Update CLI download zip.

doesn't support HTTPS fixed
www. fixed
timer removed

app.yaml

@@ -1,6 +1,6 @@
 # ffd-retief-hrd fanfictiondownloader
 application: fanfictiondownloader
-version: 4-4-84
+version: 2-0-03
 runtime: python27
 api_version: 1
 threadsafe: true

calibre-plugin/__init__.py

@@ -42,8 +42,8 @@ class FanFictionDownLoaderBase(InterfaceActionBase):
     description         = _('UI plugin to download FanFiction stories from various sites.')
     supported_platforms = ['windows', 'osx', 'linux']
     author              = 'Jim Miller'
-    version             = (1, 8, 00)
-    minimum_calibre_version = (0, 8, 57)
+    version             = (2, 0, 3)
+    minimum_calibre_version = (1, 13, 0)
 
     #: This field defines the GUI plugin class that contains all the code
     #: that actually does something. Its format is module_path:class_name

calibre-plugin/common_utils.py

@@ -8,12 +8,19 @@ __copyright__ = '2011, Grant Drake <grant.drake@gmail.com>'
 __docformat__ = 'restructuredtext en'
 
 import os
-from PyQt4 import QtGui
-from PyQt4.Qt import (Qt, QIcon, QPixmap, QLabel, QDialog, QHBoxLayout,
-                      QTableWidgetItem, QFont, QLineEdit, QComboBox,
-                      QVBoxLayout, QDialogButtonBox, QStyledItemDelegate, QDateTime,
-                      QTextEdit,
-                      QListWidget, QAbstractItemView)
+try:
+    from PyQt5 import QtWidgets as QtGui
+    from PyQt5.Qt import (Qt, QIcon, QPixmap, QLabel, QDialog, QHBoxLayout,
+                          QTableWidgetItem, QFont, QLineEdit, QComboBox,
+                          QVBoxLayout, QDialogButtonBox, QStyledItemDelegate, QDateTime,
+                          QTextEdit, QListWidget, QAbstractItemView)
+except ImportError as e:
+    from PyQt4 import QtGui
+    from PyQt4.Qt import (Qt, QIcon, QPixmap, QLabel, QDialog, QHBoxLayout,
+                          QTableWidgetItem, QFont, QLineEdit, QComboBox,
+                          QVBoxLayout, QDialogButtonBox, QStyledItemDelegate, QDateTime,
+                          QTextEdit, QListWidget, QAbstractItemView)
+    
 from calibre.constants import iswindows
 from calibre.gui2 import gprefs, error_dialog, UNDEFINED_QDATETIME, info_dialog
 from calibre.gui2.actions import menu_action_unique_name

calibre-plugin/config.py

@@ -4,7 +4,7 @@ from __future__ import (unicode_literals, division, absolute_import,
                         print_function)
 
 __license__   = 'GPL v3'
-__copyright__ = '2012, Jim Miller'
+__copyright__ = '2014, Jim Miller'
 __docformat__ = 'restructuredtext en'
 
 import logging
@@ -13,10 +13,31 @@ logger = logging.getLogger(__name__)
 import traceback, copy, threading
 from collections import OrderedDict
 
-from PyQt4.Qt import (QDialog, QWidget, QVBoxLayout, QHBoxLayout, QLabel,
-                      QLineEdit, QFont, QWidget, QTextEdit, QComboBox,
-                      QCheckBox, QPushButton, QTabWidget, QVariant, QScrollArea,
-                      QDialogButtonBox, QGroupBox )
+try:
+    from PyQt5.Qt import (QDialog, QWidget, QVBoxLayout, QHBoxLayout, QLabel,
+                          QLineEdit, QFont, QWidget, QTextEdit, QComboBox,
+                          QCheckBox, QPushButton, QTabWidget, QScrollArea,
+                          QDialogButtonBox, QGroupBox )
+except ImportError as e:
+    from PyQt4.Qt import (QDialog, QWidget, QVBoxLayout, QHBoxLayout, QLabel,
+                          QLineEdit, QFont, QWidget, QTextEdit, QComboBox,
+                          QCheckBox, QPushButton, QTabWidget, QScrollArea,
+                          QDialogButtonBox, QGroupBox )
+try:
+    from calibre.gui2 import QVariant
+    del QVariant
+except ImportError:
+    is_qt4 = False
+    convert_qvariant = lambda x: x
+else:
+    is_qt4 = True
+    def convert_qvariant(x):
+        vt = x.type()
+        if vt == x.String:
+            return unicode(x.toString())
+        if vt == x.List:
+            return [convert_qvariant(i) for i in x.toList()]
+        return x.toPyObject()
 
 from calibre.gui2.ui import get_gui
 from calibre.gui2 import dynamic, info_dialog
@@ -55,12 +76,12 @@ from calibre_plugins.fanfictiondownloader_plugin.dialogs \
             EditTextDialog, RejectUrlEntry)
     
 from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.adapters \
-    import (getConfigSections, getNormalStoryURL)
+    import getConfigSections
 
 from calibre_plugins.fanfictiondownloader_plugin.common_utils \
     import ( KeyboardConfigDialog, PrefsViewerDialog )
 
