login seems to be reasonably standard across eFiction sites.
-    def needToLoginCheck(self, data):
-        if 'This story contains adult content not suitable for children' in data \
-                or "That password doesn't match the one in our database" in data \
-                or "Registered Users Only" in data:
-            return True
-        else:
-            return False
-        
-    def performLogin(self, url):
-        params = {}
-
-        if self.password:
-            params['penname'] = self.username
-            params['password'] = self.password
-        else:
-            params['penname'] = self.getConfig("username")
-            params['password'] = self.getConfig("password")
-        params['action'] = 'login'
-        params['submit'] = 'Submit'
-    
-        loginUrl = 'http://www.' + self.getSiteDomain() + '/elysian/user.php'
-        logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
-                                                              params['penname']))
-    
-        d = self._postUrl(loginUrl, params)
-    
-        if "Member Account" not in d : #User Account Page
-            logger.info("Failed to login to URL %s as %s, or have no authorization to access the story" % (loginUrl, params['penname']))
-            raise exceptions.FailedToLogin(url,params['penname'])
-            return False
-        else:
-            return True
-
-    ## Getting the chapter list and the meta data, plus 'is adult' checking.
-    def extractChapterUrlsAndMetadata(self):
-        
-        if self.is_adult or self.getConfig("is_adult"):
-            # Weirdly, different sites use different warning numbers.
-            # If the title search below fails, there's a good chance
-            # you need a different number.  print data at that point
-            # and see what the 'click here to continue' url says.
-            addurl = "&ageconsent=ok&warning=5"
-        else:
-            addurl=""
-
-        # index=1 makes sure we see the story chapter index.  Some
-        # sites skip that for one-chapter stories.
-        url = self.url+'&index=1'+addurl
-        logger.debug("URL: "+url)
-
-        try:
-            data = self._fetchUrl(url)
-        except urllib2.HTTPError, e:
-            if e.code == 404:
-                raise exceptions.StoryDoesNotExist(self.url)
-            else:
-                raise e
-
-        if self.needToLoginCheck(data):
-            # need to log in for this one.
-            self.performLogin(url)
-            data = self._fetchUrl(url)
-            
-        m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
-        if m != None:
-            if self.is_adult or self.getConfig("is_adult"):
-                # We tried the default and still got a warning, so
-                # let's pull the warning number from the 'continue'
-                # link and reload data.
-                addurl = m.group(1)
-                # correct stupid & error in url.
-                addurl = addurl.replace("&","&")
-                url = self.url+'&index=1'+addurl
-                logger.debug("URL 2nd try: "+url)
-
-                try:
-                    data = self._fetchUrl(url)
-                except urllib2.HTTPError, e:
-                    if e.code == 404:
-                        raise exceptions.StoryDoesNotExist(self.url)
-                    else:
-                        raise e    
-            else:
-                raise exceptions.AdultCheckRequired(self.url)
-            
-        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
-        # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
-        # print data
-
-        # Now go hunting for all the meta data and the chapter list.
-        
-        ## Title and author
-        div = soup.find('div', {'id' : 'pagetitle'})
-        
-        aut = div.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
-        self.story.setMetadata('authorId',aut['href'].split('=')[1])
-        self.story.setMetadata('authorUrl','http://'+self.host+'/elysian/'+aut['href'])
-        self.story.setMetadata('author',aut.string)
-        aut.extract()
-
-        # first a tag in pagetitle is title
-        self.story.setMetadata('title',stripHTML(div.find('a')))
-        div.find('a').extract()
-        # only thing left in div(pagetitle) now should be 'by' and rating.
-        rating = stripHTML(div)
-        if '[' in rating:
-            self.story.setMetadata('rating', rating[rating.index('[')+1:-1])
-
-        for chapa in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+
-                                                       self.story.getMetadata('storyId')+'&chapter=\d+')):
-            self.chapterUrls.append((stripHTML(chapa),'http://'+self.host+'/elysian/'+chapa['href']))
-        
-        self.story.setMetadata('numChapters',len(self.chapterUrls))
-
-        asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
-        storylink = asoup.find('a', href=re.compile(r'viewstory.php\?sid='+
-                                                    self.story.getMetadata('storyId')+'($|[^\d])'))
-        # author's story list is paginated if there's a pagelinks div.
-        # Only need to look in it if the story wasn't on the first page.
-        pagelinks = asoup.find('div',{'id':'pagelinks'})
-        if pagelinks and storylink==None:
-            authpageslist = pagelinks.findAll('a',href=re.compile(r'action=storiesby'))
-            for page in authpageslist[1:]: # skip first, already checked above.
-                asoup = bs.BeautifulSoup(self._fetchUrl('http://'+self.host+'/elysian/'+page['href']))
-                storylink = asoup.find('a', href=re.compile(r'viewstory.php\?sid='+
-                                                            self.story.getMetadata('storyId')+'($|[^\d])'))
-                if storylink:
-                    break
-
-        if not storylink:
-            raise exceptions.FailedToDownload("Unable to find story metadata on author's page(s)")
-        
-        metalist = storylink.parent.parent
-        # eFiction sites don't help us out a lot with their meta data
-        # formating, so it's a little ugly.
-
-        # utility method
-        def defaultGetattr(d,k):
-            try:
-                return d[k]
-            except:
-                return ""
-                
-
-        # <span class="label">Rated:</span> NC-17<br /> etc
-        labels = metalist.findAll('span', {'class' : 'label'})
-        for labelspan in labels:
-            label = labelspan.text
-            value = labelspan.nextSibling
-
-            if 'Summary' in label:
-                ## Everything until the next span class='label'
-                svalue = ""
-                while value and not (defaultGetattr(value,'class') == 'label' or "Chapters: " in stripHTML(value)):
-                    svalue += str(value)
-                    value = value.nextSibling
-                self.setDescription(url,svalue)
-                #self.story.setMetadata('description',stripHTML(svalue))
-
-            if 'Word count' in label:
-                self.story.setMetadata('numWords', value)
-
-            if 'Categories' in label:
-                cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
-                for cat in cats:
-                    self.story.addToList('category',cat.string)
-
-            if 'Characters' in label:
-                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
-                for char in chars:
-                    self.story.addToList('characters',char.string)
-
-            if 'Genre' in label:
-                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
-                for genre in genres:
-                    self.story.addToList('genre',genre.string)
-
-            if 'Warnings' in label:
-                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2'))
-                for warning in warnings:
-                    self.story.addToList('warnings',warning.string)
-
-            if 'Completed' in label:
-                if 'Yes' in value:
-                    self.story.setMetadata('status', 'Completed')
-                else:
-                    self.story.setMetadata('status', 'In-Progress')
-
-            if 'Published' in label:
-                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
-            if 'Updated' in label:
-                # there's a stray [ at the end.
-                #value = value[0:-1]
-                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
-
-        try:
-            # Find Series name from series URL.
-            a = metalist.find('a', href=re.compile(r"series.php\?seriesid=\d+"))
-            series_name = a.string
-            series_url = 'http://'+self.host+'/elysian/'+a['href']
-
-            # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
-            # can't use ^viewstory...$ in case of higher rated stories with javascript href.
-            storylink = seriessoup.find('a', href=re.compile(r'viewstory.php\?sid='+
-                                                             self.story.getMetadata('storyId')+'($|[^\d])'))
-            if storylink and storylink.parent and storylink.parent['class'] != 'title': # in case of links inside story summaries.
-                storylink = None
-
-            offset = 0
-            # series story list is paginated if there's a pagelinks div.
-            # Only need to look in it if the story wasn't on the first page.
-            pagelinks = seriessoup.find('div',{'id':'pagelinks'})
-            if pagelinks and storylink==None:
-                authpageslist = pagelinks.findAll('a',href=re.compile(r'offset='))
-                for page in authpageslist[1:]: # skip first, already checked above.
-                    seriessoup = bs.BeautifulSoup(self._fetchUrl('http://'+self.host+'/elysian/'+page['href']))
-                    storylink = seriessoup.find('a', href=re.compile(r'viewstory.php\?sid='+
-                                                                     self.story.getMetadata('storyId')+'($|[^\d])'))
-                    if storylink and storylink.parent and storylink.parent['class'] != 'title': # in case of links inside story summaries.
-                        storylink = None
-                    if storylink:
-                        offset = int(page['href'].split('=')[-1]) # offset is last.
-                        break
-
-            # for reasons I don't understand, searching for story
-            # links by regex wasn't working reliably.  It was missing
-            # the javascript links sometimes.  This is cleaner anyway.
-            for i, div in enumerate(seriessoup.findAll('div', {'class':'title'})):
-                a = div.find('a') # first a is story link.
-                # skip 'report this' and 'TOC' links
-                if a == storylink:
-                    self.setSeries(series_name, 1+i+offset)
-                    self.story.setMetadata('seriesUrl',series_url)
-                    break
-            
-        except Exception, e:
-            logger.debug("Series parsing failed: %s"%e)
-            
-    # grab the text for an individual chapter.
-    def getChapterText(self, url):
-
-        logger.debug('Getting chapter text from: %s' % url)
-
-        soup = bs.BeautifulSoup(self._fetchUrl(url))
-        
-        div = soup.find('div', {'id' : 'story'})
-
-        if None == div:
-            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
-        return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_destinysgatewaycom.py

@@ -22,7 +22,7 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -46,21 +46,21 @@ class DestinysGatewayComAdapter(BaseSiteAdapter):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
+
+
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','dgrfa')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%b %d %Y"
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -117,23 +117,23 @@ class DestinysGatewayComAdapter(BaseSiteAdapter):
                     if e.code == 404:
                         raise exceptions.StoryDoesNotExist(self.url)
                     else:
-                        raise e    
+                        raise e
             else:
                 raise exceptions.AdultCheckRequired(self.url)
-            
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',stripHTML(a))
-        
+
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
@@ -166,8 +166,8 @@ class DestinysGatewayComAdapter(BaseSiteAdapter):
             if 'Summary' in label:
                 ## Everything until the next span class='label'
                 svalue = ""
-                while not defaultGetattr(value,'class') == 'label':
-                    svalue += str(value)
+                while value and 'label' not in defaultGetattr(value,'class'):
+                    svalue += unicode(value)
                     value = value.nextSibling
                 self.setDescription(url,svalue)
                 #self.story.setMetadata('description',stripHTML(svalue))
@@ -201,7 +201,7 @@ class DestinysGatewayComAdapter(BaseSiteAdapter):
 
             if 'Published' in label:
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
+
             if 'Updated' in label:
                 # there's a stray [ at the end.
                 #value = value[0:-1]
@@ -214,7 +214,7 @@ class DestinysGatewayComAdapter(BaseSiteAdapter):
             series_url = 'http://'+self.host+'/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            seriessoup = self.make_soup(self._fetchUrl(series_url))
             storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
             i=1
             for a in storyas:
@@ -223,22 +223,21 @@ class DestinysGatewayComAdapter(BaseSiteAdapter):
                     self.story.setMetadata('seriesUrl',series_url)
                     break
                 i+=1
-            
+
         except:
             # I find it hard to care if the series parsing fails
             pass
-            
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
+        soup = self.make_soup(self._fetchUrl(url))
+
         div = soup.find('div', {'id' : 'story'})
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_dokugacom.py

@@ -21,7 +21,7 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -45,10 +45,10 @@ class DokugaComAdapter(BaseSiteAdapter):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[3])
-        
+
 
         # www.dokuga.com has two 'sections', shown in URL as
         # 'fanfiction' and 'spark' that change how things should be
@@ -56,10 +56,10 @@ class DokugaComAdapter(BaseSiteAdapter):
         # http://www.dokuga.com/fanfiction/story/7528/1
         # http://www.dokuga.com/spark/story/7299/1
         self.section=self.parsedUrl.path.split('/',)[1]
-        
+
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/'+self.parsedUrl.path.split('/',)[1]+'/story/'+self.story.getMetadata('storyId'))
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','dkg')
 
@@ -69,7 +69,7 @@ class DokugaComAdapter(BaseSiteAdapter):
             self.dateformat = "%d %b %Y"
         else:
             self.dateformat = "%m-%d-%y"
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -88,7 +88,7 @@ class DokugaComAdapter(BaseSiteAdapter):
             return True
         else:
             return False
-        
+
     def performLogin(self, url,soup):
         params = {}
 
@@ -103,11 +103,11 @@ class DokugaComAdapter(BaseSiteAdapter):
         # copy all hidden input tags to pick up appropriate tokens.
         for tag in soup.findAll('input',{'type':'hidden'}):
             params[tag['name']] = tag['value']
-    
+
         loginUrl = 'http://' + self.getSiteDomain() + '/fanfiction'
         logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
                                                               params['username']))
-    
+
         d = self._postUrl(loginUrl, params)
 
         if "Your session has expired. Please log in again." in d:
@@ -136,25 +136,25 @@ class DokugaComAdapter(BaseSiteAdapter):
                 raise exceptions.StoryDoesNotExist(self.url)
             else:
                 raise e
-                
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
-        
+        soup = self.make_soup(data)
+
         if self.needToLoginCheck(data):
             # need to log in for this one.
             self.performLogin(url,soup)
             data = self._fetchUrl(url)
-            soup = bs.BeautifulSoup(data)
-            
+            soup = self.make_soup(data)
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
         ## Title and author
         a = soup.find('div', {'align' : 'center'}).find('h3')
-        
+
         # Find authorid and URL from... author url.
         aut = a.find('a')
         self.story.setMetadata('authorId',aut['href'].split('=')[1])
@@ -162,7 +162,7 @@ class DokugaComAdapter(BaseSiteAdapter):
         self.story.setMetadata('authorUrl','http://'+self.host+aut['href'])
         self.story.setMetadata('author',aut.string)
         aut.extract()
-        
+
         a = a.string[:(len(a.string)-4)]
         self.story.setMetadata('title',stripHTML(a))
 
@@ -176,12 +176,12 @@ class DokugaComAdapter(BaseSiteAdapter):
                 self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+self.section+'/story/'+self.story.getMetadata('storyId')+'/'+chapter['value']))
 
         self.story.setMetadata('numChapters',len(self.chapterUrls))
-        
-        asoup = bs.BeautifulSoup(self._fetchUrl(alink))
-        
+
+        asoup = self.make_soup(self._fetchUrl(alink))
+
         if 'fanfiction' in self.section:
             asoup=asoup.find('div', {'id' : 'cb_tabid_52'}).find('div')
-        
+
             #grab the rest of the metadata from the author's page
             for div in asoup.findAll('div'):
                 nav=div.find('a', href=re.compile(r'/fanfiction/story/'+self.story.getMetadata('storyId')+"/1$"))
@@ -189,90 +189,89 @@ class DokugaComAdapter(BaseSiteAdapter):
                     break
             div=div.nextSibling
             self.setDescription(url,div)
-        
+
             div=div.nextSibling
-            
-            a=div.text.split('Rating: ')
-            if len(a) == 2: self.story.setMetadata('rating', a[1].split('&')[0])
-        
-            a=div.text.split('Status: ')
+
+            a=div.string.split('Rating: ')
+            if len(a) == 2: self.story.setMetadata('rating', a[1].split('-')[0])
+
+            a=div.string.split('Status: ')
             if len(a)==2:
-                iscomp=a[1].split('&')[0]
+                iscomp=a[1].split('-')[0]
                 if 'Complete' in iscomp:
                     self.story.setMetadata('status', 'Completed')
                 else:
                     self.story.setMetadata('status', 'In-Progress')
-            
-            a=div.text.split('Category: ')
-            if len(a) == 2: self.story.addToList('category', a[1].split('&')[0])
-        
-            a=div.text.split('Created: ')
-            if len(a) == 2: self.story.setMetadata('datePublished', makeDate(stripHTML(a[1].split('&')[0]), self.dateformat))
-        
-            a=div.text.split('Updated: ')
+
+            a=div.string.split('Category: ')
+            if len(a) == 2: self.story.addToList('category', a[1].split('-')[0])
+
+            a=div.string.split('Created: ')
+            if len(a) == 2: self.story.setMetadata('datePublished', makeDate(stripHTML(a[1].split('-')[0]), self.dateformat))
+
+            a=div.string.split('Updated: ')
             if len(a) == 2: self.story.setMetadata('dateUpdated', makeDate(stripHTML(a[1]), self.dateformat))
-            
+
             div=div.nextSibling.nextSibling
-            a=div.text.split('Words: ')
-            if len(a) == 2: self.story.setMetadata('numWords', a[1].split('&')[0])
-        
-            a=div.text.split('Genre: ')
+            a=div.string.split('Words: ')
+            if len(a) == 2: self.story.setMetadata('numWords', a[1].split('-')[0])
+
+            a=div.string.split('Genre: ')
             if len(a) == 2:
-                for genre in a[1].split('&')[0].split(', '):
+                for genre in a[1].split('-')[0].split(', '):
                     self.story.addToList('genre',genre)
-        
+
         else:
             asoup=asoup.find('div', {'id' : 'maincol'}).find('div', {'class' : 'padding'})
             for div in asoup.findAll('div'):
                 nav=div.find('a', href=re.compile(r'/spark/story/'+self.story.getMetadata('storyId')+"/1$"))
                 if nav != None:
                     break
-                    
+
             div=div.nextSibling.nextSibling
             self.setDescription(url,div)
             self.story.addToList('category', 'Spark')
-            
+
             div=div.nextSibling.nextSibling
-            a=div.text.split('Rating: ')
+            a=div.string.split('Rating: ')
             if len(a) == 2: self.story.setMetadata('rating', a[1].split(' - ')[0])
-            
-            a=div.text.split('Status: ')
+
+            a=div.string.split('Status: ')
             if len(a)==2:
                 iscomp=a[1].split(' - ')[0]
                 if 'Complete' in iscomp:
                     self.story.setMetadata('status', 'Completed')
                 else:
                     self.story.setMetadata('status', 'In-Progress')
-            
-            a=div.text.split('Genre: ')
+
+            a=div.string.split('Genre: ')
             if len(a)==2:
                 for genre in a[1].split(' - ')[0].split('/'):
                     self.story.addToList('genre',genre)
-                
+
             div=div.nextSibling.nextSibling
-            
-            a=div.text.split('Updated: ')
+
+            a=div.string.split('Updated: ')
             if len(a)==2:
                 date=a[1].split('      -')[0]
                 self.story.setMetadata('dateUpdated', makeDate(date, self.dateformat))
-        
+
                 # does not have published date anywhere
                 self.story.setMetadata('datePublished', makeDate(date, self.dateformat))
-            
-            a=div.text.split('Words ')
+
+            a=div.string.split('Words ')
             if len(a)==2: self.story.setMetadata('numWords', a[1])
-            
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
+        soup = self.make_soup(self._fetchUrl(url))
+
         div = soup.find('div', {'id' : 'chtext'})
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_dracoandginnycom.py

@@ -22,7 +22,7 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -46,21 +46,21 @@ class DracoAndGinnyComAdapter(BaseSiteAdapter):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
+
+
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','dcagn')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%b %d, %Y"
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -81,7 +81,7 @@ class DracoAndGinnyComAdapter(BaseSiteAdapter):
             return True
         else:
             return False
-        
+
     def performLogin(self, url):
         params = {}
 
@@ -93,13 +93,13 @@ class DracoAndGinnyComAdapter(BaseSiteAdapter):
             params['password'] = self.getConfig("password")
         params['cookiecheck'] = '1'
         params['submit'] = 'Submit'
-    
+
         loginUrl = 'http://' + self.getSiteDomain() + '/user.php?action=login'
         logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
                                                               params['penname']))
-    
+
         d = self._fetchUrl(loginUrl, params)
-    
+
         if "Member Account" not in d : #Member Account
             logger.info("Failed to login to URL %s as %s" % (loginUrl,
                                                               params['penname']))
@@ -156,23 +156,23 @@ class DracoAndGinnyComAdapter(BaseSiteAdapter):
                     if e.code == 404:
                         raise exceptions.StoryDoesNotExist(self.url)
                     else:
-                        raise e    
+                        raise e
             else:
                 raise exceptions.AdultCheckRequired(self.url)
-            
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',stripHTML(a))
-        
+
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
@@ -198,17 +198,17 @@ class DracoAndGinnyComAdapter(BaseSiteAdapter):
 
         # <span class="label">Rated:</span> NC-17<br /> etc
         content=soup.find('div',{'class' : 'listbox'})
-        
+
         self.setDescription(url,content.find('blockquote'))
-        
+
         for genre in content.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1')):
             self.story.addToList('genre',genre.string)
 
         for warning in content.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')):
             self.story.addToList('warnings',warning.string)
-        
+
         labels = content.findAll('b')
-        
+
         for labelspan in labels:
             value = labelspan.nextSibling
             label = labelspan.string
@@ -216,14 +216,14 @@ class DracoAndGinnyComAdapter(BaseSiteAdapter):
             if 'Summary' in label:
                 ## Everything until the next span class='label'
                 svalue = ""
-                while not defaultGetattr(value,'class') == 'label':
-                    svalue += str(value)
+                while value and 'label' not in defaultGetattr(value,'class'):
+                    svalue += unicode(value)
                     value = value.nextSibling
                 self.setDescription(url,svalue)
 
             if 'Word count' in label:
                 self.story.setMetadata('numWords', value.split(' |')[0])
-                
+
             if 'Rating' in label:
                 self.story.setMetadata('rating', value)
 
@@ -254,8 +254,8 @@ class DracoAndGinnyComAdapter(BaseSiteAdapter):
                     self.story.setMetadata('status', 'In-Progress')
 
             if 'Published' in label:
-                self.story.setMetadata('datePublished', makeDate(stripHTML(value.nextSibling).split(' |')[0], self.dateformat))
-            
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value).split(' |')[0], self.dateformat))
+
             if 'Updated' in label:
                 self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
 
@@ -266,7 +266,7 @@ class DracoAndGinnyComAdapter(BaseSiteAdapter):
             series_url = 'http://'+self.host+'/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            seriessoup = self.make_soup(self._fetchUrl(series_url))
             # can't use ^viewstory...$ in case of higher rated stories with javascript href.
             storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+'))
             i=1
@@ -278,25 +278,24 @@ class DracoAndGinnyComAdapter(BaseSiteAdapter):
                         self.story.setMetadata('seriesUrl',series_url)
                         break
                     i+=1
-            
+
         except:
             # I find it hard to care if the series parsing fails
             pass
-            
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
+        soup = self.make_soup(self._fetchUrl(url))
+
         div = soup.find('div', {'class' : 'listbox'})
-        
+
         if None == div:
             div = soup.find('div', {'id' : 'story'})
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_dramioneorg.py

@@ -22,7 +22,7 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+from bs4.element import Tag
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -38,29 +38,30 @@ class DramioneOrgAdapter(BaseSiteAdapter):
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
 
-        self.decode = ["Windows-1252",
-                       "utf8"] # 1252 is a superset of iso-8859-1.
+        self.decode = ["utf8",
+                       "Windows-1252",]
+                               # 1252 is a superset of iso-8859-1.
                                # Most sites that claim to be
                                # iso-8859-1 (and some that claim to be
                                # utf8) are really windows-1252.
         self.username = "" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
+
+
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','drmn')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%d %B %Y"
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -81,7 +82,7 @@ class DramioneOrgAdapter(BaseSiteAdapter):
             return True
         else:
             return False
-        
+
     def performLogin(self, url):
         params = {}
 
@@ -93,13 +94,13 @@ class DramioneOrgAdapter(BaseSiteAdapter):
             params['password'] = self.getConfig("password")
         params['cookiecheck'] = '1'
         params['submit'] = 'Submit'
-    
+
         loginUrl = 'http://' + self.getSiteDomain() + '/user.php?action=login'
         logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
                                                               params['penname']))
-    
+
         d = self._fetchUrl(loginUrl, params)
-    
+
         if "Member Account" not in d : #Member Account
             logger.info("Failed to login to URL %s as %s" % (loginUrl,
                                                               params['penname']))
@@ -143,20 +144,20 @@ class DramioneOrgAdapter(BaseSiteAdapter):
         # the title search to troubleshoot.
         if "Stories that are suitable for ages 16 and older" in data:
             raise exceptions.AdultCheckRequired(self.url)
-            
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',stripHTML(a))
-        
+
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
@@ -228,8 +229,8 @@ class DramioneOrgAdapter(BaseSiteAdapter):
             if 'Summary' in label:
                 ## Everything until the next strong tag.
                 svalue = ""
-                while not isinstance(value,bs.Tag) or value.name != 'strong':
-                    svalue += str(value)
+                while not isinstance(value,Tag) or value.name != 'strong':
+                    svalue += unicode(value)
                     value = value.nextSibling
                 self.setDescription(url,svalue)
 
@@ -261,7 +262,7 @@ class DramioneOrgAdapter(BaseSiteAdapter):
             if 'Published' in label:
                 value=re.sub(r"(\d+)(st|nd|rd|th)",r"\1",value)
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
+
             if 'Updated' in label:
                 value=re.sub(r"(\d+)(st|nd|rd|th)",r"\1",value)
                 self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
@@ -273,7 +274,7 @@ class DramioneOrgAdapter(BaseSiteAdapter):
             series_url = 'http://'+self.host+'/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            seriessoup = self.make_soup(self._fetchUrl(series_url))
             storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
             i=1
             for a in storyas:
@@ -282,11 +283,11 @@ class DramioneOrgAdapter(BaseSiteAdapter):
                     self.story.setMetadata('seriesUrl',series_url)
                     break
                 i+=1
-            
+
         except:
             # I find it hard to care if the series parsing fails
             pass
-            
+
         try:
             self.story.setMetadata('reviews',
                                    stripHTML(soup.find('h2',{'id':'pagetitle'}).
@@ -294,18 +295,17 @@ class DramioneOrgAdapter(BaseSiteAdapter):
         except:
             # I find it hard to care if the series parsing fails
             pass
-            
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
+        soup = self.make_soup(self._fetchUrl(url))
+
         div = soup.find('div', {'id' : 'story'})
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_efictionestelielde.py

@@ -22,7 +22,7 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -46,21 +46,21 @@ class EfictionEstelielDeAdapter(BaseSiteAdapter):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
+
+
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','eesd')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%B %d, %Y"
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -72,7 +72,7 @@ class EfictionEstelielDeAdapter(BaseSiteAdapter):
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
-       
+
 
     ## Getting the chapter list and the meta data, plus 'is adult' checking.
     def extractChapterUrlsAndMetadata(self):
@@ -89,15 +89,15 @@ class EfictionEstelielDeAdapter(BaseSiteAdapter):
                 raise exceptions.StoryDoesNotExist(self.url)
             else:
                 raise e
-            
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
         ## Title and author
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
@@ -106,7 +106,7 @@ class EfictionEstelielDeAdapter(BaseSiteAdapter):
         ## Title
         a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',stripHTML(a))
-        
+
         # Find authorid and URL from... author url.
         a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
@@ -138,7 +138,7 @@ class EfictionEstelielDeAdapter(BaseSiteAdapter):
         genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
         for genre in genres:
             self.story.addToList('genre',genre.string)
-        
+
         labels = list.findAll('b')
         for labelspan in labels:
             value = labelspan.nextSibling
@@ -147,8 +147,8 @@ class EfictionEstelielDeAdapter(BaseSiteAdapter):
             if 'Summary' in label:
                 ## Everything until the next span class='label'
                 svalue = ""
-                while 'Rating' not in str(value):
-                    svalue += str(value)
+                while 'Rating' not in unicode(value):
+                    svalue += unicode(value)
                     value = value.nextSibling
                 self.setDescription(url,svalue)
                 #self.story.setMetadata('description',stripHTML(svalue))
@@ -177,7 +177,7 @@ class EfictionEstelielDeAdapter(BaseSiteAdapter):
 
             if 'Published' in label:
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
+
             if 'Updated' in label:
                 # there's a stray [ at the end.
                 #value = value[0:-1]
@@ -189,7 +189,7 @@ class EfictionEstelielDeAdapter(BaseSiteAdapter):
                     # Find Series name from series URL.
                     series_url = 'http://'+self.host+'/'+series['href']
                     # use BeautifulSoup HTML parser to make everything easier to find.
-                    seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+                    seriessoup = self.make_soup(self._fetchUrl(series_url))
                     storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
                     i=1
                     for a in storyas:
@@ -203,22 +203,21 @@ class EfictionEstelielDeAdapter(BaseSiteAdapter):
                         i+=1
                     if i == 0:
                         break
-            
+
         except:
             # I find it hard to care if the series parsing fails
             pass
-            
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-                                     
+        soup = self.make_soup(self._fetchUrl(url))
+
         div = soup.find('div', {'id' : 'story'})
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_efpfanficnet.py

@@ -22,7 +22,7 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -46,21 +46,21 @@ class EFPFanFicNet(BaseSiteAdapter):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
+
+
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','efp')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%d/%m/%y"
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -80,7 +80,7 @@ class EFPFanFicNet(BaseSiteAdapter):
             return True
         else:
             return False
-        
+
     def performLogin(self, url):
         params = {}
 
@@ -96,9 +96,9 @@ class EFPFanFicNet(BaseSiteAdapter):
         loginUrl = 'http://' + self.getSiteDomain() + '/user.php?sid='+self.story.getMetadata('storyId')
         logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
                                                               params['penname']))
-    
+
         d = self._fetchUrl(loginUrl, params)
-    
+
         if '<a class="menu" href="newaccount.php">' in d : # register for new account link
             logger.info("Failed to login to URL %s as %s" % (loginUrl,
                                                               params['penname']))
@@ -127,27 +127,27 @@ class EFPFanFicNet(BaseSiteAdapter):
             data = self._fetchUrl(url)
 
         # if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-        #     raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+        #     raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
 
         ## Title
-        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        a = soup.find('a', href=re.compile(r'^viewstory\.php\?sid='+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',stripHTML(a))
-        
+
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
         self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
         self.story.setMetadata('author',a.string)
 
-        # Find the chapter selector 
+        # Find the chapter selector
         select = soup.find('select', { 'name' : 'sid' } )
-    	 
+    	
         if select is None:
     	   # no selector found, so it's a one-chapter story.
     	   self.chapterUrls.append((self.story.getMetadata('title'),url))
@@ -162,13 +162,13 @@ class EFPFanFicNet(BaseSiteAdapter):
 
         self.story.setMetadata('numChapters',len(self.chapterUrls))
         self.story.setMetadata('language','Italian')
-        
+
         # normalize story URL to first chapter if later chapter URL was given:
         url = self.chapterUrls[0][1].replace('&i=1','')
         logger.debug("Normalizing to URL: "+url)
         self._setURL(url)
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
+
 
         # eFiction sites don't help us out a lot with their meta data
         # formating, so it's a little ugly.
@@ -177,7 +177,7 @@ class EFPFanFicNet(BaseSiteAdapter):
         authsoup = None
         storyblock = None
         authurl = self.story.getMetadata('authorUrl')
-        
+
         ## author can have more than one page of stories.
         while storyblock == None:
 
@@ -186,10 +186,10 @@ class EFPFanFicNet(BaseSiteAdapter):
                 # last author link with offset should be the 'next' link.
                 authurl = u'http://%s/%s' % ( self.getSiteDomain(),
                                               authsoup.findAll('a',href=re.compile(r'viewuser\.php\?uid=\d+&catid=&offset='))[-1]['href'] )
-            
+
             # Need author page for most of the metadata.
             logger.debug("fetching author page: (%s)"%authurl)
-            authsoup = bs.BeautifulSoup(self._fetchUrl(authurl))
+            authsoup = self.make_soup(self._fetchUrl(authurl))
             #print("authsoup:%s"%authsoup)
 
             storyas = authsoup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+r'&i=1$'))
@@ -204,7 +204,7 @@ class EFPFanFicNet(BaseSiteAdapter):
 
         noteblock = storyblock.find('div', {'class':'notebloc'})
         #print("%s"%noteblock)
-        notetext = ("%s" % noteblock).replace("<br />"," |")
+        notetext = ("%s" % noteblock).replace("<br/>"," |")
         # <div class="notebloc">Autore: <a href="viewuser.php?uid=243036">Cendrillon89</a> | Pubblicata: 23/10/12 | Aggiornata: 30/10/12 | Rating: Arancione | Genere: Drammatico, Sentimentale | Capitoli: 10 | Completa<br />
         # Tipo di coppia: Het |  Personaggi: Akasuna no Sasori , Akatsuki, Nuovo Personaggio |   Note: OOC | Avvertimenti: Tematiche delicate<br />
         # Categoria: <a href="categories.php?catid=1&amp;parentcatid=1">Anime & Manga</a> > <a href="categories.php?catid=108&amp;parentcatid=108">Naruto</a> | Contesto: Naruto Shippuuden | Leggi le <a href="reviews.php?sid=1331275&amp;a=">3</a> recensioni</div>
@@ -212,7 +212,7 @@ class EFPFanFicNet(BaseSiteAdapter):
         cats = noteblock.findAll('a',href=re.compile(r'browse.php\?type=categories'))
         for cat in cats:
             self.story.addToList('category',cat.string)
-            
+
         for item in notetext.split("|"):
             if ":" in item:
                 (label,value) = item.split(":")
@@ -223,13 +223,13 @@ class EFPFanFicNet(BaseSiteAdapter):
 
             if 'Pubblicata' in label:
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
+
             if 'Aggiornata' in label:
                 self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
 
             if label == "Completa":
                 self.story.setMetadata('status', 'Completed')
-            
+
             if label == "In corso":
                 self.story.setMetadata('status', 'In-Progress')
 
@@ -239,11 +239,11 @@ class EFPFanFicNet(BaseSiteAdapter):
             if 'Personaggi' in label:
                 for val in value.split(","):
                     self.story.addToList('characters',val)
-                    
+
             if 'Genere' in label:
                 for val in value.split(","):
                     self.story.addToList('genre',val)
-                    
+
             if 'Coppie' in label:
                 for val in value.split(","):
                     self.story.addToList('ships',val)
@@ -254,21 +254,21 @@ class EFPFanFicNet(BaseSiteAdapter):
                         self.story.addToList('warnings',val)
 
             # 'extra' metadata for this adapter:
-                    
+
             if 'Tipo di coppia' in label:
                 for val in value.split(","):
                     self.story.addToList('type',val)
-                    
+
             if 'Note' in label:
                 for val in value.split(","):
                     if val != "None":
                         self.story.addToList('notes',val)
-                    
+
             if 'Contesto' in label:
                 self.story.setMetadata('context', value)
 
             ## Note--efp doesn't provide word count.
-                
+
         try:
             # Find Series name from series URL.
             a = soup.find('a', href=re.compile(r"viewseries.php\?ssid=\d+&i=1"))
@@ -276,7 +276,7 @@ class EFPFanFicNet(BaseSiteAdapter):
             series_url = 'http://'+self.host+'/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            seriessoup = self.make_soup(self._fetchUrl(series_url))
             # can't use ^viewstory...$ in case of higher rated stories with javascript href.
             storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+&i=1'))
             i=1
@@ -286,23 +286,23 @@ class EFPFanFicNet(BaseSiteAdapter):
                     self.story.setMetadata('seriesUrl',series_url)
                     break
                 i+=1
-            
+
         except:
             # I find it hard to care if the series parsing fails
             pass
-            
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulSoup(self._fetchUrl(url))
-        
+        soup = self.make_soup(self._fetchUrl(url))
+
         div = soup.find('div', {'class' : 'storia'})
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         # remove any header and 'o:p' tags.
         for tag in div.findAll("head") + div.findAll("o:p"):
             tag.extract()

fanficfare/adapters/adapter_erosnsapphosycophanthexcom.py

@@ -22,7 +22,7 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -46,22 +46,22 @@ class ErosnSapphoSycophantHexComAdapter(BaseSiteAdapter):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
+
 		