-from calibre.gui2.complete import MultiCompleteLineEdit
+from calibre.gui2.complete2 import EditWithComplete  #MultiCompleteLineEdit
 
 class RejectURLList:
     def __init__(self,prefs):
@@ -209,6 +230,7 @@ class ConfigWidget(QWidget):
         prefs['suppresstitlesort'] = self.basic_tab.suppresstitlesort.isChecked()
         prefs['mark'] = self.basic_tab.mark.isChecked()
         prefs['showmarked'] = self.basic_tab.showmarked.isChecked()
+        prefs['autoconvert'] = self.basic_tab.autoconvert.isChecked()
         prefs['urlsfromclip'] = self.basic_tab.urlsfromclip.isChecked()
         prefs['updatedefault'] = self.basic_tab.updatedefault.isChecked()
         prefs['deleteotherforms'] = self.basic_tab.deleteotherforms.isChecked()
@@ -219,6 +241,7 @@ class ConfigWidget(QWidget):
         prefs['checkforurlchange'] = self.basic_tab.checkforurlchange.isChecked()
         prefs['injectseries'] = self.basic_tab.injectseries.isChecked()
         prefs['smarten_punctuation'] = self.basic_tab.smarten_punctuation.isChecked()
+        prefs['reject_always'] = self.basic_tab.reject_always.isChecked()
 
         if self.readinglist_tab:
             # lists
@@ -242,12 +265,13 @@ class ConfigWidget(QWidget):
         prefs['gcnewonly'] = self.generatecover_tab.gcnewonly.isChecked()
         gc_site_settings = {}
         for (site,combo) in self.generatecover_tab.gc_dropdowns.iteritems():
-            val = unicode(combo.itemData(combo.currentIndex()).toString())
+            val = unicode(convert_qvariant(combo.itemData(combo.currentIndex())))
             if val != 'none':
                 gc_site_settings[site] = val
                 #print("gc_site_settings[%s]:%s"%(site,gc_site_settings[site]))
         prefs['gc_site_settings'] = gc_site_settings
         prefs['allow_gc_from_ini'] = self.generatecover_tab.allow_gc_from_ini.isChecked()
+        prefs['gc_polish_cover'] = self.generatecover_tab.gc_polish_cover.isChecked()
 
         # Count Pages tab
         countpagesstats = []
@@ -273,12 +297,12 @@ class ConfigWidget(QWidget):
 
         # Custom Columns tab
         # error column
-        prefs['errorcol'] = unicode(self.cust_columns_tab.errorcol.itemData(self.cust_columns_tab.errorcol.currentIndex()).toString())
+        prefs['errorcol'] = unicode(convert_qvariant(self.cust_columns_tab.errorcol.itemData(self.cust_columns_tab.errorcol.currentIndex())))
 
         # cust cols tab
         colsmap = {}
         for (col,combo) in self.cust_columns_tab.custcol_dropdowns.iteritems():
-            val = unicode(combo.itemData(combo.currentIndex()).toString())
+            val = unicode(convert_qvariant(combo.itemData(combo.currentIndex())))
             if val != 'none':
                 colsmap[col] = val
                 #print("colsmap[%s]:%s"%(col,colsmap[col]))
@@ -422,6 +446,11 @@ class BasicTab(QWidget):
         self.showmarked.setChecked(prefs['showmarked'])
         self.l.addWidget(self.showmarked)
 
+        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'])
+        self.l.addWidget(self.autoconvert)
+
         gui_gb = groupbox = QGroupBox(_("GUI Options"))
         self.l = QVBoxLayout()
         groupbox.setLayout(self.l)
@@ -475,6 +504,11 @@ class BasicTab(QWidget):
         self.reject_reasons.clicked.connect(self.show_reject_reasons)
         self.l.addWidget(self.reject_reasons)
 
+        self.reject_always = QCheckBox(_('Reject Without Confirmation?'),self)
+        self.reject_always.setToolTip(_("Always reject URLs on the Reject List without stopping and asking."))
+        self.reject_always.setChecked(prefs['reject_always'])
+        self.l.addWidget(self.reject_always)
+
         topl.addWidget(defs_gb)
 
         horz = QHBoxLayout()
@@ -642,7 +676,7 @@ class ReadingListTab(QWidget):
         label = QLabel(_('"Send to Device" Reading Lists'))
         label.setToolTip(_("When enabled, new/updated stories will be automatically added to these lists."))
         horz.addWidget(label)        
-        self.send_lists_box = MultiCompleteLineEdit(self)
+        self.send_lists_box = EditWithComplete(self)
         self.send_lists_box.setToolTip(_("When enabled, new/updated stories will be automatically added to these lists."))
         self.send_lists_box.update_items_cache(reading_lists)
         self.send_lists_box.setText(prefs['send_lists'])
@@ -658,7 +692,7 @@ class ReadingListTab(QWidget):
         label = QLabel(_('"To Read" Reading Lists'))
         label.setToolTip(_("When enabled, new/updated stories will be automatically added to these lists."))
         horz.addWidget(label)        
-        self.read_lists_box = MultiCompleteLineEdit(self)
+        self.read_lists_box = EditWithComplete(self)
         self.read_lists_box.setToolTip(_("When enabled, new/updated stories will be automatically added to these lists."))
         self.read_lists_box.update_items_cache(reading_lists)
         self.read_lists_box.setText(prefs['read_lists'])
@@ -720,12 +754,17 @@ class GenerateCoverTab(QWidget):
             horz.addWidget(label)
             dropdown = QComboBox(self)
             dropdown.setToolTip(s)
-            dropdown.addItem('',QVariant('none'))
+            dropdown.addItem('','none')
             for setting in gc_settings:
-                dropdown.addItem(setting,QVariant(setting))
-            self.gc_dropdowns[site] = dropdown
+                dropdown.addItem(setting,setting)
+            if site == _("Default"):
+                self.gc_dropdowns["Default"] = dropdown
+                if 'Default' in prefs['gc_site_settings']:
+                    dropdown.setCurrentIndex(dropdown.findData(prefs['gc_site_settings']['Default']))
+            else:
+                self.gc_dropdowns[site] = dropdown
             if site in prefs['gc_site_settings']:
-                dropdown.setCurrentIndex(dropdown.findData(QVariant(prefs['gc_site_settings'][site])))
+                dropdown.setCurrentIndex(dropdown.findData(prefs['gc_site_settings'][site]))
 
             horz.addWidget(dropdown)
             self.sl.addLayout(horz)
@@ -742,6 +781,11 @@ class GenerateCoverTab(QWidget):
         self.allow_gc_from_ini.setChecked(prefs['allow_gc_from_ini'])
         self.l.addWidget(self.allow_gc_from_ini)
             