-        
+
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','essph')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%d/%m/%y"
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -117,24 +117,24 @@ class ErosnSapphoSycophantHexComAdapter(BaseSiteAdapter):
                     if e.code == 404:
                         raise exceptions.StoryDoesNotExist(self.url)
                     else:
-                        raise e    
+                        raise e
             else:
                 raise exceptions.AdultCheckRequired(self.url)
-            
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
         ## Title
         pt = soup.find('div', {'id' : 'pagetitle'})
         a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',stripHTML(a))
-        
+
         # Find authorid and URL from... author url.
         a = pt.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
@@ -171,8 +171,8 @@ class ErosnSapphoSycophantHexComAdapter(BaseSiteAdapter):
         while value != None:
             val = value
             value = value.previousSibling
-        while not defaultGetattr(val,'class') == 'label':
-            svalue += str(val)
+        while 'label' not in defaultGetattr(val,'class'):
+            svalue += unicode(val)
             val = val.nextSibling
         self.setDescription(url,svalue)
 		
@@ -211,7 +211,7 @@ class ErosnSapphoSycophantHexComAdapter(BaseSiteAdapter):
 
             if 'Published' in label:
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value.split(' -')[0]), self.dateformat))
-            
+
             if 'Updated' in label:
                 # there's a stray [ at the end.
                 #value = value[0:-1]
@@ -224,7 +224,7 @@ class ErosnSapphoSycophantHexComAdapter(BaseSiteAdapter):
             series_url = 'http://'+self.host+'/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            seriessoup = self.make_soup(self._fetchUrl(series_url))
             storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+'))
             i=1
             for a in storyas:
@@ -235,22 +235,21 @@ class ErosnSapphoSycophantHexComAdapter(BaseSiteAdapter):
                         self.story.setMetadata('seriesUrl',series_url)
                         break
                     i+=1
-            
+
         except:
             # I find it hard to care if the series parsing fails
             pass
-            
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
+        soup = self.make_soup(self._fetchUrl(url))
+
         div = soup.find('div', {'id' : 'story'})
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_fanficcastletvnet.py

@@ -22,7 +22,7 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -61,22 +61,22 @@ class FanficCastleTVNetAdapter(BaseSiteAdapter): # XXX
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
+
+
         # normalized story URL.
         # XXX Most sites don't have the /fanfic part.  Replace all to remove it usually.
         self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','csltv') # XXX
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%b %d, %Y" # XXX
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -97,7 +97,7 @@ class FanficCastleTVNetAdapter(BaseSiteAdapter): # XXX
             return True
         else:
             return False
-        
+
     def performLogin(self, url):
         params = {}
 
@@ -109,13 +109,13 @@ class FanficCastleTVNetAdapter(BaseSiteAdapter): # XXX
             params['password'] = self.getConfig("password")
         params['cookiecheck'] = '1'
         params['submit'] = 'Submit'
-    
+
         loginUrl = 'http://' + self.getSiteDomain() + '/user.php?action=login'
         logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
                                                               params['penname']))
-    
+
         d = self._fetchUrl(loginUrl, params)
-    
+
         if "Member Account" not in d : #Member Account
             logger.info("Failed to login to URL %s as %s" % (loginUrl,
                                                               params['penname']))
@@ -172,15 +172,15 @@ class FanficCastleTVNetAdapter(BaseSiteAdapter): # XXX
                     if e.code == 404:
                         raise exceptions.StoryDoesNotExist(self.url)
                     else:
-                        raise e    
+                        raise e
             else:
                 raise exceptions.AdultCheckRequired(self.url)
-            
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
@@ -189,17 +189,17 @@ class FanficCastleTVNetAdapter(BaseSiteAdapter): # XXX
         ## Title
         a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',stripHTML(a))
-        
+
         # Find authorid and URL from... author url.
         a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
         self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
         self.story.setMetadata('author',a.string)
-        
+
         # Reviews
         reviewdata = soup.find('div', {'id' : 'sort'})
         a = reviewdata.findAll('a', href=re.compile(r'reviews.php\?type=ST&(amp;)?item='+self.story.getMetadata('storyId')+"$"))[1] # second one.
-        self.story.setMetadata('reviews',stripHTML(a)) 
+        self.story.setMetadata('reviews',stripHTML(a))
 
         # Find the chapters:
         for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
@@ -227,8 +227,8 @@ class FanficCastleTVNetAdapter(BaseSiteAdapter): # XXX
             if 'Summary' in label:
                 ## Everything until the next span class='label'
                 svalue = ""
-                while not defaultGetattr(value,'class') == 'label':
-                    svalue += str(value)
+                while value and 'label' not in defaultGetattr(value,'class'):
+                    svalue += unicode(value)
                     value = value.nextSibling
                 self.setDescription(url,svalue)
                 #self.story.setMetadata('description',stripHTML(svalue))
@@ -279,7 +279,7 @@ class FanficCastleTVNetAdapter(BaseSiteAdapter): # XXX
 
             if 'Published' in label:
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
+
             if 'Updated' in label:
                 # there's a stray [ at the end.
                 #value = value[0:-1]
@@ -292,7 +292,7 @@ class FanficCastleTVNetAdapter(BaseSiteAdapter): # XXX
             series_url = 'http://'+self.host+'/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            seriessoup = self.make_soup(self._fetchUrl(series_url))
             storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
             i=1
             for a in storyas:
@@ -301,22 +301,21 @@ class FanficCastleTVNetAdapter(BaseSiteAdapter): # XXX
                     self.story.setMetadata('seriesUrl',series_url)
                     break
                 i+=1
-            
+
         except:
             # I find it hard to care if the series parsing fails
             pass
-            
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
+        soup = self.make_soup(self._fetchUrl(url))
+
         div = soup.find('div', {'id' : 'story'})
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_fanfichu.py

@@ -4,8 +4,6 @@ import re
 import urllib2
 import urlparse
 
-from .. import BeautifulSoup
-
 from base_adapter import BaseSiteAdapter, makeDate
 from .. import exceptions
 
@@ -55,7 +53,7 @@ class FanficHuAdapter(BaseSiteAdapter):
         else:
             data = self._fetchUrl(url, parameters)
 
-        return BeautifulSoup.BeautifulSoup(data)
+        return self.make_soup(data)
 
     @staticmethod
     def getSiteDomain():

fanficfare/adapters/adapter_fanfictioncsodaidokhu.py

@@ -4,8 +4,7 @@ import re
 import urllib2
 import urlparse
 
-from .. import BeautifulSoup
-
+from bs4.element import Tag
 from base_adapter import BaseSiteAdapter, makeDate
 from .. import exceptions
 
@@ -65,7 +64,7 @@ class FanfictionCsodaidokHuAdapter(BaseSiteAdapter):
         else:
             data = self._fetchUrl(url, parameters)
 
-        return BeautifulSoup.BeautifulSoup(data)
+        return self.make_soup(data)
 
     @staticmethod
     def getSiteDomain():
@@ -147,7 +146,7 @@ class FanfictionCsodaidokHuAdapter(BaseSiteAdapter):
                     keep_summary_html = self.getConfig('keep_summary_html')
 
                     for sibling in _yield_next_siblings(element):
-                        if isinstance(sibling, BeautifulSoup.Tag):
+                        if isinstance(sibling, Tag):
                             if sibling.name == 'span' and sibling.get('class', None) == 'classification':
                                 break
 

fanficfare/adapters/adapter_fanfictionjunkiesde.py

@@ -22,7 +22,7 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -70,22 +70,22 @@ class FanfictionJunkiesDeAdapter(BaseSiteAdapter): # XXX
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
+
+
         # normalized story URL.
         # XXX Most sites don't have the /fanfic part.  Replace all to remove it usually.
         self._setURL('http://' + self.getSiteDomain() + '/efiction/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','ffjde') # XXX
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%d/%m/%y" # XXX
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -106,7 +106,7 @@ class FanfictionJunkiesDeAdapter(BaseSiteAdapter): # XXX
             return True
         else:
             return False
-        
+
     def performLogin(self, url):
         params = {}
 
@@ -118,13 +118,13 @@ class FanfictionJunkiesDeAdapter(BaseSiteAdapter): # XXX
             params['password'] = self.getConfig("password")
         params['cookiecheck'] = '1'
         params['submit'] = 'Submit'
-    
+
         loginUrl = 'http://' + self.getSiteDomain() + '/efiction/user.php?action=login'
         logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
                                                               params['penname']))
-    
+
         d = self._fetchUrl(loginUrl, params)
-    
+
         if "Member Account" not in d : #Member Account
             logger.info("Failed to login to URL %s as %s" % (loginUrl,
                                                               params['penname']))
@@ -166,33 +166,33 @@ class FanfictionJunkiesDeAdapter(BaseSiteAdapter): # XXX
         # The actual text that is used to announce you need to be an
         # adult varies from site to site.  Again, print data before
         # the title search to troubleshoot.
-        if "For adults only " in data: # XXX 
+        if "For adults only " in data: # XXX
             raise exceptions.AdultCheckRequired(self.url)
-            
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
 
         pagetitle = soup.find('h4')
-        ## Title      
+        ## Title
         a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',a.string)
-        
+
         # Find authorid and URL from... author url.
         a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
         self.story.setMetadata('authorUrl','http://'+self.host+'/efiction/'+a['href'])
         self.story.setMetadata('author',a.string)
-        
+
         # Reviews
         reviewdata = soup.find('div', {'id' : 'sort'})
         a = reviewdata.findAll('a', href=re.compile(r'reviews.php\?type=ST&(amp;)?item='+self.story.getMetadata('storyId')+"$"))[1] # second one.
-        self.story.setMetadata('reviews',stripHTML(a)) 
+        self.story.setMetadata('reviews',stripHTML(a))
 
         # Find the chapters:
         for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
@@ -210,12 +210,12 @@ class FanfictionJunkiesDeAdapter(BaseSiteAdapter): # XXX
                 return d[k]
             except:
                 return ""
-                           
+
 
         # <span class="label">Rated:</span> NC-17<br /> etc
         list = soup.find('div', {'class':'listbox'})
-        
-        
+
+
         labels = list.findAll('b')
         for labelspan in labels:
             value = labelspan.nextSibling
@@ -227,7 +227,7 @@ class FanfictionJunkiesDeAdapter(BaseSiteAdapter): # XXX
             if 'Eingestuft' in label:
                 self.story.setMetadata('rating', value)
 
-            if 'W&ouml;rter' in label:
+            if u'Wörter' in label:
                 self.story.setMetadata('numWords', value)
 
             if 'Kategorie' in label:
@@ -246,9 +246,9 @@ class FanfictionJunkiesDeAdapter(BaseSiteAdapter): # XXX
                 else:
                     self.story.setMetadata('status', 'In-Progress')
 
-            if 'Ver&ouml;ffentlicht' in label:
+            if u'Veröffentlicht' in label:
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
+
             if 'Aktualisiert' in label:
                 # there's a stray [ at the end.
                 #value = value[0:-1]
@@ -261,7 +261,7 @@ class FanfictionJunkiesDeAdapter(BaseSiteAdapter): # XXX
             series_url = 'http://'+self.host+'/efiction/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            seriessoup = self.make_soup(self._fetchUrl(series_url))
             storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
             i=1
             for a in storyas:
@@ -270,22 +270,21 @@ class FanfictionJunkiesDeAdapter(BaseSiteAdapter): # XXX
                     self.story.setMetadata('seriesUrl',series_url)
                     break
                 i+=1
-            
+
         except:
             # I find it hard to care if the series parsing fails
             pass
-            
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
+        soup = self.make_soup(self._fetchUrl(url))
+
         div = soup.find('div', {'id' : 'story'})
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_fanfictionnet.py

@@ -38,7 +38,7 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
         self.story.setMetadata('siteabbrev','ffnet')
-        
+
         # get storyId from url--url validation guarantees second part is storyId
         self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2])
 
@@ -90,7 +90,7 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         this and change it to True.
         '''
         return True
-    
+
     def doExtractChapterUrlsAndMetadata(self,get_cover=True):
 
         # fetch the chapter.  From that we will get almost all the
@@ -104,12 +104,12 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
             data = self._fetchUrl(url)
             #logger.debug("\n===================\n%s\n===================\n"%data)
             soup = self.make_soup(data)
-        except urllib2.HTTPError, e:
+        except urllib2.HTTPError as e:
             if e.code == 404:
                 raise exceptions.StoryDoesNotExist(url)
             else:
                 raise e
-            
+
         if "Unable to locate story" in data:
             raise exceptions.StoryDoesNotExist(url)
 
@@ -135,13 +135,17 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
                                                 chapcount+1)
                 logger.debug('=Trying newer chapter: %s' % tryurl)
                 newdata = self._fetchUrl(tryurl)
-                if "not found. Please check to see you are not using an outdated url." \
-                        not in newdata:
+                if "not found. Please check to see you are not using an outdated url." not in newdata \
+                        and "This request takes too long to process, it is timed out by the server." not in newdata:
                     logger.debug('=======Found newer chapter: %s' % tryurl)
                     soup = self.make_soup(newdata)
-            except:
+            except urllib2.HTTPError as e:
+                if e.code == 503:
+                    raise e
+            except e:
+                logger.warn("Caught an exception reading URL: %s sleeptime(%s) Exception %s."%(unicode(url),sleeptime,unicode(e)))
                 pass
-            
+
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"^/u/\d+"))
         self.story.setMetadata('authorId',a['href'].split('/')[2])
@@ -176,14 +180,14 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
                 logger.info("Fall back category collection")
                 for c in stripHTML(categories[0]).replace(" Crossover","").split(' + '):
                     self.story.addToList('category',c)
-                
-                
-            
+
+
+
         a = soup.find('a', href=re.compile(r'https?://www\.fictionratings\.com/'))
         rating = a.string
         if 'Fiction' in rating: # if rating has 'Fiction ', strip that out for consistency with past.
             rating = rating[8:]
-            
+
         self.story.setMetadata('rating',rating)
 
         # after Rating, the same bit of text containing id:123456 contains
@@ -195,7 +199,7 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         summarydiv = gui_table1i.find('div',{'style':'margin-top:2px'})
         if summarydiv:
             self.setDescription(url,stripHTML(summarydiv))
-            
+
 
         grayspan = gui_table1i.find('span', {'class':'xgray xcontrast_txt'})
         # for b in grayspan.findAll('button'):
@@ -206,7 +210,7 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         #logger.debug("metalist:(%s)"%metalist)
 
         # Rated: Fiction K - English - Words: 158,078 - Published: 02-04-11
-        # Rated: Fiction T - English - Adventure/Sci-Fi - Naruto U. - Chapters: 22 - Words: 114,414 - Reviews: 395 - Favs: 779 - Follows: 835 - Updated: 03-21-13 - Published: 04-28-12 - id: 8067258 
+        # Rated: Fiction T - English - Adventure/Sci-Fi - Naruto U. - Chapters: 22 - Words: 114,414 - Reviews: 395 - Favs: 779 - Follows: 835 - Updated: 03-21-13 - Published: 04-28-12 - id: 8067258
 
         # rating is obtained above more robustly.
         if metalist[0].startswith('Rated:'):
@@ -235,7 +239,7 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
             # updated get set to the same as published upstream if not found.
             self.story.setMetadata('dateUpdated',datetime.fromtimestamp(float(dates[0]['data-xutime'])))
         self.story.setMetadata('datePublished',datetime.fromtimestamp(float(dates[-1]['data-xutime'])))
-            
+
         donechars = False
         while len(metalist) > 0:
             if  metalist[0].startswith('Chapters') or metalist[0].startswith('Status') or metalist[0].startswith('id:') or metalist[0].startswith('Updated:') or metalist[0].startswith('Published:'):
@@ -290,7 +294,7 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
                         authimg_url=img[0]['src']
 
                 logger.debug("authimg_url:%s"%authimg_url)
-            
+
                 ## ffnet uses different sizes on auth & story pages, but same id.
                 ## //ffcdn2012t-fictionpressllc.netdna-ssl.com/image/1936929/150/
                 ## //ffcdn2012t-fictionpressllc.netdna-ssl.com/image/1936929/180/
@@ -306,14 +310,14 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
                 ## don't use cover if it matches the auth image.
                 if cover_id and authimg_id and cover_id == authimg_id:
                     cover_url = None
-                    
+
             if cover_url:
                 self.setCoverImage(url,cover_url)
 
-                    
-        # Find the chapter selector 
+
+        # Find the chapter selector
         select = soup.find('select', { 'name' : 'chapter' } )
-    	 
+    	
         if select is None:
     	   # no selector found, so it's a one-chapter story.
     	   self.chapterUrls.append((self.story.getMetadata('title'),url))
@@ -342,7 +346,7 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
 
         if "Please email this error message in full to <a href='mailto:support@fanfiction.com'>support@fanfiction.com</a>" in data:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  FanFiction.net Site Error!" % url)
-        
+
         # some ancient stories have body tags inside them that cause
         # soup parsing to discard the content.  For story text we
         # don't care about anything before "<div role='main'" and
@@ -352,9 +356,9 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         # if divstr not in data:
         #     raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
         # else:
-        #     data = data[data.index(divstr):] 
+        #     data = data[data.index(divstr):]
         # data = data.replace("<body","<notbody").replace("<BODY","<NOTBODY")
-        
+
         soup = self.make_soup(data)
 
         ## Remove the 'share' button.
@@ -362,9 +366,9 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         # sharediv = soup.find('div', {'class' : 'a2a_kit a2a_default_style'})
         # if sharediv:
         #     sharediv.extract()
-        
+
         div = soup.find('div', {'id' : 'storytextp'})
-        
+
         if None == div:
             logger.debug('div id=storytextp not found.  data:%s'%data)
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)

fanficfare/adapters/adapter_fanfiktionde.py

@@ -22,7 +22,7 @@ import re
 import urllib
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -47,21 +47,21 @@ class FanFiktionDeAdapter(BaseSiteAdapter):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2])
-        
-        
+
+
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/s/'+self.story.getMetadata('storyId') + '/1')
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','ffde')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%d.%m.%Y"
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -73,14 +73,14 @@ class FanFiktionDeAdapter(BaseSiteAdapter):
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/s/")+r"\w+(/\d+)?"
-        
+
     def use_pagecache(self):
         '''
         adapters that will work with the page cache need to implement
         this and change it to True.
         '''
         return True
-    
+
         ## Login seems to be reasonably standard across eFiction sites.
     def needToLoginCheck(self, data):
         if 'Diese Geschichte wurde als entwicklungsbeeintr' in data \
@@ -89,7 +89,7 @@ class FanFiktionDeAdapter(BaseSiteAdapter):
             return True
         else:
             return False
-        
+
     def performLogin(self,url):
         params = {}
 
@@ -106,7 +106,7 @@ class FanFiktionDeAdapter(BaseSiteAdapter):
         loginUrl = 'https://ssl.fanfiktion.de/'
         logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
                                                               params['nickname']))
-        soup = bs.BeautifulSoup(self._postUrl(loginUrl,params))
+        soup = self.make_soup(self._postUrl(loginUrl,params))
         if not soup.find('a', title='Logout'):
             logger.info("Failed to login to URL %s as %s" % (loginUrl,
                                                               params['nickname']))
@@ -128,25 +128,25 @@ class FanFiktionDeAdapter(BaseSiteAdapter):
                 raise exceptions.StoryDoesNotExist(self.url)
             else:
                 raise e
-                
+
         if self.needToLoginCheck(data):
             # need to log in for this one.
             self.performLogin(url)
             data = self._fetchUrl(url,usecache=False)
-            
+
         if "Uhr ist diese Geschichte nur nach einer" in data:
             raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Auserhalb der Zeit von 23:00 Uhr bis 04:00 Uhr ist diese Geschichte nur nach einer erfolgreichen Altersverifikation zuganglich.")
-            
+
         # use BeautifulSoup HTML parser to make everything easier to find.
         soup = self.make_soup(data)
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
         ## Title
         a = soup.find('a', href=re.compile(r'/s/'+self.story.getMetadata('storyId')+"/"))
         self.story.setMetadata('title',stripHTML(a))
-        
+
         # Find authorid and URL from... author url.
         head = soup.find('div', {'class' : 'story-left'})
         a = head.find('a')
@@ -167,11 +167,11 @@ class FanFiktionDeAdapter(BaseSiteAdapter):
         # second colspan=3 td in head.
         genres=stripHTML(head.find('span',class_='fa-angle-right').next_sibling)
         self.story.extendList('genre',genres[:genres.index('/')].split(', '))
-        
+
         if head.find('span',title='Fertiggestellt'):
             self.story.setMetadata('status', 'Completed')
         else:
-            self.story.setMetadata('status', 'In Progress')
+            self.story.setMetadata('status', 'In-Progress')
 
         #find metadata on the author's page
         asoup = self.make_soup(self._fetchUrl("http://"+self.getSiteDomain()+"?a=q&a1=v&t=nickdetailsstories&lbi=stories&ar=0&nick="+self.story.getMetadata('authorId')))
@@ -181,13 +181,13 @@ class FanFiktionDeAdapter(BaseSiteAdapter):
             if '/s/'+self.story.getMetadata('storyId')+'/1/' in a['href']:
                 break
         self.setDescription(url,a['onmouseover'].split("', '")[1])
-        
+
         td = tr[i].findAll('td')
         self.story.addToList('category',stripHTML(td[2]))
         self.story.setMetadata('rating', stripHTML(td[5]))
         self.story.setMetadata('numWords', stripHTML(td[6]))
- 
-            
+
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
@@ -195,12 +195,12 @@ class FanFiktionDeAdapter(BaseSiteAdapter):
         time.sleep(0.5) ## ffde has "floodlock" protection
 
         soup = self.make_soup(self._fetchUrl(url))
-        
+
         div = soup.find('div', {'id' : 'storytext'})
         for a in div.findAll('script'):
             a.extract()
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_fhsarchivecom.py

@@ -32,11 +32,11 @@ class FHSArchiveComAdapter(BaseEfictionAdapter):
     @classmethod
     def getSiteAbbrev(self):
         return 'fhsa'
-        
+
     @classmethod
     def getDateFormat(self):
-        return "%m/%d/%y" 
-   
+        return "%m/%d/%y"
+
     def handleMetadataPair(self, key, value):
         if key == 'Warnings':
             for val in re.split("\s*,\s*", value):
@@ -45,13 +45,13 @@ class FHSArchiveComAdapter(BaseEfictionAdapter):
                 else:
                     # toss numbers only.
                     self.story.addToList('warnings', filter(lambda x : not x.isdigit() , val))
-     
+
     #     elif 'Categories' in key:
     #         for val in re.split("\s*>\s*", value):
     #             self.story.addToList('category', val)
         else:
-            super(FHSArchiveComAdapter, self).handleMetadataPair(key, value) 
-                           
+            super(FHSArchiveComAdapter, self).handleMetadataPair(key, value)
+
 def getClass():
     return FHSArchiveComAdapter
-    
+

fanficfare/adapters/adapter_ficbooknet.py

@@ -23,7 +23,7 @@ import re
 import urllib2
 from .. import translit
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -49,21 +49,21 @@ class FicBookNetAdapter(BaseSiteAdapter):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2])
-        
-        
+
+
         # normalized story URL.
-        self._setURL('http://' + self.getSiteDomain() + '/readfic/'+self.story.getMetadata('storyId'))
-        
+        self._setURL('https://' + self.getSiteDomain() + '/readfic/'+self.story.getMetadata('storyId'))
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','fbn')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = "%d %m %Y" 
-            
+        self.dateformat = "%d %m %Y"
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -71,10 +71,10 @@ class FicBookNetAdapter(BaseSiteAdapter):
 
     @classmethod
     def getSiteExampleURLs(cls):
-        return "http://"+cls.getSiteDomain()+"/readfic/12345 http://"+cls.getSiteDomain()+"/readfic/93626/246417#part_content"
+        return "https://"+cls.getSiteDomain()+"/readfic/12345 https://"+cls.getSiteDomain()+"/readfic/93626/246417#part_content"
 
     def getSiteURLPattern(self):
-        return re.escape("http://"+self.getSiteDomain()+"/readfic/")+r"\d+"
+        return r"https?://"+re.escape(self.getSiteDomain()+"/readfic/")+r"\d+"
 
     ## Getting the chapter list and the meta data, plus 'is adult' checking.
     def extractChapterUrlsAndMetadata(self):
@@ -90,41 +90,53 @@ class FicBookNetAdapter(BaseSiteAdapter):
 				
 
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
 
+        adult_div = soup.find('div',id='adultCoverWarning')
+        if adult_div:
+            if self.is_adult or self.getConfig("is_adult"):
+                adult_div.extract()
+            else:
+                raise exceptions.AdultCheckRequired(self.url)
+        
         # Now go hunting for all the meta data and the chapter list.
 		
-        table = soup.find('td',{'width':'50%'})
-        
         ## Title
-        a = soup.find('h1')
+        a = soup.find('section',{'class':'chapter-info'}).find('h1')
+        # kill '+' marks if present.
+        sup = a.find('sup')
+        if sup:
+            sup.extract()
         self.story.setMetadata('title',stripHTML(a))
         logger.debug("Title: (%s)"%self.story.getMetadata('title'))
-        
+
         # Find authorid and URL from... author url.
-        a = table.find('a')
+        # assume first avatar-nickname -- there can be a second marked 'beta'.
+        a = soup.find('a',{'class':'avatar-nickname'})
         self.story.setMetadata('authorId',a.text) # Author's name is unique
-        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('authorUrl','https://'+self.host+'/'+a['href'])
         self.story.setMetadata('author',a.text)
         logger.debug("Author: (%s)"%self.story.getMetadata('author'))
 
         # Find the chapters:
-        chapters = soup.find('div', {'class' : 'part_list'})
+        chapters = soup.find('ul', {'class' : 'table-of-contents'})
         if chapters != None:
             chapters=chapters.findAll('a', href=re.compile(r'/readfic/'+self.story.getMetadata('storyId')+"/\d+#part_content$"))
             self.story.setMetadata('numChapters',len(chapters))
             for x in range(0,len(chapters)):
                 chapter=chapters[x]
-                churl='http://'+self.host+chapter['href']
+                churl='https://'+self.host+chapter['href']
                 self.chapterUrls.append((stripHTML(chapter),churl))
                 if x == 0:
-                    pubdate = translit.translit(stripHTML(bs.BeautifulSoup(self._fetchUrl(churl)).find('div', {'class' : 'part_added'}).find('span')))
+                    pubdate = translit.translit(stripHTML(chapter.parent.find('span')))
+                    # pubdate = translit.translit(stripHTML(self.make_soup(self._fetchUrl(churl)).find('div', {'class' : 'part_added'}).find('span')))
                 if x == len(chapters)-1:
-                    update = translit.translit(stripHTML(bs.BeautifulSoup(self._fetchUrl(churl)).find('div', {'class' : 'part_added'}).find('span')))
+                    update = translit.translit(stripHTML(chapter.parent.find('span')))
+                    # update = translit.translit(stripHTML(self.make_soup(self._fetchUrl(churl)).find('div', {'class' : 'part_added'}).find('span')))
         else:
             self.chapterUrls.append((self.story.getMetadata('title'),url))
             self.story.setMetadata('numChapters',1)
-            pubdate=translit.translit(stripHTML(soup.find('div', {'class' : 'part_added'}).find('span')))
+            pubdate=translit.translit(stripHTML(soup.find('div',{'class':'title-area'}).find('span')))
             update=pubdate
 
         logger.debug("numChapters: (%s)"%self.story.getMetadata('numChapters'))
@@ -135,19 +147,20 @@ class FicBookNetAdapter(BaseSiteAdapter):
             update=datetime.date.today().strftime(self.dateformat)
         pubdate=pubdate.split(',')[0]
         update=update.split(',')[0]
-		
-        fullmon = {"yanvarya":"01", "января":"01",
-           "fievralya":"02", "февраля":"02",
-           "marta":"03", "марта":"03",
-           "aprielya":"04", "апреля":"04",
-           "maya":"05", "мая":"05",
-           "iyunya":"06", "июня":"06",
-           "iyulya":"07", "июля":"07",
-           "avghusta":"08", "августа":"08",
-           "sentyabrya":"09", "сентября":"09",
-           "oktyabrya":"10", "октября":"10",
-           "noyabrya":"11", "ноября":"11",
-           "diekabrya":"12", "декабря":"12" }
+
+        fullmon = {"yanvarya":"01", u"января":"01",
+           "fievralya":"02", u"февраля":"02",
+           "marta":"03", u"марта":"03",
+           "aprielya":"04", u"апреля":"04",
+           "maya":"05", u"мая":"05",
+           "iyunya":"06", u"июня":"06",
+           "iyulya":"07", u"июля":"07",
+           "avghusta":"08", u"августа":"08",
+           "sentyabrya":"09", u"сентября":"09",
+           "oktyabrya":"10", u"октября":"10",
+           "noyabrya":"11", u"ноября":"11",
+           "diekabrya":"12", u"декабря":"12" }
+
         for (name,num) in fullmon.items():
             if name in pubdate:
                 pubdate = pubdate.replace(name,num)
@@ -157,70 +170,78 @@ class FicBookNetAdapter(BaseSiteAdapter):
         self.story.setMetadata('dateUpdated', makeDate(update, self.dateformat))
         self.story.setMetadata('datePublished', makeDate(pubdate, self.dateformat))
         self.story.setMetadata('language','Russian')
-		
-        pr=soup.find('a', href=re.compile(r'/printfic/\w+'))
-        pr='http://'+self.host+pr['href']
-        pr = bs.BeautifulSoup(self._fetchUrl(pr))
-        pr=pr.findAll('div', {'class' : 'part_text'})
+
+        ## after site change, I don't see word count anywhere.
+        # pr=soup.find('a', href=re.compile(r'/printfic/\w+'))
+        # pr='https://'+self.host+pr['href']
+        # pr = self.make_soup(self._fetchUrl(pr))
+        # pr=pr.findAll('div', {'class' : 'part_text'})
+        # i=0
+        # for part in pr:
+        #     i=i+len(stripHTML(part).split(' '))
+        # self.story.setMetadata('numWords', unicode(i))
+
+
+        dlinfo = soup.find('dl',{'class':'info'})
+        
         i=0
-        for part in pr:
-            i=i+len(stripHTML(part).split(' '))
-        self.story.setMetadata('numWords', str(i))
-		
-        i=0
-        fandoms = table.findAll('a', href=re.compile(r'/fanfiction/\w+'))
+        fandoms = dlinfo.find('dd').findAll('a', href=re.compile(r'/fanfiction/\w+'))
         for fandom in fandoms:
             self.story.addToList('category',fandom.string)
             i=i+1
         if i > 1:
-            self.story.addToList('genre', 'Кроссовер')
-		
-        meta=table.findAll('a', href=re.compile(r'/ratings/'))
-        i=0
-        for m in meta:
-            if i == 0:
-                self.story.setMetadata('rating', m.find('b').text)
-                i=1
-            elif i == 1:
-                if not "," in m.nextSibling:
-                    i=2
-                self.story.addToList('genre', m.find('b').text)
-            elif i == 2:
-                self.story.addToList('warnings', m.find('b').text)
-		
+            self.story.addToList('genre', u'Кроссовер')
 
-        if table.find('span', {'style' : 'color: green'}):
+        for genre in dlinfo.findAll('a',href=re.compile(r'/genres/')):
+            self.story.addToList('genre',stripHTML(genre))
+
+        ratingdt = dlinfo.find('dt',text='Рейтинг:')
+        self.story.setMetadata('rating', stripHTML(ratingdt.next_sibling))
+            
+        # meta=table.findAll('a', href=re.compile(r'/ratings/'))
+        # i=0
+        # for m in meta:
+        #     if i == 0:
+        #         self.story.setMetadata('rating', stripHTML(m))
+        #         i=1
+        #     elif i == 1:
+        #         if not "," in m.nextSibling:
+        #             i=2
+        #         self.story.addToList('genre', m.find('b').text)
+        #     elif i == 2:
+        #         self.story.addToList('warnings', m.find('b').text)		
+
+        if dlinfo.find('span', {'style' : 'color: green'}):
             self.story.setMetadata('status', 'Completed')
         else:
-            self.story.setMetadata('status', 'In Progress')
+            self.story.setMetadata('status', 'In-Progress')
 		
 
-        tags = table.findAll('b')
+        tags = dlinfo.findAll('dt')
         for tag in tags:
             label = translit.translit(tag.text)
-            if 'Piersonazhi:' in label or 'Персонажи:' in label:
-                chars=tag.nextSibling.string.split(', ')
+            if 'Piersonazhi:' in label or u'Персонажи:' in label:
+                chars=stripHTML(tag.next_sibling).split(', ')
                 for char in chars:
                     self.story.addToList('characters',char)
                 break
 				
-        summary=soup.find('span', {'class' : 'urlize'})
+        summary=soup.find('div', {'class' : 'urlize'})
         self.setDescription(url,summary)
         #self.story.setMetadata('description', summary.text)
-            
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
+        soup = self.make_soup(self._fetchUrl(url))
+
         chapter = soup.find('div', {'class' : 'public_beta'})
         if chapter == None:
             chapter = soup.find('div', {'class' : 'public_beta_disabled'})
 
         if None == chapter:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,chapter)

fanficfare/adapters/adapter_fictionalleyorg.py

@@ -22,7 +22,7 @@ import re
 import urllib
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -39,20 +39,20 @@ class FictionAlleyOrgSiteAdapter(BaseSiteAdapter):
                                # iso-8859-1 (and some that claim to be
                                # utf8) are really windows-1252.
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query correct
         m = re.match(self.getSiteURLPattern(),url)
         if m:
             self.story.setMetadata('authorId',m.group('auth'))
             self.story.setMetadata('storyId',m.group('id'))
-            
+
             # normalized story URL.
             self._setURL(url)
         else:
             raise exceptions.InvalidStoryURL(url,
                                              self.getSiteDomain(),
                                              self.getSiteExampleURLs())
-            
+
     @staticmethod
     def getSiteDomain():
         return 'www.fictionalley.org'
@@ -92,17 +92,17 @@ class FictionAlleyOrgSiteAdapter(BaseSiteAdapter):
                 raise e
 
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
 
         chapterdata = data
         # If chapter list page, get the first chapter to look for adult check
         chapterlinklist = soup.findAll('a',{'class':'chapterlink'})
         if chapterlinklist:
             chapterdata = self._postFetchWithIAmOld(chapterlinklist[0]['href'])
-            
+
         if "Are you over seventeen years old" in chapterdata:
             raise exceptions.AdultCheckRequired(self.url)
-        
+
         if not chapterlinklist:
             # no chapter list, chapter URL: change to list link.
             # second a tag inside div breadcrumbs
@@ -113,19 +113,19 @@ class FictionAlleyOrgSiteAdapter(BaseSiteAdapter):
             ## title's right there...
             self.story.setMetadata('title',stripHTML(storya))
             data = self._fetchUrl(url)
-            soup = bs.BeautifulSoup(data)
+            soup = self.make_soup(data)
             chapterlinklist = soup.findAll('a',{'class':'chapterlink'})
         else:
             ## still need title from somewhere.  If chapterlinklist,
             ## then chapterdata contains a chapter, find title the
             ## same way.
-            chapsoup = bs.BeautifulSoup(chapterdata)
+            chapsoup = self.make_soup(chapterdata)
             storya = chapsoup.find('div',{'class':'breadcrumbs'}).findAll('a')[1]
             self.story.setMetadata('title',stripHTML(storya))
             del chapsoup
 
         del chapterdata
-        
+
         ## authorid already set.
         ## <h1 class="title" align="center">Just Off The Platform II by <a href="http://www.fictionalley.org/authors/drt/">DrT</a></h1>
         authora=soup.find('h1',{'class':'title'}).find('a')
@@ -144,7 +144,7 @@ class FictionAlleyOrgSiteAdapter(BaseSiteAdapter):
 