+        self.gc_polish_cover = QCheckBox(_("Use calibre's Polish feature to inject/update the cover"),self)
+        self.gc_polish_cover.setToolTip(_("Calibre's Polish feature will be used to inject or update the generated cover into the ebook, EPUB only."))
+        self.gc_polish_cover.setChecked(prefs['gc_polish_cover'])
+        self.l.addWidget(self.gc_polish_cover)
+            
 class CountPagesTab(QWidget):
 
     def __init__(self, parent_dialog, plugin_action):
@@ -949,12 +993,12 @@ class CustomColumnsTab(QWidget):
                 label.setToolTip(_("Update this %s column(%s) with...")%(key,column['datatype']))
                 horz.addWidget(label)
                 dropdown = QComboBox(self)
-                dropdown.addItem('',QVariant('none'))
+                dropdown.addItem('','none')
                 for md in permitted_values[column['datatype']]:
-                    dropdown.addItem(titleLabels[md],QVariant(md))
+                    dropdown.addItem(titleLabels[md],md)
                 self.custcol_dropdowns[key] = dropdown
                 if key in prefs['custom_cols']:
-                    dropdown.setCurrentIndex(dropdown.findData(QVariant(prefs['custom_cols'][key])))
+                    dropdown.setCurrentIndex(dropdown.findData(prefs['custom_cols'][key]))
                 if column['datatype'] == 'enumeration':
                     dropdown.setToolTip(_("Metadata values valid for this type of column.")+"\n"+_("Values that aren't valid for this enumeration column will be ignored."))
                 else:
@@ -990,11 +1034,11 @@ class CustomColumnsTab(QWidget):
         horz.addWidget(label)
         self.errorcol = QComboBox(self)
         self.errorcol.setToolTip(tooltip)
-        self.errorcol.addItem('',QVariant('none'))
+        self.errorcol.addItem('','none')
         for key, column in custom_columns.iteritems():
             if column['datatype'] in ('text','comments'):
-                self.errorcol.addItem(column['name'],QVariant(key))
-        self.errorcol.setCurrentIndex(self.errorcol.findData(QVariant(prefs['errorcol'])))
+                self.errorcol.addItem(column['name'],key)
+        self.errorcol.setCurrentIndex(self.errorcol.findData(prefs['errorcol']))
         horz.addWidget(self.errorcol)
         self.l.addLayout(horz)
 

calibre-plugin/dialogs.py

@@ -19,12 +19,36 @@ logger = logging.getLogger(__name__)
 import urllib
 import email
 
-from PyQt4 import QtGui
-from PyQt4.Qt import (QDialog, QTableWidget, QVBoxLayout, QHBoxLayout, QGridLayout,
-                      QPushButton, QString, QLabel, QCheckBox, QIcon, QLineEdit,
-                      QComboBox, QVariant, QProgressDialog, QTimer, QDialogButtonBox,
-                      QPixmap, Qt, QAbstractItemView, SIGNAL, QTextEdit, pyqtSignal,
-                      QGroupBox, QFrame)
+try:
+    from PyQt5 import QtWidgets as QtGui
+    from PyQt5.Qt import (QDialog, QTableWidget, QVBoxLayout, QHBoxLayout, QGridLayout,
+                          QPushButton, QLabel, QCheckBox, QIcon, QLineEdit,
+                          QComboBox, QProgressDialog, QTimer, QDialogButtonBox,
+                          QPixmap, Qt, QAbstractItemView, QTextEdit, pyqtSignal,
+                          QGroupBox, QFrame)
+except ImportError as e:
+    from PyQt4 import QtGui
+    from PyQt4.Qt import (QDialog, QTableWidget, QVBoxLayout, QHBoxLayout, QGridLayout,
+                          QPushButton, QLabel, QCheckBox, QIcon, QLineEdit,
+                          QComboBox, QProgressDialog, QTimer, QDialogButtonBox,
+                          QPixmap, Qt, QAbstractItemView, QTextEdit, pyqtSignal,
+                          QGroupBox, QFrame)
+
+try:
+    from calibre.gui2 import QVariant
+    del QVariant
+except ImportError:
+    is_qt4 = False
+    convert_qvariant = lambda x: x
+else:
+    is_qt4 = True
+    def convert_qvariant(x):
+        vt = x.type()
+        if vt == x.String:
+            return unicode(x.toString())
+        if vt == x.List:
+            return [convert_qvariant(i) for i in x.toList()]
+        return x.toPyObject()
 
 from calibre.gui2.dialogs.confirm_delete import confirm
 from calibre.gui2.complete2 import EditWithComplete
@@ -136,7 +160,8 @@ class RejectUrlEntry:
     def fullnote(self):
         retval = ""
         if self.title and self.auth:
-            retval = retval + _("%s by %s")%(self.title,self.auth)
+            # don't translate--ends up being saved and confuses regex above.
+            retval = retval + "%s by %s"%(self.title,self.auth)
             if self.note:
                 retval = retval + " - "
                 