         ## Go scrape the rest of the metadata from the author's page.
         data = self._fetchUrl(self.story.getMetadata('authorUrl'))
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
 
         # <dl><dt><a class = "Rid story" href = "http://www.fictionalley.org/authors/aafro_man_ziegod/TMH.html">
         # [Rid] The Magical Hottiez</a> by <a class = "pen_name" href = "http://www.fictionalley.org/authors/aafro_man_ziegod/">Aafro Man Ziegod</a> </small></dt>
@@ -153,15 +153,15 @@ class FictionAlleyOrgSiteAdapter(BaseSiteAdapter):
         # Chaos ensues after Witch Weekly, seeking to increase readers, decides to create a boyband out of five seemingly talentless wizards: Harry Potter, Draco Malfoy, Ron Weasley, Neville Longbottom, and Oliver "Toss Your Knickers Here" Wood.<br />
         # <small class = "storyinfo">Published: June 3, 2002 (between Goblet of Fire and Order of Phoenix) - Updated: June 3, 2002</small>
         # </dd></dl>
-        
+
         storya = soup.find('a',{'href':self.story.getMetadata('storyUrl')})
         storydd = storya.findNext('dd')
 
         # Rating: PG - Spoilers: None - 2525 hits - 736 words
         # Genre: Humor - Main character(s): H, R - Ships: None - Era: Multiple Eras
         # Harry and Ron are back at it again! They reeeeeeally don't want to be back, because they know what's awaiting them. "VH1 Goes Inside..." is back! Why? 'Cos there are soooo many more couples left to pick on.
-        # Published: September 25, 2004 (between Order of Phoenix and Half-Blood Prince) - Updated: September 25, 2004 
-               
+        # Published: September 25, 2004 (between Order of Phoenix and Half-Blood Prince) - Updated: September 25, 2004
+
         ## change to text and regexp find.
         metastr = stripHTML(storydd).replace('\n',' ').replace('\t',' ')
 
@@ -173,7 +173,7 @@ class FictionAlleyOrgSiteAdapter(BaseSiteAdapter):
         if m:
             for g in m.group(1).split(','):
                 self.story.addToList('genre',g)
-        
+
         m = re.match(r".*?Published: ([a-zA-Z]+ \d\d?, \d\d\d\d).*?",metastr)
         if m:
             self.story.setMetadata('datePublished',makeDate(m.group(1), "%B %d, %Y"))
@@ -185,12 +185,13 @@ class FictionAlleyOrgSiteAdapter(BaseSiteAdapter):
         m = re.match(r".*? (\d+) words Genre.*?",metastr)
         if m:
             self.story.setMetadata('numWords', m.group(1))
-            
+
         for small in storydd.findAll('small'):
             small.extract() ## removes the <small> tags, leaving only the summary.
+        storydd.name = 'div' ## change tag name else Calibre treats it oddly.
         self.setDescription(url,storydd)
         #self.story.setMetadata('description',stripHTML(storydd))
-        
+
         return
 
     def getChapterText(self, url):
@@ -203,14 +204,16 @@ class FictionAlleyOrgSiteAdapter(BaseSiteAdapter):
 	# Yes, it's an evil kludge, but what can ya do?  Using
 	# something other than div prevents soup from pairing
 	# our div with poor html inside the story text.
-	data = data.replace('<!-- headerend -->','<crazytagstringnobodywouldstumbleonaccidently id="storytext">').replace('<!-- footerstart -->','</crazytagstringnobodywouldstumbleonaccidently>')
-        
+        crazy = "crazytagstringnobodywouldstumbleonaccidently"
+	data = data.replace('<!-- headerend -->','<'+crazy+' id="storytext">').replace('<!-- footerstart -->','</'+crazy+'>')
+
         # problems with some stories confusing Soup.  This is a nasty
         # hack, but it works.
-        data = data[data.index("<crazytagstringnobodywouldstumbleonaccidently"):]
+        data = data[data.index('<'+crazy+''):]
+        # ditto with extra crap at the end.
+        data = data[:data.index('</'+crazy+'>')+len('</'+crazy+'>')]
 
-        soup = bs.BeautifulStoneSoup(data,
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        soup = self.make_soup(data)
         body = soup.findAll('body') ## some stories use a nested body and body
                                     ## tag, in which case we don't
                                     ## need crazytagstringnobodywouldstumbleonaccidently
@@ -219,9 +222,9 @@ class FictionAlleyOrgSiteAdapter(BaseSiteAdapter):
             text = body[1]
             text.name='div' # force to be a div to avoid multiple body tags.
         else:
-            text = soup.find('crazytagstringnobodywouldstumbleonaccidently', {'id' : 'storytext'})
+            text = soup.find(crazy, {'id' : 'storytext'})
             text.name='div' # change to div tag.
-            
+
         if not data or not text:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
 
@@ -230,10 +233,10 @@ class FictionAlleyOrgSiteAdapter(BaseSiteAdapter):
         # epubutils.py
         for tag in text.findAll('head'):
             tag.extract()
-        
+
         for tag in text.findAll('body') + text.findAll('html'):
             tag.name = 'div'
-            
+
         return self.utf8FromSoup(url,text)
 
 def getClass():

fanficfare/adapters/adapter_fictionmaniatv.py

@@ -117,7 +117,7 @@ class FictionManiaTVAdapter(BaseSiteAdapter):
                 self.story.setMetadata('rating', value)
 
             elif key == 'Complete':
-                self.story.setMetadata('status', 'Complete' if value == 'Complete' else 'In-Progress')
+                self.story.setMetadata('status', 'Completed' if value == 'Complete' else 'In-Progress')
 
             elif key == 'Categories':
                 for element in cells[1]('a'):
@@ -158,7 +158,7 @@ class FictionManiaTVAdapter(BaseSiteAdapter):
         # While wrapping in paragraphs would be possible, it's too much work,
         # I'd rather display the story 1:1 like it was found in the pre tag.
         content = unicode(element)
-        content = content.replace('\n', '<br />')
+        content = content.replace('\n', '<br/>')
 
         if self.getConfig('non_breaking_spaces'):
             return content.replace(' ', '&nbsp;')

fanficfare/adapters/adapter_fictionpadcom.py

@@ -23,7 +23,7 @@ import urllib2
 import time
 import json
 
-from .. import BeautifulSoup as bs
+
 #from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -42,7 +42,7 @@ class FictionPadSiteAdapter(BaseSiteAdapter):
         m = re.match(self.getSiteURLPattern(),url)
         if m:
             self.story.setMetadata('storyId',m.group('id'))
-            
+
             # normalized story URL.
             self._setURL("https://"+self.getSiteDomain()
                          +"/author/"+m.group('author')
@@ -59,7 +59,7 @@ class FictionPadSiteAdapter(BaseSiteAdapter):
     @classmethod
     def getSiteExampleURLs(cls):
         return "https://fictionpad.com/author/Author/stories/1234/Some-Title"
-    
+
     def getSiteURLPattern(self):
         # http://fictionpad.com/author/Serdd/stories/4275
         return r"http(s)?://(www\.)?fictionpad\.com/author/(?P<author>[^/]+)/stories/(?P<id>\d+)"
@@ -93,16 +93,16 @@ class FictionPadSiteAdapter(BaseSiteAdapter):
                                                               params['login']))
 
         ## need to pull empty login page first to get authenticity_token
-        soup = bs.BeautifulSoup(self._fetchUrl(loginUrl))
+        soup = self.make_soup(self._fetchUrl(loginUrl))
         params['authenticity_token']=soup.find('input', {'name':'authenticity_token'})['value']
-        
+
         data = self._postUrl(loginUrl, params)
 
         if "Invalid email/pseudonym and password combination." in data:
             logger.info("Failed to login to URL %s as %s" % (loginUrl,
                                                               params['login']))
             raise exceptions.FailedToLogin(loginUrl,params['login'])
-            
+
 
     def extractChapterUrlsAndMetadata(self):
         # fetch the chapter.  From that we will get almost all the
@@ -116,7 +116,7 @@ class FictionPadSiteAdapter(BaseSiteAdapter):
             if "This is a mature story.  Please sign in to read it." in data:
                 self.performLogin()
                 data = self._fetchUrl(url)
-            
+
             find = "wordyarn.config.page = "
             data = data[data.index(find)+len(find):]
             data = data[:data.index("</script>")]
@@ -134,14 +134,14 @@ class FictionPadSiteAdapter(BaseSiteAdapter):
         story = tables['stories'][0]
         story_ver = tables['story_versions'][0]
         logger.debug("story:%s"%story)
-        
+
         self.story.setMetadata('authorId',author['id'])
         self.story.setMetadata('author',author['display_name'])
         self.story.setMetadata('authorUrl','https://'+self.host+'/author/'+author['display_name']+'/stories')
 
         self.story.setMetadata('title',story_ver['title'])
         self.setDescription(url,story_ver['description'])
-        
+
         if not ('assets/story_versions/covers' in story_ver['profile_image_url@2x']):
             self.setCoverImage(url,story_ver['profile_image_url@2x'])
 
@@ -165,10 +165,10 @@ class FictionPadSiteAdapter(BaseSiteAdapter):
 
         for i in tables['fandoms']:
             self.story.addToList('category',i['name'])
-        
+
         for i in tables['genres']:
             self.story.addToList('genre',i['name'])
-        
+
         for i in tables['characters']:
             self.story.addToList('characters',i['name'])
 
@@ -179,16 +179,16 @@ class FictionPadSiteAdapter(BaseSiteAdapter):
             self.chapterUrls.append((chtitle,c['body_url']))
 
         self.story.setMetadata('numChapters',len(self.chapterUrls))
-            
+
     def getChapterText(self, url):
         logger.debug('Getting chapter text from: %s' % url)
         if not url:
             data = u"<em>This chapter has no text.</em>"
         else:
             data = self._fetchUrl(url)
-        soup = bs.BeautifulSoup(u"<div id='story'>"+data+u"</div>")
+        soup = self.make_soup(u"<div id='story'>"+data+u"</div>")
         return self.utf8FromSoup(url,soup)
-    
+
 def getClass():
     return FictionPadSiteAdapter
 

fanficfare/adapters/adapter_ficwadcom.py

@@ -33,10 +33,10 @@ class FicwadComSiteAdapter(BaseSiteAdapter):
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
         self.story.setMetadata('siteabbrev','fw')
-        
+
         # get storyId from url--url validation guarantees second part is storyId
         self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2])
-        
+
         self.username = "NoneGiven"
         self.password = ""
 
@@ -72,8 +72,8 @@ class FicwadComSiteAdapter(BaseSiteAdapter):
             raise exceptions.FailedToLogin(url,params['username'])
             return False
         else:
-            return True        
-    
+            return True
+
     def use_pagecache(self):
         '''
         adapters that will work with the page cache need to implement
@@ -93,7 +93,7 @@ class FicwadComSiteAdapter(BaseSiteAdapter):
         try:
             data = self._fetchUrl(url)
             # non-existent/removed story urls get thrown to the front page.
-            if "<h2>Welcome to FicWad</h2>" in data:
+            if "<h4>Featured Story</h4>" in data:
                 raise exceptions.StoryDoesNotExist(self.url)
             soup = self.make_soup(data)
         except urllib2.HTTPError, e:
@@ -101,7 +101,7 @@ class FicwadComSiteAdapter(BaseSiteAdapter):
                 raise exceptions.StoryDoesNotExist(self.url)
             else:
                 raise e
-            
+
         # if blocked, attempt login.
         if soup.find("div",{"class":"blocked"}) or soup.find("li",{"class":"blocked"}):
             if self.performLogin(url): # performLogin raises
@@ -159,7 +159,7 @@ class FicwadComSiteAdapter(BaseSiteAdapter):
         ## perhaps not the most efficient way to parse this, using
         ## regexps for each rather than something more complex, but
         ## IMO, it's more readable and amenable to change.
-        metastr = stripHTML(str(metap)).replace('\n',' ').replace('\t',' ').replace(u'\u00a0',' ')
+        metastr = stripHTML(unicode(metap)).replace('\n',' ').replace('\t',' ').replace(u'\u00a0',' ')
 
         m = re.match(r".*?Rating: (.+?) -.*?",metastr)
         if m:
@@ -169,19 +169,19 @@ class FicwadComSiteAdapter(BaseSiteAdapter):
         if m:
             for g in m.group(1).split(','):
                 self.story.addToList('genre',g)
-        
+
         m = re.match(r".*?Characters: (.*?) -.*?",metastr)
         if m:
             for g in m.group(1).split(','):
                 if g:
                     self.story.addToList('characters',g)
-        
+
         m = re.match(r".*?Published: ([0-9-]+?) -.*?",metastr)
         if m:
             self.story.setMetadata('datePublished',makeDate(m.group(1), "%Y-%m-%d"))
 
         # Updated can have more than one space after it. <shrug>
-        m = re.match(r".*?Updated: ([0-9-]+?) +-.*?",metastr) 
+        m = re.match(r".*?Updated: ([0-9-]+?) +-.*?",metastr)
         if m:
             self.story.setMetadata('dateUpdated',makeDate(m.group(1), "%Y-%m-%d"))
 

fanficfare/adapters/adapter_fimfictionnet.py

@@ -34,18 +34,18 @@ def getClass():
     return FimFictionNetSiteAdapter
 
 class FimFictionNetSiteAdapter(BaseSiteAdapter):
-    
+
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
         self.story.setMetadata('siteabbrev','fimficnet')
         self.story.setMetadata('storyId', self.parsedUrl.path.split('/',)[2])
         self._setURL("http://"+self.getSiteDomain()+"/story/"+self.story.getMetadata('storyId')+"/")
         self.is_adult = False
-        
+
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%d %b %Y"
-            
+
     @staticmethod
     def getSiteDomain():
         return 'www.fimfiction.net'
@@ -61,29 +61,32 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
 
     def getSiteURLPattern(self):
         return r"https?://(www|mobile)\.fimfiction\.(net|com)/story/\d+/?.*"
-        
+
     def use_pagecache(self):
         '''
         adapters that will work with the page cache need to implement
         this and change it to True.
         '''
         return True
-    
+
+    def set_adult_cookie(self):
+        cookie = cl.Cookie(version=0, name='view_mature', value='true',
+                           port=None, port_specified=False,
+                           domain=self.getSiteDomain(), domain_specified=False, domain_initial_dot=False,
+                           path='/', path_specified=True,
+                           secure=False,
+                           expires=time.time()+10000,
+                           discard=False,
+                           comment=None,
+                           comment_url=None,
+                           rest={'HttpOnly': None},
+                           rfc2109=False)
+        self.get_cookiejar().set_cookie(cookie)
+
     def doExtractChapterUrlsAndMetadata(self,get_cover=True):
-        
+
         if self.is_adult or self.getConfig("is_adult"):
-            cookie = cl.Cookie(version=0, name='view_mature', value='true',
-                               port=None, port_specified=False,
-                               domain=self.getSiteDomain(), domain_specified=False, domain_initial_dot=False,
-                               path='/story', path_specified=True,
-                               secure=False,
-                               expires=time.time()+10000,
-                               discard=False,
-                               comment=None,
-                               comment_url=None,
-                               rest={'HttpOnly': None},
-                               rfc2109=False)
-            self.cookiejar.set_cookie(cookie)
+            self.set_adult_cookie()
 
         ##---------------------------------------------------------------------------------------------------
         ## Get the story's title page. Check if it exists.
@@ -99,13 +102,13 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
                 raise exceptions.StoryDoesNotExist(self.url)
             else:
                 raise e
-        
+
         if "Warning: mysql_fetch_array(): supplied argument is not a valid MySQL result resource" in data:
             raise exceptions.StoryDoesNotExist(self.url)
 
         if "This story has been marked as having adult content. Please click below to confirm you are of legal age to view adult material in your country." in data:
             raise exceptions.AdultCheckRequired(self.url)
-        
+
         if self.password:
             params = {}
             params['password'] = self.password
@@ -178,8 +181,11 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
             if get_cover:
                 # try setting from href, if fails, try using the img src
                 if self.setCoverImage(self.url,coverurl)[0] == "failedtoload":
-                    coverurl = storyImage.find('img')['src']
-                    self.setCoverImage(self.url,coverurl)
+                    img = storyImage.find('img')
+                    # try src, then data-src, then leave None.
+                    coverurl = img.get('src',img.get('data-src',None))
+                    if coverurl:
+                        self.setCoverImage(self.url,coverurl)
 
             coverSource = storyImage.find('a', {'class':'source'})
             if coverSource:
@@ -266,7 +272,7 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
 
         #groups
         if soup.find('button', {'id':'button-view-all-groups'}):
-            groupResponse = self._fetchUrl("http://www.fimfiction.net/ajax/groups/story_groups_list.php?story=%s" % (self.story.getMetadata("storyId")))
+            groupResponse = self._fetchUrl("https://www.fimfiction.net/ajax/stories/%s/groups" % (self.story.getMetadata("storyId")))
             groupData = json.loads(groupResponse)
             groupList = self.make_soup(groupData["content"])
         else:
@@ -274,7 +280,7 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
 
         if not (groupList == None):
             for groupName in groupList.find_all('a'):
-                self.story.addToList("groupsUrl", 'http://'+self.host+groupName["href"]) 
+                self.story.addToList("groupsUrl", 'http://'+self.host+groupName["href"])
                 self.story.addToList("groups",stripHTML(groupName).replace(',', ';'))
 
         #sequels
@@ -283,7 +289,7 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
             if header.text.startswith('Sequels'):
                 sequelContainer = header.parent
                 for sequel in sequelContainer.find_all('a', {'class':'story_link'}):
-                    self.story.addToList("sequelsUrl", 'http://'+self.host+sequel["href"]) 
+                    self.story.addToList("sequelsUrl", 'http://'+self.host+sequel["href"])
                     self.story.addToList("sequels", stripHTML(sequel).replace(',', ';'))
 
         #author last login
@@ -302,7 +308,7 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
                 durationGroups = re.match(r"(?:[^0-9]*(\d+?)w)?[^0-9]*(?:(\d+?)d)?", lastLoginString)
                 lastLogin = date.today() - timedelta(days=int(durationGroups.group(2) or 0), weeks=int(durationGroups.group(1) or 0))
             self.story.setMetadata("authorLastLogin", lastLogin)
-                
+
         #The link to the prequel is embedded in the description text, so erring
         #on the side of caution and wrapping this whole thing in a try block.
         #If anything goes wrong this probably wasn't a valid prequel link.
@@ -336,7 +342,7 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
             data = re.sub(r'<p([^>]*>\s*)<blockquote([^>]*>)',r'<blockquote\2<p\1',data)
             data = re.sub(r'</blockquote(>\s*)</p>',r'</p\1</blockquote>',data)
         return data
-        
+
     def getChapterText(self, url):
         logger.debug('Getting chapter text from: %s' % url)
 

fanficfare/adapters/adapter_finestoriescom.py

@@ -15,274 +15,32 @@
 # limitations under the License.
 #
 
-import time
 import logging
 logger = logging.getLogger(__name__)
-import re
-import urllib2
-
-from .. import BeautifulSoup as bs
-from ..htmlcleanup import stripHTML
-from .. import exceptions as exceptions
-
-from base_adapter import BaseSiteAdapter,  makeDate
+from adapter_storiesonlinenet import StoriesOnlineNetAdapter
 
 def getClass():
     return FineStoriesComAdapter
 
 # Class name has to be unique.  Our convention is camel case the
 # sitename with Adapter at the end.  www is skipped.
-class FineStoriesComAdapter(BaseSiteAdapter):
+class FineStoriesComAdapter(StoriesOnlineNetAdapter):
 
-    def __init__(self, config, url):
-        BaseSiteAdapter.__init__(self, config, url)
+    @classmethod
+    def getSiteAbbrev(self):
+        return 'fnst'
 
-        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
-        self.password = ""
-        self.is_adult=False
-        
-        # get storyId from url
-        self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2].split(':')[0])
-        if 'storyInfo' in self.story.getMetadata('storyId'):
-            self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        # normalized story URL.
-        self._setURL('http://' + self.getSiteDomain() + '/s/storyInfo.php?id='+self.story.getMetadata('storyId'))
-        
-        # Each adapter needs to have a unique site abbreviation.
-        self.story.setMetadata('siteabbrev','fnst')
-
-        # The date format will vary from site to site.
-        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = "%Y-%m-%d"
-            
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
         return 'finestories.com'
 
-    @classmethod
-    def getSiteExampleURLs(cls):
-        return "http://"+cls.getSiteDomain()+"/s/1234 http://"+cls.getSiteDomain()+"/s/1234:4010 http://"+cls.getSiteDomain()+"/library/storyInfo.php?id=1234"
-
-    def getSiteURLPattern(self):
-        return re.escape("http://"+self.getSiteDomain())+r"/(s|library)?/(storyInfo.php\?id=)?\d+(:\d+)?(;\d+)?$"
-
     ## Login seems to be reasonably standard across eFiction sites.
     def needToLoginCheck(self, data):
         if 'Free Registration' in data \
+                or "Log In" in data \
                 or "Invalid Password!" in data \
                 or "Invalid User Name!" in data:
             return True
         else:
             return False
-        
-    def performLogin(self, url):
-        params = {}
-
-        if self.password:
-            params['theusername'] = self.username
-            params['thepassword'] = self.password
-        else:
-            params['theusername'] = self.getConfig("username")
-            params['thepassword'] = self.getConfig("password")
-        params['rememberMe'] = '1'
-        params['page'] = 'http://'+self.getSiteDomain()+'/'
-        params['submit'] = 'Login'
-    
-        loginUrl = 'http://' + self.getSiteDomain() + '/login.php'
-        logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
-                                                              params['theusername']))
-    
-        d = self._fetchUrl(loginUrl, params)
-    
-        if "My Account" not in d : #Member Account
-            logger.info("Failed to login to URL %s as %s" % (loginUrl,
-                                                              params['theusername']))
-            raise exceptions.FailedToLogin(url,params['theusername'])
-            return False
-        else:
-            return True
-
-    ## Getting the chapter list and the meta data, plus 'is adult' checking.
-    def extractChapterUrlsAndMetadata(self):
-
-        # index=1 makes sure we see the story chapter index.  Some
-        # sites skip that for one-chapter stories.
-        url = self.url
-        logger.debug("URL: "+url)
-
-        try:
-            data = self._fetchUrl(url)
-        except urllib2.HTTPError, e:
-            if e.code == 404:
-                raise exceptions.StoryDoesNotExist(self.url)
-            else:
-                raise e
-
-        if self.needToLoginCheck(data):
-            # need to log in for this one.
-            self.performLogin(url)
-            data = self._fetchUrl(url)
-            
-        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
-        # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
-        # print data
-
-        # Now go hunting for all the meta data and the chapter list.
-        
-        ## Title
-        a = soup.find('a', href=re.compile(r'/s/'+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',stripHTML(a))
-        
-        # Find authorid and URL from... author url.
-        a = soup.find('a', href=re.compile(r"/a/\w+"))
-        self.story.setMetadata('authorId',a['href'].split('/')[2])
-        self.story.setMetadata('authorUrl','http://'+self.host+a['href'])
-        self.story.setMetadata('author',a.text)
-
-        # Find the chapters:
-        chapters = soup.findAll('a', href=re.compile(r'/s/'+self.story.getMetadata('storyId')+":\d+$"))
-        if len(chapters) != 0:
-            for chapter in chapters:
-                # just in case there's tags, like <i> in chapter titles.
-                self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+chapter['href']))
-        else:
-            self.chapterUrls.append((self.story.getMetadata('title'),'http://'+self.host+'/s/'+self.story.getMetadata('storyId')))
-
-        self.story.setMetadata('numChapters',len(self.chapterUrls))
-
-        # surprisingly, the detailed page does not give enough details, so go to author's page
-        
-        skip=0
-        i=0
-        while i == 0:
-            asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')+"&skip="+str(skip)))
-        
-            a = asoup.findAll('td', {'class' : 'lc2'})
-            for lc2 in a:
-                if lc2.find('a')['href'] == '/s/'+self.story.getMetadata('storyId'):
-                    i=1
-                    break
-                if a[len(a)-1] == lc2:
-                    skip=skip+10
-        
-        for cat in lc2.findAll('div', {'class' : 'typediv'}):
-            self.story.addToList('category',cat.text)
-        
-        self.story.setMetadata('size', lc2.findNext('td', {'class' : 'num'}).text)
-        
-        lc4 = lc2.findNext('td', {'class' : 'lc4'})
-        
-        
-        try:
-            a = lc4.find('a', href=re.compile(r"/library/show_series.php\?id=\d+"))
-            i = a.parent.text.split('(')[1].split(')')[0]
-            self.setSeries(a.text, i)
-            self.story.setMetadata('seriesUrl','http://'+self.host+a['href'])
-        except:
-            pass
-        try:
-            a = lc4.find('a', href=re.compile(r"/library/universe.php\?id=\d+"))
-            self.story.addToList("category",a.text)
-        except:
-            pass
-            
-        for a in lc4.findAll('span', {'class' : 'help'}):
-            a.extract()
-            
-        self.setDescription('http://'+self.host+'/s/'+self.story.getMetadata('storyId'),lc4.text.split('[More Info')[0])
-            
-        for b in lc4.findAll('b'):
-            label = b.text
-            value = b.nextSibling
-            
-            if 'For Age' in label:
-                self.story.setMetadata('rating', value)
-                
-            if 'Tags' in label:
-                for genre in value.split(', '):
-                    self.story.addToList('genre',genre)
-                    
-            if 'Posted' in label:
-                self.story.setMetadata('datePublished', makeDate(stripHTML(value.split('/ (')[0]), self.dateformat))
-                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value.split('/ (')[0]), self.dateformat))
-                
-            if 'Concluded' in label:
-                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value.split('/ (')[0]), self.dateformat))
-                
-            if 'Updated' in label:
-                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value.split('/ (')[0]), self.dateformat))
-                
-        status = lc4.find('span', {'class' : 'ab'})
-        if  status != None:
-            self.story.setMetadata('status', 'In-Progress')
-            if "Last Activity" in status.text:
-                self.story.setMetadata('dateUpdated', makeDate(status.text.split('Activity: ')[1].split(')')[0], self.dateformat))
-        else:
-            self.story.setMetadata('status', 'Completed')
-
-            
-    # grab the text for an individual chapter.
-    def getChapterText(self, url):
-
-        logger.debug('Getting chapter text from: %s' % url)
-
-        soup = bs.BeautifulSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
-        div = soup.find('div', {'id' : 'story'})
-        
-        # some big chapters are split over several pages
-        pager = div.find('span', {'class' : 'pager'})
-        if pager != None:
-            urls=pager.findAll('a')
-            urls=urls[:len(urls)-1]
-            
-            
-            for ur in urls:
-                soup = bs.BeautifulSoup(self._fetchUrl("http://"+self.getSiteDomain()+ur['href']),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
-                div1 = soup.find('div', {'id' : 'story'})
-                
-                # appending next section
-                last=div.findAll('p')
-                next=div1.find('span', {'class' : 'conTag'}).nextSibling
-            
-                last[len(last)-1]=last[len(last)-1].append(next)
-                div.append(div1)
-            
-        # removing all the left-over stuff    
-        for a in div.findAll('span'):
-            a.extract()
-            
-        for a in div.findAll('h1'):
-            a.extract()
-        for a in div.findAll('h2'):
-            a.extract()
-        for a in div.findAll('h3'):
-            a.extract()
-        for a in div.findAll('h4'):
-            a.extract()
-        for a in div.findAll('br'):
-            a.extract()
-        for a in div.findAll('div', {'class' : 'date'}):
-            a.extract()
-            
-        a = div.find('form')
-        if a != None:
-            b = a.nextSibling
-            while b != None:
-                a.extract()
-                a=b
-                b=b.nextSibling
-        
-
-        if None == div:
-            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
-        return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_forumquestionablequestingcom.py

@@ -0,0 +1,36 @@
+#  -*- coding: utf-8 -*-
+
+# Copyright 2015 FanFicFare team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+import re
+
+from base_xenforoforum_adapter import BaseXenForoForumAdapter
+
+def getClass():
+    return QuestionablequestingComAdapter
+
+class QuestionablequestingComAdapter(BaseXenForoForumAdapter):
+
+    def __init__(self, config, url):
+        BaseXenForoForumAdapter.__init__(self, config, url)
+
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','qq')
+
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'forum.questionablequesting.com'
+

fanficfare/adapters/adapter_forumsspacebattlescom.py

@@ -0,0 +1,35 @@
+#  -*- coding: utf-8 -*-
+
+# Copyright 2015 FanFicFare team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+from base_xenforoforum_adapter import BaseXenForoForumAdapter
+
+def getClass():
+    return ForumsSpacebattlesComAdapter
+
+class ForumsSpacebattlesComAdapter(BaseXenForoForumAdapter):
+
+    def __init__(self, config, url):
+        BaseXenForoForumAdapter.__init__(self, config, url)
+
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','fsb')
+
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'forums.spacebattles.com'
+

fanficfare/adapters/adapter_forumssufficientvelocitycom.py

@@ -0,0 +1,34 @@
+#  -*- coding: utf-8 -*-
+
+# Copyright 2015 FanFicFare team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+from base_xenforoforum_adapter import BaseXenForoForumAdapter
+
+def getClass():
+    return ForumsSufficientVelocityComAdapter
+
+class ForumsSufficientVelocityComAdapter(BaseXenForoForumAdapter):
+
+    def __init__(self, config, url):
+        BaseXenForoForumAdapter.__init__(self, config, url)
+
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','fsv')
+
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'forums.sufficientvelocity.com'

fanficfare/adapters/adapter_harrypotterfanfictioncom.py

@@ -23,7 +23,7 @@ import re
 import urllib
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -40,15 +40,15 @@ class HarryPotterFanFictionComSiteAdapter(BaseSiteAdapter):
                                # iso-8859-1 (and some that claim to be
                                # utf8) are really windows-1252.
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only psid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
+
+
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?psid='+self.story.getMetadata('storyId'))
 
-            
+
     @staticmethod
     def getSiteDomain():
         return 'www.harrypotterfanfiction.com'
@@ -86,10 +86,10 @@ class HarryPotterFanFictionComSiteAdapter(BaseSiteAdapter):
                 raise e
 
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
 
         ## Title
         a = soup.find('a', href=re.compile(r'\?psid='+self.story.getMetadata('storyId')))
@@ -97,8 +97,8 @@ class HarryPotterFanFictionComSiteAdapter(BaseSiteAdapter):
         ## javascript:if (confirm('Please note. This story may contain adult themes. By clicking here you are stating that you are over 17. Click cancel if you do not meet this requirement.')) location = '?psid=290995'
         if "This story may contain adult themes." in a['href'] and not (self.is_adult or self.getConfig("is_adult")):
             raise exceptions.AdultCheckRequired(self.url)
-            
-        
+
+
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?showuid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
@@ -113,8 +113,8 @@ class HarryPotterFanFictionComSiteAdapter(BaseSiteAdapter):
             tdstr = tr.findAll('td')[2].string
             if tdstr and tdstr.isdigit():
                 words+=int(tdstr)
-        self.story.setMetadata('numWords',str(words))
-        
+        self.story.setMetadata('numWords',unicode(words))
+
         # Find the chapters:
         tablelist = soup.find('table',{'class':'text'})
         for chapter in tablelist.findAll('a', href=re.compile(r'\?chapterid=\d+')):
@@ -135,7 +135,7 @@ class HarryPotterFanFictionComSiteAdapter(BaseSiteAdapter):
         #for center in soup.findAll('center'):
         table = soup.find('table',{'class':'storymaininfo'})
         if table:
-            metastr = stripHTML(str(table)).replace('\n',' ').replace('\t',' ')
+            metastr = stripHTML(unicode(table)).replace('\n',' ').replace('\t',' ')
             # Rating: 12+ Story Reviews: 3
             # Chapters: 3
             # Characters: Andromeda, Ted, Bellatrix, R. Lestrange, Lucius, Narcissa, OC
@@ -161,18 +161,18 @@ class HarryPotterFanFictionComSiteAdapter(BaseSiteAdapter):
             if m:
                 for g in m.group(1).split(','):
                     self.story.addToList('genre',g)
-    
+
             m = re.match(r".*?Characters: (.+?) Genre.*?",metastr)
             if m:
                 for g in m.group(1).split(','):
                     self.story.addToList('characters',g)
-    
+
             m = re.match(r".*?Warnings: (.+).*?",metastr)
             if m:
                 for w in m.group(1).split(','):
                     if w != 'Now Warnings':
                         self.story.addToList('warnings',w)
-    
+
             m = re.match(r".*?First Published: ([0-9\.]+).*?",metastr)
             if m:
                 self.story.setMetadata('datePublished',makeDate(m.group(1), "%Y.%m.%d"))
@@ -186,11 +186,18 @@ class HarryPotterFanFictionComSiteAdapter(BaseSiteAdapter):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        ## most adapters use BeautifulStoneSoup here, but non-Stone
-        ## allows nested div tags.
-        soup = bs.BeautifulSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        data = self._fetchUrl(url)
+
+        try:
+            # remove everything after here--the site's chapters break
+            # the BS4 parser.
+            data = data[:data.index('<script type="text/javascript" src="reviewjs.js">')]
+        except:
+            # some older stories don't have the code at the end that breaks things.
+            pass
         
+        soup = self.make_soup(data)
+
         div = soup.find('div', {'id' : 'fluidtext'})
 
         if None == div:

fanficfare/adapters/adapter_hlfictionnet.py

@@ -22,7 +22,7 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -46,21 +46,21 @@ class HLFictionNetAdapter(BaseSiteAdapter):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
+
+
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','hlf')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%m/%d/%y"
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -88,41 +88,41 @@ class HLFictionNetAdapter(BaseSiteAdapter):
                 raise exceptions.StoryDoesNotExist(self.url)
             else:
                 raise e
-            
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
         ## Title and author
         a = soup.find('div', {'id' : 'pagetitle'})
-        
+
         aut = a.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',aut['href'].split('=')[1])
         self.story.setMetadata('authorUrl','http://'+self.host+'/'+aut['href'])
         self.story.setMetadata('author',aut.string)
         aut.extract()
-        
+
         self.story.setMetadata('title',stripHTML(a)[:(len(a.string)-3)])
 