@@ -145,19 +170,6 @@ class RejectUrlEntry:
             
         return retval
 
-# This is a more than slightly kludgey way to get
-# EditWithComplete to *not* alpha-order the reasons, but leave
-# them in the order entered.  If
-# calibre.gui2.complete2.CompleteModel.set_items ever changes,
-# this function will need to also.
-def complete_model_set_items_kludge(self, items):
-    items = [unicode(x.strip()) for x in items]
-    items = [x for x in items if x]
-    items = tuple(items)
-    self.all_items = self.current_items = items
-    self.current_prefix = ''
-    self.reset()
-    
 class NotGoingToDownload(Exception):
     def __init__(self,error,icon='dialog_error.png'):
         self.error=error
@@ -195,9 +207,9 @@ class DroppableQTextEdit(QTextEdit):
                             urllist.extend(get_urls_from_text(part.get_payload(decode=True)))
                 else:
                     urllist.extend(get_urls_from_text("%s"%msg))
-        
         if urllist:
             self.append("\n".join(urllist))
+            return None
         return QTextEdit.dropEvent(self,event)
         
     def canInsertFromMimeData(self, source):
@@ -558,7 +570,7 @@ class LoopProgressDialog(QProgressDialog):
                  status_prefix=_("Fetched metadata for")):
         QProgressDialog.__init__(self,
                                  init_label,
-                                 QString(), 0, len(book_list), gui)
+                                 _('Cancel'), 0, len(book_list), gui)
         self.setWindowTitle(win_title)
         self.setMinimumWidth(500)
         self.book_list = book_list
@@ -828,11 +840,11 @@ class StoryListTableWidget(QTableWidget):
             icon = get_icon(book['icon'])
 
         status_cell = IconWidgetItem(None,icon,val)
-        status_cell.setData(Qt.UserRole, QVariant(val))
+        status_cell.setData(Qt.UserRole, val)
         self.setItem(row, 0, status_cell)
         
         title_cell = ReadOnlyTableWidgetItem(book['title'])
-        title_cell.setData(Qt.UserRole, QVariant(row))
+        title_cell.setData(Qt.UserRole, row)
         self.setItem(row, 1, title_cell)
         
         self.setItem(row, 2, AuthorTableWidgetItem(", ".join(book['author']), ", ".join(book['author_sort'])))
@@ -847,7 +859,7 @@ class StoryListTableWidget(QTableWidget):
         books = []
         #print("=========================\nbooks:%s"%self.books)
         for row in range(self.rowCount()):
-            rnum = self.item(row, 1).data(Qt.UserRole).toPyObject()
+            rnum = convert_qvariant(self.item(row, 1).data(Qt.UserRole))
             book = self.books[rnum]
             books.append(book)
         return books
@@ -913,15 +925,12 @@ class RejectListTableWidget(QTableWidget):
     def populate_table_row(self, row, rej):
 
         url_cell = ReadOnlyTableWidgetItem(rej.url)
-        url_cell.setData(Qt.UserRole, QVariant(rej.book_id))
+        url_cell.setData(Qt.UserRole, rej.book_id)
         self.setItem(row, 0, url_cell)
         self.setItem(row, 1, ReadOnlyTableWidgetItem(rej.title))
         self.setItem(row, 2, ReadOnlyTableWidgetItem(rej.auth))
         
-        note_cell = EditWithComplete(self)
-        note_cell.lineEdit().mcompleter.model().set_items = \
-            partial(complete_model_set_items_kludge,
-                    note_cell.lineEdit().mcompleter.model())
+        note_cell = EditWithComplete(self,sort_func=lambda x:1)
         
         items = [rej.note]+self.rejectreasons
         note_cell.update_items_cache(items)
@@ -991,10 +1000,7 @@ class RejectListDialog(SizePersistedDialog):
         button_layout.addItem(spacerItem1)
 
         if show_all_reasons:
-            self.reason_edit = EditWithComplete(self)
-            self.reason_edit.lineEdit().mcompleter.model().set_items = \
-                partial(complete_model_set_items_kludge,
-                        self.reason_edit.lineEdit().mcompleter.model())
+            self.reason_edit = EditWithComplete(self,sort_func=lambda x:1)
             
             items = ['']+rejectreasons
             self.reason_edit.update_items_cache(items)
@@ -1036,7 +1042,7 @@ class RejectListDialog(SizePersistedDialog):
         rejectrows = []
         for row in range(self.rejects_table.rowCount()):
             url = unicode(self.rejects_table.item(row, 0).text()).strip()
-            book_id = self.rejects_table.item(row, 0).data(Qt.UserRole).toPyObject()
+            book_id =convert_qvariant(self.rejects_table.item(row, 0).data(Qt.UserRole))
             title = unicode(self.rejects_table.item(row, 1).text()).strip()
             auth = unicode(self.rejects_table.item(row, 2).text()).strip()
             note = unicode(self.rejects_table.cellWidget(row, 3).currentText()).strip()
@@ -1046,7 +1052,7 @@ class RejectListDialog(SizePersistedDialog):
     def get_reject_list_ids(self):
         rejectrows = []
         for row in range(self.rejects_table.rowCount()):
-            book_id = self.rejects_table.item(row, 0).data(Qt.UserRole).toPyObject()
+            book_id = convert_qvariant(self.rejects_table.item(row, 0).data(Qt.UserRole))
             if book_id:
                 rejectrows.append(book_id)
         return rejectrows
@@ -1088,11 +1094,7 @@ class EditTextDialog(QDialog):
             self.textedit.setToolTip(tooltip)
 
         if rejectreasons or reasonslabel:
-            self.reason_edit = EditWithComplete(self)
-
-            self.reason_edit.lineEdit().mcompleter.model().set_items = \
-                partial(complete_model_set_items_kludge,
-                        self.reason_edit.lineEdit().mcompleter.model())
+            self.reason_edit = EditWithComplete(self,sort_func=lambda x:1)
             
             items = ['']+rejectreasons
             self.reason_edit.update_items_cache(items)

calibre-plugin/ffdl_plugin.py

@@ -4,7 +4,7 @@ from __future__ import (unicode_literals, division, absolute_import,
                         print_function)
 
 __license__   = 'GPL v3'
-__copyright__ = '2012, Jim Miller'
+__copyright__ = '2014, Jim Miller'
 __docformat__ = 'restructuredtext en'
 
 import logging
@@ -13,16 +13,18 @@ logger = logging.getLogger(__name__)
 import time, os, copy, threading, re, platform, sys
 from StringIO import StringIO
 from functools import partial
-from datetime import datetime
+from datetime import datetime, time
 from string import Template
 import urllib
 import email
 import traceback
 
-from PyQt4.Qt import (QApplication, QMenu, QToolButton, QTimer)
-
-from PyQt4.Qt import QPixmap, Qt
-from PyQt4.QtCore import QBuffer
+try:
+    from PyQt5.Qt import (QApplication, QMenu, QTimer)
+    from PyQt5.QtCore import QBuffer
+except ImportError as e:
+    from PyQt4.Qt import (QApplication, QMenu, QTimer)
+    from PyQt4.QtCore import QBuffer
 
 from calibre.constants import numeric_version as calibre_version
 
@@ -32,6 +34,7 @@ from calibre.ebooks.metadata.meta import get_metadata
 from calibre.gui2 import error_dialog, warning_dialog, question_dialog, info_dialog
 from calibre.gui2.dialogs.message_box import ViewLog
 from calibre.gui2.dialogs.confirm_delete import confirm
+from calibre.utils.config import prefs as calibre_prefs
 from calibre.utils.date import local_tz
 from calibre.library.comments import sanitize_comments_html
 from calibre.constants import config_dir as calibre_config_dir
@@ -206,7 +209,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                 #print("text/plain:%s"%event.mimeData().data(mimetype))
                 urllist.extend(get_urls_from_text(event.mimeData().data(mimetype)))
 
-        #print("urllist:%s\ndropped_ids:%s"%(urllist,dropped_ids))
+        # print("urllist:%s\ndropped_ids:%s"%(urllist,dropped_ids))
         if urllist or dropped_ids:
             QTimer.singleShot(1, partial(self.do_drop,
                                          dropped_ids=dropped_ids,
@@ -384,6 +387,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
 
     def get_urls_from_page_menu(self):
 
+        urltxt = ""
         if prefs['urlsfromclip']:
             try:
                 urltxt = self.get_urls_clip(storyurls=False)[0]
@@ -660,13 +664,13 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         #print("update_dialog()")
         
         db = self.gui.current_db
-        book_list = map( self.make_book_id_only, id_list )
+        books = map( self.make_book_id_only, id_list )
 
-        for j, book in enumerate(book_list):
+        for j, book in enumerate(books):
             book['listorder'] = j
-            
+
         LoopProgressDialog(self.gui,
-                           book_list,
+                           books,
                            partial(self.populate_book_from_calibre_id, db=self.gui.current_db),
                            self.update_dialog_finish,
                            init_label=_("Collecting stories for update..."),
@@ -711,6 +715,11 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         # No need to do anything with perfs here, but we could.
         prefs
 
+    def make_id_searchstr(self,url):
+        # older idents can be uri vs url and have | instead of : after
+        # http, plus many sites are now switching to https.
+        return 'identifiers:"~ur(i|l):~^%s$"'%re.sub(r'https?\\\:','https?(\:|\|)',re.escape(url))
+
     def prep_downloads(self, options, books, merge=False, extrapayload=None):
         '''Fetch metadata for stories from servers, launch BG job when done.'''
 
@@ -718,6 +727,9 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             url_list = split_text_to_urls(books)
             books = self.convert_urls_to_books(url_list)
 
+        ## for tweak_fg_sleep
+        options['ffnetcount']=len(filter(lambda x : x['site']=='www.fanfiction.net', books))
+
         options['version'] = self.version
         logger.debug(self.version)
         
@@ -760,7 +772,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         if not merge: # skip reject list when merging.
             if rejecturllist.check(url):
                 rejnote = rejecturllist.get_full_note(url)
-                if question_dialog(self.gui, _('Reject URL?'),'''
+                if prefs['reject_always'] or question_dialog(self.gui, _('Reject URL?'),'''
                           <h3>%s</h3>
                           <p>%s</p>
                           <p>"<b>%s</b>"</p>
@@ -815,6 +827,18 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         
         options['personal.ini'] = get_ffdl_personalini()
         adapter = get_ffdl_adapter(url,fileform)
+        # reduce foreground sleep time for ffnet when few books.
+        if 'ffnetcount' in options and \
+                adapter.getConfig('tweak_fg_sleep') and \
+                adapter.getSiteDomain() == 'www.fanfiction.net':
+            minslp = float(adapter.getConfig('min_fg_sleep'))
+            maxslp = float(adapter.getConfig('max_fg_sleep'))
+            dwnlds = float(adapter.getConfig('max_fg_sleep_at_downloads'))
+            m = (maxslp-minslp) / (dwnlds-1)
+            b = minslp - m
+            slp = min(maxslp,m*float(options['ffnetcount'])+b)
+            #print("m:%s b:%s = %s"%(m,b,slp))
+            adapter.set_sleep(slp)
 
         ## three tries, that's enough if both user/pass & is_adult needed,
         ## or a couple tries of one or the other
@@ -841,7 +865,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         series = story.getMetadata('series')
         if not merge and series and prefs['checkforseriesurlid']:
             # try to find *series anthology* by *seriesUrl* identifier url or uri first.
-            searchstr = 'identifiers:"~ur(i|l):=%s"'%story.getMetadata('seriesUrl').replace(":","|")
+            searchstr = self.make_id_searchstr(story.getMetadata('seriesUrl'))
             identicalbooks = db.search_getting_ids(searchstr, None)
             # print("searchstr:%s"%searchstr)
             # print("identicalbooks:%s"%identicalbooks)
@@ -873,7 +897,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
 