         # Find the chapters:
         chapters=soup.find('select')
         if chapters != None:
             for chapter in chapters.findAll('option'):
-                # just in case there's tags, like <i> in chapter titles. 
+                # just in case there's tags, like <i> in chapter titles.
                 self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/viewstory.php?sid='+self.story.getMetadata('storyId')+'&chapter='+chapter['value']))
         else:
             self.chapterUrls.append((self.story.getMetadata('title'),url))
 
         self.story.setMetadata('numChapters',len(self.chapterUrls))
-        
-        asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
-        
-        for list in asoup.findAll('div', {'class' : re.compile('listbox\s+')}):
+
+        asoup = self.make_soup(self._fetchUrl(self.story.getMetadata('authorUrl')))
+
+        for list in asoup.findAll('div', {'class' : re.compile('listbox')}):
             a = list.find('a')
             if ('viewstory.php?sid='+self.story.getMetadata('storyId')) in a['href']:
                 break
@@ -146,8 +146,8 @@ class HLFictionNetAdapter(BaseSiteAdapter):
             if 'Summary' in label:
                 ## Everything until the next span class='label'
                 svalue = ""
-                while not defaultGetattr(value,'class') == 'classification':
-                    svalue += str(value)
+                while 'classification' not in defaultGetattr(value,'class'):
+                    svalue += unicode(value)
                     value = value.nextSibling
                 self.setDescription(url,svalue)
                 #self.story.setMetadata('description',stripHTML(svalue))
@@ -186,7 +186,7 @@ class HLFictionNetAdapter(BaseSiteAdapter):
 
             if 'Published' in label:
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
+
             if 'Updated' in label:
                 # there's a stray [ at the end.
                 #value = value[0:-1]
@@ -199,7 +199,7 @@ class HLFictionNetAdapter(BaseSiteAdapter):
             series_url = 'http://'+self.host+'/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            seriessoup = self.make_soup(self._fetchUrl(series_url))
             # can't use ^viewstory...$ in case of higher rated stories with javascript href.
             storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+'))
             i=1
@@ -211,22 +211,21 @@ class HLFictionNetAdapter(BaseSiteAdapter):
                         self.story.setMetadata('seriesUrl',series_url)
                         break
                     i+=1
-            
+
         except:
             # I find it hard to care if the series parsing fails
             pass
-            
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
+        soup = self.make_soup(self._fetchUrl(url))
+
         div = soup.find('div', {'id' : 'story'})
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_hpfandomnet.py

@@ -22,7 +22,6 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -50,22 +49,22 @@ class HPFandomNetAdapterAdapter(BaseSiteAdapter): # XXX
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
+
+
         # normalized story URL.
         # XXX Most sites don't have the /eff part.  Replace all to remove it usually.
         self._setURL('http://' + self.getSiteDomain() + '/eff/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','hpfdm') # XXX
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%Y.%m.%d" # XXX
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -93,11 +92,33 @@ class HPFandomNetAdapterAdapter(BaseSiteAdapter): # XXX
                 raise e
 
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
+        # set first URL
+        a = soup.find('a', href=re.compile(r"viewstory.php\?sid=\d+"))
+        ## href = "javascript:if (confirm('Slash/het fiction which incorporates sexual situations to a somewhat graphic degree  as well as graphic violent situations.  ')) location = 'viewstory.php?sid=49111&i=1'"
+        m = re.match(r'.*?(viewstory.php\?sid=\d+)',a['href'])
+        self._setURL('http://'+self.host+'/eff/'+m.group(1))
+        if self.parsedUrl.query.split('=',)[1] != self.story.getMetadata('storyId'):
+            self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+            url = self.url
+            logger.debug("reset URL: "+url)
+            try:
+                data = self._fetchUrl(url)
+            except urllib2.HTTPError, e:
+                if e.code == 404:
+                    raise exceptions.StoryDoesNotExist(self.url)
+                else:
+                    raise e
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            soup = self.make_soup(data)
+
+#        self.story.setMetadata('storyId', re.compile(self.getSiteURLPattern()).match(a).group('storyId'))
+
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
@@ -109,25 +130,26 @@ class HPFandomNetAdapterAdapter(BaseSiteAdapter): # XXX
         # fix a typo in the site HTML so I can find the Characters list.
         authdata = authdata.replace('<td width=10%">','<td width="10%">')
 
-        # hpfandom.net only seems to indicate adult-only by javascript on the story/chapter links.
-        if "javascript:if (confirm('Slash/het fiction which incorporates sexual situations to a somewhat graphic degree and some violence. ')) location = 'viewstory.php?sid=%s'"%self.story.getMetadata('storyId') in authdata \
+        if "javascript:if (confirm('Slash/het fiction which incorporates sexual situations to a somewhat graphic degree  as well as graphic violent situations.  ')) location = 'viewstory.php?sid=%s&i=1'"%self.story.getMetadata('storyId') in authdata \
                 and not (self.is_adult or self.getConfig("is_adult")):
             raise exceptions.AdultCheckRequired(self.url)
-        
-        authsoup = bs.BeautifulSoup(authdata)
 
-        reviewsa = authsoup.find('a', href="reviews.php?sid="+self.story.getMetadata('storyId')+"&a=")
+        authsoup = self.make_soup(authdata)
+
+        reviewsa = authsoup.find_all('a', href=re.compile(r"reviews\.php\?sid="+self.story.getMetadata('storyId')+r".*"))
         # <table><tr><td><p><b><a ...>
-        metablock = reviewsa.findParent("table")
+        metablock = reviewsa[0].findParent("table")
         #print("metablock:%s"%metablock)
-        
+        self.story.setMetadata('reviews',stripHTML(reviewsa[-1]))
+
         ## Title
         titlea = metablock.find('a', href=re.compile("viewstory.php"))
         #print("titlea:%s"%titlea)
         if titlea == None:
             raise exceptions.FailedToDownload("Story URL (%s) not found on author's page, can't use chapter URLs"%url)
         self.story.setMetadata('title',stripHTML(titlea))
-        
+
+        total_reads = 0
         # Find the chapters: !!! hpfandom.net differs from every other
         # eFiction site--the sid on viewstory for chapters is
         # *different* for each chapter
@@ -136,10 +158,16 @@ class HPFandomNetAdapterAdapter(BaseSiteAdapter): # XXX
             # just in case there's tags, like <i> in chapter titles.
             #print("====chapter===%s"%m.group(1))
             self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/eff/'+m.group(1)))
-
+            try:
+                total_reads += int(stripHTML((chapter.find_parent('tr').find_all('td')[-1])))
+            except:
+                pass # don't care
         if len(self.chapterUrls) == 0:
             self.chapterUrls.append((stripHTML(self.story.getMetadata('title')),url))
 
+        if total_reads > 0:
+            self.story.setMetadata('reads',total_reads)
+
         self.story.setMetadata('numChapters',len(self.chapterUrls))
 
         # eFiction sites don't help us out a lot with their meta data
@@ -163,7 +191,7 @@ class HPFandomNetAdapterAdapter(BaseSiteAdapter): # XXX
         if m != None:
             if m.group('rating') != None:
                 self.story.setMetadata('rating', m.group('rating'))
-                
+
             if m.group('words') != None:
                 self.story.setMetadata('numWords', m.group('words'))
 
@@ -172,7 +200,7 @@ class HPFandomNetAdapterAdapter(BaseSiteAdapter): # XXX
                     self.story.setMetadata('status', 'Completed')
                 else:
                     self.story.setMetadata('status', 'In-Progress')
-                
+
 
         # <tr><td width="10%" valign="top">Chapters:</td><td width="40%" valign="top">4</td>
         # <td width="10%" valign="top">Published:</td><td width="40%" valign="top">2010.09.29</td></tr>
@@ -205,10 +233,10 @@ class HPFandomNetAdapterAdapter(BaseSiteAdapter): # XXX
 
             if 'Published' in label:
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
+
             if 'Updated' in label:
                 self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
-            
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
@@ -219,15 +247,15 @@ class HPFandomNetAdapterAdapter(BaseSiteAdapter): # XXX
         # There are, however, tables with width=100% just above and below the real text.
         data = re.sub(r'<table width="100%">.*?</table>','<div name="storybody">',
                       data,count=1,flags=re.DOTALL)
-        
+
         data = re.sub(r'<table width="100%">.*?</table>','</div>',
                       data,count=1,flags=re.DOTALL)
-        
-        soup = bs.BeautifulStoneSoup(data,selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+
+        soup = self.make_soup(data)
 
         div = soup.find("div",{'name':'storybody'})
         #print("\n\ndiv:%s\n\n"%div)
-        
+
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
         return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_hpfanficarchivecom.py

@@ -22,7 +22,7 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+from bs4.element import Comment
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -46,21 +46,21 @@ class HPFanficArchiveComAdapter(BaseSiteAdapter):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
+
+
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/stories/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','hpffa')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%B %d, %Y"
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -89,20 +89,20 @@ class HPFanficArchiveComAdapter(BaseSiteAdapter):
             else:
                 raise e
 
-            
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',stripHTML(a))
-        
+
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
@@ -131,11 +131,13 @@ class HPFanficArchiveComAdapter(BaseSiteAdapter):
         for labelspan in labels:
             val = labelspan.nextSibling
             value = unicode('')
-            while val and not defaultGetattr(val,'class') == 'label':
-                value += unicode(val)
+            while val and not 'label' in defaultGetattr(val,'class'):
+                # print("val:%s"%val)
+                if not isinstance(val,Comment):
+                    value += unicode(val)
                 val = val.nextSibling
             label = labelspan.string
-            #print("label:%s\nvalue:%s"%(label,value))
+            # print("label:%s\nvalue:%s"%(label,value))
 
             if 'Summary' in label:
                 self.setDescription(url,value)
@@ -179,7 +181,7 @@ class HPFanficArchiveComAdapter(BaseSiteAdapter):
 
             if 'Published' in label:
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
+
             if 'Updated' in label:
                 self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
 
@@ -190,7 +192,7 @@ class HPFanficArchiveComAdapter(BaseSiteAdapter):
             series_url = 'http://'+self.host+'/stories/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            seriessoup = self.make_soup(self._fetchUrl(series_url))
             # can't use ^viewstory...$ in case of higher rated stories with javascript href.
             storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+'))
             i=1
@@ -202,21 +204,20 @@ class HPFanficArchiveComAdapter(BaseSiteAdapter):
                         self.story.setMetadata('seriesUrl',series_url)
                         break
                     i+=1
-            
+
         except:
             # I find it hard to care if the series parsing fails
             pass
-            
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
-        
-        soup = bs.BeautifulSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
+
+        soup = self.make_soup(self._fetchUrl(url))
+
         div = soup.find('div', {'id' : 'story'})
-        
+
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
 

fanficfare/adapters/adapter_iketernalnet.py

@@ -22,7 +22,6 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -46,21 +45,21 @@ class IkEternalNetAdapter(BaseSiteAdapter):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
+
+
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','ike')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%B %d, %Y"
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -81,7 +80,7 @@ class IkEternalNetAdapter(BaseSiteAdapter):
             return True
         else:
             return False
-        
+
     def performLogin(self, url):
         params = {}
 
@@ -93,13 +92,13 @@ class IkEternalNetAdapter(BaseSiteAdapter):
             params['password'] = self.getConfig("password")
         params['cookiecheck'] = '1'
         params['submit'] = 'Submit'
-    
+
         loginUrl = 'http://' + self.getSiteDomain() + '/user.php?action=login'
         logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
                                                               params['penname']))
-    
+
         d = self._fetchUrl(loginUrl, params)
-    
+
         if "Member Account" not in d : #Member Account
             logger.info("Failed to login to URL %s as %s" % (loginUrl,
                                                               params['penname']))
@@ -141,12 +140,12 @@ class IkEternalNetAdapter(BaseSiteAdapter):
         # The actual text that is used to announce you need to be an
         # adult varies from site to site.  Again, print data before
         # the title search to troubleshoot.
-            
+
         # Since the warning text can change by warning level, let's
         # look for the warning pass url.  ksarchive uses
         # &warning= -- actually, so do other sites.  Must be an
         # eFiction book.
-            
+
         # viewstory.php?sid=1882&warning=4
         # viewstory.php?sid=1654&ageconsent=ok&warning=5
         #print data
@@ -169,23 +168,23 @@ class IkEternalNetAdapter(BaseSiteAdapter):
                     if e.code == 404:
                         raise exceptions.StoryDoesNotExist(self.url)
                     else:
-                        raise e    
+                        raise e
             else:
                 raise exceptions.AdultCheckRequired(self.url)
-            
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data,selfClosingTags=('p')) #poor formatting of the paragraphs in the title page
+        soup = self.make_soup(data)
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',stripHTML(a))
-        
+
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
@@ -221,8 +220,8 @@ class IkEternalNetAdapter(BaseSiteAdapter):
             if 'Summary' in label:
                 ## Everything until the next span class='label'
                 svalue = ""
-                while not defaultGetattr(value,'class') == 'label':
-                    svalue += str(value)
+                while 'label' not in defaultGetattr(value,'class'):
+                    svalue += unicode(value)
                     value = value.nextSibling
                 self.setDescription(url,svalue)
                 #self.story.setMetadata('description',stripHTML(svalue))
@@ -261,23 +260,22 @@ class IkEternalNetAdapter(BaseSiteAdapter):
 
             if 'Published' in label:
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
+
             if 'Updated' in label:
                 # there's a stray [ at the end.
                 #value = value[0:-1]
                 self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
-            
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
+        soup = self.make_soup(self._fetchUrl(url))
+
         div = soup.find('div', {'id' : 'story'})
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_imagineeficcom.py

@@ -22,7 +22,7 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -46,21 +46,21 @@ class ImagineEFicComAdapter(BaseSiteAdapter):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
+
+
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','ime')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%Y.%m.%d"
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -81,7 +81,7 @@ class ImagineEFicComAdapter(BaseSiteAdapter):
             return True
         else:
             return False
-        
+
     def performLogin(self, url):
         params = {}
 
@@ -93,13 +93,13 @@ class ImagineEFicComAdapter(BaseSiteAdapter):
             params['password'] = self.getConfig("password")
         params['cookiecheck'] = '1'
         params['submit'] = 'Submit'
-    
+
         loginUrl = 'http://' + self.getSiteDomain() + '/user.php?action=login'
         logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
                                                               params['penname']))
-    
+
         d = self._fetchUrl(loginUrl, params)
-    
+
         if "Member Account" not in d : #Member Account
             logger.info("Failed to login to URL %s as %s" % (loginUrl,
                                                               params['penname']))
@@ -156,23 +156,23 @@ class ImagineEFicComAdapter(BaseSiteAdapter):
                     if e.code == 404:
                         raise exceptions.StoryDoesNotExist(self.url)
                     else:
-                        raise e    
+                        raise e
             else:
                 raise exceptions.AdultCheckRequired(self.url)
-            
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',stripHTML(a))
-        
+
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
@@ -195,7 +195,7 @@ class ImagineEFicComAdapter(BaseSiteAdapter):
                 return d[k]
             except:
                 return ""
-                
+
 
         # <span class="label">Rated:</span> NC-17<br /> etc
         labels = soup.findAll('span',{'class':'label'})
@@ -206,8 +206,8 @@ class ImagineEFicComAdapter(BaseSiteAdapter):
             if 'Summary' in label:
                 ## Everything until the next span class='label'
                 svalue = ""
-                while not defaultGetattr(value,'class') == 'label':
-                    svalue += str(value)
+                while 'label' not in defaultGetattr(value,'class'):
+                    svalue += unicode(value)
                     value = value.nextSibling
                 self.setDescription(url,svalue)
                 #self.story.setMetadata('description',stripHTML(svalue))
@@ -246,7 +246,7 @@ class ImagineEFicComAdapter(BaseSiteAdapter):
 
             if 'Published' in label:
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
+
             if 'Updated' in label:
                 self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
 
@@ -257,7 +257,7 @@ class ImagineEFicComAdapter(BaseSiteAdapter):
             series_url = 'http://'+self.host+'/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            seriessoup = self.make_soup(self._fetchUrl(series_url))
             # can't use ^viewstory...$ in case of higher rated stories with javascript href.
             storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+'))
             i=1
@@ -269,22 +269,21 @@ class ImagineEFicComAdapter(BaseSiteAdapter):
                         self.story.setMetadata('seriesUrl',series_url)
                         break
                     i+=1
-            
+
         except:
             # I find it hard to care if the series parsing fails
             pass
-            
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
+        soup = self.make_soup(self._fetchUrl(url))
+
         div = soup.find('div', {'id' : 'story'})
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_indeathnet.py

@@ -21,7 +21,7 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -45,27 +45,27 @@ class InDeathNetAdapter(BaseSiteAdapter):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
-        
+
+
         # get storyId from url--url validation guarantees query correct
         m = re.match(self.getSiteURLPattern(),url)
         if m:
             self.story.setMetadata('storyId',m.group('id'))
-            
+
             # normalized story URL.
             self._setURL('http://www.' + self.getSiteDomain() + '/blog/archive/'+self.story.getMetadata('storyId')+'-'+m.group('name')+'/')
         else:
             raise exceptions.InvalidStoryURL(url,
                                              self.getSiteDomain(),
                                              self.getSiteExampleURLs())
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','idn')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%d %B %Y"
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -78,22 +78,22 @@ class InDeathNetAdapter(BaseSiteAdapter):
 
     def getSiteURLPattern(self):
         # http://www.indeath.net/blog/archive/169-ransom-in-death/
-        return re.escape("http://")+re.escape(self.getSiteDomain())+r"/blog/(archive/)?(?P<id>\d+)\-(?P<name>[a-z0-9\-]*)/?$"     
-        
-            
+        return re.escape("http://")+re.escape(self.getSiteDomain())+r"/blog/(archive/)?(?P<id>\d+)\-(?P<name>[a-z0-9\-]*)/?$"
+
+
     def getDateFromComponents(self, postmonth, postday):
-        ym = re.search("Entries\ in\ (?P<mon>January|February|March|April|May|June|July|August|September|October|November|December)\ (?P<year>\d{4})",postmonth)
-        d = re.search("(?P<day>\d{2})\ (Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)",postday)
+        ym = re.search("Entries in (?P<mon>January|February|March|April|May|June|July|August|September|October|November|December) (?P<year>\d{4})",stripHTML(postmonth))
+        d = re.search("(?P<day>\d{2})\ (Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)",stripHTML(postday))
         postdate = makeDate(d.group('day')+' '+ym.group('mon')+' '+ym.group('year'),self.dateformat)
         return postdate
 
     def getAuthorData(self):
-        
+
         mainUrl = self.url.replace("/archive","")
-        
+
         try:
             maindata = self._fetchUrl(mainUrl)
-            
+
         except urllib2.HTTPError, e:
             if e.code == 404:
                 raise exceptions.StoryDoesNotExist(self.meta)
@@ -101,45 +101,45 @@ class InDeathNetAdapter(BaseSiteAdapter):
                 raise e
 
         # use BeautifulSoup HTML parser to make everything easier to find.
-        mainsoup = bs.BeautifulSoup(maindata)
+        mainsoup = self.make_soup(maindata)
 
         # find first entry
         e = mainsoup.find('div',{'class':"entry"})
-        
+
         # get post author as author
         d = e.find('div',{'class':"desc"})
         a = d.find('strong')
         self.story.setMetadata('author',a.contents[0].string.strip())
-        
+
         # Don't seem to be able to get author pages anymore
         self.story.setMetadata('authorUrl','http://www.indeath.net/')
         self.story.setMetadata('authorId','0')
-        
+
     ## Getting the chapter list and the meta data, plus 'is adult' checking.
     def extractChapterUrlsAndMetadata(self):
 
         url = self.url
         try:
             data = self._fetchUrl(url)
-            
+
         except urllib2.HTTPError, e:
             if e.code == 404:
                 raise exceptions.StoryDoesNotExist(self.meta)
             else:
                 raise e
-                
-            
+
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
         ## Title
         h = soup.find('a', id="blog_title")
         t = h.find('span')
         self.story.setMetadata('title',stripHTML(t.contents[0]).strip())
-        
-        s = t.find('div')        
+
+        s = t.find('div')
         if s != None:
             self.setDescription(url,s)
 
@@ -151,20 +151,20 @@ class InDeathNetAdapter(BaseSiteAdapter):
 
         #reverse the list since newest at the top
         chapters.reverse()
-        
+
         # Get date published & updated from first & last entries
         posttable=soup.find('div', id="main_column")
-        
+
         postmonths=posttable.findAll('th', text=re.compile(r'Entries\ in\ '))
         postmonths.reverse()
-        
-        postdates=posttable.findAll('span', _class="desc", text=re.compile('\d{2}\ (Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)'))
+
+        postdates=posttable.findAll('span', class_="desc")
         postdates.reverse()
-        
+
         self.story.setMetadata('datePublished',self.getDateFromComponents(postmonths[0],postdates[0]))
         self.story.setMetadata('dateUpdated',self.getDateFromComponents(postmonths[len(postmonths)-1],postdates[len(postdates)-1]))
-        
-        # Process List of Chapters              
+
+        # Process List of Chapters
         self.story.setMetadata('numChapters',len(chapters))
         logger.debug("numChapters: (%s)"%self.story.getMetadata('numChapters'))
         for x in range(0,len(chapters)):
@@ -181,18 +181,18 @@ class InDeathNetAdapter(BaseSiteAdapter):
                     chaptertitle = ct
                 self.chapterUrls.append((chaptertitle,chapter['href']))
 
-        
-        
+
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
         logger.debug('Getting chapter text from: %s' % url)
-        
-        #chapter=bs.BeautifulSoup('<div class="story"></div>')
+
+        #chapter=self.make_soup('<div class="story"></div>')
         data = self._fetchUrl(url)
-        soup = bs.BeautifulSoup(data,selfClosingTags=('br','hr','span','center'))
+        soup = self.make_soup(data)
 
         chapter = soup.find("div", "entry_content")
-        
+
         if None == chapter:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
 

fanficfare/adapters/adapter_ksarchivecom.py

@@ -22,7 +22,7 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -50,22 +50,22 @@ class KSArchiveComAdapter(BaseSiteAdapter): # XXX
                                # iso-8859-1 (and some that claim to be
                                # utf8) are really windows-1252.
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
+
+
         # normalized story URL.
         # XXX Most sites don't have the /fanfic part.  Replace all to remove it usually.
         self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','ksa') # XXX
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%b/%d/%Y" # XXX
-            
+
     @classmethod
     def getAcceptDomains(cls):
         return ['www.ksarchive.com','ksarchive.com']
@@ -115,12 +115,12 @@ class KSArchiveComAdapter(BaseSiteAdapter): # XXX
         # The actual text that is used to announce you need to be an
         # adult varies from site to site.  Again, print data before
         # the title search to troubleshoot.
-            
+
         # Since the warning text can change by warning level, let's
         # look for the warning pass url.  ksarchive uses
         # &warning= -- actually, so do other sites.  Must be an
         # eFiction book.
-            
+
         # viewstory.php?sid=1882&warning=4
         # viewstory.php?sid=1654&ageconsent=ok&warning=5
         #print data
@@ -143,20 +143,20 @@ class KSArchiveComAdapter(BaseSiteAdapter): # XXX
                     if e.code == 404:
                         raise exceptions.StoryDoesNotExist(self.url)
                     else:
-                        raise e    
+                        raise e
             else:
                 raise exceptions.AdultCheckRequired(self.url)
-            
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         # print data
 
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',stripHTML(a)) # title's inside a <b> tag.
@@ -194,8 +194,8 @@ class KSArchiveComAdapter(BaseSiteAdapter): # XXX
             if 'Summary' in label:
                 ## Everything until the next span class='label'
                 svalue = ""
-                while not defaultGetattr(value,'class') == 'label':
-                    svalue += str(value)
+                while 'label' not in defaultGetattr(value,'class'):
+                    svalue += unicode(value)
                     # poor HTML(unclosed <p> for one) can cause run on
                     # over the next label.
                     if '<span class="label">' in svalue:
@@ -281,7 +281,7 @@ class KSArchiveComAdapter(BaseSiteAdapter): # XXX
 
             if 'Published' in label:
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
+
             if 'Updated' in label:
                 # there's a stray [ at the end.
                 #value = value[0:-1]
@@ -294,7 +294,7 @@ class KSArchiveComAdapter(BaseSiteAdapter): # XXX
             series_url = 'http://'+self.host+'/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            seriessoup = self.make_soup(self._fetchUrl(series_url))
             storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+'))
             i=1
             for a in storyas:
@@ -305,20 +305,19 @@ class KSArchiveComAdapter(BaseSiteAdapter): # XXX
                         self.story.setMetadata('seriesUrl',series_url)
                         break
                     i+=1
-            
+
         except:
             # I find it hard to care if the series parsing fails
             pass
-            
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
         data = self._fetchUrl(url)
-        soup = bs.BeautifulStoneSoup(data,
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
+        soup = self.make_soup(data)
+
         div = soup.find('div', {'id' : 'story'})
 
         if None == div:
@@ -326,5 +325,5 @@ class KSArchiveComAdapter(BaseSiteAdapter): # XXX
                 raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Database error on the site reported!" % url)
             else:
                 raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_literotica.py

@@ -21,9 +21,8 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 import urlparse
-import time
 
-from .. import BeautifulSoup as bs
+from bs4.element import Comment
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -33,13 +32,15 @@ class LiteroticaSiteAdapter(BaseSiteAdapter):
 
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
+        logger.debug("LiteroticaComAdapter:__init__ - url='%s'" % url)
 
         self.decode = ["utf8",
                        "Windows-1252"] # 1252 is a superset of iso-8859-1.
-                               # Most sites that claim to be
-                               # iso-8859-1 (and some that claim to be
-                               # utf8) are really windows-1252.
+                            # Most sites that claim to be
+                            # iso-8859-1 (and some that claim to be
+                            # utf8) are really windows-1252.
 
+        # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','litero')
 
         # normalize to first chapter.  Not sure if they ever have more than 2 digits.
@@ -62,7 +63,7 @@ class LiteroticaSiteAdapter(BaseSiteAdapter):
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = '%m/%d/%y'
+        self.dateformat = "%m/%d/%y"
 
     @staticmethod
     def getSiteDomain():
@@ -96,9 +97,21 @@ class LiteroticaSiteAdapter(BaseSiteAdapter):
     def getSiteURLPattern(self):
         return r"https?://(www|german|spanish|french|dutch|italian|romanian|portuguese|other)(\.i)?\.literotica\.com/s/([a-zA-Z0-9_-]+)"
 
+    def getCategories(self, soup):
+        if self.getConfig("use_meta_keywords"):
+            categories = soup.find("meta", {"name":"keywords"})['content'].split(', ')
+            categories = [c for c in categories if not self.story.getMetadata('title') in c]
+            if self.story.getMetadata('author') in categories:
+                categories.remove(self.story.getMetadata('author'))
+            logger.debug("Meta = %s" % categories)
+            for category in categories:
+    #            logger.debug("\tCategory=%s" % category)
+#                 self.story.addToList('category', category.title())
+                self.story.addToList('eroticatags', category.title())
+
     def extractChapterUrlsAndMetadata(self):
         """
-        NOTE: Some stories can have versions, 
+        NOTE: Some stories can have versions,
               e.g. /my-story-ch-05-version-10
         NOTE: If two stories share the same title, a running index is added,
               e.g.: /my-story-ch-02-1
@@ -119,11 +132,12 @@ class LiteroticaSiteAdapter(BaseSiteAdapter):
             raise exceptions.AdultCheckRequired(self.url)
 
         logger.debug("Chapter/Story URL: <%s> " % self.url)
+
         try:
             data1 = self._fetchUrl(self.url)
-            soup1 = bs.BeautifulSoup(data1)
+            soup1 = self.make_soup(data1)
             #strip comments from soup
-            [comment.extract() for comment in soup1.findAll(text=lambda text:isinstance(text, bs.Comment))]
+            [comment.extract() for comment in soup1.findAll(text=lambda text:isinstance(text, Comment))]
         except urllib2.HTTPError, e:
             if e.code == 404:
                 raise exceptions.StoryDoesNotExist(self.url)
@@ -142,9 +156,10 @@ class LiteroticaSiteAdapter(BaseSiteAdapter):
         # get the author page
         try:
             dataAuth = self._fetchUrl(authorurl)
-            soupAuth = bs.BeautifulSoup(dataAuth)
+            soupAuth = self.make_soup(dataAuth)
             #strip comments from soup
-            [comment.extract() for comment in soupAuth.findAll(text=lambda text:isinstance(text, bs.Comment))]
+            [comment.extract() for comment in soupAuth.findAll(text=lambda text:isinstance(text, Comment))]
+#            logger.debug(soupAuth)
         except urllib2.HTTPError, e:
             if e.code == 404:
                 raise exceptions.StoryDoesNotExist(authorurl)
@@ -155,10 +170,19 @@ class LiteroticaSiteAdapter(BaseSiteAdapter):
         ## site has started using //domain.name/asdf urls remove https?: from front
         ## site has started putting https back on again.
         storyLink = soupAuth.find('a', href=re.compile(r'(https?:)?'+re.escape(self.url[self.url.index(':')+1:])))
+#         storyLink = soupAuth.find('a', href=self.url)#[self.url.index(':')+1:])
+
+        if storyLink is not None:
+            # pull the published date from the author page
+            # default values from single link.  Updated below if multiple chapter.
+            logger.debug("Found story on the author page.")
+            date = storyLink.parent.parent.findAll('td')[-1].text
+            self.story.setMetadata('datePublished', makeDate(date, self.dateformat))
+            self.story.setMetadata('dateUpdated',makeDate(date, self.dateformat))
 
         if storyLink is not None:
             urlTr = storyLink.parent.parent
-            if urlTr['class'] == "sl":
+            if "sl" in urlTr['class']:
                 isSingleStory = False
             else:
                 isSingleStory = True
@@ -166,101 +190,184 @@ class LiteroticaSiteAdapter(BaseSiteAdapter):
             raise exceptions.FailedToDownload("Couldn't find story <%s> on author's page <%s>" % (self.url, authorurl))
 
         if isSingleStory:
-            self.story.setMetadata('title', storyLink.text)
+#             self.chapterUrls = [(soup1.h1.string, self.url)]
+#             self.story.setMetadata('title', soup1.h1.string)
+
+            self.story.setMetadata('title', storyLink.text.strip('/'))
+            logger.debug('Title: "%s"' % storyLink.text.strip('/'))
             self.story.setMetadata('description', urlTr.findAll("td")[1].text)
-            self.story.addToList('eroticatags', urlTr.findAll("td")[2].text)
+            self.story.addToList('category', urlTr.findAll("td")[2].text)
+#             self.story.addToList('eroticatags', urlTr.findAll("td")[2].text)
             date = urlTr.findAll('td')[-1].text
             self.story.setMetadata('datePublished', makeDate(date, self.dateformat))
             self.story.setMetadata('dateUpdated',makeDate(date, self.dateformat))
             self.chapterUrls = [(storyLink.text, self.url)]
+            averrating = stripHTML(storyLink.parent)
+            ## title (0.00)
+            averrating = averrating[averrating.rfind('(')+1:averrating.rfind(')')]
+            try:
+                self.story.setMetadata('averrating', float(averrating))
+            except:
+                pass
+#             self.story.setMetadata('averrating',averrating)
+        # parse out the list of chapters
         else:
             seriesTr = urlTr.previousSibling
-            while seriesTr['class'] != 'ser-ttl':
+            while 'ser-ttl' not in seriesTr['class']:
                 seriesTr = seriesTr.previousSibling
             m = re.match("^(?P<title>.*?):\s(?P<numChapters>\d+)\sPart\sSeries$", seriesTr.find("strong").text)
             self.story.setMetadata('title', m.group('title'))
+            seriesTitle = m.group('title')
 
             ## Walk the chapters
             chapterTr = seriesTr.nextSibling
             self.chapterUrls = []
             dates = []
             descriptions = []
-            while chapterTr is not None and chapterTr['class'] == 'sl':
-                descriptions.append(chapterTr.findAll("td")[1].text)
+            ratings = []
+            chapters = []
+            while chapterTr is not None and 'sl' in chapterTr['class']:
+                description = "%d. %s" % (len(descriptions)+1,stripHTML(chapterTr.findAll("td")[1]))
+                description = stripHTML(chapterTr.findAll("td")[1])
                 chapterLink = chapterTr.find("td", "fc").find("a")
-                if not chapterLink["href"].startswith('http'):
-                    chapterLink["href"] = "http:" + chapterLink["href"] 
-                self.chapterUrls.append((chapterLink.text, chapterLink["href"]))
                 self.story.addToList('eroticatags', chapterTr.findAll("td")[2].text)
-                dates.append(makeDate(chapterTr.findAll('td')[-1].text, self.dateformat))
+                pub_date = makeDate(chapterTr.findAll('td')[-1].text, self.dateformat)
+                dates.append(pub_date)
                 chapterTr = chapterTr.nextSibling
+                
+                chapter_title = chapterLink.text
+                if self.getConfig("clean_chapter_titles"):
+                    logger.debug('\tChapter Name: "%s"' % chapterLink.string)
+                    logger.debug('\tChapter Name: "%s"' % chapterLink.text)
+                    if chapterLink.text.lower().startswith(seriesTitle.lower()):
+                        chapter = chapterLink.text[len(seriesTitle):].strip()
+                        logger.debug('\tChapter: "%s"' % chapter)
+                        if chapter == '':
+                            chapter_title = 'Chapter %d' % (len(self.chapterUrls) + 1)
+                        else:
+                            separater_char = chapter[0]
+                            logger.debug('\tseparater_char: "%s"' % separater_char)
+                            chapter = chapter[1:].strip() if separater_char in [":", "-"] else chapter
+                            logger.debug('\tChapter: "%s"' % chapter)
+                            if chapter.lower().startswith('ch.'):
+                                chapter = chapter[len('ch.'):]
+                                try:
+                                    chapter_title = 'Chapter %d' % int(chapter)
+                                except:
+                                    chapter_title = 'Chapter %s' % chapter
+                            elif chapter.lower().startswith('pt.'):
+                                chapter = chapter[len('pt.'):]
+                                try:
+                                    chapter_title = 'Part %d' % int(chapter)
+                                except:
+                                    chapter_title = 'Part %s' % chapter
+                            elif separater_char in [":", "-"]:
+                                chapter_title = chapter
+    
+    #                 if chapter_title == '':
+    #                     chapter_title = chapterLink.string
 
-            ## Set description to joint chapter descriptions
-            self.story.setMetadata('description', " / ".join(descriptions))
+                # pages include full URLs.
+                chapurl = chapterLink['href']
+                if chapurl.startswith('//'):
+                    chapurl = self.parsedUrl.scheme + ':' + chapurl
+                logger.debug("Chapter URL: " + chapurl)
+                logger.debug("Chapter Title: " + chapter_title)
+                logger.debug("Chapter description: " + description)
+                chapters.append((chapter_title, chapurl, description, pub_date))
+#                 self.chapterUrls.append((chapter_title, chapurl))
+                numrating = stripHTML(chapterLink.parent)
+                ## title (0.00)
+                numrating = numrating[numrating.rfind('(')+1:numrating.rfind(')')]
+                try:
+                    ratings.append(float(numrating))
+                except:
+                    pass
 
+            chapters = sorted(chapters, key=lambda chapter: chapter[3])
+            for i, chapter in enumerate(chapters):
+                self.chapterUrls.append((chapter[0], chapter[1]))
+                descriptions.append("%d. %s" % (i + 1, chapter[2]))
             ## Set the oldest date as publication date, the newest as update date
             dates.sort()
             self.story.setMetadata('datePublished', dates[0])
             self.story.setMetadata('dateUpdated', dates[-1])
+            self.story.setMetadata('datePublished', chapters[0][3])
+            self.story.setMetadata('dateUpdated', chapters[-1][3])
+            ## Set description to joint chapter descriptions
+            self.setDescription(authorurl,"<p>"+"</p>\n<p>".join(descriptions)+"</p>")
 