         # all_metadata duplicates some data, but also includes extra_entries, etc.
         book['all_metadata'] = story.getAllMetadata(removeallentities=True)
-        
+
         book['title'] = story.getMetadata("title", removeallentities=True)
         book['author_sort'] = book['author'] = story.getList("author", removeallentities=True)
         book['publisher'] = story.getMetadata("site")
@@ -918,18 +942,13 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                 logger.debug("from URL(%s)"%url)
     
                 # try to find by identifier url or uri first.
-                searchstr = 'identifiers:"~ur(i|l):=%s"'%url.replace(":","|")
+                searchstr = self.make_id_searchstr(url)
                 identicalbooks = db.search_getting_ids(searchstr, None)
+                # print("searchstr:%s"%searchstr)
+                # print("identicalbooks:%s"%identicalbooks)
                 if len(identicalbooks) < 1:
                     # find dups
                     authlist = story.getList("author", removeallentities=True)
-                    if len(authlist) > 100 and calibre_version < (0, 8, 61):
-                        ## should be fixed from 0.8.61 on.  In the
-                        ## meantime, if it matches the title *and* first
-                        ## 100 authors, I'm prepared to assume it's a
-                        ## match.
-                        logger.debug("reduce author list to 100 only when calibre < 0.8.61")
-                        authlist = authlist[:100]
                     mi = MetaInformation(story.getMetadata("title", removeallentities=True),
                                          authlist)
                     identicalbooks = db.find_identical_books(mi)
@@ -943,7 +962,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                     raise NotGoingToDownload(_("Skipping duplicate story."),"list_remove.png")
     
                 if len(identicalbooks) > 1:
-                    raise NotGoingToDownload("More than one identical book by Identifer URL or title/author(s)--can't tell which book to update/overwrite.","minusminus.png")
+                    raise NotGoingToDownload(_("More than one identical book by Identifer URL or title/author(s)--can't tell which book to update/overwrite."),"minusminus.png")
     
                 ## changed: add new book when CALIBREONLY if none found.
                 if collision == CALIBREONLY and not identicalbooks:
@@ -959,7 +978,8 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                 if book_id and mi: # book_id and mi only set if matched by title/author.
                     liburl = self.get_story_url(db,book_id)
                     if book['url'] != liburl and prefs['checkforurlchange'] and \
-                        not (book['url'].replace('https','http') == liburl and 'fanfiction.net' in liburl):
+                        not (book['url'].replace('https','http') == liburl): # several sites have been changing to
+                                                                             # https now.  Don't flag when that's the only change.
                         # special case for ffnet urls change to https.
                         if not question_dialog(self.gui, _('Change Story URL?'),'''
                                                   <h3>%s</h3>
@@ -1014,7 +1034,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                         (epuburl,chaptercount) = \
                             get_dcsource_chaptercount(StringIO(db.format(book_id,'EPUB',
                                                                          index_is_id=True)))
-                        urlchaptercount = int(story.getMetadata('numChapters'))
+                        urlchaptercount = int(story.getMetadata('numChapters').replace(',',''))
                         if chaptercount == urlchaptercount:
                             if collision == UPDATE:
                                 raise NotGoingToDownload(_("Already contains %d chapters.")%chaptercount,'edit-undo.png')
@@ -1029,10 +1049,16 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                 if collision == OVERWRITE and \
                         db.has_format(book_id,formmapping[fileform],index_is_id=True):
                     # check make sure incoming is newer.
-                    lastupdated=story.getMetadataRaw('dateUpdated').date()
-                    fileupdated=datetime.fromtimestamp(os.stat(db.format_abspath(book_id, formmapping[fileform], index_is_id=True))[8]).date()
-                    if fileupdated > lastupdated:
+                    lastupdated=story.getMetadataRaw('dateUpdated')
+                    fileupdated=datetime.fromtimestamp(os.stat(db.format_abspath(book_id, formmapping[fileform], index_is_id=True))[8])
+
+                    # 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')
+                    
+                    
         
                 # For update, provide a tmp file copy of the existing epub so
                 # it can't change underneath us.  Now also overwrite for logpage preserve.
@@ -1130,6 +1156,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                 func, args=args,
                 description=desc)
         
+        self.gui.jobs_pointer.start()
         self.gui.status_bar.show_message(_('Starting %d FanFictionDownLoads')%len(book_list),3000)
 
     def update_books_loop(self,book,db=None,
@@ -1224,6 +1251,10 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             cp_plugin = self.gui.iactions['Count Pages']
             cp_plugin.count_statistics(all_ids,prefs['countpagesstats'])
 
+        if prefs['autoconvert'] and options['collision'] != CALIBREONLY:
+            self.gui.status_bar.show_message(_('Starting auto conversion of %d books.')%(len(all_ids)), 3000)
+            self.gui.iactions['Convert Books'].auto_convert_auto_add(all_ids)
+
     def download_list_completed(self, job, options={},merge=False):
         if job.failed:
             self.gui.job_exception(job, dialog_title='Failed to Download Stories')
@@ -1327,7 +1358,6 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         bad_list = sorted(bad_list,key=lambda x : x['listorder'])
         
         self.gui.status_bar.show_message(_('Merging %s books.')%total_good)
-
         
         existingbook = None
         if 'mergebook' in options:
@@ -1385,7 +1415,10 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         if prefs['mark'] or (prefs['errorcol'] != '' and prefs['errorcol'] in custom_columns):
             self.previous = self.gui.library_view.currentIndex() # used by update_books_finish.
             self.gui.status_bar.show_message(_('Adding/Updating %s BAD books.')%len(book_list))
-            label = custom_columns[prefs['errorcol']]['label']
+            if (prefs['errorcol'] != '' and prefs['errorcol'] in custom_columns):
+                label = custom_columns[prefs['errorcol']]['label']
+            else:
+                label = None
             LoopProgressDialog(self.gui,
                                book_list,
                                partial(self.update_error_column_loop, db=self.gui.current_db, label=label),
@@ -1394,12 +1427,10 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                                win_title=_("Update calibre for BAD FanFiction stories"),
                                status_prefix=_("Updated"))
 
-    def update_error_column_loop(self,book,db=None,label='errorcol'):
-        if book['calibre_id']:
-            custom_columns = self.gui.library_view.model().custom_columns
-            if (prefs['errorcol'] != '' and prefs['errorcol'] in custom_columns):
-                logger.debug("add/update bad %s %s %s"%(book['title'],book['url'],book['comment']))
-                db.set_custom(book['calibre_id'], book['comment'], label=label, commit=True)
+    def update_error_column_loop(self,book,db=None,label=None):
+        if book['calibre_id'] and label:
+            logger.debug("add/update bad %s %s %s"%(book['title'],book['url'],book['comment']))
+            db.set_custom(book['calibre_id'], book['comment'], label=label, commit=True)
 
     def add_book_or_update_format(self,book,options,prefs,mi=None):
         db = self.gui.current_db
@@ -1428,8 +1459,18 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             fmts = db.formats(book['calibre_id'], index_is_id=True).split(',')
             for fmt in fmts:
                 if fmt != formmapping[options['fileform']]:
-                    logger.debug("remove f:"+fmt)
+                    logger.debug("deleteotherforms remove f:"+fmt)
                     db.remove_format(book['calibre_id'], fmt, index_is_id=True)#, notify=False
+        elif prefs['autoconvert']:
+            ## 'Convert Book'.auto_convert_auto_add doesn't convert if
+            ## the format is already there.
+            fmt = calibre_prefs['output_format']
+            # delete if there, but not if the format we just made.
+            if fmt != formmapping[options['fileform']] and \
+                    db.has_format(book_id,fmt,index_is_id=True):
+                logger.debug("autoconvert remove f:"+fmt)
+                db.remove_format(book['calibre_id'], fmt, index_is_id=True)#, notify=False
+                
 
         return book_id
 
@@ -1537,8 +1578,15 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                         (custcol,flag) = map( lambda x: x.strip(), custcol.split(",") )
 
                     if meta not in book['all_metadata']:
-                        logger.debug("No value for %s, skipping custom column(%s) update."%(meta,custcol))
-                        continue
+                        # if double quoted, use as a literal value.
+                        if meta[0] == '"' and meta[-1] == '"':
+                            val = meta[1:-1]
+                            logger.debug("No metadata value for %s, setting custom column(%s) literally to %s."%(meta,custcol,val))
+                        else:
+                            logger.debug("No value for %s, skipping custom column(%s) update."%(meta,custcol))
+                            continue
+                    else:
+                        val = book['all_metadata'][meta]    
                     
                     if custcol not in custom_columns:
                         continue
@@ -1550,12 +1598,19 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                         if coldef['datatype'] in ('int','float'): # for favs, etc--site specific metadata.
                             if 'anthology_meta_list' in book and meta in book['anthology_meta_list']:
                                 # re-split list, strip commas, convert to floats, sum up.
-                                val = sum([ float(x.replace(",","")) for x in book['all_metadata'][meta].split(", ") ])
+                                val = sum([ float(x.replace(",","")) for x in val.split(", ") ])
                             else:
-                                val = unicode(book['all_metadata'][meta]).replace(",","")
+                                val = unicode(val).replace(",","")
                         else:
-                            val = book['all_metadata'][meta]
+                            val = val
                         if val != '':
+                            if coldef['datatype'] == 'bool':
+                                if val.lower() in ('t','true','1','yes','y'):
+                                    val = True
+                                elif val.lower() in ('f','false','0','no','n'):
+                                    val = False
+                                else:
+                                    val = None # for tri-state 'booleans'. Yes/No/Null
                             db.set_custom(book_id, val, label=label, commit=False)
 
                     if flag == 'a':
@@ -1569,8 +1624,8 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                         except:
                             pass
 
-                        if book['all_metadata'][meta]:
-                            vallist = [book['all_metadata'][meta]]
+                        if val:
+                            vallist.append(val)
                             
                         db.set_custom(book_id, ", ".join(vallist), label=label, commit=False)
 
@@ -1579,28 +1634,23 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         if 'authorUrl' in book['all_metadata']:
             authurls = book['all_metadata']['authorUrl'].split(", ")
             authorlist = [ a.replace('&',';') for a in book['author'] ]
-            if hasattr(db, 'new_api'): # new_api starts in calibre 1.0.0
-                authorids = db.new_api.get_item_ids('authors',authorlist)
-                authordata = db.new_api.author_data(authorids.values())
-                # print("\n\nauthorids:%s"%authorids)
-                # print("authordata:%s"%authordata)
+            authorids = db.new_api.get_item_ids('authors',authorlist)
+            authordata = db.new_api.author_data(authorids.values())
+            # print("\n\nauthorids:%s"%authorids)
+            # print("authordata:%s"%authordata)
 
-                author_id_to_link_map = dict()
-                for i, author in enumerate(authorlist):
-                    author_id_to_link_map[authorids[author]] = authurls[i]
+            author_id_to_link_map = dict()
+            for i, author in enumerate(authorlist):
+                author_id_to_link_map[authorids[author]] = authurls[i]
 