-            # normalize on first chapter URL.
-            self._setURL(self.chapterUrls[0][1])
+            if len(ratings) > 0:
+                self.story.setMetadata('averrating','%4.2f' % (sum(ratings) / float(len(ratings))))
+
+        # normalize on first chapter URL.
+        self._setURL(self.chapterUrls[0][1])
+
+        # reset storyId to first chapter.
+        self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2])
 
         self.story.setMetadata('numChapters', len(self.chapterUrls))
-                
-        # set storyId to 'title-author' to avoid duplicates
-        # self.story.setMetadata('storyId', 
-        #     re.sub("[^a-z0-9]", "", self.story.getMetadata('title').lower())
-        #     + "-"
-        #     + re.sub("[^a-z0-9]", "", self.story.getMetadata('author').lower()))
+
+        self.story.setMetadata('category', soup1.find('div', 'b-breadcrumbs').findAll('a')[1].string)
+        self.getCategories(soup1)
+#         self.story.setMetadata('description', soup1.find('meta', {'name': 'description'})['content'])
 
         return
 
+
+    def getPageText(self, raw_page, url):
+        logger.debug('Getting page text')
+#         logger.debug(soup)
+        raw_page = raw_page.replace('<div class="b-story-body-x x-r15"><div><p>','<div class="b-story-body-x x-r15"><div>')
+#         logger.debug("\tChapter text: %s" % raw_page)
+        page_soup = self.make_soup(raw_page)
+        [comment.extract() for comment in page_soup.findAll(text=lambda text:isinstance(text, Comment))]
+        story2 = page_soup.find('div', 'b-story-body-x').div
+#         logger.debug("getPageText- name div div...")
+#         logger.debug(soup)
+#         story2.append(page_soup.new_tag('br'))
+        div = self.utf8FromSoup(url, story2)
+#        logger.debug(div)
+
+        fullhtml = unicode(div)
+#         logger.debug(fullhtml)
+        fullhtml = re.sub(r'<br />\s*<br />', r'</p><p>', fullhtml)
+        fullhtml = re.sub(r'^<div>', r'', fullhtml)
+        fullhtml = re.sub(r'</div>$', r'', fullhtml)
+        fullhtml = re.sub(r'(<p><br/></p>\s+)+$', r'', fullhtml)
+#         logger.debug(fullhtml)
+        return fullhtml
+
     def getChapterText(self, url):
-        logger.debug('Getting chapter text from <%s>' % url)
-        data1 = self._fetchUrl(url)
-        # brute force approach to replace the wrapping <p> tag.  If
-        # done by changing tag name, it causes problems with nested
-        # <p> tags.
-        data1 = data1.replace('<div class="b-story-body-x x-r15"><div><p>','<div class="b-story-body-x x-r15"><div>')
-        soup1 = bs.BeautifulSoup(data1)
 
-        #strip comments from soup
-        [comment.extract() for comment in soup1.findAll(text=lambda text:isinstance(text, bs.Comment))]
+        logger.debug('Getting chapter text from: %s' % url)
 
-        # get story text
-        story1 = soup1.find('div', 'b-story-body-x').div
-        #print("story1:%s"%story1)
-        # story1.name='div'
-        story1.append('<br />')
-        storytext = self.utf8FromSoup(url,story1)
+        raw_page = self._fetchUrl(url)
+        page_soup = self.make_soup(raw_page)
+        pages = page_soup.find('select', {'name' : 'page'})
+        page_nums = [page.text for page in pages.findAll('option')] if pages else 0
 
-        # find num pages
-        pgs = int(soup1.find("span", "b-pager-caption-t r-d45").string.split(' ')[0])
-        logger.debug("pages: "+str(pgs))
+        fullhtml = "" 
+        self.getCategories(page_soup)
+        if self.getConfig("description_in_chapter"):
+            chapter_description = page_soup.find("meta", {"name" : "description"})['content']
+            logger.debug("\tChapter description: %s" % chapter_description)
+            fullhtml += '<p><b>Description:</b> %s</p><hr />' % chapter_description
+        fullhtml += self.getPageText(raw_page, url)
+        if pages:
+            for page_no in xrange(2, len(page_nums) + 1):
+                page_url = url +  "?page=%s" % page_no
+                logger.debug("page_url= %s" % page_url)
+                raw_page = self._fetchUrl(page_url)
+                fullhtml += self.getPageText(raw_page, url)
+        
+#        fullhtml = self.utf8FromSoup(url, bs.BeautifulSoup(fullhtml))
+#        fullhtml = re.sub(r'^<div>', r'', fullhtml)
+#        fullhtml = re.sub(r'</div>$', r'', fullhtml)
+#        if None == div:
+#            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
 
-        # get all the pages
-        for i in xrange(2, pgs+1):
-            try:
-                logger.debug("fetching page "+str(i))
-                time.sleep(0.5)
-                data2 = self._fetchUrl(url, {'page': i})
-                # brute force approach to replace the wrapping <p> tag.  If
-                # done by changing tag name, it causes problems with nested
-                # <p> tags.
-                data2 = data2.replace('<div class="b-story-body-x x-r15"><div><p>','<div class="b-story-body-x x-r15"><div>')
-                soup2 = bs.BeautifulSoup(data2)
-                [comment.extract() for comment in soup2.findAll(text=lambda text:isinstance(text, bs.Comment))]
-                story2 = soup2.find('div', 'b-story-body-x').div
-                # story2.name='div'
-                story2.append('<br />')
-                storytext += self.utf8FromSoup(url,story2)
-            except urllib2.HTTPError, e:
-                if e.code == 404:
-                    raise exceptions.StoryDoesNotExist(url)
-                else:
-                    raise e
-        return storytext
+        return fullhtml
 
 
 def getClass():

fanficfare/adapters/adapter_lucifaelff.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2012 Fanficdownloader team, 2015 FanFicFare team
+# Copyright 2016 FanFicFare team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -22,18 +22,18 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+from bs4.element import Comment
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
 from base_adapter import BaseSiteAdapter,  makeDate
 
 def getClass():
-    return GrangerEnchantedCom
+    return Lucifaelff
 
 # Class name has to be unique.  Our convention is camel case the
 # sitename with Adapter at the end.  www is skipped.
-class GrangerEnchantedCom(BaseSiteAdapter):
+class Lucifaelff(BaseSiteAdapter):
 
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
@@ -46,41 +46,32 @@ class GrangerEnchantedCom(BaseSiteAdapter):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        self.section=self.parsedUrl.path.split('/',)[1]
-             
+
+
         # normalized story URL.
-        if "malfoymanor" in self.parsedUrl.netloc:
-            self._setURL('http://malfoymanor.' + self.getSiteDomain() + '/themanor/viewstory.php?sid='+self.story.getMetadata('storyId'))
-            self.story.addToList("category","The Manor")
-        else:
-            self._setURL('http://' + self.getSiteDomain() + '/enchant/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
+        self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
+
         # Each adapter needs to have a unique site abbreviation.
-        self.story.setMetadata('siteabbrev','gech')
+        self.story.setMetadata('siteabbrev','luci')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = "%d/%b/%Y"
-            
+        self.dateformat = "%d/%m/%Y"
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
-        return 'grangerenchanted.com'
-        
-    @classmethod
-    def getAcceptDomains(cls):
-        return ['grangerenchanted.com','malfoymanor.grangerenchanted.com']
+        return 'fanfiction.lucifael.com'
 
     @classmethod
     def getSiteExampleURLs(cls):
-        return "http://grangerenchanted.com/enchant/viewstory.php?sid=1234 http://malfoymanor.grangerenchanted.com/themanor/viewstory.php?sid=1234"
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
-        return r"http://(malfoymanor.)?grangerenchanted.com/(enchant|themanor)?/viewstory.php\?sid=\d+$"
+        return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
 
     ## Login seems to be reasonably standard across eFiction sites.
     def needToLoginCheck(self, data):
@@ -90,7 +81,7 @@ class GrangerEnchantedCom(BaseSiteAdapter):
             return True
         else:
             return False
-        
+
     def performLogin(self, url):
         params = {}
 
@@ -102,16 +93,13 @@ class GrangerEnchantedCom(BaseSiteAdapter):
             params['password'] = self.getConfig("password")
         params['cookiecheck'] = '1'
         params['submit'] = 'Submit'
-    
-        if "enchant" in self.section:
-            loginUrl = 'http://grangerenchanted.com/enchant/user.php?action=login'
-        else:
-            loginUrl = 'http://malfoymanor.grangerenchanted.com/themanor/user.php?action=login'
+
+        loginUrl = 'http://' + self.getSiteDomain() + '/user.php?action=login'
         logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
                                                               params['penname']))
-    
+
         d = self._fetchUrl(loginUrl, params)
-    
+
         if "Member Account" not in d : #Member Account
             logger.info("Failed to login to URL %s as %s" % (loginUrl,
                                                               params['penname']))
@@ -128,13 +116,13 @@ class GrangerEnchantedCom(BaseSiteAdapter):
             # If the title search below fails, there's a good chance
             # you need a different number.  print data at that point
             # and see what the 'click here to continue' url says.
-            addurl = "&ageconsent=ok&warning=1"
+            addurl = "&ageconsent=ok&warning=4"
         else:
             addurl=""
 
         # index=1 makes sure we see the story chapter index.  Some
         # sites skip that for one-chapter stories.
-        url = self.url+addurl
+        url = self.url
         logger.debug("URL: "+url)
 
         try:
@@ -145,11 +133,21 @@ class GrangerEnchantedCom(BaseSiteAdapter):
             else:
                 raise e
 
-        if self.needToLoginCheck(data):
+
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
             # need to log in for this one.
             self.performLogin(url)
             data = self._fetchUrl(url)
 
+        # Since the warning text can change by warning level, let's
+        # look for the warning pass url.  ksarchive uses
+        # &warning= -- actually, so do other sites.  Must be an
+        # eFiction book.
+
+        # viewstory.php?sid=1882&warning=4
+        # viewstory.php?sid=1654&ageconsent=ok&warning=5
+        #print data
+        #m = re.search(r"'viewstory.php\?sid=1882(&warning=4)'",data)
         m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
         if m != None:
             if self.is_adult or self.getConfig("is_adult"):
@@ -168,25 +166,27 @@ class GrangerEnchantedCom(BaseSiteAdapter):
                     if e.code == 404:
                         raise exceptions.StoryDoesNotExist(self.url)
                     else:
-                        raise e    
+                        raise e
             else:
                 raise exceptions.AdultCheckRequired(self.url)
-            
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
             raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+
         # use BeautifulSoup HTML parser to make everything easier to find.
         soup = self.make_soup(data)
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
+        pagetitle = soup.find('div',{'id':'pagetitle'})
+
         ## Title
-        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',stripHTML(a))
-        
+
         # Find authorid and URL from... author url.
-        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
         self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
         self.story.setMetadata('author',a.string)
@@ -194,7 +194,7 @@ class GrangerEnchantedCom(BaseSiteAdapter):
         # Find the chapters:
         for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
             # just in case there's tags, like <i> in chapter titles.
-            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+self.section+'/'+chapter['href']+addurl))
+            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']+addurl))
 
         self.story.setMetadata('numChapters',len(self.chapterUrls))
 
@@ -217,10 +217,11 @@ class GrangerEnchantedCom(BaseSiteAdapter):
             if 'Summary' in label:
                 ## Everything until the next span class='label'
                 svalue = ""
-                while value and not defaultGetattr(value,'class') == 'label' and '<span class="label">' not in unicode(value):
+                while 'label' not in defaultGetattr(value,'class'):
                     svalue += unicode(value)
                     value = value.nextSibling
                 self.setDescription(url,svalue)
+                #self.story.setMetadata('description',stripHTML(svalue))
 
             if 'Rated' in label:
                 self.story.setMetadata('rating', value)
@@ -228,9 +229,6 @@ class GrangerEnchantedCom(BaseSiteAdapter):
             if 'Word count' in label:
                 self.story.setMetadata('numWords', value)
 
-            if 'Read' in label:
-                self.story.setMetadata('read', value)
-
             if 'Categories' in label:
                 cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
                 for cat in cats:
@@ -242,12 +240,12 @@ class GrangerEnchantedCom(BaseSiteAdapter):
                     self.story.addToList('characters',char.string)
 
             if 'Genre' in label:
-                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=4'))
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
                 for genre in genres:
                     self.story.addToList('genre',genre.string)
 
             if 'Warnings' in label:
-                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2'))
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=3'))
                 for warning in warnings:
                     self.story.addToList('warnings',warning.string)
 
@@ -259,51 +257,43 @@ class GrangerEnchantedCom(BaseSiteAdapter):
 
             if 'Published' in label:
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
+
             if 'Updated' in label:
+                # there's a stray [ at the end.
+                #value = value[0:-1]
                 self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
 
         try:
             # Find Series name from series URL.
             a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
             series_name = a.string
-            series_url = 'http://'+self.host+'/'+self.section+'/'+a['href']
+            series_url = 'http://'+self.host+'/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
             seriessoup = self.make_soup(self._fetchUrl(series_url))
-            # can't use ^viewstory...$ in case of higher rated stories with javascript href.
-            storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+'))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
             i=1
             for a in storyas:
-                # skip 'report this' and 'TOC' links
-                if 'contact.php' not in a['href'] and 'index' not in a['href']:
-                    if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
-                        self.setSeries(series_name, i)
-                        self.story.setMetadata('seriesUrl',series_url)
-                        break
-                    i+=1
+                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                    self.setSeries(series_name, i)
+                    self.story.setMetadata('seriesUrl',series_url)
+                    break
+                i+=1
+
         except:
             # I find it hard to care if the series parsing fails
             pass
 
-        try:
-            self.story.setMetadata('reviews',
-                                   stripHTML(soup.find('div',{'id':'sort'}).
-                                             findAll('a', href=re.compile(r'^reviews.php'))[1]))
-        except:
-            # I find it hard to care if the series parsing fails
-            pass
-            
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
         soup = self.make_soup(self._fetchUrl(url))
-        
-        div = soup.find('div', {'id' : 'story1'})
+
+        div = soup.find('div', {'id' : 'story'})
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_lumossycophanthexcom.py

@@ -22,7 +22,7 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -46,22 +46,22 @@ class LumosSycophantHexComAdapter(BaseSiteAdapter):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
+
 		
-        
+
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','lsph')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%m/%d/%Y"
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -104,21 +104,21 @@ class LumosSycophantHexComAdapter(BaseSiteAdapter):
         # the title search to troubleshoot.
         if "Age Consent Required" in data:
             raise exceptions.AdultCheckRequired(self.url)
-            
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
         ## Title
         pt = soup.find('div', {'id' : 'pagetitle'})
         a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',stripHTML(a))
-        
+
         # Find authorid and URL from... author url.
         a = pt.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
@@ -155,8 +155,8 @@ class LumosSycophantHexComAdapter(BaseSiteAdapter):
         while value != None:
             val = value
             value = value.previousSibling
-        while not defaultGetattr(val,'class') == 'label':
-            svalue += str(val)
+        while 'label' not in defaultGetattr(val,'class'):
+            svalue += unicode(val)
             val = val.nextSibling
         self.setDescription(url,svalue)
 		
@@ -195,7 +195,7 @@ class LumosSycophantHexComAdapter(BaseSiteAdapter):
 
             if 'Published' in label:
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value.split(' -')[0]), self.dateformat))
-            
+
             if 'Updated' in label:
                 # there's a stray [ at the end.
                 #value = value[0:-1]
@@ -208,7 +208,7 @@ class LumosSycophantHexComAdapter(BaseSiteAdapter):
             series_url = 'http://'+self.host+'/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            seriessoup = self.make_soup(self._fetchUrl(series_url))
             storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
             i=1
             for a in storyas:
@@ -217,22 +217,21 @@ class LumosSycophantHexComAdapter(BaseSiteAdapter):
                     self.story.setMetadata('seriesUrl',series_url)
                     break
                 i+=1
-            
+
         except:
             # I find it hard to care if the series parsing fails
             pass
-            
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
+        soup = self.make_soup(self._fetchUrl(url))
+
         div = soup.find('div', {'id' : 'story'})
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_masseffect2in.py

@@ -0,0 +1,718 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2015 FanFicFare team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import bs4
+import datetime
+import logging
+import re
+import urllib2
+
+from ..htmlcleanup import removeEntities, stripHTML
+from .. import exceptions as exceptions
+from base_adapter import BaseSiteAdapter, makeDate
+
+
+_logger = logging.getLogger(__name__)
+
+
+def getClass():
+    """Returns adapter class defined in this module."""
+    return MassEffect2InAdapter
+
+
+class ParsingError(Exception):
+    """Indicates an error while parsing web page content."""
+    def __init__(self, message):
+        Exception.__init__(self)
+        self.message = message
+
+    def __str__(self):
+        return self.message
+
+
+class MassEffect2InAdapter(BaseSiteAdapter):
+    """
+    Provides support for MassEffect2.in site as story source.
+    Can be used as a template for sites build upon Ucoz.com engine (until no base class extracted).
+    Specializations:
+        1) Russian content (date format, genre names, etc.);
+        2) original `E.R.A.T.I.N.G.' rating scale, used by masseffect2.in
+           and some affiliated sites, denoted with images;
+        3) editor signatures an an option to remove them.
+    """
+
+    WORD_PATTERN = re.compile(u'\w+', re.UNICODE)
+    DOCUMENT_ID_PATTERN = re.compile(u'\d+-\d+-\d+-\d+')
+    SITE_LANGUAGE = u'Russian'
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["utf8"]
+
+        self.story.setMetadata('siteabbrev', 'me2in')
+        self.story.setMetadata('storyId', self._getDocumentId(self.url))
+
+        self._setURL(self._makeDocumentUrl(self.story.getMetadata('storyId')))
+
+        self._chapters = {}
+        self._parsingConfiguration = None
+
+    # Must be @staticmethod, not @classmethod!
+    @staticmethod
+    def getSiteDomain():
+        return 'www.masseffect2.in'
+
+    @classmethod
+    def getSiteExampleURLs(cls):
+        return u' '.join([cls._makeDocumentUrl('19-1-0-1234'),
+                          cls._makeDocumentUrl('24-1-0-4321')])
+
+    def getSiteURLPattern(self):
+        return re.escape(self._makeDocumentUrl('')) + self.DOCUMENT_ID_PATTERN.pattern
+
+    def use_pagecache(self):
+        """Allows use of downloaded page cache.  It is essential for this
+        adapter, because the site does not offers chapter URL list, and many
+        pages have to be fetched and parsed repeatedly."""
+        return True
+
+    def extractChapterUrlsAndMetadata(self):
+        """Extracts chapter URLs and story metadata.  Actually downloads all
+        chapters, which is not exactly right, but necessary due to technical
+        limitations of the site."""
+
+        def followChapters(starting, forward=True):
+            if forward:
+                url = starting.getNextChapterUrl()
+            else:
+                url = starting.getPreviousChapterUrl()
+            if url:
+                url = self._makeDocumentUrl(self._getDocumentId(url))
+                following = self._makeChapter(url)
+                # Do not follow links to related, but different stories (prequels or sequels).
+                if not following.isFromStory(starting.getHeading()):
+                    return
+                if forward:
+                    yield following
+                for chapter in followChapters(following, forward):
+                    yield chapter
+                if not forward:
+                    yield following
+
+        try:
+            startingChapter = self._makeChapter(self.url)
+        except urllib2.HTTPError, error:
+            if error.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            raise
+
+        # We only have one date for each chapter and assume the oldest one
+        # to be publication date and the most recent one to be update date.
+        datePublished = datetime.datetime.max
+        dateUpdated = datetime.datetime.min
+        wordCount = 0
+        # We aim at counting chapters, not chapter parts.
+        chapterCount = 0
+        storyInProgress = False
+
+        chapters = \
+            list(followChapters(startingChapter, forward=False)) + \
+            [startingChapter] + \
+            list(followChapters(startingChapter, forward=True))
+
+        headings = [chapter.getHeading() for chapter in chapters]
+        largestCommonPrefix = _getLargestCommonPrefix(*headings)
+        prefixLength = len(largestCommonPrefix)
+        storyTitleEnd, chapterTitleStart = prefixLength, prefixLength
+        match = re.search(u'[:\.\s]*(?P<chapter>глава\s+)?$', largestCommonPrefix, re.IGNORECASE | re.UNICODE)
+        if match:
+            storyTitleEnd -= len(match.group())
+            label = match.group('chapter')
+            if label:
+                chapterTitleStart -= len(label)
+        storyTitle = largestCommonPrefix[:storyTitleEnd]
+        self.story.setMetadata('title', storyTitle)
+
+        garbagePattern = re.compile(u'(?P<start>^)?[:\.\s]*(?(start)|$)', re.UNICODE)
+        indexPattern = re.compile(u'(?:глава\s)?(?:(?<!\d)(?P<index>\d{1,3})(?=\D|$))', re.IGNORECASE | re.UNICODE)
+
+        for chapter in chapters:
+            url = chapter.getUrl()
+            self._chapters[url] = chapter
+            _logger.debug(u"Processing chapter `%s'.", url)
+
+            try:
+                authorName = chapter.getAuthorName()
+                if authorName:
+                    self.story.extendList('author', [authorName])
+                    authorId = chapter.getAuthorId()
+                    if authorId:
+                        authorUrl = 'http://%s/index/%s' % (self.getSiteDomain(), authorId)
+                    else:
+                        authorId = u''
+                        authorUrl = u''
+                    self.story.extendList('authorId', [authorId])
+                    self.story.extendList('authorUrl', [authorUrl])
+
+                if not self.story.getMetadata('rating'):
+                    ratingTitle = chapter.getRatingTitle()
+                    if ratingTitle:
+                        self.story.setMetadata('rating', ratingTitle)
+
+                if not self.story.getMetadata('description'):
+                    summary = chapter.getSummary()
+                    if summary:
+                        self.story.setMetadata('description', summary)
+
+                datePublished = min(datePublished, chapter.getDate())
+                dateUpdated = max(dateUpdated, chapter.getDate())
+
+                self.story.extendList('genre', chapter.getGenres())
+                self.story.extendList('characters', chapter.getCharacters())
+                self.story.extendList('ships', chapter.getPairings())
+
+                wordCount += self._getWordCount(chapter.getTextElement())
+
+                # Chapter status usually represents the story status, so we want the last chapter status.
+                # Some chapters may have no status attribute.
+                chapterInProgress = chapter.isInProgress()
+                if chapterInProgress is not None:
+                    storyInProgress = chapterInProgress
+
+                # If any chapter is adult, consider the whole story adult.
+                if chapter.isAdult():
+                    self.story.setMetadata('is_adult', True)
+                    warning = chapter.getWarning()
+                    if warning:
+                        self.story.extendList('warnings', [warning])
+
+                chapterTitle = re.sub(garbagePattern, u'', chapter.getHeading()[chapterTitleStart:])
+
+                match = re.search(indexPattern, chapterTitle)
+                if match:
+                    index = int(match.group('index'))
+                    chapterCount = max(chapterCount, index)
+                else:
+                    chapterCount += 1
+
+                self.chapterUrls.append((chapterTitle, url))
+            except ParsingError, error:
+                raise exceptions.FailedToDownload(u"Failed to download chapter `%s': %s" % (url, error))
+
+        # Some metadata are handled separately due to format conversions.
+        self.story.setMetadata('status', 'In Progress' if storyInProgress else 'Completed')
+        self.story.setMetadata('datePublished', datePublished)
+        self.story.setMetadata('dateUpdated', dateUpdated)
+        self.story.setMetadata('numWords', unicode(wordCount))
+        self.story.setMetadata('numChapters', chapterCount)
+
+        # Site-specific metadata.
+        self.story.setMetadata('language', self.SITE_LANGUAGE)
+
+    def getChapterText(self, url):
+        """Grabs the text for an individual chapter."""
+        if url not in self._chapters:
+            raise exceptions.FailedToDownload(u"No chapter `%s' present!" % url)
+        chapter = self._chapters[url]
+        return self.utf8FromSoup(url, chapter.getTextElement())
+
+    def _makeChapter(self, url):
+        """Creates a chapter object given a URL."""
+        document = self.make_soup(self._fetchUrl(url))
+        chapter = Chapter(self._getParsingConfiguration(), url, document)
+        return chapter
+
+    def _getWordCount(self, element):
+        """Returns word count in plain text extracted from chapter body."""
+        text = stripHTML(element)
+        count = len(re.findall(self.WORD_PATTERN, text))
+        return count
+
+    def _getParsingConfiguration(self):
+        if not self._parsingConfiguration:
+            self._parsingConfiguration = {}
+
+            adultRatings = self.getConfigList('adult_ratings')
+            if not adultRatings:
+                raise exceptions.PersonalIniFailed(
+                    u"Missing `adult_ratings' setting", u"MassEffect2.in", u"?")
+            adultRatings = set(adultRatings)
+            self._parsingConfiguration['adultRatings'] = adultRatings
+
+            ratingTitleDescriptions = self.getConfigList('rating_titles')
+            if ratingTitleDescriptions:
+                ratingTitles = {}
+                for ratingDescription in ratingTitleDescriptions:
+                    parts = ratingDescription.split(u'=')
+                    if len(parts) < 2:
+                        _logger.warning(
+                            u"Invalid `rating_titles' setting, missing `=' in `%s'."
+                            % ratingDescription)
+                        continue
+                    labels = parts[:-1]
+                    title = parts[-1]
+                    for label in labels:
+                        ratingTitles[label] = title
+                        # Duplicate label aliasing in adult rating set.
+                        if label in adultRatings:
+                            adultRatings.add(*labels)
+                self._parsingConfiguration['adultRatings'] = list(adultRatings)
+                self._parsingConfiguration['ratingTitles'] = ratingTitles
+            else:
+                raise exceptions.PersonalIniFailed(
+                    u"Missing `rating_titles' setting", u"MassEffect2.in", u"?")
+
+            self._parsingConfiguration['excludeEditorSignature'] = \
+                self.getConfig('exclude_editor_signature', False)
+
+        return self._parsingConfiguration
+
+    def _getDocumentId(self, url):
+        """Extract document ID from MassEffect2.in URL."""
+        match = re.search(self.DOCUMENT_ID_PATTERN, url)
+        if not match:
+            raise ValueError(u"Failed to extract document ID from `'" % url)
+        documentId = url[match.start():match.end()]
+        return documentId
+
+    @classmethod
+    def _makeDocumentUrl(cls, documentId):
+        """Make a chapter URL given a document ID."""
+        return 'http://%s/publ/%s' % (cls.getSiteDomain(), documentId)
+
+
+class Chapter(object):
+    """Represents a lazily-parsed chapter of a story."""
+    def __init__(self, configuration, url, document):
+        self._configuration = configuration
+        self._url = url
+        self._document = document
+        # Lazy-loaded:
+        self._heading = None
+        self._date = None
+        self._author = None
+        self._attributes = None
+        self._textElement = None
+        self._infoBar = None
+
+    def getHeading(self):
+        return self._extractHeading()
+
+    def getSummary(self):
+        attributes = self.__getAttributes()
+        if 'summary' in attributes:
+            return attributes['summary']
+
+    def getAuthorId(self):
+        author = self._getAuthor()
+        if author:
+            return author['id']
+
+    def getAuthorName(self):
+        author = self._getAuthor()
+        if author:
+            return author['name']
+
+    def getDate(self):
+        return self.__getDate()
+
+    def getRatingTitle(self):
+        attributes = self.__getAttributes()
+        if 'rating' in attributes:
+            return attributes['rating']['title']
+
+    def isAdult(self):
+        attributes = self.__getAttributes()
+        if 'rating' in attributes and attributes['rating']['isAdult']:
+            return True
+        if 'warning' in attributes:
+            return True
+        return False
+
+    def getWarning(self):
+        attributes = self.__getAttributes()
+        if 'warning' in attributes:
+            return attributes['warning']
+
+    def getCharacters(self):
+        return self._getListAttribute('characters')
+
+    def getPairings(self):
+        return self._getListAttribute('pairings')
+
+    def getGenres(self):
+        return self._getListAttribute('genres')
+
+    def isInProgress(self):
+        attributes = self.__getAttributes()
+        if 'isInProgress' in attributes:
+            return attributes['isInProgress']
+
+    def getUrl(self):
+        return self._url
+
+    def getTextElement(self):
+        return self._getTextElement()
+
+    def getPreviousChapterUrl(self):
+        """Download chapters following `Previous chapter' links.
+        Returns a list of chapters' URLs."""
+        return self._getSiblingChapterUrl({'class': 'fl tal'})
+
+    def getNextChapterUrl(self):
+        """Download chapters following `Next chapter' links.
+        Returns a list of chapters' URLs."""
+        return self._getSiblingChapterUrl({'class': 'tar fr'})
+
+    def isFromStory(self, storyTitle, prefixThreshold=-1):
+        """Check if this chapter is from a story different from the given one.
+        Prefix threshold specifies how long common story title prefix shall be
+        for chapters from one story: negative value means implementation-defined
+        optimum, zero inhibits the check, and positive value adjusts threshold."""
+
+        def getFirstWord(string):
+            match = re.search(u'^\s*\w+', string, re.UNICODE)
+            return string[match.start():match.end()]
+
+        thisStoryTitle = self.getHeading()
+        if prefixThreshold != 0:
+            if prefixThreshold < 0:
+                prefixThreshold = min(
+                    len(getFirstWord(storyTitle)), len(getFirstWord(thisStoryTitle)))
+            else:
+                prefixThreshold = min(
+                    prefixThreshold, len(storyTitle), len(thisStoryTitle))
+            result = len(_getLargestCommonPrefix(storyTitle, thisStoryTitle)) >= prefixThreshold
+            return result
+        else:
+            return storyTitle != thisStoryTitle
+
+    def _getListAttribute(self, name):
+        """Return an attribute value as a list or an empty list if the attribute is absent."""
+        attributes = self.__getAttributes()
+        if name in attributes:
+            return attributes[name]
+        return []
+
+    def _extractHeading(self):
+        """Extract header text from the document."""
+        return stripHTML(
+            self._document.find('div', {'class': 'eTitle'}).string)
+
+    def __getHeading(self):
+        """Lazily parse and return heading."""
+        if not self._heading:
+            self._heading = self._extractHeading()
+        return self._heading
+
+    def _getAuthor(self):
+        """Lazily parse and return author's information."""
+        if not self._author:
+            self._author = self._parseAuthor()
+        return self._author
+
+    def _parseAuthor(self):
+        """Locate and parse chapter author's information to a dictionary with author's `id' and `name'."""
+        try:
+            authorLink = self._getInfoBarElement() \
+                .find('i', {'class': 'icon-user'}) \
+                .findNextSibling('a')
+        except AttributeError:
+            raise ParsingError(u'Failed to locate author link.')
+        match = re.search(u'(8-\d+)', authorLink['onclick'])
+        if not match:
+            raise ParsingError(u'Failed to extract author ID.')
+        authorId = match.group(0)
+        authorName = stripHTML(authorLink.text)
+        return {
+            'id': authorId,
+            'name': authorName
+        }
+
+    def __getDate(self):
+        """Lazily parse chapter date."""
+        if not self._date:
+            self._date = self._parseDate()
+        return self._date
+
+    def _parseDate(self):
+        """Locate and parse chapter date."""
+        try:
+            dateText = self._getInfoBarElement() \
+                .find('i', {'class': 'icon-eye'}) \
+                .findPreviousSibling(text=True) \
+                .strip(u'| \n')
+        except AttributeError:
+            raise ParsingError(u'Failed to locate date.')
+        date = makeDate(dateText, '%d.%m.%Y')
+        return date
+
+    def _getInfoBarElement(self):
+        """Locate informational bar element, containing chapter date and author, on the page."""
+        if not self._infoBar:
+            self._infoBar = self._document.find('td', {'class': 'eDetails2'})
+            if not self._infoBar:
+                raise ParsingError(u'No informational bar found.')
+        return self._infoBar
+
+    def __getAttributes(self):
+        """Lazily parse attributes."""
+        if not self._attributes:
+            self._attributes = self._parseAttributes()
+        return self._attributes
+
+    def _parseAttributes(self):
+        """Parse chapter attribute block and return it as a dictionary with standard entries."""
+
+        attributes = {}
+        attributesText = u''
+        try:
+            starter = self._document \
+                .find('div', {'class': 'comm-div'}) \
+                .findNextSibling('div', {'class': 'cb'})
+            bound = starter.findNextSibling('div', {'class': 'cb'})
+
+            def processElement(element):
+                """Return textual representation an *inline* element of chapter attribute block."""
+                result = u''
+                if isinstance(element, bs4.Tag):
+                    if element.name in ('b', 'strong', 'font', 'br'):
+                        result += u"\n"
+                    if element.name == 's':
+                        result += u"<s>%s</s>" % stripHTML(element)
+                    else:
+                        result += stripHTML(element)
+                else:
+                    result += removeEntities(element)
+                return result
+
+            elements = starter.nextSiblingGenerator()
+            for element in elements:
+                if isinstance(element, bs4.Tag):
+                    if element == bound:
+                        break
+                    else:
+                        if element.name in ('div', 'p'):
+                            attributesText += u"\n"
+                            for child in element.childGenerator():
+                                attributesText += processElement(child)
+                            continue
+                attributesText += processElement(element)
+
+            elements = starter.nextGenerator()
+            for element in elements:
+                if isinstance(element, bs4.Tag):
+                    if element == bound:
+                        break
+                    elif element.name == 'img':
+                        rating = self._parseRatingFromImage(element)
+                        if rating:
+                            attributes['rating'] = rating
+                            break
+        except AttributeError or TypeError:
+            raise ParsingError(u'Failed to locate and collect attributes.')
+
+        separators = u"\r\n :;."
+        freestandingText = u''
+        for line in attributesText.split(u'\n'):
+            if line.count(u':') != 1:
+                freestandingText += line
+                continue
+            key, value = line.split(u':', 1)
+            key = key.strip(separators).lower()
+            value = value.strip().strip(separators)
+            parsed = self._parseAttribute(key, value)
+            for parsedKey, parsedValue in parsed.iteritems():
+                attributes[parsedKey] = parsedValue
+
+        freestandingText = freestandingText.strip()
+        if 'summary' not in attributes and freestandingText:
+            attributes['summary'] = freestandingText
+
+        if 'rating' not in attributes:
+            _logger.warning(u"Failed to locate or recognize rating for `%s'!", self.getUrl())
+
+        return attributes
+
+    # Most, but not all, URLs of rating icons match this.
+    RATING_LABEL_PATTERN = re.compile(u'/(?P<rating>[ERATINnG]+)\.png$')
+
+    def _parseRatingFromImage(self, element):
+        """Given an image element, try to parse story rating from it."""
+        if not element.has_attr('src'):
+            return
+        source = element['src']
+        if 'REITiNG' in source:
+            match = re.search(self.RATING_LABEL_PATTERN, source)
+            if not match:
+                return
+            label = match.group('rating')
+            if label in self._configuration['ratingTitles']:
+                return {
+                    'label': label,
+                    'title': self._configuration['ratingTitles'][label],
+                    'isAdult': label in self._configuration['adultRatings']
+                }
+            else:
+                _logger.warning(u"No title found for rating label `%s'!" % label)
+        # TODO: conduct a research on such abnormal URLs.
+        elif source == 'http://www.masseffect2.in/_fr/10/1360399.png':
+            label = 'Nn'
+            return {
+                'label': 'Nn',
+                'title': self._configuration['ratingTitles'][label],
+                'isAdult': label in self._configuration['adultRatings']
+            }
+
+    # Various `et cetera' and `et al' forms in Russian texts.
+    # Intended to be used with whole strings!
+    ETC_PATTERN = re.compile(
+        u'''[и&]\s(?:
+              (?:т\.?\s?[пд]?\.?)|
+              (?:др(?:угие|\.)?)|
+              (?:пр(?:очие|\.)?)|
+              # Note: identically looking letters `K' and `o'
+              # below are from Latin and Cyrillic alphabets.
+              (?:ко(?:мпания)?|[KК][oо°])
+            )$
+        ''',
+        re.IGNORECASE + re.UNICODE + re.VERBOSE)
+
+    # `Author's Notes' and its variants in Russian.
+    ANNOTATION_PATTERN = re.compile(u'аннотация|описание|(?:(?:за|при)мечание\s)?(?:от\s)?автора', re.UNICODE)
+
+    def _parseAttribute(self, key, value):
+        """
+        Parse a single a single record in chapter attributes for chapter metadata.
+        Return a dictionary of canonical attributes and values (i. e. multiple attributes may be discovered).
+        """
+
+        def refineCharacter(name):
+            """Refines character name from stop-words and distortions."""
+            strippedName = name.strip()
+            nameOnly = re.sub(self.ETC_PATTERN, u'', strippedName)
+            # TODO: extract canonical name (even ME-specific?).
+            canonicalName = nameOnly
+            return canonicalName
+
+        if re.match(u'жанры?', key, re.UNICODE):
+            genres = filter(bool, map(unicode.strip, re.split(u'[,;/]', value)))
+            return {'genres': genres}
+        elif key == u'статус':
+            isInProgress = value == u'в процессе'
+            return {'isInProgress': isInProgress}
+        elif key == u'персонажи':
+            participants = map(refineCharacter, re.split(u'[,;]', value))
+            characters = []
+            pairings = []
+            for participant in participants:
+                if u'/' in participant:
+                    pairings.append(participant)
+                else:
+                    characters.append(participant)
+            return {
+                'characters': characters,
+                'pairings': pairings
+            }
+        elif key == u'предупреждение':
+            return {'warning': value}
+        elif re.match(self.ANNOTATION_PATTERN, key):
+            if not value.endswith(u'.'):
+                value += u'.'
+            # Capitalize would make value[1:] lowercase, which we don't want.
+            value = value[:1].upper() + value[1:]
+            return {'summary': value}
+        else:
+            _logger.info(u"Unrecognized attribute `%s' ignored.", key)
+            return {}
+
+    def _getTextElement(self):
+        """Locate chapter body text element on the page."""
+        if not self._textElement:
+            self._textElement = self.__collectTextElements()
+        return self._textElement
+
+    def __collectTextElements(self):
+        """Return all elements containing parts of chapter text (which may be
+        <p>aragraphs, <div>isions or plain text nodes) under a single root."""
+        starter = self._document.find('div', {'id': u'article'})
+        if starter is None:
+            # FIXME: This will occur if the method is called more than once.
+            # The reason is elements appended to `root' are removed from the document.
+            # BS 4.4 implements cloning via `copy.copy()', but supporting it for BS 4.3
+            # would be error-prone (due to relying on BS internals) and is not needed.
+            if self._textElement:
+                _logger.debug(u"You may not call this function more than once!")
+            raise ParsingError(u'Failed to locate text.')
+        collection = [starter]
+        for element in starter.nextSiblingGenerator():
+            if element is None:
+                break
+            if isinstance(element, bs4.Tag) and element.name == 'tr':
+                break
+            collection.append(element)
+        root = bs4.Tag(name='td')
+        for element in collection:
+            root.append(element)
+
+        if self._configuration['excludeEditorSignature']:
+            root = self._excludeEditorSignature(root)
+
+        return root
+
+    def _getSiblingChapterUrl(self, selector):
+        """Locate a link to a sibling chapter, either previous or next one, and return its URL."""
+        block = self._document \
+            .find('td', {'class': 'eDetails1'}) \
+            .find('div', selector)
+        if not block:
+            return
+        link = block.find('a')
+        if not link:
+            return
+        return link['href']
+
+    # Editor signature always starts with something like this.
+    SIGNED_PATTERN = re.compile(u'отредактирова(?:но|ла?)[:.\s]', re.IGNORECASE + re.UNICODE)
+
+    def _excludeEditorSignature(self, root):
+        """Exclude editor signature from within `root' element."""
+        for textNode in root.findAll(text=True):
+            if re.match(self.SIGNED_PATTERN, textNode.string):
+                editorLink = textNode.findNext('a')
+                if editorLink:
+                    editorLink.extract()
+                # Seldom editor link has inner formatting, which is sibling DOM-wise.
+                editorName = textNode.findNext('i')
+                if editorName:
+                    editorName.extract()
+                textNode.extract()
+                # We could try removing container element, but there is a risk
+                # of removing text ending with it.  Better play safe here.
+                break
+        return root
+
+
+def _getLargestCommonPrefix(*args):
+    """Returns largest common prefix of all unicode arguments, ignoring case.
+    :rtype : unicode
+    """
+    from itertools import takewhile, izip
+    toLower = lambda xs: map(lambda x: x.lower(), xs)
+    allSame = lambda xs: len(set(toLower(xs))) == 1
+    return u''.join([i[0] for i in takewhile(allSame, izip(*args))])

fanficfare/adapters/adapter_mcstoriescom.py

@@ -0,0 +1,189 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2013 Fanficdownloader team, 2016 FanFicFare team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+logger = logging.getLogger(__name__)
+import re
+import urllib2
+import urlparse
+import time
+import os
+
+from bs4.element import Comment
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter, makeDate
+
+class MCStoriesComSiteAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["utf8",
+                       "Windows-1252"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+
+        self.story.setMetadata('siteabbrev','mcstories')
+
+        # Normalize story URL to the chapter index page (.../index.html)
+        url = re.sub("/([a-zA-Z0-9_-]+.html)?$", "/index.html", url)
+
+        # Extract story ID from base URL, http://mcstories.com/STORY_ID/index.html
+        storyId = self.parsedUrl.path.split('/',)[1]
+        self.story.setMetadata('storyId', storyId)
+
+        ## set url
+        self._setURL(url)
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = '%d %B %Y'
+
+    @staticmethod
+    def getSiteDomain():
+        return 'mcstories.com'
+
+    @classmethod
+    def getAcceptDomains(cls):
+        return ['mcstories.com',
+                'www.mcstories.com']
+
+    @classmethod
+    def getSiteExampleURLs(cls):
+        return "http://mcstories.com/StoryTitle http://mcstories.com/StoryTitle/index.html http://mcstories.com/StoryTitle/StoryTitle1.html"
+
+    def getSiteURLPattern(self):
+        return r"https?://(www\.)?mcstories\.com/([a-zA-Z0-9_-]+)/"
+
+    def extractChapterUrlsAndMetadata(self):
+        """
+        Chapters are located at /StoryName/StoryName.html (for single-chapter
+        stories), or /StoryName/StoryName#.html for multiple chapters (# is a
+        non-padded incrementing number, like StoryName1, StoryName2.html, ...,
+        StoryName10.html)
+
+        The story metadata page is at /StoryName/index.html , including a list
+        of chapters.
+        """
+
+        if not (self.is_adult or self.getConfig("is_adult")):
+            raise exceptions.AdultCheckRequired(self.url)
+
+        try:
+            data1 = self._fetchUrl(self.url)
+            soup1 = self.make_soup(data1)
+            #strip comments from soup
+            [comment.extract() for comment in soup1.find_all(text=lambda text:isinstance(text, Comment))]
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        # Extract metadata
+        title = soup1.find('h3', class_='title')
+        self.story.setMetadata('title', title.text)
+
+        # Author
+        author = soup1.find('h3', class_='byline').a
+        authorurl = urlparse.urljoin(self.url, author['href'])
+        self.story.setMetadata('author', author.text)
+        self.story.setMetadata('authorUrl', authorurl)
+        authorid = os.path.splitext(os.path.basename(authorurl))[0]
+        self.story.setMetadata('authorId', authorid)
+
+        # Description
+        synopsis = soup1.find('section', class_='synopsis')
+        description = "\n\n".join([p.text for p in synopsis.find_all('p')])
+        self.story.setMetadata('description', description)
+
+        # Tags
+        codesDiv = soup1.find('div', class_="storyCodes")
+        for a in codesDiv.find_all('a'):
+            self.story.addToList('eroticatags', a.text)
+
+        # Publish and update dates
+        publishdate = None
+        updatedate = None
+        datelines = soup1.find_all('h3', class_='dateline')
+        for dateline in datelines:
+            if dateline.text.startswith('Added '):
+                publishdate = makeDate(dateline.text, "Added " + self.dateformat)
+            elif dateline.text.startswith('Updated '):
+                updatedate = makeDate(dateline.text, "Updated " + self.dateformat)
+
+        if publishdate is not None: self.story.setMetadata('datePublished', publishdate)
+        if updatedate is not None: self.story.setMetadata('dateUpdated', updatedate)
+
+        # Get chapter URLs
+        self.chapterUrls = []
+        chapterTable = soup1.find('table', class_='index')
+
+        if chapterTable is not None:
+            # Multi-chapter story
+            chapterRows = chapterTable.find_all('tr')
+
+            for row in chapterRows:
+                chapterCell = row.td
+                if chapterCell is not None:
+                    link = chapterCell.a
+                    chapterTitle = link.text
+                    chapterUrl = urlparse.urljoin(self.url, link['href'])
+                    self.chapterUrls.append((chapterTitle, chapterUrl))
+        else:
+            # Single chapter
+            chapterDiv = soup1.find('div', class_='chapter')
+            chapterTitle = chapterDiv.a.text
+            chapterUrl = urlparse.urljoin(self.url, chapterDiv.a['href'])
+            self.chapterUrls = [(chapterTitle, chapterUrl)]
+
+        self.story.setMetadata('numChapters', len(self.chapterUrls))
+
+        logger.debug("Story: <%s>", self.story)
+
+        return
+
+    def getChapterText(self, url):
+        """
+        Clean up a mcstories chapter page.
+
+        All content is in article#mcstories, with chapter headers in h3
+        """
+        logger.debug('Getting chapter text from <%s>' % url)
+        data1 = self._fetchUrl(url)
+        soup1 = self.make_soup(data1)
+
+        #strip comments from soup
+        [comment.extract() for comment in soup1.find_all(text=lambda text:isinstance(text, Comment))]
+
+        # get story text
+        story1 = soup1.find('article', id='mcstories')
+
+        # Remove duplicate name and author headers
+        [h3.extract() for h3 in story1.find_all('h3',class_=re.compile(r'(title|chapter|byline)'))]
+
+        storytext = self.utf8FromSoup(url, story1)
+
+        return storytext
+
+
+def getClass():
+    return MCStoriesComSiteAdapter

fanficfare/adapters/adapter_mediaminerorg.py

@@ -22,7 +22,6 @@ import re
 import urllib
 import urllib2
 
-from .. import BeautifulSoup as bs
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -38,32 +37,74 @@ class MediaMinerOrgSiteAdapter(BaseSiteAdapter):
                                # Most sites that claim to be
                                # iso-8859-1 (and some that claim to be
                                # utf8) are really windows-1252.
-        
+
         # get storyId from url--url validation guarantees query correct
         m = re.match(self.getSiteURLPattern(),url)
+        urltitle='urltitle'
+        cattitle='cattitle'
         if m:
-            self.story.setMetadata('storyId',m.group('id'))
-            
+            if m.group('id1'):
+                self.story.setMetadata('storyId',m.group('id1'))
+                urltitle=m.group('urltitle1')
+            elif m.group('id2'):
+                self.story.setMetadata('storyId',m.group('id2'))
+                urltitle=m.group('urltitle2')
+            elif m.group('id3'):
+                self.story.setMetadata('storyId',m.group('id3'))
+            elif m.group('id4'):
+                self.story.setMetadata('storyId',m.group('id4'))
+                cattitle=m.group('cattitle4')
+                urltitle=m.group('urltitle4')
+            elif m.group('id5'):
+                self.story.setMetadata('storyId',m.group('id5'))
+                cattitle=m.group('cattitle5')
+                urltitle=m.group('urltitle5')
+            else:
+                raise InvalidStoryURL(url,
+                                      self.getSiteDomain(),
+                                      self.getSiteExampleURLs())
+
             # normalized story URL.
-            self._setURL('http://' + self.getSiteDomain() + '/fanfic/view_st.php/'+self.story.getMetadata('storyId'))
+            self._setURL('http://' + self.getSiteDomain() + '/fanfic/s/'+cattitle+'/'+urltitle+'/'+self.story.getMetadata('storyId'))
         else:
             raise exceptions.InvalidStoryURL(url,
                                              self.getSiteDomain(),
                                              self.getSiteExampleURLs())
-            
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%B %d, %Y %H:%M"
+
     @staticmethod
     def getSiteDomain():
         return 'www.mediaminer.org'
 
     @classmethod
     def getSiteExampleURLs(cls):
-        return "http://"+cls.getSiteDomain()+"/fanfic/view_st.php/123456 http://"+cls.getSiteDomain()+"/fanfic/view_ch.php/1234123/123444#fic_c"
+        return "http://"+cls.getSiteDomain()+"/fanfic/s/category-name/story-title/123456 http://"+cls.getSiteDomain()+"/fanfic/c/category-name/story-title/123456/987612"
 
     def getSiteURLPattern(self):
-        ##  http://www.mediaminer.org/fanfic/view_st.php/76882
-        ##  http://www.mediaminer.org/fanfic/view_ch.php/167618/594087#fic_c
-        return re.escape("http://"+self.getSiteDomain())+\
-            "/fanfic/view_(st|ch)\.php/"+r"(?P<id>\d+)(/\d+(#fic_c)?)?$"
+        ## old urls
+        ## http://www.mediaminer.org/fanfic/view_st.php/76882
+        ## new urls
+        ## http://www.mediaminer.org/fanfic/s/ghosts-from-the-past/72
+        ## http://www.mediaminer.org/fanfic/c/ghosts-from-the-past/chapter-2/72/174
+        ## http://www.mediaminer.org/fanfic/s/robtech-final-missions/61553
+        ## http://www.mediaminer.org/fanfic/c/robtech-final-missions/robotech-final-missions-oneshot/61553/189830
+        ## even newer urls
+        ## http://www.mediaminer.org/fanfic/s/gundam-wing-fan-fiction/the-preventer-operatives/171000
+        ## http://www.mediaminer.org/fanfic/c/gundam-wing-fan-fiction/the-preventer-operatives/171000/608822
+        return re.escape("http://"+self.getSiteDomain())+r"/fanfic/"+\
+            r"((s/(?P<cattitle4>[^/]+)/(?P<urltitle4>[^/]+)/(?P<id4>\d+))|"+\
+            r"((c/(?P<cattitle5>[^/]+)/(?P<urltitle5>[^/]+)/(?P<id5>\d+))/\d+)|"+\
+            r"(s/(?P<urltitle1>[^/]+)/(?P<id1>\d+))|"+\
+            r"((c/(?P<urltitle2>[^/]+)/[^/]+/(?P<id2>\d+))/\d+)|"+\
+            r"(view_st\.php/(?P<id3>\d+)))"
+
+    # Override stripURLParameters so the id parameter won't get stripped
+    @classmethod
+    def stripURLParameters(cls, url):
+        return url
 
     def extractChapterUrlsAndMetadata(self):
 
@@ -71,110 +112,78 @@ class MediaMinerOrgSiteAdapter(BaseSiteAdapter):
         logger.debug("URL: "+url)
 
         try:
-            data = self._fetchUrl(url)
+            data = self._fetchUrl(url) # w/o trailing / gets 'chapter list' page even for one-shots.
         except urllib2.HTTPError, e:
             if e.code == 404:
+                logger.error("404 on %s"%url)
                 raise exceptions.StoryDoesNotExist(self.url)
             else:
                 raise e
 
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
 
-        # [ A - All Readers ], strip '[' ']'
+        ## title:
+        ## <h1 id="post-title">A, A' Fan Fiction &#10095; Mmmmm</h1>
+        titletext = stripHTML(soup.find("h1",{"id":"post-title"}))
+        titletext = titletext[titletext.index(u'❯')+2:]
+        # print("title:(%s)"%titletext)
+        self.story.setMetadata('title',titletext)
+
+        # [ A - All Readers ], strip '[ ' ' ]'
         ## Above title because we remove the smtxt font to get title.
-        smtxt = soup.find("font",{"class":"smtxt"})
+        smtxt = soup.find("div",{"id":"post-rating"})
         if not smtxt:
+            logger.error("can't find rating")
             raise exceptions.StoryDoesNotExist(self.url)
-        rating = smtxt.string[1:-1]
-        self.story.setMetadata('rating',rating)
+        else:
+            rating = smtxt.string[2:-2]
+            self.story.setMetadata('rating',rating)
 
         # Find authorid and URL from... author url.
-        a = soup.find('a', href=re.compile(r"/fanfic/src.php/u/\d+"))
+        a = soup.find('a', href=re.compile(r"/user_info.php/\d+"))
         self.story.setMetadata('authorId',a['href'].split('/')[-1])
         self.story.setMetadata('authorUrl','http://'+self.host+a['href'])
         self.story.setMetadata('author',a.string)
 
-        ## Title - Good grief.  Title varies by chaptered, 1chapter and 'type=one shot'--and even 'one-shot's can have titled chapter.
-        ## But, if colspan=2, there's no chapter title.
-        ## <td class="ffh">Atmosphere: Chapter 1</b> <font class="smtxt">[ P - Pre-Teen ]</font></td>
-        ## <td colspan=2 class="ffh">Hearts of Ice <font class="smtxt">[ P - Pre-Teen ]</font></td>
-        ## <td colspan=2 class="ffh">Suzaku no Princess <font class="smtxt">[ P - Pre-Teen ]</font></td>
-        ## <td class="ffh">The Kraut, The Bartender, and The Drunkard: Chapter 1</b> <font class="smtxt">[ P - Pre-Teen ]</font></td>
-        ## <td class="ffh">Betrayal and Justice: A Cold Heart</b> <font size="-1">( Chapter 1 )</font> <font class="smtxt">[ A - All Readers ]</font></td>
-        ## <td class="ffh">Question and Answer: Question and Answer</b> <font size="-1">( One-Shot )</font> <font class="smtxt">[ A - All Readers ]</font></td>
-        title = soup.find('td',{'class':'ffh'})
-        for font in title.findAll('font'):
-            font.extract() # removes 'font' tags from inside the td.        
-        if title.has_key('colspan'):
-            titlet = stripHTML(title)
-        else:
-            ## No colspan, it's part chapter title--even if it's a one-shot.
-            titlet = ':'.join(stripHTML(title).split(':')[:-1]) # strip trailing 'Chapter X' or chapter title
-        self.story.setMetadata('title',titlet)
-        ## The story title is difficult to reliably parse from the
-        ## story pages.  Getting it from the author page is, but costs
-        ## another fetch.
-        # authsoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
-        # titlea = authsoup.find('a',{'href':'/fanfic/view_st.php/'+self.story.getMetadata('storyId')})
-        # self.story.setMetadata('title',titlea.text)
-
         # save date from first for later.
         firstdate=None
-        
-        # Find the chapters
-        select = soup.find('select',{'name':'cid'})
-        if not select:
-            self.chapterUrls.append(( self.story.getMetadata('title'),self.url))
-        else:
-            for option in select.findAll("option"):
-                chapter = stripHTML(option.string)
-                ## chapter can be: Chapter 7 [Jan 23, 2011]
-                ##             or: Vigilant Moonlight ( Chapter 1 ) [Jan 30, 2004]
-                ##        or even: Prologue ( Prologue ) [Jul 31, 2010]
-                m = re.match(r'^(.*?) (\( .*? \) )?\[(.*?)\]$',chapter)
-                chapter = m.group(1)
-                # save date from first for later.
-                if not firstdate:
-                    firstdate = m.group(3)
-                self.chapterUrls.append((chapter,'http://'+self.host+'/fanfic/view_ch.php/'+self.story.getMetadata('storyId')+'/'+option['value']))
+
+        # Find the chapters - one-shot now have chapter list, too.
+        chap_p = soup.find('p',{'style':'margin-left:10px;'})
+        for (atag,aurl,name) in [ (x,x['href'],stripHTML(x)) for x in chap_p.find_all('a') ]:
+            self.chapterUrls.append((name,'http://'+self.host+aurl))
+
         self.story.setMetadata('numChapters',len(self.chapterUrls))
 
         # category
         # <a href="/fanfic/src.php/a/567">Ranma 1/2</a>
-        for a in soup.findAll('a',href=re.compile(r"^/fanfic/src.php/a/")):
+        for a in soup.findAll('a',href=re.compile(r"^/fanfic/a/")):
             self.story.addToList('category',a.string)
-        
+
         # genre
-        # <a href="/fanfic/src.php/a/567">Ranma 1/2</a>
+        # <a href="/fanfic/src.php/g/567">Ranma 1/2</a>
         for a in soup.findAll('a',href=re.compile(r"^/fanfic/src.php/g/")):
             self.story.addToList('genre',a.string)
 
-        # if firstdate, then the block below will only have last updated.
-        if firstdate:
-            self.story.setMetadata('datePublished', makeDate(firstdate, "%b %d, %Y"))
-        # Everything else is in <tr bgcolor="#EEEED4">
+        metastr = stripHTML(soup.find("div",{"class":"post-meta"}))
 
-        metastr = stripHTML(soup.find("tr",{"bgcolor":"#EEEED4"})).replace('\n',' ').replace('\r',' ').replace('\t',' ')
-        # Latest Revision: August 03, 2010
-        m = re.match(r".*?(?:Latest Revision|Uploaded On): ([a-zA-Z]+ \d\d, \d\d\d\d)",metastr)
+        # Latest Revision: February 07, 2015 15:21 PST
+        m = re.match(r".*?(?:Latest Revision|Uploaded On): ([a-zA-Z]+ \d\d, \d\d\d\d \d\d:\d\d)",metastr)
         if m:
-            self.story.setMetadata('dateUpdated', makeDate(m.group(1), "%B %d, %Y"))
-            if not firstdate:
-                self.story.setMetadata('datePublished',
-                                       self.story.getMetadataRaw('dateUpdated'))
-                
-        else:
-            self.story.setMetadata('dateUpdated',
-                                   self.story.getMetadataRaw('datePublished'))
+            self.story.setMetadata('dateUpdated', makeDate(m.group(1), self.dateformat))
+            # site doesn't give date published on index page.
+            # set to updated, change in chapters below.
+            # self.story.setMetadata('datePublished',
+            #                        self.story.getMetadataRaw('dateUpdated'))
 
         # Words: 123456
         m = re.match(r".*?\| Words: (\d+) \|",metastr)
         if m:
             self.story.setMetadata('numWords', m.group(1))
-            
+
         # Summary: ....
-        m = re.match(r".*?Summary: (.*)$",metastr) 
+        m = re.match(r".*?Summary: (.*)$",metastr)
         if m:
             self.setDescription(url, m.group(1))
             #self.story.setMetadata('description', m.group(1))
@@ -192,45 +201,55 @@ class MediaMinerOrgSiteAdapter(BaseSiteAdapter):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        data=self._fetchUrl(url)
-        soup = bs.BeautifulStoneSoup(data,
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        data = self._fetchUrl(url)
+        soup = self.make_soup(data)
 
-        anchor = soup.find('a',{'name':'fic_c'})
+        headerstr = stripHTML(soup.find('div',{'class':'post-meta clearfix '}))
+        # print("data:%s"%data)
+        #header.extract()
 
-        if None == anchor:
-            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+        m = re.match(r".*?Uploaded On: ([a-zA-Z]+ \d\d, \d\d\d\d \d\d:\d\d)",headerstr)
+        if m:
+            date = makeDate(m.group(1), self.dateformat)
+            if not self.story.getMetadataRaw('datePublished') or date < self.story.getMetadataRaw('datePublished'):
+                self.story.setMetadata('datePublished', date)
+
+        chapter = soup.find('div',{'id':'fanfic-text'})
+
+        return self.utf8FromSoup(url,chapter)
+
+        # chapter=self.make_soup('<div class="story"></div>').find('div')
+
+        # if None == header:
+        #     raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+
+        # ## find divs with align=left, those are paragraphs in newer stories.
+        # divlist = header.findAllNext('div',{'align':'left'})
+        # if divlist:
+        #     for div in divlist:
+        #         div.name='p' # convert to <p> mediaminer uses div with
+        #                      # a margin for paragraphs.
+        #         chapter.append(div)
+        #         del div['style']
+        #         del div['align']
+        #     return self.utf8FromSoup(url,chapter)
+
+        # else:
+        #     logger.debug('Using kludgey text find for older mediaminer story.')
+        #     ## Some older mediaminer stories are unparsable with BeautifulSoup.
+        #     ## Really nasty formatting.  Sooo... Cheat!  Parse it ourselves a bit first.
+        #     ## Story stuff falls between:
+        #     data = "<div id='HERE'>" + data[data.find('<div class="adWrap">'):data.find('<div class="addthis_sharing_toolbox">')] +"</div>"
+        #     soup = self.make_soup(data)
+        #     for tag in soup.findAll('td',{'class':'ffh'}) + \
+        #             soup.findAll('div',{'class':'acl'}) + \
+        #             soup.findAll('div',{'class':'adWrap'}) + \
+        #             soup.findAll('div',{'class':'footer smtxt'}) + \
+        #             soup.findAll('table',{'class':'tbbrdr'}):
+        #         tag.extract() # remove tag from soup.
+
+        #     return self.utf8FromSoup(url,soup)
 
-        ## find divs with align=left, those are paragraphs in newer stories.
-        divlist = anchor.findAllNext('div',{'align':'left'})
-        if divlist:
-            for div in divlist:
-                div.name='p' # convert to <p> mediaminer uses div with
-                             # a margin for paragraphs.
-                anchor.append(div) # cheat!  stuff all the content
-                                   # divs into anchor just as a
-                                   # holder.
-                del div['style']
-                del div['align']
-            anchor.name='div'
-            return self.utf8FromSoup(url,anchor)
-        
-        else:
-            logger.debug('Using kludgey text find for older mediaminer story.')
-            ## Some older mediaminer stories are unparsable with BeautifulSoup.
-            ## Really nasty formatting.  Sooo... Cheat!  Parse it ourselves a bit first.
-            ## Story stuff falls between:
-            data = "<div id='HERE'>" + data[data.find('<a name="fic_c">'):] +"</div>"
-            soup = bs.BeautifulStoneSoup(data,
-                                         selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-            for tag in soup.findAll('td',{'class':'ffh'}) + \
-                    soup.findAll('div',{'class':'acl'}) + \
-                    soup.findAll('div',{'class':'footer smtxt'}) + \
-                    soup.findAll('table',{'class':'tbbrdr'}):
-                tag.extract() # remove tag from soup.
-                
-            return self.utf8FromSoup(url,soup)
-        
 
 def getClass():
     return MediaMinerOrgSiteAdapter

fanficfare/adapters/adapter_merlinficdtwinscouk.py

@@ -22,7 +22,7 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -46,21 +46,21 @@ class MerlinFicDtwinsCoUk(BaseSiteAdapter):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
+
+
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','mrfd')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%b %d, %Y"
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -81,7 +81,7 @@ class MerlinFicDtwinsCoUk(BaseSiteAdapter):
             return True
         else:
             return False
-        
+
     def performLogin(self, url):
         params = {}
 
@@ -93,13 +93,13 @@ class MerlinFicDtwinsCoUk(BaseSiteAdapter):
             params['password'] = self.getConfig("password")
         params['cookiecheck'] = '1'
         params['submit'] = 'Submit'
-    
+
         loginUrl = 'http://' + self.getSiteDomain() + '/user.php?action=login'
         logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
                                                               params['penname']))
-    
+
         d = self._fetchUrl(loginUrl, params)
-    
+
         if "Member Account" not in d : #Member Account
             logger.info("Failed to login to URL %s as %s" % (loginUrl,
                                                               params['penname']))
@@ -156,23 +156,23 @@ class MerlinFicDtwinsCoUk(BaseSiteAdapter):
                     if e.code == 404:
                         raise exceptions.StoryDoesNotExist(self.url)
                     else:
-                        raise e    
+                        raise e
             else:
                 raise exceptions.AdultCheckRequired(self.url)
-            
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',stripHTML(a))
-        
+
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
@@ -205,8 +205,8 @@ class MerlinFicDtwinsCoUk(BaseSiteAdapter):
             if 'Summary' in label:
                 ## Everything until the next span class='label'
                 svalue = ""
-                while not defaultGetattr(value,'class') == 'label':
-                    svalue += str(value)
+                while 'label' not in defaultGetattr(value,'class'):
+                    svalue += unicode(value)
                     value = value.nextSibling
                 self.setDescription(url,svalue)
                 #self.story.setMetadata('description',stripHTML(svalue))
@@ -226,7 +226,7 @@ class MerlinFicDtwinsCoUk(BaseSiteAdapter):
                 chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
                 for char in chars:
                     self.story.addToList('characters',char.string)
-                    
+
             if 'Pairing' in label:
                 ships = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
                 for ship in ships:
@@ -250,7 +250,7 @@ class MerlinFicDtwinsCoUk(BaseSiteAdapter):
 
             if 'Published' in label:
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
+
             if 'Updated' in label:
                 self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
 
@@ -261,7 +261,7 @@ class MerlinFicDtwinsCoUk(BaseSiteAdapter):
             series_url = 'http://'+self.host+'/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            seriessoup = self.make_soup(self._fetchUrl(series_url))
             # can't use ^viewstory...$ in case of higher rated stories with javascript href.
             storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+'))
             i=1
@@ -273,22 +273,21 @@ class MerlinFicDtwinsCoUk(BaseSiteAdapter):
                         self.story.setMetadata('seriesUrl',series_url)
                         break
                     i+=1
-            
+
         except:
             # I find it hard to care if the series parsing fails
             pass
-            
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
+        soup = self.make_soup(self._fetchUrl(url))
+
         div = soup.find('div', {'id' : 'story'})
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_midnightwhispersca.py

@@ -22,7 +22,7 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -50,22 +50,22 @@ class MidnightwhispersCaAdapter(BaseSiteAdapter): # XXX
                                # iso-8859-1 (and some that claim to be
                                # utf8) are really windows-1252.
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
+
+
         # normalized story URL.
         # XXX Most sites don't have the /fanfic part.  Replace all to remove it usually.
         self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','mw') # XXX
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%B %d, %Y" # XXX
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -111,12 +111,12 @@ class MidnightwhispersCaAdapter(BaseSiteAdapter): # XXX
         # The actual text that is used to announce you need to be an
         # adult varies from site to site.  Again, print data before
         # the title search to troubleshoot.
-            
+
         # Since the warning text can change by warning level, let's
         # look for the warning pass url.  nfacommunity uses
         # &warning= -- actually, so do other sites.  Must be an
         # eFiction book.
-            
+
         # viewstory.php?sid=1882&warning=4
         # viewstory.php?sid=1654&ageconsent=ok&warning=5
         #print data
@@ -139,20 +139,20 @@ class MidnightwhispersCaAdapter(BaseSiteAdapter): # XXX
                     if e.code == 404:
                         raise exceptions.StoryDoesNotExist(self.url)
                     else:
-                        raise e    
+                        raise e
             else:
                 raise exceptions.AdultCheckRequired(self.url)
-            
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         # print data
 
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',stripHTML(a)) # title's inside a <b> tag.
@@ -189,8 +189,8 @@ class MidnightwhispersCaAdapter(BaseSiteAdapter): # XXX
             if 'Summary' in label:
                 ## Everything until the next span class='label'
                 svalue = ""
-                while not defaultGetattr(value,'class') == 'label':
-                    svalue += str(value)
+                while 'label' not in defaultGetattr(value,'class'):
+                    svalue += unicode(value)
                     value = value.nextSibling
                 self.setDescription(url,svalue)
                 #self.story.setMetadata('description',stripHTML(svalue))
@@ -241,7 +241,7 @@ class MidnightwhispersCaAdapter(BaseSiteAdapter): # XXX
 
             if 'Published' in label:
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
+
             if 'Updated' in label:
                 # there's a stray [ at the end.
                 #value = value[0:-1]
@@ -254,7 +254,7 @@ class MidnightwhispersCaAdapter(BaseSiteAdapter): # XXX
             series_url = 'http://'+self.host+'/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            seriessoup = self.make_soup(self._fetchUrl(series_url))
             storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
             i=1
             for a in storyas:
@@ -265,20 +265,19 @@ class MidnightwhispersCaAdapter(BaseSiteAdapter): # XXX
                         self.story.setMetadata('seriesUrl',series_url)
                         break
                     i+=1
-            
+
         except:
             # I find it hard to care if the series parsing fails
             pass
-            
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
         data = self._fetchUrl(url)
-        soup = bs.BeautifulStoneSoup(data,
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
+        soup = self.make_soup(data)
+
         div = soup.find('div', {'id' : 'story'})
 
         if None == div:
@@ -286,5 +285,5 @@ class MidnightwhispersCaAdapter(BaseSiteAdapter): # XXX
                 raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Database error on the site reported!" % url)
             else:
                 raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_mugglenetcom.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
+# Copyright 2011 Fanficdownloader team, 2016 FanFicFare team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -16,58 +16,12 @@
 #
 
 # Software: eFiction
-import time
-import logging
-logger = logging.getLogger(__name__)
-import re
-import urllib2
+from base_efiction_adapter import BaseEfictionAdapter
 
-from .. import BeautifulSoup as bs
-from ..htmlcleanup import stripHTML
-from .. import exceptions as exceptions
+class MuggleNetComAdapter(BaseEfictionAdapter):
 
-from base_adapter import BaseSiteAdapter,  makeDate
-
-# This function is called by the downloader in all adapter_*.py files
-# in this dir to register the adapter class.  So it needs to be
-# updated to reflect the class below it.  That, plus getSiteDomain()
-# take care of 'Registering'.
-def getClass():
-    return MuggleNetComAdapter # XXX
-
-# Class name has to be unique.  Our convention is camel case the
-# sitename with Adapter at the end.  www is skipped.
-class MuggleNetComAdapter(BaseSiteAdapter): # XXX
-
-    def __init__(self, config, url):
-        BaseSiteAdapter.__init__(self, config, url)
-
-        self.decode = ["Windows-1252",
-                       "utf8"] # 1252 is a superset of iso-8859-1.
-                               # Most sites that claim to be
-                               # iso-8859-1 (and some that claim to be
-                               # utf8) are really windows-1252.
-        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
-        self.password = ""
-        self.is_adult=False
-        
-        # get storyId from url--url validation guarantees query is only sid=1234
-        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
-        # normalized story URL.
-        self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
-        # Each adapter needs to have a unique site abbreviation.
-        self.story.setMetadata('siteabbrev','mgln') # XXX
-
-        # The date format will vary from site to site.
-        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = "%m/%d/%y" # XXX
-            
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
-        # The site domain.
         return 'fanfiction.mugglenet.com'
 
     @classmethod
@@ -75,262 +29,12 @@ class MuggleNetComAdapter(BaseSiteAdapter): # XXX
         return ['fanfiction.mugglenet.com','fanfic.mugglenet.com']
 
     @classmethod
-    def getSiteExampleURLs(cls):
-        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
+    def getSiteAbbrev(self):
+        return 'mgln'
 
-    def getSiteURLPattern(self):
-        return re.escape("http://")+r"fanfic(tion)?\.mugglenet\.com"+re.escape("/viewstory.php?sid=")+r"\d+$"
+    @classmethod
+    def getDateFormat(self):
+        return "%m/%d/%y"
 
-    ## Login seems to be reasonably standard across eFiction sites.
-    def needToLoginCheck(self, data):
-        if "class='errortext'>Registered Users Only" in data \
-                or 'There is no such account on our website' in data \
-                or "That password doesn't match the one in our database" in data:
-            return True
-        else:
-            return False
-        
-    def performLogin(self, url):
-        params = {}
-
-        if self.password:
-            params['penname'] = self.username
-            params['password'] = self.password
-        else:
-            params['penname'] = self.getConfig("username")
-            params['password'] = self.getConfig("password")
-        params['cookiecheck'] = '1'
-        params['submit'] = 'Submit'
-    
-        loginUrl = 'http://' + self.getSiteDomain() + '/user.php?action=login&sid='+self.story.getMetadata('storyId')
-        logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
-                                                              params['penname']))
-    
-        d = self._fetchUrl(loginUrl, params)
-    
-        if "Member Account" not in d : #Member Account
-            logger.info("Failed to login to URL %s as %s" % (loginUrl,
-                                                              params['penname']))
-            raise exceptions.FailedToLogin(url,params['penname'])
-            return False
-        else:
-            return True
-
-    ## Getting the chapter list and the meta data, plus 'is adult' checking.
-    def extractChapterUrlsAndMetadata(self):
-
-        if self.is_adult or self.getConfig("is_adult"):
-            # Weirdly, different sites use different warning numbers.
-            # If the title search below fails, there's a good chance
-            # you need a different number.  print data at that point
-            # and see what the 'click here to continue' url says.
-            # http://fanfiction.mugglenet.com/viewstory.php?sid=91079&ageconsent=ok&warning=3
-            addurl = "&ageconsent=ok&warning=3" # XXX  &warning=5
-        else:
-            addurl=""
-
-        # index=1 makes sure we see the story chapter index.  Some
-        # sites skip that for one-chapter stories.
-        url = self.url+'&index=1'+addurl
-        logger.debug("URL: "+url)
-
-        try:
-            data = self._fetchUrl(url)
-        except urllib2.HTTPError, e:
-            if e.code == 404:
-                raise exceptions.StoryDoesNotExist(self.url)
-            else:
-                raise e
-
-        if self.needToLoginCheck(data):
-            # need to log in for this one.
-            self.performLogin(url)
-            data = self._fetchUrl(url)
-            #print("\nurl:%s\ndata:\n%s\n"%(url,data))
-
-        # The actual text that is used to announce you need to be an
-        # adult varies from site to site.  Again, print data before
-        # the title search to troubleshoot.
-            
-        # Since the warning text can change by warning level, let's
-        # look for the warning pass url.  nfacommunity uses
-        # &warning= -- actually, so do other sites.  Must be an
-        # eFiction book.
-            
-        # viewstory.php?sid=1882&warning=4
-        # viewstory.php?sid=1654&ageconsent=ok&warning=5
-        #print data
-        #m = re.search(r"'viewstory.php\?sid=1882(&warning=4)'",data)
-        m = re.search(r"'viewstory.php\?sid=%s((?:&ageconsent=ok)?&warning=\d+)'"%self.story.getMetadata('storyId'),data)
-        if m != None:
-            if self.is_adult or self.getConfig("is_adult"):
-                # We tried the default and still got a warning, so
-                # let's pull the warning number from the 'continue'
-                # link and reload data.
-                addurl = m.group(1)
-                # correct stupid & error in url.
-                addurl = addurl.replace("&","&")
-                url = self.url+'&index=1'+addurl
-                logger.debug("URL 2nd try: "+url)
-
-                try:
-                    data = self._fetchUrl(url)
-                except urllib2.HTTPError, e:
-                    if e.code == 404:
-                        raise exceptions.StoryDoesNotExist(self.url)
-                    else:
-                        raise e    
-            else:
-                raise exceptions.AdultCheckRequired(self.url)
-            
-        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
-        # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
-        # print data
-
-        # Now go hunting for all the meta data and the chapter list.
-        
-        ## Title
-        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',stripHTML(a))
-        
-        # Find authorid and URL from... author url.
-        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
-        self.story.setMetadata('authorId',a['href'].split('=')[1])
-        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
-        self.story.setMetadata('author',a.string)
-
-        # Find the chapters:
-        for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
-            # just in case there's tags, like <i> in chapter titles.
-            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']+addurl))
-
-        self.story.setMetadata('numChapters',len(self.chapterUrls))
-
-
-        # Not good enough-- content can contain a ('), which ends the content prematurely.
-        # metadesc = soup.find('meta',{'name':'description'})
-        # print("removeAllEntities(metadesc['content']):\n%s\n"%removeAllEntities(metadesc['content']))
-        start='<span class="label">Summary: </span>'
-        end='<span class="label">Rated:</span>'
-        summarydata = data[data.index(start)+len(start):data.index(end)]
-        #print("summarydata:\n%s\n"%summarydata)
-        self.setDescription(url,bs.BeautifulSoup(summarydata))
-        
-        # eFiction sites don't help us out a lot with their meta data
-        # formating, so it's a little ugly.
-
-        # utility method
-        def defaultGetattr(d,k):
-            try:
-                return d[k]
-            except:
-                return ""
-
-        # <span class="label">Rated:</span> NC-17<br /> etc
-        labels = soup.findAll('span',{'class':'label'})
-        for labelspan in labels:
-            value = labelspan.nextSibling
-            label = labelspan.string
-
-            # not good enough--poorly formated summary html will break it.
-            # if 'Summary' in label:
-            #     ## Everything until the next span class='label'
-            #     svalue = ""
-            #     while not defaultGetattr(value,'class') == 'label':
-            #         svalue += str(value)
-            #         value = value.nextSibling
-            #     self.setDescription(url,svalue)
-                #self.story.setMetadata('description',stripHTML(svalue))
-
-            if 'Rated' in label:
-                self.story.setMetadata('rating', value)
-
-            if 'Word count' in label:
-                self.story.setMetadata('numWords', value)
-
-            if 'Categories' in label:
-                cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
-                catstext = [cat.string for cat in cats]
-                for cat in catstext:
-                    self.story.addToList('category',cat.string)
-
-            if 'Characters' in label:
-                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
-                charstext = [char.string for char in chars]
-                for char in charstext:
-                    self.story.addToList('characters',char.string)
-
-            ## Not all sites use Genre, but there's no harm to
-            ## leaving it in.  Check to make sure the type_id number
-            ## is correct, though--it's site specific.
-            if 'Genre' in label:
-                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')) # XXX
-                genrestext = [genre.string for genre in genres]
-                self.genre = ', '.join(genrestext)
-                for genre in genrestext:
-                    self.story.addToList('genre',genre.string)
-
-            ## Not all sites use Warnings, but there's no harm to
-            ## leaving it in.  Check to make sure the type_id number
-            ## is correct, though--it's site specific.
-            if 'Warnings' in label:
-                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')) # XXX
-                warningstext = [warning.string for warning in warnings]
-                self.warning = ', '.join(warningstext)
-                for warning in warningstext:
-                    self.story.addToList('warnings',warning.string)
-
-            if 'Completed' in label:
-                if 'Yes' in value:
-                    self.story.setMetadata('status', 'Completed')
-                else:
-                    self.story.setMetadata('status', 'In-Progress')
-
-            if 'Published' in label:
-                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
-            if 'Updated' in label:
-                # there's a stray [ at the end.
-                #value = value[0:-1]
-                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
-
-        try:
-            # Find Series name from series URL.
-            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
-            series_name = a.string
-            series_url = 'http://'+self.host+'/'+a['href']
-
-            # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
-            storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+'))
-            i=1
-            for a in storyas:
-                # skip 'report this' and 'TOC' links
-                if 'contact.php' not in a['href'] and 'index' not in a['href']:
-                    if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
-                        self.setSeries(series_name, i)
-                        self.story.setMetadata('seriesUrl',series_url)
-                        break
-                    i+=1
-            
-        except:
-            # I find it hard to care if the series parsing fails
-            pass
-            
-    # grab the text for an individual chapter.
-    def getChapterText(self, url):
-
-        logger.debug('Getting chapter text from: %s' % url)
-
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
-        div = soup.find('div', {'id' : 'story'})
-
-        if None == div:
-            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
-        return self.utf8FromSoup(url,div)
+def getClass():
+    return MuggleNetComAdapter

fanficfare/adapters/adapter_naiceanilmenet.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2015 Fanficdownloader team, 2015 FanFicFare team
+# Copyright 2016 FanFicFare team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -16,23 +16,21 @@
 #
 
 # Software: eFiction
-import re
 from base_efiction_adapter import BaseEfictionAdapter
 
-class DeviantHeartsAdapter(BaseEfictionAdapter):
+class NaiceaNilmeNetAdapter(BaseEfictionAdapter):
 
     @staticmethod
     def getSiteDomain():
-        return 'devianthearts.com'
+        return 'www.naiceanilme.net'
 
     @classmethod
     def getSiteAbbrev(self):
-        return 'devhrt'
-        
+        return 'nnnet'
+
     @classmethod
     def getDateFormat(self):
-        return "%m/%d/%y" 
-                           
+        return "%m/%d/%y"
+
 def getClass():
-    return DeviantHeartsAdapter
-    
+    return NaiceaNilmeNetAdapter

fanficfare/adapters/adapter_nationallibrarynet.py

@@ -22,7 +22,7 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -46,32 +46,32 @@ class NationalLibraryNetAdapter(BaseSiteAdapter):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only storyid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
+
+
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?storyid='+self.story.getMetadata('storyId'))
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','ntlb')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%m-%d-%y"
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         return 'national-library.net'
-        
+
     @classmethod
     def getAcceptDomains(cls):
         return ['www.national-library.net','national-library.net']
 
     @classmethod
     def getSiteExampleURLs(cls):
-        # ONLY the stories archived on or after June 17, 2006 and that are hosted on the website: 
+        # ONLY the stories archived on or after June 17, 2006 and that are hosted on the website:
         return "http://"+cls.getSiteDomain()+"/viewstory.php?storyid=1234"
 
     def getSiteURLPattern(self):
@@ -93,20 +93,20 @@ class NationalLibraryNetAdapter(BaseSiteAdapter):
                 raise exceptions.StoryDoesNotExist(self.url)
             else:
                 raise e
-            
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
         ## Title
         a = soup.find('h1')
         self.story.setMetadata('title',stripHTML(a))
-        
+
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"authorresults.php\?author=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
@@ -130,7 +130,7 @@ class NationalLibraryNetAdapter(BaseSiteAdapter):
         for x in range(2,len(labels)):
             value = labels[x].nextSibling
             label = labels[x].string
-            
+
             if 'Summary' in label:
                 self.setDescription(url,value)
                 #self.story.setMetadata('description',stripHTML(svalue))
@@ -152,43 +152,42 @@ class NationalLibraryNetAdapter(BaseSiteAdapter):
             if 'Character' in label:
                 for char in value.string.split(', '):
                     self.story.addToList('characters',char)
-                    
+
             if 'Pairing' in label:
                 for char in value.string.split(', '):
                     self.story.addToList('ships',char)
-                    
+
             if 'Warnings' in label:
                 for warning in value.string.split(', '):
                     self.story.addToList('warnings',warning)
 
             if 'Published' in label:
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
+
             if 'Series' in label:
                 self.setSeries(stripHTML(value.nextSibling), value.nextSibling.nextSibling.string[2:])
                 self.story.setMetadata('seriesUrl','http://'+self.host+'/'+value.nextSibling['href'])
-                
-        asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
+
+        asoup = self.make_soup(self._fetchUrl(self.story.getMetadata('authorUrl')))
         story=asoup.find('a', href=re.compile(r'viewstory.php\?storyid='+self.story.getMetadata('storyId')))
-            
+
         a=story.findNext(text=re.compile('Genre')).parent.nextSibling.string.split(', ')
         for genre in a:
             self.story.setMetadata('genre', genre)
-        
+
         a=story.findNext(text=re.compile('Archived'))
         self.story.setMetadata('datePublished', makeDate(stripHTML(a.parent.nextSibling), self.dateformat))
         self.story.setMetadata('dateUpdated', makeDate(stripHTML(a.parent.nextSibling), self.dateformat))
-            
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
+        soup = self.make_soup(self._fetchUrl(url))
+
         div = soup.find('div')
-        
+
         # bit messy since higly inconsistent
         for p in soup.findAll('p', {'align' : 'center'}):
             p.extract()
@@ -209,5 +208,5 @@ class NationalLibraryNetAdapter(BaseSiteAdapter):
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_ncisficcom.py

@@ -22,7 +22,7 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -46,25 +46,25 @@ class NCISFicComAdapter(BaseSiteAdapter):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only storyid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
+
+
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?storyid='+self.story.getMetadata('storyId'))
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','ncisf')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%m-%d-%y"
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         return 'ncisfic.com'
-        
+
     @classmethod
     def getAcceptDomains(cls):
         return ['www.ncisfic.com','ncisfic.com']
@@ -92,20 +92,20 @@ class NCISFicComAdapter(BaseSiteAdapter):
                 raise exceptions.StoryDoesNotExist(self.url)
             else:
                 raise e
-            
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
         ## Title
         a = soup.find('h1')
         self.story.setMetadata('title',stripHTML(a))
-        
+
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"authorresults.php\?author=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
@@ -129,7 +129,7 @@ class NCISFicComAdapter(BaseSiteAdapter):
         for x in range(2,len(labels)):
             value = labels[x].nextSibling
             label = labels[x].string
-            
+
             if 'Summary' in label:
                 self.setDescription(url,value)
                 #self.story.setMetadata('description',stripHTML(svalue))
@@ -151,50 +151,49 @@ class NCISFicComAdapter(BaseSiteAdapter):
             if 'Character' in label:
                 for char in value.string.split(', '):
                     self.story.addToList('characters',char)
-                    
+
             if 'Pairing' in label:
                 for char in value.string.split(', '):
                     self.story.addToList('ships',char)
-                    
+
             if 'Warnings' in label:
                 for warning in value.string.split(', '):
                     self.story.addToList('warnings',warning)
 
             if 'Published' in label:
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
+
             if 'Series' in label:
                 if "No Series" not in value.nextSibling.string:
                     self.setSeries(stripHTML(value.nextSibling), value.nextSibling.nextSibling.string[2:])
                     self.story.setMetadata('seriesUrl','http://'+self.host+'/'+value.nextSibling['href'])
-                
-        asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
+
+        asoup = self.make_soup(self._fetchUrl(self.story.getMetadata('authorUrl')))
         story=asoup.find('a', href=re.compile(r'viewstory.php\?storyid='+self.story.getMetadata('storyId')))
-        
+
         a=story.findNext('font')
         if 'Complete' in a.string:
             self.story.setMetadata('status', 'Completed')
         else:
             self.story.setMetadata('status', 'In-Progress')
-            
+
         a=story.findNext(text=re.compile('Genre')).parent.nextSibling.string.split(', ')
         for genre in a:
             self.story.setMetadata('genre', genre)
-        
+
         a=story.findNext(text=re.compile('Archived'))
         self.story.setMetadata('datePublished', makeDate(stripHTML(a.parent.nextSibling), self.dateformat))
         self.story.setMetadata('dateUpdated', makeDate(stripHTML(a.parent.nextSibling), self.dateformat))
-            
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
+        soup = self.make_soup(self._fetchUrl(url))
+
         div = soup.find('div')
-        
+
         # bit messy since higly inconsistent
         for p in soup.findAll('p', {'align' : 'center'}):
             p.extract()
@@ -215,5 +214,5 @@ class NCISFicComAdapter(BaseSiteAdapter):
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_ncisfictionnet.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2012 Fanficdownloader team, 2015 FanFicFare team
+# Copyright 2012 Fanficdownloader team, 2016 FanFicFare team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -15,196 +15,22 @@
 # limitations under the License.
 #
 
-import time
-import logging
-logger = logging.getLogger(__name__)
-import re
-import urllib2
+# Software: eFiction
+from base_efiction_adapter import BaseEfictionAdapter
 
-from .. import BeautifulSoup as bs
-from ..htmlcleanup import stripHTML
-from .. import exceptions as exceptions
+class NCISFictionNetAdapter(BaseEfictionAdapter):
 
-from base_adapter import BaseSiteAdapter,  makeDate
+    @staticmethod
+    def getSiteDomain():
+        return 'ncisfiction.net'
+
+    @classmethod
+    def getSiteAbbrev(self):
+        return 'ncisfn'
+
+    @classmethod
+    def getDateFormat(self):
+        return "%m/%d/%Y"
 
 def getClass():
     return NCISFictionNetAdapter
-
-# Class name has to be unique.  Our convention is camel case the
-# sitename with Adapter at the end.  www is skipped.
-class NCISFictionNetAdapter(BaseSiteAdapter):
-
-    def __init__(self, config, url):
-        BaseSiteAdapter.__init__(self, config, url)
-
-        self.decode = ["iso-8859-1",
-                       "Windows-1252"] # 1252 is a superset of iso-8859-1.
-                               # Most sites that claim to be
-                               # iso-8859-1 (and some that claim to be
-                               # utf8) are really windows-1252.
-        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
-        self.password = ""
-        self.is_adult=False
-        
-        # get storyId from url--url validation guarantees query is only sid=1234
-        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
-        # normalized story URL.
-        self._setURL("http://"+self.getSiteDomain()\
-                         +"/chapters.php?stid="+self.story.getMetadata('storyId'))
-        
-        # Each adapter needs to have a unique site abbreviation.
-        self.story.setMetadata('siteabbrev','ncisfn')
-
-        # The date format will vary from site to site.
-        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = "%d/%m/%Y"
-            
-    @staticmethod # must be @staticmethod, don't remove it.
-    def getSiteDomain():
-        # The site domain.  Does have www here, if it uses it.
-        return 'www.ncisfiction.net'
-
-    ## Changed from www.ncisfiction.com to www.ncisfiction.net Oct
-    ## 2012 due to the ncisfiction.com domain expiring.  Still accept
-    ## .com domains for existing updates, etc.
-    
-    @classmethod
-    def getAcceptDomains(cls):
-        return ['www.ncisfiction.net','www.ncisfiction.com']
-
-    @classmethod
-    def getSiteExampleURLs(cls):
-        return "http://"+cls.getSiteDomain()+"/story.php?stid=01234 http://"+cls.getSiteDomain()+"/chapters.php?stid=1234"
-
-    def getSiteURLPattern(self):
-        return r'http://www\.ncisfiction\.(net|com)/(chapters|story)?.php\?stid=\d+'
-       
-
-    ## Getting the chapter list and the meta data, plus 'is adult' checking.
-    def extractChapterUrlsAndMetadata(self):
-
-        # index=1 makes sure we see the story chapter index.  Some
-        # sites skip that for one-chapter stories.
-        url = self.url
-        logger.debug("URL: "+url)
-
-        try:
-            data = self._fetchUrl(url)
-        except urllib2.HTTPError, e:
-            if e.code == 404:
-                raise exceptions.StoryDoesNotExist(self.url)
-            else:
-                raise e
-
-            
-        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
-        # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulStoneSoup(data)
-        # print data
-
-        # Now go hunting for all the meta data and the chapter list.
-        
-        ## Title and author
-        a = soup.find('div', {'class' : 'main_title'})
-        
-        aut = a.find('a')
-        self.story.setMetadata('authorId',aut['href'].split('=')[1])
-        self.story.setMetadata('authorUrl','http://'+self.host+'/'+aut['href'])
-        self.story.setMetadata('author',aut.string)
-        
-        aut.extract()
-        self.story.setMetadata('title',stripHTML(a)[:len(stripHTML(a))-2])
-
-        # Find the chapters:
-        i=0
-        chapters=soup.findAll('table', {'class' : 'story_table'})
-        for chapter in chapters:
-            ch=chapter.find('a')
-            # just in case there's tags, like <i> in chapter titles.
-            self.chapterUrls.append((stripHTML(ch),'http://'+self.host+'/'+ch['href']))
-            if i == 0:
-                self.story.setMetadata('datePublished', makeDate(stripHTML(chapter.find('td')).split('Added: ')[1], self.dateformat))
-            if i == len(chapters)-1:
-                self.story.setMetadata('dateUpdated', makeDate(stripHTML(chapter.find('td')).split('Added: ')[1], self.dateformat))
-            i=i+1
-
-        self.story.setMetadata('numChapters',len(self.chapterUrls))
-
-        # eFiction sites don't help us out a lot with their meta data
-        # formating, so it's a little ugly.
-
-        info = soup.find('table', {'class' : 'story_info'})
-        
-        # no convenient way to calculate word count as it is logged differently for stories with and without series
-        
-        labels = info.findAll('tr')
-        for tr in labels:
-            value = tr.find('td')
-            label = tr.find('th').string
-
-            if 'Summary' in label:
-                self.setDescription(url,value)
-
-            if 'Rating' in label:
-                self.story.setMetadata('rating', value.string)
-
-            if 'Category' in label:
-                cats = value.findAll('a')
-                for cat in cats:
-                    self.story.addToList('category',cat.string)
-
-            if 'Characters' in label:
-                chars = value.findAll('a')
-                for char in chars:
-                    self.story.addToList('characters',char.string)
-
-            if 'Pairing' in label:
-                ships = value.findAll('a')
-                for ship in ships:
-                    self.story.addToList('ships',ship.string)
-
-            if 'Genre' in label:
-                genres = value.findAll('a')
-                for genre in genres:
-                    self.story.addToList('genre',genre.string)
-
-            if 'Warnings' in label:
-                warnings = value.findAll('a')
-                for warning in warnings:
-                    self.story.addToList('warnings',warning.string)
-
-            if 'Status' in label:
-                if 'not completed' in value.text:
-                    self.story.setMetadata('status', 'In-Progress')
-                else:
-                    self.story.setMetadata('status', 'Completed')
-                    
-        try:
-            # Find Series name from series URL.
-            a = soup.find('div',{'class' : 'sub_header'})
-            series_name = a.find('a').string
-            i = a.text.split('#')[1]
-            self.setSeries(series_name, i)
-            self.story.setMetadata('seriesUrl','http://'+self.host+'/'+a.find('a')['href'])
-        except:
-            # I find it hard to care if the series parsing fails
-            pass
-            
-    # grab the text for an individual chapter.
-    def getChapterText(self, url):
-
-        logger.debug('Getting chapter text from: %s' % url)
-
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
-        div = soup.find('div', {'class' : 'story_text'})
-
-        if None == div:
-            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
-        return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_nfacommunitycom.py

@@ -22,7 +22,7 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -50,22 +50,22 @@ class NfaCommunityComAdapter(BaseSiteAdapter): # XXX
                                # iso-8859-1 (and some that claim to be
                                # utf8) are really windows-1252.
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
+
+
         # normalized story URL.
         # XXX Most sites don't have the /fanfic part.  Replace all to remove it usually.
         self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','nfa') # XXX
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%m/%d/%Y" # XXX
-            
+
     @classmethod
     def getAcceptDomains(cls):
         return ['www.nfacommunity.com','nfacommunity.com']
@@ -115,12 +115,12 @@ class NfaCommunityComAdapter(BaseSiteAdapter): # XXX
         # The actual text that is used to announce you need to be an
         # adult varies from site to site.  Again, print data before
         # the title search to troubleshoot.
-            
+
         # Since the warning text can change by warning level, let's
         # look for the warning pass url.  nfacommunity uses
         # &warning= -- actually, so do other sites.  Must be an
         # eFiction book.
-            
+
         # viewstory.php?sid=1882&warning=4
         # viewstory.php?sid=1654&ageconsent=ok&warning=5
         #print data
@@ -143,22 +143,22 @@ class NfaCommunityComAdapter(BaseSiteAdapter): # XXX
                     if e.code == 404:
                         raise exceptions.StoryDoesNotExist(self.url)
                     else:
-                        raise e    
+                        raise e
             else:
                 raise exceptions.AdultCheckRequired(self.url)
-            
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',stripHTML(a))
-        
+
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
@@ -193,8 +193,8 @@ class NfaCommunityComAdapter(BaseSiteAdapter): # XXX
             if 'Summary' in label:
                 ## Everything until the next span class='label'
                 svalue = ""
-                while not defaultGetattr(value,'class') == 'label':
-                    svalue += str(value)
+                while 'label' not in defaultGetattr(value,'class'):
+                    svalue += unicode(value)
                     value = value.nextSibling
                 self.setDescription(url,svalue)
                 #self.story.setMetadata('description',stripHTML(svalue))
@@ -245,7 +245,7 @@ class NfaCommunityComAdapter(BaseSiteAdapter): # XXX
 
             if 'Published' in label:
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
+
             if 'Updated' in label:
                 # there's a stray [ at the end.
                 #value = value[0:-1]
@@ -258,7 +258,7 @@ class NfaCommunityComAdapter(BaseSiteAdapter): # XXX
             series_url = 'http://'+self.host+'/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            seriessoup = self.make_soup(self._fetchUrl(series_url))
             storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+'))
             i=1
             for a in storyas:
@@ -269,22 +269,21 @@ class NfaCommunityComAdapter(BaseSiteAdapter): # XXX
                         self.story.setMetadata('seriesUrl',series_url)
                         break
                     i+=1
-            
+
         except:
             # I find it hard to care if the series parsing fails
             pass
-            
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
+        soup = self.make_soup(self._fetchUrl(url))
+
         div = soup.find('div', {'id' : 'story'})
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_nhamagicalworldsus.py

@@ -16,222 +16,24 @@
 #
 
 # Software: eFiction
-import time
-import logging
-logger = logging.getLogger(__name__)
-import re
-import urllib2
+from base_efiction_adapter import BaseEfictionAdapter
 
-from .. import BeautifulSoup as bs
-from ..htmlcleanup import stripHTML
-from .. import exceptions as exceptions
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class NHAMagicalWorldsUsAdapter(BaseEfictionAdapter):
 
-from base_adapter import BaseSiteAdapter,  makeDate
+    @staticmethod
+    def getSiteDomain():
+        return 'nha.magical-worlds.us'
+
+    @classmethod
+    def getSiteAbbrev(self):
+        return 'nha'
+
+    @classmethod
+    def getDateFormat(self):
+        return "%d/%m/%y"
 
 def getClass():
     return NHAMagicalWorldsUsAdapter
 
-# Class name has to be unique.  Our convention is camel case the
-# sitename with Adapter at the end.  www is skipped.
-class NHAMagicalWorldsUsAdapter(BaseSiteAdapter):
-
-    def __init__(self, config, url):
-        BaseSiteAdapter.__init__(self, config, url)
-
-        self.decode = ["Windows-1252",
-                       "utf8"] # 1252 is a superset of iso-8859-1.
-                               # Most sites that claim to be
-                               # iso-8859-1 (and some that claim to be
-                               # utf8) are really windows-1252.
-        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
-        self.password = ""
-        self.is_adult=False
-        
-        # get storyId from url--url validation guarantees query is only sid=1234
-        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-		
-        
-        # normalized story URL.
-        self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
-        # Each adapter needs to have a unique site abbreviation.
-        self.story.setMetadata('siteabbrev','nha')
-
-        # The date format will vary from site to site.
-        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = " %d/%m/%y"
-            
-    @staticmethod # must be @staticmethod, don't remove it.
-    def getSiteDomain():
-        # The site domain.  Does have www here, if it uses it.
-        return 'nha.magical-worlds.us'
-
-    @classmethod
-    def getSiteExampleURLs(cls):
-        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
-
-    def getSiteURLPattern(self):
-        return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
-
-    ## Getting the chapter list and the meta data, plus 'is adult' checking.
-    def extractChapterUrlsAndMetadata(self):
-        url = self.url
-        logger.debug("URL: "+url)
-
-        try:
-            data = self._fetchUrl(url)
-        except urllib2.HTTPError, e:
-            if e.code == 404:
-                raise exceptions.StoryDoesNotExist(self.url)
-            else:
-                raise e
-            
-        m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
-        if m != None:
-            if self.is_adult or self.getConfig("is_adult"):
-                # We tried the default and still got a warning, so
-                # let's pull the warning number from the 'continue'
-                # link and reload data.
-                addurl = m.group(1)
-                # correct stupid & error in url.
-                addurl = addurl.replace("&","&")
-                url = self.url+'&index=1'+addurl
-                logger.debug("URL 2nd try: "+url)
-
-                try:
-                    data = self._fetchUrl(url)
-                except urllib2.HTTPError, e:
-                    if e.code == 404:
-                        raise exceptions.StoryDoesNotExist(self.url)
-                    else:
-                        raise e    
-            else:
-                raise exceptions.AdultCheckRequired(self.url)
-            
-        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
-        # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
-        # print data
-
-        # Now go hunting for all the meta data and the chapter list.
-            
-        # Find authorid and URL from... author url.
-        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
-        self.story.setMetadata('authorId',a['href'].split('=')[1])
-        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
-        self.story.setMetadata('author',a.string)
-        asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
-		
-        try:
-            # in case link points somewhere other than the first chapter
-            a = soup.findAll('option')[1]['value']
-            self.story.setMetadata('storyId',a.split('=',)[1])
-            url = 'http://'+self.host+'/'+a
-            soup = bs.BeautifulSoup(self._fetchUrl(url))
-        except:
-            pass
-		
-        for info in asoup.findAll('table', {'width' : '100%', 'bordercolor' : re.compile(r'#')}):
-            a = info.find('a')
-            if 'viewstory.php?sid='+self.story.getMetadata('storyId') == a['href'] or \
-                    ('viewstory.php?sid='+self.story.getMetadata('storyId')+'&') in a['href']:
-                self.story.setMetadata('title',stripHTML(a))
-                break
-		
-
-        # Find the chapters:
-        chapters=soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+'&chapter=\d+$'))
-        if len(chapters) == 0:
-            self.chapterUrls.append((self.story.getMetadata('title'),url))
-        else:
-            for chapter in chapters:
-                # just in case there's tags, like <i> in chapter titles.
-                self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']))
-
-        self.story.setMetadata('numChapters',len(self.chapterUrls))
-
-        # eFiction sites don't help us out a lot with their meta data
-        # formating, so it's a little ugly.
-
-        # utility method
-        def defaultGetattr(d):
-            try:
-                return d.name
-            except:
-                return ""
-				
-        cats = info.findAll('a',href=re.compile('categories.php'))
-        for cat in cats:
-            self.story.addToList('category',cat.string)
-					
-        a = info.find('a', href=re.compile(r'viewuser.php'))
-        val = a.nextSibling
-        svalue = ""
-        while not defaultGetattr(val) == 'br':
-            val = val.nextSibling
-        val = val.nextSibling
-        while not defaultGetattr(val) == 'br':
-            svalue += unicode(val)
-            val = val.nextSibling
-        self.setDescription(url,svalue)
-        
-        #does not provide convenient way to get word count
-        labels = info.findAll('i')
-        for labelspan in labels:
-            value = labelspan.nextSibling
-            label = stripHTML(labelspan)
-
-            if 'Rating' in label:
-                self.story.setMetadata('rating', value.split(' -')[0])
-
-            if 'Genres' in label:
-                genres = value.string.split(', ')
-                for genre in genres:
-                    if 'None' not in genre:
-                        self.story.addToList('genre',genre.split(' -')[0])
-            
-            if 'Characters' in label:
-                chars = value.string.split(', ')
-                for char in chars:
-                    if 'None' not in char:
-                        self.story.addToList('characters',char.split(' -')[0])
-
-            if 'Warnings' in label:
-                warnings = value.string.split(', ')
-                for warning in warnings:
-                    if 'None' not in warning:
-                        self.story.addToList('warnings',warning.split(' -')[0])
-
-            if 'Completed' in label:
-                if 'Yes' in value:
-                    self.story.setMetadata('status', 'Completed')
-                else:
-                    self.story.setMetadata('status', 'In-Progress')
-
-            if 'Published' in label:
-                self.story.setMetadata('datePublished', makeDate(value.split(' -')[0], self.dateformat))
-            
-            if 'Updated' in label:
-                # there's a stray [ at the end.
-                #value = value[0:-1]
-                self.story.setMetadata('dateUpdated', makeDate(value.split(' -')[0], self.dateformat))
-
-            
-    # grab the text for an individual chapter.
-    def getChapterText(self, url):
-
-        logger.debug('Getting chapter text from: %s' % url)
-		
-        data = self._fetchUrl(url)
-
-        soup = bs.BeautifulSoup(data, selfClosingTags=('br','hr','span','center')) # some chapters seem to be hanging up on those tags, so it is safer to close them
-        
-        story = soup.find('div', {"id" : "story"})
-
-        if None == story:
-            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
-        return self.utf8FromSoup(url,story)

fanficfare/adapters/adapter_nickandgregnet.py

@@ -1,177 +0,0 @@
-# -*- coding: utf-8 -*-
-
-# Copyright 2013 Fanficdownloader team, 2015 FanFicFare team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-#
-
-# Software: eFiction
-import time
-import logging
-logger = logging.getLogger(__name__)
-import re
-import urllib2
-
-from .. import BeautifulSoup as bs
-from ..htmlcleanup import stripHTML
-from .. import exceptions as exceptions
-
-from base_adapter import BaseSiteAdapter,  makeDate
-
-def getClass():
-    return NickAndGregNetAdapter
-
-# Class name has to be unique.  Our convention is camel case the
-# sitename with Adapter at the end.  www is skipped.
-class NickAndGregNetAdapter(BaseSiteAdapter):
-
-    def __init__(self, config, url):
-        BaseSiteAdapter.__init__(self, config, url)
-
-        self.decode = ["Windows-1252",
-                       "utf8"] # 1252 is a superset of iso-8859-1.
-                               # Most sites that claim to be
-                               # iso-8859-1 (and some that claim to be
-                               # utf8) are really windows-1252.
-        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
-        self.password = ""
-        self.is_adult=False
-        
-        # get storyId from url--url validation guarantees query is only sid=1234
-        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
-        # normalized story URL.
-        # XXX Most sites don't have the /fanfic part.  Replace all to remove it usually.
-        self._setURL('http://' + self.getSiteDomain() + '/desert_archive/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
-        # Each adapter needs to have a unique site abbreviation.
-        self.story.setMetadata('siteabbrev','nag')
-
-        # The date format will vary from site to site.
-        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = "%Y/%m/%d"
-            
-    @staticmethod # must be @staticmethod, don't remove it.
-    def getSiteDomain():
-        # The site domain.  Does have www here, if it uses it.
-        return 'www.nickandgreg.net'
-
-    @classmethod
-    def getSiteExampleURLs(cls):
-        return "http://"+cls.getSiteDomain()+"/desert_archive/viewstory.php?sid=1234"
-
-    def getSiteURLPattern(self):
-        return re.escape("http://"+self.getSiteDomain()+"/desert_archive/viewstory.php?sid=")+r"\d+$"
-    
-
-    ## Getting the chapter list and the meta data, plus 'is adult' checking.
-    def extractChapterUrlsAndMetadata(self):
-
-        # index=1 makes sure we see the story chapter index.  Some
-        # sites skip that for one-chapter stories.
-        url = self.url+'&i=1'
-        logger.debug("URL: "+url)
-
-        try:
-            data = self._fetchUrl(url)
-        except urllib2.HTTPError, e:
-            if e.code == 404:
-                raise exceptions.StoryDoesNotExist(self.url)
-            else:
-                raise e
-            
-        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
-        # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
-        # print data
-
-        # Now go hunting for all the meta data and the chapter list.
-
-        ## Title
-        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',stripHTML(a))
-        
-        # Find authorid and URL from... author url.
-        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
-        self.story.setMetadata('authorId',a['href'].split('=')[1])
-        self.story.setMetadata('authorUrl','http://'+self.host+'/desert_archive/'+a['href'])
-        self.story.setMetadata('author',a.string)
-
-        # Find the chapters:
-        chapters = soup.find('select')
-        for chapter in chapters.findAll('option'):
-            if chapter.text != 'Story Index' and chapter.text != 'Chapters':
-                self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/desert_archive/'+chapter['value']))
-
-        self.story.setMetadata('numChapters',len(self.chapterUrls))
-        
-        asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
-        
-        for div in asoup.findAll('td', {'class' : 'tblborder6'}):
-            a = div.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-            if a != None:
-                break
-        
-        self.setDescription(url,div.find('br').nextSibling)
-        
-        a=div.text.split('Rating:')
-        if len(a) == 2: self.story.setMetadata('rating', a[1].split(' -')[0])
-        
-        a=div.text.split('Characters:')
-        if len(a) == 2: 
-        	for char in a[1].split(' -')[0].split(', '):
-        	    self.story.addToList('characters',char)
-        	    
-        a=div.text.split('Genres:')
-        if len(a) == 2: 
-        	for genre in a[1].split(' -')[0].split(', '):
-        	    self.story.addToList('genre',genre)
-        	    
-        a=div.text.split('Warnings:')
-        if len(a) == 2: 
-        	for warn in a[1].split(' -')[0].split(', '):
-        	    if 'none' not in warn:
-        	        self.story.addToList('warnings',warn)
-        	    
-        a=div.text.split('Completed:')
-        if len(a) ==2:
-            if 'Yes' in a[1]:
-                self.story.setMetadata('status', 'Completed')
-            else:
-                self.story.setMetadata('status', 'In-Progress')
-                
-        a=div.text.split('Published:')
-        if len(a) == 2: self.story.setMetadata('datePublished', makeDate(stripHTML(a[1].split(' -')[0]), self.dateformat))
-        
-        a=div.text.split('Updated:')
-        if len(a) == 2: self.story.setMetadata('dateUpdated', makeDate(stripHTML(a[1].split(' -')[0]), self.dateformat))
-
-            
-    # grab the text for an individual chapter.
-    def getChapterText(self, url):
-
-        logger.debug('Getting chapter text from: %s' % url)
-
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-
-        # wrap a div around it.
-        divsoup = bs.BeautifulStoneSoup('<div class="story"></div>',
-                                        selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        div = divsoup.find('div')
-        div.append(soup.find('table', {'class' : 'tblborder6'}))
-
-        return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_ninelivesarchivecom.py

@@ -0,0 +1,55 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2015 Fanficdownloader team, 2015 FanFicFare team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+# Software: eFiction
+import re
+from base_efiction_adapter import BaseEfictionAdapter
+
+class NineLivesAdapter(BaseEfictionAdapter):
+
+    @staticmethod
+    def getSiteDomain():
+        return 'ninelivesarchive.com'
+
+    @classmethod
+    def getAcceptDomains(cls):
+        return ['ninelivesarchive.com','ninelives.dark-solace.org']
+
+    @classmethod
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
+
+    @classmethod
+    def getSiteURLPattern(self):
+        return "http://("+self.getSiteDomain()+"|ninelives.dark-solace.org)"+re.escape("/viewstory.php?sid=")+r"(?P<storyId>\d+)$"
+
+    @classmethod
+    def getConfigSections(cls):
+        "Only needs to be overriden if has additional ini sections."
+        return ['base_efiction','ninelives.dark-solace.org',cls.getSiteDomain()]
+
+    @classmethod
+    def getSiteAbbrev(self):
+        return '9lvs'
+
+    @classmethod
+    def getDateFormat(self):
+        return "%B %d, %Y"
+
+def getClass():
+    return NineLivesAdapter
+

fanficfare/adapters/adapter_nocturnallightnet.py

@@ -1,8 +1,10 @@
+# -*- coding: utf-8 -*-
+
 import re
 import urllib2
 import urlparse
 
-from .. import BeautifulSoup
+from bs4.element import Tag
 
 from base_adapter import BaseSiteAdapter, makeDate
 from .. import exceptions
@@ -52,7 +54,7 @@ class NocturnalLightNetAdapter(BaseSiteAdapter):
         else:
             data = self._fetchUrl(url, parameters)
 
-        return BeautifulSoup.BeautifulSoup(data)
+        return self.make_soup(data)
 
     @staticmethod
     def getSiteDomain():
@@ -111,7 +113,7 @@ class NocturnalLightNetAdapter(BaseSiteAdapter):
         for b_tag in listbox('b'):
             key = b_tag.string.strip(':')
             try:
-                value = b_tag.nextSibling.string.replace('•', '').strip(': ')
+                value = b_tag.nextSibling.string.replace('•', '').replace(u'•','').strip(': ')
             # This can happen with some fancy markup in the summary. Just
             # ignore this error and set value to None, the summary parsing
             # takes care of this
@@ -123,7 +125,7 @@ class NocturnalLightNetAdapter(BaseSiteAdapter):
                 keep_summary_html = self.getConfig('keep_summary_html')
 
                 for sibling in _yield_next_siblings(b_tag):
-                    if isinstance(sibling, BeautifulSoup.Tag):
+                    if isinstance(sibling, Tag):
                         if sibling.name == 'b' and sibling.findPreviousSibling().name == 'br':
                             break
 
@@ -149,6 +151,7 @@ class NocturnalLightNetAdapter(BaseSiteAdapter):
                 self.story.setMetadata('rating', value)
 
             elif key == 'Chapters':
+                print("cahpter value:%s"%value)
                 self.story.setMetadata('numChapters', int(value))
 
                 # Also parse reviews number which lies right after the chapters

fanficfare/adapters/adapter_occlumencysycophanthexcom.py

@@ -22,7 +22,7 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -46,22 +46,22 @@ class OcclumencySycophantHexComAdapter(BaseSiteAdapter):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
+
 		
-        
+
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','osph')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%m/%d/%Y"
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -81,7 +81,7 @@ class OcclumencySycophantHexComAdapter(BaseSiteAdapter):
             return True
         else:
             return False
-        
+
     def performLogin(self, url):
         params = {}
 
@@ -95,13 +95,13 @@ class OcclumencySycophantHexComAdapter(BaseSiteAdapter):
         params['sid'] = ''
         params['intent'] = ''
         params['submit'] = 'Submit'
-    
+
         loginUrl = 'http://' + self.getSiteDomain() + '/user.php'
         logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
                                                               params['penname']))
-    
+
         d = self._fetchUrl(loginUrl, params)
-    
+
         if "Logout" not in d : #Member Account
             logger.info("Failed to login to URL %s as %s" % (loginUrl,
                                                               params['penname']))
@@ -129,30 +129,30 @@ class OcclumencySycophantHexComAdapter(BaseSiteAdapter):
             # need to log in for this one.
             self.performLogin(url)
             data = self._fetchUrl(url)
-            
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
-        
-        
+
+
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
         self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
         self.story.setMetadata('author',a.string)
-        asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
+        asoup = self.make_soup(self._fetchUrl(self.story.getMetadata('authorUrl')))
 		
         try:
             # in case link points somewhere other than the first chapter
             a = soup.findAll('option')[1]['value']
             self.story.setMetadata('storyId',a.split('=',)[1])
             url = 'http://'+self.host+'/'+a
-            soup = bs.BeautifulSoup(self._fetchUrl(url))
+            soup = self.make_soup(self._fetchUrl(url))
         except:
             pass
 		
@@ -196,7 +196,7 @@ class OcclumencySycophantHexComAdapter(BaseSiteAdapter):
             val = val.nextSibling
         val = val.nextSibling
         while not defaultGetattr(val) == 'table':
-            svalue += str(val)
+            svalue += unicode(val)
             val = val.nextSibling
         self.setDescription(url,svalue)
 
@@ -238,13 +238,13 @@ class OcclumencySycophantHexComAdapter(BaseSiteAdapter):
 
             if 'Published' in label:
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
+
             if 'Updated' in label:
                 # there's a stray [ at the end.
                 #value = value[0:-1]
                 self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
 
-            
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
@@ -253,11 +253,11 @@ class OcclumencySycophantHexComAdapter(BaseSiteAdapter):
         data = self._fetchUrl(url)
         data = data.replace('<div align="left"', '<div align="left">')
 
-        soup = bs.BeautifulSoup(data, selfClosingTags=('br','hr'))
-        
+        soup = self.make_soup(data)
+
         story = soup.find('div', {"align" : "left"})
 
         if None == story:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,story)

fanficfare/adapters/adapter_onedirectionfanfictioncom.py

@@ -22,7 +22,7 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -46,26 +46,26 @@ class OneDirectionFanfictionComAdapter(BaseSiteAdapter):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
+
+
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','odf')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%m/%d/%Y"
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
         return 'onedirectionfanfiction.com'
-        
+
     @classmethod
     def getAcceptDomains(cls):
         return ['www.onedirectionfanfiction.com','onedirectionfanfiction.com']
@@ -77,7 +77,7 @@ class OneDirectionFanfictionComAdapter(BaseSiteAdapter):
 
     def getSiteURLPattern(self):
         return re.escape("http://")+"(www\.)?"+re.escape(self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
-        
+
         ## Login seems to be reasonably standard across eFiction sites.
     def needToLoginCheck(self, data):
         if 'Registered Users Only' in data \
@@ -86,7 +86,7 @@ class OneDirectionFanfictionComAdapter(BaseSiteAdapter):
             return True
         else:
             return False
-        
+
     def performLogin(self, url):
         params = {}
 
@@ -98,13 +98,13 @@ class OneDirectionFanfictionComAdapter(BaseSiteAdapter):
             params['password'] = self.getConfig("password")
         params['cookiecheck'] = '1'
         params['submit'] = 'Submit'
-    
+
         loginUrl = 'http://' + self.getSiteDomain() + '/user.php?action=login'
         logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
                                                               params['penname']))
-    
+
         d = self._fetchUrl(loginUrl, params)
-    
+
         if "Member Account" not in d : #Member Account
             logger.info("Failed to login to URL %s as %s" % (loginUrl,
                                                               params['penname']))
@@ -115,7 +115,7 @@ class OneDirectionFanfictionComAdapter(BaseSiteAdapter):
 
     ## Getting the chapter list and the meta data, plus 'is adult' checking.
     def extractChapterUrlsAndMetadata(self):
-    
+
         if self.is_adult or self.getConfig("is_adult"):
             # Weirdly, different sites use different warning numbers.
             # If the title search below fails, there's a good chance
@@ -137,30 +137,30 @@ class OneDirectionFanfictionComAdapter(BaseSiteAdapter):
                 raise exceptions.StoryDoesNotExist(self.url)
             else:
                 raise e
-            
+
         if self.needToLoginCheck(data):
             # need to log in for this one.
             self.performLogin(url)
             data = self._fetchUrl(url)
-        
+
         # The actual text that is used to announce you need to be an
         # adult varies from site to site.  Again, print data before
         # the title search to troubleshoot.
         if "Age Consent Required" in data:
             raise exceptions.AdultCheckRequired(self.url)
-            
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
 
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
-        
+        soup = self.make_soup(data)
+
         # Now go hunting for all the meta data and the chapter list.
-        
+
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',stripHTML(a))
-        
+
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
@@ -193,8 +193,8 @@ class OneDirectionFanfictionComAdapter(BaseSiteAdapter):
             if 'Summary' in label:
                 ## Everything until the next span class='label'
                 svalue = ""
-                while value and not defaultGetattr(value,'class') == 'label':
-                    svalue += str(value)
+                while value and 'label' not in defaultGetattr(value,'class'):
+                    svalue += unicode(value)
                     value = value.nextSibling
                 self.setDescription(url,svalue)
 
@@ -227,7 +227,7 @@ class OneDirectionFanfictionComAdapter(BaseSiteAdapter):
 
             if 'Published' in label:
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
+
             if 'Updated' in label:
                 # there's a stray [ at the end.
                 #value = value[0:-1]
@@ -240,7 +240,7 @@ class OneDirectionFanfictionComAdapter(BaseSiteAdapter):
             series_url = 'http://'+self.host+'/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            seriessoup = self.make_soup(self._fetchUrl(series_url))
             storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
             i=1
             for a in storyas:
@@ -249,22 +249,21 @@ class OneDirectionFanfictionComAdapter(BaseSiteAdapter):
                     self.story.setMetadata('seriesUrl',series_url)
                     break
                 i+=1
-            
+
         except:
             # I find it hard to care if the series parsing fails
             pass
-            
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
+        soup = self.make_soup(self._fetchUrl(url))
+
         div = soup.find('div', {'id' : 'story'})
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_phoenixsongnet.py

@@ -21,7 +21,7 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2, urllib, cookielib
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -45,21 +45,21 @@ class PhoenixSongNetAdapter(BaseSiteAdapter):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[3])
-        
-        
+
+
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/fanfiction/story/' +self.story.getMetadata('storyId')+'/')
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','phs')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%B %d %Y"
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -78,7 +78,7 @@ class PhoenixSongNetAdapter(BaseSiteAdapter):
             return True
         else:
             return False
-        
+
     def performLogin(self, url):
         params = {}
 		
@@ -90,12 +90,12 @@ class PhoenixSongNetAdapter(BaseSiteAdapter):
             params['txtpassword'] = self.getConfig("password")
         #params['remember'] = '1'
         params['login'] = 'Login'
-    
+
         loginUrl = 'http://' + self.getSiteDomain() + '/users/processlogin.php'
         logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
                                                               params['txtusername']))
         d = self._fetchUrl(loginUrl, params)
-    
+
         if 'Please login to continue.' in d : #Member Account
             logger.info("Failed to login to URL %s as %s" % (loginUrl,
                                                               params['txtusername']))
@@ -126,18 +126,18 @@ class PhoenixSongNetAdapter(BaseSiteAdapter):
             # need to log in for this one.
             self.performLogin(url)
             data = self._fetchUrl(url)
-            
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
         ## Title
         b = soup.find('div', {'id' : 'nav25'})
         a = b.find('a', href=re.compile(r'fanfiction/story/'+self.story.getMetadata('storyId')+"/$"))
         self.story.setMetadata('title',stripHTML(a))
-        
+
         # Find authorid and URL from... author url.  /fanfiction/stories.php?psid=125
         a = b.find('a', href=re.compile(r"/fanfiction/stories.php\?psid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
@@ -160,14 +160,14 @@ class PhoenixSongNetAdapter(BaseSiteAdapter):
                 self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+chapter['value']))
                 if i == 0:
                     self.story.setMetadata('storyId',chapter['value'].split('/')[3])
-                    head = bs.BeautifulSoup(self._fetchUrl('http://'+self.host+chapter['value'])).findAll('b')
+                    head = self.make_soup(self._fetchUrl('http://'+self.host+chapter['value'])).findAll('b')
                     for b in head:
                         if b.text == "Updated":
                             date = b.nextSibling.string.split(': ')[1].split(',')
                             self.story.setMetadata('datePublished', makeDate(date[0]+date[1], self.dateformat))
-                            
+
                 if  i == (len(chapters)-1):
-                    head = bs.BeautifulSoup(self._fetchUrl('http://'+self.host+chapter['value'])).findAll('b')
+                    head = self.make_soup(self._fetchUrl('http://'+self.host+chapter['value'])).findAll('b')
                     for b in head:
                         if b.text == "Updated":
                             date = b.nextSibling.string.split(': ')[1].split(',')
@@ -177,14 +177,14 @@ class PhoenixSongNetAdapter(BaseSiteAdapter):
 
         self.story.setMetadata('numChapters',len(self.chapterUrls))        	
 				
-        asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
-        
+        asoup = self.make_soup(self._fetchUrl(self.story.getMetadata('authorUrl')))
+
         info = asoup.find('a', href=re.compile(r'fanfiction/story/'+self.story.getMetadata('storyId')+"/$"))
         while info != None:
             info = info.findNext('div')
             b = info.find('b')
             val = b.nextSibling
-            
+
             if 'Rating' in b.string:
                 self.story.setMetadata('rating', val.string.split(': ')[1])
 				
@@ -200,7 +200,7 @@ class PhoenixSongNetAdapter(BaseSiteAdapter):
                 else:
                     val = 'In-Progress'
                 self.story.setMetadata('status', val)
-            
+
             if 'Summary' in b.string:
                 b.extract()
                 info.find('br').extract()
@@ -213,10 +213,9 @@ class PhoenixSongNetAdapter(BaseSiteAdapter):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        soup = self.make_soup(self._fetchUrl(url))
 
-        chapter=bs.BeautifulSoup('<div class="story"></div>')
+        chapter=self.make_soup('<div class="story"></div>')
         for p in soup.findAll('p'):
             if "This is for problems with the formatting or the layout of the chapter." in stripHTML(p):
                 break
@@ -236,5 +235,5 @@ class PhoenixSongNetAdapter(BaseSiteAdapter):
 
         if None == chapter:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,chapter)

fanficfare/adapters/adapter_pommedesangcom.py

@@ -22,7 +22,7 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -46,21 +46,21 @@ class PommeDeSangComAdapter(BaseSiteAdapter):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
+
+
         # pommedesang.com has two 'sections', shown in URL as
         # 'efiction' and 'sds' that change how things should be
         # handled.
         # http://pommedesang.com/efiction/viewstory.php?sid=1234
         # http://pommedesang.com/sds/viewstory.php?sid=1234
         self.section=self.parsedUrl.path.split('/',)[1]
-        
+
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/'+self.section+'/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','pmds')
 
@@ -70,7 +70,7 @@ class PommeDeSangComAdapter(BaseSiteAdapter):
             self.dateformat = "%b %d, %Y"
         else:
             self.dateformat = "%m/%d/%y"
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -91,7 +91,7 @@ class PommeDeSangComAdapter(BaseSiteAdapter):
             return True
         else:
             return False
-        
+
     def performLogin(self, url):
         params = {}
 
@@ -103,13 +103,13 @@ class PommeDeSangComAdapter(BaseSiteAdapter):
             params['password'] = self.getConfig("password")
         params['cookiecheck'] = '1'
         params['submit'] = 'Submit'
-    
+
         loginUrl = 'http://' + self.getSiteDomain() + '/'+self.section+'/user.php?action=login'
         logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
                                                               params['penname']))
-    
+
         d = self._fetchUrl(loginUrl, params)
-    
+
         if "Member Account" not in d : #Member Account
             logger.info("Failed to login to URL %s as %s" % (loginUrl,
                                                               params['penname']))
@@ -166,23 +166,23 @@ class PommeDeSangComAdapter(BaseSiteAdapter):
                     if e.code == 404:
                         raise exceptions.StoryDoesNotExist(self.url)
                     else:
-                        raise e    
+                        raise e
             else:
                 raise exceptions.AdultCheckRequired(self.url)
-            
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
         ## Title
         a = soup.find('a', href=re.compile('viewstory.php\?sid=\d+'))
         self.story.setMetadata('title',stripHTML(a))
-        
+
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
@@ -205,7 +205,7 @@ class PommeDeSangComAdapter(BaseSiteAdapter):
                 return d[k]
             except:
                 return ""
-                
+
 # summary, rated, word count, categories, characters, genre, warnings, completed, published, updated, seires
 
         # <span class="label">Rated:</span> NC-17<br /> etc
@@ -217,8 +217,8 @@ class PommeDeSangComAdapter(BaseSiteAdapter):
             if 'Summary' in label:
                 ## Everything until the next span class='label'
                 svalue = ""
-                while not defaultGetattr(value,'class') == 'label':
-                    svalue += str(value)
+                while 'label' not in defaultGetattr(value,'class'):
+                    svalue += unicode(value)
                     value = value.nextSibling
                 self.setDescription(url,svalue)
                 #self.story.setMetadata('description',stripHTML(svalue))
@@ -257,7 +257,7 @@ class PommeDeSangComAdapter(BaseSiteAdapter):
 
             if 'Published' in label:
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
+
             if 'Updated' in label:
                 self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
 
@@ -268,7 +268,7 @@ class PommeDeSangComAdapter(BaseSiteAdapter):
             series_url = 'http://'+self.host+'/'+self.section+'/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            seriessoup = self.make_soup(self._fetchUrl(series_url))
             # can't use ^viewstory...$ in case of higher rated stories with javascript href.
             storyas = seriessoup.findAll('a', href=re.compile('viewstory.php\?sid=\d+'))
             i=1
@@ -280,22 +280,21 @@ class PommeDeSangComAdapter(BaseSiteAdapter):
                         self.story.setMetadata('seriesUrl',series_url)
                         break
                     i+=1
-            
+
         except:
             # I find it hard to care if the series parsing fails
             pass
-            
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
+        soup = self.make_soup(self._fetchUrl(url))
+
         div = soup.find('div', {'id' : 'story'})
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_ponyfictionarchivenet.py

@@ -22,7 +22,7 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -46,10 +46,10 @@ class PonyFictionArchiveNetAdapter(BaseSiteAdapter):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
+
         # normalized story URL.
         if "explicit" in self.parsedUrl.netloc:
             self._setURL('http://explicit.' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -57,7 +57,7 @@ class PonyFictionArchiveNetAdapter(BaseSiteAdapter):
         else:
             self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
             self.dateformat = "%d %b %Y"
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','pffa')
 
@@ -65,7 +65,7 @@ class PonyFictionArchiveNetAdapter(BaseSiteAdapter):
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
         return 'ponyfictionarchive.net'
-        
+
     @classmethod
     def getAcceptDomains(cls):
         return ['www.ponyfictionarchive.net','ponyfictionarchive.net','explicit.ponyfictionarchive.net']
@@ -122,23 +122,23 @@ class PonyFictionArchiveNetAdapter(BaseSiteAdapter):
                     if e.code == 404:
                         raise exceptions.StoryDoesNotExist(self.url)
                     else:
-                        raise e    
+                        raise e
             else:
                 raise exceptions.AdultCheckRequired(self.url)
-            
+
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',stripHTML(a))
-        
+
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
@@ -165,27 +165,27 @@ class PonyFictionArchiveNetAdapter(BaseSiteAdapter):
         genres = soup.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
         for genre in genres:
             self.story.addToList('genre',genre.string)
-           
+
         warnings = soup.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=3'))
         for warning in warnings:
             self.story.addToList('warnings',warning.string)
-        
+
         status = soup.find('a',href=re.compile(r'browse.php\?type=class&type_id=2'))
         if status: # apparently this site can have stories with neither In-Progress or Complete.
             self.story.setMetadata('status',status.string)
-        
-        section = soup.findAll('span', {'class' : 'General'})[1]            
-        
+
+        section = soup.findAll('span', {'class' : 'General'})[1]
+
         self.story.setMetadata('rating', section.previousSibling.previousSibling.string)
 
         value = section.nextSibling
         svalue = ""
-        while not defaultGetattr(value,'class') == 'label':
-            svalue += str(value)
+        while 'label' not in defaultGetattr(value,'class'):
+            svalue += unicode(value)
             value = value.nextSibling
         self.setDescription(url,svalue)
-        
-        # <span class="label">Rated:</span> NC-17<br /> etc           
+
+        # <span class="label">Rated:</span> NC-17<br /> etc
         labels = soup.findAll('span',{'class':'label'})
         for labelspan in labels:
             value = labelspan.nextSibling
@@ -207,7 +207,7 @@ class PonyFictionArchiveNetAdapter(BaseSiteAdapter):
 
             if 'Published' in label:
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
+
             if 'Updated' in label:
                 self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
 
@@ -218,7 +218,7 @@ class PonyFictionArchiveNetAdapter(BaseSiteAdapter):
             series_url = 'http://'+self.host+'/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            seriessoup = self.make_soup(self._fetchUrl(series_url))
             # can't use ^viewstory...$ in case of higher rated stories with javascript href.
             storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+'))
             i=1
@@ -230,21 +230,21 @@ class PonyFictionArchiveNetAdapter(BaseSiteAdapter):
                         self.story.setMetadata('seriesUrl',series_url)
                         break
                     i+=1
-            
+
         except:
             # I find it hard to care if the series parsing fails
             pass
-            
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulSoup(self._fetchUrl(url)) # otherwise soup eats the br/hr tags.
-        
+        soup = self.make_soup(self._fetchUrl(url))
+
         div = soup.find('div', {'id' : 'story'})
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_portkeyorg.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
+# Copyright 2011 Fanficdownloader team, 2016 FanFicFare team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -22,7 +22,7 @@ import re
 import urllib2
 import cookielib as cl
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -52,21 +52,21 @@ class PortkeyOrgAdapter(BaseSiteAdapter): # XXX
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2])
-        
-        
+
+
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/story/'+self.story.getMetadata('storyId'))
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','prtky') # XXX
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%d/%m/%y" # XXX
-            
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -85,7 +85,7 @@ class PortkeyOrgAdapter(BaseSiteAdapter): # XXX
         this and change it to True.
         '''
         return True
-    
+
     ## Getting the chapter list and the meta data, plus 'is adult' checking.
     def extractChapterUrlsAndMetadata(self):
 
@@ -105,26 +105,26 @@ class PortkeyOrgAdapter(BaseSiteAdapter): # XXX
                                comment=None,
                                comment_url=None,
                                rest={'HttpOnly': None},
-                               rfc2109=False) 
-            self.cookiejar.set_cookie(cookie)
+                               rfc2109=False)
+            self.get_cookiejar().set_cookie(cookie)
 
         try:
-            data = self._fetchUrl(url)
+            data = self._fetchUrl(url,usecache=False)
         except urllib2.HTTPError, e:
             if e.code == 404:
                 raise exceptions.StoryDoesNotExist(self.url)
             else:
                 raise e
 
-        if "You must be over 18 years of age to view it" in data: # XXX 
+        if "You must be over 18 years of age to view it" in data: # XXX
             raise exceptions.AdultCheckRequired(self.url)
-            
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         #print data
 
         # Now go hunting for all the meta data and the chapter list.
-        
+
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"/profile/\d+"))
         #print("======a:%s"%a)
@@ -133,13 +133,13 @@ class PortkeyOrgAdapter(BaseSiteAdapter): # XXX
         self.story.setMetadata('author',a.string)
 
         ## Going to get the rest from the author page.
-        authsoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
-        
+        authsoup = self.make_soup(self._fetchUrl(self.story.getMetadata('authorUrl')))
+
         ## Title
         titlea = authsoup.find('a', href=re.compile(r'/story/'+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',stripHTML(titlea))
         metablock = titlea.parent
-        
+
         # Find the chapters:
         for chapter in soup.find('select',{'name':'select5'}).findAll('option', {'value':re.compile(r'/story/'+self.story.getMetadata('storyId')+"/\d+$")}):
             # just in case there's tags, like <i> in chapter titles.
@@ -147,7 +147,7 @@ class PortkeyOrgAdapter(BaseSiteAdapter): # XXX
             if not chtitle:
                 chtitle = "(Untitled Chapter)"
             self.chapterUrls.append((chtitle,'http://'+self.host+chapter['value']))
-            
+
         if len(self.chapterUrls) == 0:
             self.chapterUrls.append((stripHTML(self.story.getMetadata('title')),url))
 
@@ -162,7 +162,7 @@ class PortkeyOrgAdapter(BaseSiteAdapter): # XXX
                 return d[k]
             except:
                 return ""
-        # <SPAN class="dark-small-bold">Contents:</SPAN> <SPAN class="small-grey">NC17 </SPAN> 
+        # <SPAN class="dark-small-bold">Contents:</SPAN> <SPAN class="small-grey">NC17 </SPAN>
         # <SPAN class="dark-small-bold">Published: </SPAN><SPAN class="small-grey">12/11/07</SPAN>
         # <SPAN class="dark-small-bold"><BR>
         # Description:</SPAN> <SPAN class="small-black">A special book helps Harry tap into the power the Dark Lord knows not.  Of course it’s a book on sex magic and rituals… but Harry’s not complaining.  Spurned on by the ghost of a pervert founder, Harry leads his friends in the hunt for Voldemort’s Horcruxes.
@@ -201,10 +201,10 @@ class PortkeyOrgAdapter(BaseSiteAdapter): # XXX
                 # spans.
                 svalue = ""
                 value = labelspan.nextSibling
-                while not defaultGetattr(value,'class') == 'dark-small-bold':
-                    svalue += str(value)
+                while 'dark-small-bold' not in defaultGetattr(value,'class'):
+                    svalue += unicode(value)
                     value = value.nextSibling
-                    
+
                 for genre in svalue.split("/"):
                     genre = genre.strip()
                     if genre != 'None':
@@ -228,7 +228,7 @@ class PortkeyOrgAdapter(BaseSiteAdapter): # XXX
 
             if 'Published' in label:
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
+
             if 'Updated' in label:
                 self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
 
@@ -239,18 +239,18 @@ class PortkeyOrgAdapter(BaseSiteAdapter): # XXX
         #     series_url = 'http://'+self.host+'/'+a['href']
 
         #     # use BeautifulSoup HTML parser to make everything easier to find.
-        #     seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+        #     seriessoup = self.make_soup(self._fetchUrl(series_url))
         #     storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
         #     i=1
         #     for a in storyas:
         #         if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
         #             self.setSeries(series_name, i)
         #             break
-        #         i+=1            
+        #         i+=1
         # except:
         #     # I find it hard to care if the series parsing fails
         #     pass
-            
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
@@ -258,8 +258,9 @@ class PortkeyOrgAdapter(BaseSiteAdapter): # XXX
         data = self._fetchUrl(url)
 
         data = data.replace("HTML>","div>")
-        
-        soup = bs.BeautifulSoup(data)
+        data = data.replace("html>","div>")
+
+        soup = self.make_soup(data)
 
         # remove ad blocks so they don't become covers.
         for ns in soup.findAll('noscript'):
@@ -269,7 +270,10 @@ class PortkeyOrgAdapter(BaseSiteAdapter): # XXX
         tag = soup.find('td', {'class' : 'story'})
         if tag == None and "<center><b>Chapter does not exist!</b></center>" in data:
             logger.error("Chapter is missing at: %s"%url)
-            return  self.utf8FromSoup(url,bs.BeautifulStoneSoup("<div><p><center><b>Chapter does not exist!</b></center></p><p>Chapter is missing at: <a href='%s'>%s</a></p></div>"%(url,url)))
+            return  self.utf8FromSoup(url,self.make_soup("<div><p><center><b>Site says: Chapter does not exist!</b></center></p><p>Chapter is missing at: <a href='%s'>%s</a></p></div>"%(url,url)))
+        elif tag == None and "<center><b>This chapter has corrupted or a blank chapter was uploaded. Please contact the author and request that they re-upload the chapter</b></center>" in data:
+            logger.error("Chapter is missing at: %s"%url)
+            return  self.utf8FromSoup(url,self.make_soup("<div><p><center><b>Site says: This chapter has corrupted or a blank chapter was uploaded.</b></center></p><p>Chapter is missing at: <a href='%s'>%s</a></p></div>"%(url,url)))
         tag.name='div' # force to be a div to avoid problems with nook.
 
         centers = tag.findAll('center')
@@ -282,5 +286,5 @@ class PortkeyOrgAdapter(BaseSiteAdapter): # XXX
 
         if None == tag:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,tag)

fanficfare/adapters/adapter_potionsandsnitches.py

@@ -23,7 +23,7 @@ import re
 import urllib
 import urllib2
 
-from .. import BeautifulSoup as bs
+
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -39,15 +39,15 @@ class PotionsAndSnitchesOrgSiteAdapter(BaseSiteAdapter):
                                # Most sites that claim to be
                                # iso-8859-1 (and some that claim to be
                                # utf8) are really windows-1252.
-        
+
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        
-        
+
+
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/fanfiction/viewstory.php?sid='+self.story.getMetadata('storyId'))
 
-            
+
     @staticmethod
     def getSiteDomain():
         return 'www.potionsandsnitches.org'
@@ -77,15 +77,15 @@ class PotionsAndSnitchesOrgSiteAdapter(BaseSiteAdapter):
                 raise e
 
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
 
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',stripHTML(a))
-        
+
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
@@ -99,20 +99,12 @@ class PotionsAndSnitchesOrgSiteAdapter(BaseSiteAdapter):
 
         self.story.setMetadata('numChapters',len(self.chapterUrls))
 
-        ## <meta name='description' content='&lt;p&gt;Description&lt;/p&gt; ...' >
-        ## Summary, strangely, is in the content attr of a <meta name='description'> tag
-        ## which is escaped HTML.  Unfortunately, we can't use it because they don't
-        ## escape (') chars in the desc, breakin the tag.
-        #meta_desc = soup.find('meta',{'name':'description'})
-        #metasoup = bs.BeautifulStoneSoup(meta_desc['content'])
-        #self.story.setMetadata('description',stripHTML(metasoup))
-
         def defaultGetattr(d,k):
             try:
                 return d[k]
             except:
                 return ""
-        
+
         # <span class="label">Rated:</span> NC-17<br /> etc
         labels = soup.findAll('span',{'class':'label'})
         for labelspan in labels:
@@ -122,8 +114,8 @@ class PotionsAndSnitchesOrgSiteAdapter(BaseSiteAdapter):
             if 'Summary' in label:
                 ## Everything until the next div class='listbox'
                 svalue = ""
-                while not defaultGetattr(value,'class') == 'listbox':
-                    svalue += str(value)
+                while 'listbox' not in defaultGetattr(value,'class'):
+                    svalue += unicode(value)
                     value = value.nextSibling
                 self.setDescription(url,svalue)
                 #self.story.setMetadata('description',stripHTML(svalue))
@@ -134,6 +126,9 @@ class PotionsAndSnitchesOrgSiteAdapter(BaseSiteAdapter):
             if 'Word count' in label:
                 self.story.setMetadata('numWords', value)
 
+            if 'Read' in label:
+                self.story.setMetadata('reads', value)
+
             if 'Categories' in label:
                 cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
                 catstext = [cat.string for cat in cats]
@@ -150,12 +145,30 @@ class PotionsAndSnitchesOrgSiteAdapter(BaseSiteAdapter):
                     else:
                         self.story.addToList('characters',char.string)
 
+            if 'Warning' in label:
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class'))
+                for warning in warnings:
+                    self.story.addToList('warnings',stripHTML(warning))
+
             if 'Genre' in label:
                 genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class'))
-                genrestext = [genre.string for genre in genres]
-                self.genre = ', '.join(genrestext)
-                for genre in genrestext:
-                    self.story.addToList('genre',genre.string)
+                for genre in genres:
+                    self.story.addToList('genre',stripHTML(genre))
+
+            if 'Takes Place' in label:
+                takesplaces = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class'))
+                for takesplace in takesplaces:
+                    self.story.addToList('takesplaces',stripHTML(takesplace))
+
+            if 'Snape flavour' in label:
+                snapeflavours = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class'))
+                for snapeflavour in snapeflavours:
+                    self.story.addToList('snapeflavours',stripHTML(snapeflavour))
+
+            if 'Tags' in label:
+                sitetags = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class'))
+                for sitetag in sitetags:
+                    self.story.addToList('sitetags',stripHTML(sitetag))
 
             if 'Completed' in label:
                 if 'Yes' in value:
@@ -166,7 +179,7 @@ class PotionsAndSnitchesOrgSiteAdapter(BaseSiteAdapter):
             if 'Published' in label:
                 # limit date values, there's some extra chars.
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value[:12]), "%d %b %Y"))
-            
+
             if 'Updated' in label:
                 self.story.setMetadata('dateUpdated', makeDate(stripHTML(value[:12]), "%d %b %Y"))
 
@@ -177,7 +190,7 @@ class PotionsAndSnitchesOrgSiteAdapter(BaseSiteAdapter):
             series_url = 'http://'+self.host+'/fanfiction/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            seriessoup = self.make_soup(self._fetchUrl(series_url))
             storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
             i=1
             for a in storyas:
@@ -186,24 +199,31 @@ class PotionsAndSnitchesOrgSiteAdapter(BaseSiteAdapter):
                     self.story.setMetadata('seriesUrl',series_url)
                     break
                 i+=1
-            
+
         except:
             # I find it hard to care if the series parsing fails
             pass
-            
+
+        divsort = soup.find('div',id='sort')
+        stars = len(divsort.find_all('img',src='images/star.gif'))
+        stars = stars + 0.5 * len(divsort.find_all('img',src='images/starhalf.gif'))
+        self.story.setMetadata('stars',stars)
+
+        a = divsort.find_all('a', href=re.compile(r'reviews.php\?type=ST&(amp;)?item='+self.story.getMetadata('storyId')+"$"))[1] # second one.
+        self.story.setMetadata('reviews',stripHTML(a))
         
+
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
+        soup = self.make_soup(self._fetchUrl(url))
+
         div = soup.find('div', {'id' : 'story'})
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
         return self.utf8FromSoup(url,div)
 
 def getClass():