-                # print("author_id_to_link_map:%s\n\n"%author_id_to_link_map)
-                db.new_api.set_link_for_authors(author_id_to_link_map)
-            else:
-                # keep for pre-calibre 1.0.0
-                for i, auth in enumerate(authorlist):
-                    #print("===Update author url for %s to %s"%(auth,authurls[i]))
-                    autid=db.get_author_id(auth)
-                    db.set_link_field_for_author(autid, unicode(authurls[i]),
-                                             commit=False, notify=False)
+            # print("author_id_to_link_map:%s\n\n"%author_id_to_link_map)
+            db.new_api.set_link_for_authors(author_id_to_link_map)
+            
         db.commit()
 
         if 'Generate Cover' in self.gui.iactions and (book['added'] or not prefs['gcnewonly']):
+
+            #logger.debug("Do Generate Cover added:%s gcnewonly:%s"%(book['added'],prefs['gcnewonly']))
             
             # force a refresh if generating cover so complex composite
             # custom columns are current and correct
@@ -1632,15 +1682,39 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                 
             if not setting_name and book['all_metadata']['site'] in prefs['gc_site_settings']:
                 setting_name =  prefs['gc_site_settings'][book['all_metadata']['site']]
+                logger.debug("Generate Cover Setting from site(%s)"%setting_name)
 
             if not setting_name and 'Default' in prefs['gc_site_settings']:
                 setting_name =  prefs['gc_site_settings']['Default']
+                logger.debug("Generate Cover Setting from Default(%s)"%setting_name)
                 
             if setting_name:
                 logger.debug("Running Generate Cover with settings %s."%setting_name)
                 realmi = db.get_metadata(book_id, index_is_id=True)
                 gc_plugin.generate_cover_for_book(realmi,saved_setting_name=setting_name)
 
+                if prefs['gc_polish_cover'] and \
+                        options['fileform'] == "epub":
+                    # set cover inside epub from calibre's polish feature
+                    from calibre.ebooks.oeb.polish.main import polish, ALL_OPTS
+                    from calibre.utils.logging import Log
+                    from collections import namedtuple
+
+                    # Couldn't find a better way to get the cover path.
+                    cover_path = os.path.join(db.library_path, db.path(book_id, index_is_id=True), 'cover.jpg')
+                    data = {'cover':cover_path}
+                    #print("cover_path:%s"%cover_path)
+                    opts = ALL_OPTS.copy()
+                    opts.update(data)
+                    O = namedtuple('Options', ' '.join(ALL_OPTS.iterkeys()))
+                    opts = O(**opts)
+                
+                    log = Log(level=Log.DEBUG)
+                    outfile = db.format_abspath(book_id, formmapping[options['fileform']], index_is_id=True)
+                    #print("polish cover outfile:%s"%outfile)
+                    polish({outfile:outfile}, opts, log, logger.info)
+                
+
     def get_clean_reading_lists(self,lists):
         if lists == None or lists.strip() == "" :
             return []
@@ -1729,7 +1803,9 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         book['end'] = None
         book['comment'] = '' # note this is a comment on the d/l or update.
         book['url'] = ''
+        book['site'] = ''
         book['added'] = False
+        book['pubdate'] = None
         return book
     
     def convert_urls_to_books(self, urls):
@@ -1805,13 +1881,15 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             book['status'] = _('Not Found')
         else:
             # get normalized url or None.
-            book['url'] = self.is_good_downloader_url(url)
-            if book['url'] == None:
+            urlsitetuple = adapters.getNormalStoryURLSite(url)
+            if urlsitetuple == None:
                 book['url'] = url
                 book['comment'] = _("URL is not a valid story URL.")
                 book['good'] = False
                 book['icon']='dialog_error.png'
                 book['status'] = _('Bad URL')
+            else:
+                (book['url'],book['site'])=urlsitetuple
     
     def get_story_url(self, db, book_id=None, path=None):
         if book_id == None:
@@ -1893,9 +1971,9 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                         
             # fill from first of each if not already present:
             for k in ('pubdate', 'timestamp', 'updatedate'):
-                if k not in b: # not in this book?  Skip it.
+                if k not in b or not b[k]: # not in this book?  Skip it.
                     continue
-                if k not in book: # first is good enough for publisher.
+                if k not in book or not book[k]: # first is good enough for publisher.
                     book[k]=b[k]
 
                 # Do these even on first to get the all_metadata settings.
@@ -1916,11 +1994,12 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             for (k,v) in b['all_metadata'].iteritems():
                 #print("merge_meta_books v:%s k:%s"%(v,k))
                 if k in ('numChapters','numWords'):
-                    if k not in book['all_metadata']:
-                        book['all_metadata'][k] = b['all_metadata'][k]
-                    else:
-                        # lot of work for a simple add.
-                        book['all_metadata'][k] = unicode(int(book['all_metadata'][k].replace(',',''))+int(b['all_metadata'][k].replace(',','')))
+                    if k in b['all_metadata'] and b['all_metadata'][k]:
+                        if k not in book['all_metadata']:
+                            book['all_metadata'][k] = b['all_metadata'][k]
+                        else:
+                            # lot of work for a simple add.
+                            book['all_metadata'][k] = unicode(int(book['all_metadata'][k].replace(',',''))+int(b['all_metadata'][k].replace(',','')))
                 elif k in ('dateUpdated','datePublished','dateCreated',
                            'series','status','title'):
                     pass # handled above, below or skip these for now, not going to do anything with them.
@@ -1935,14 +2014,20 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                         # cust cols can convert back to numbers and
                         # add.
                         book['anthology_meta_list'][k]=True
-    
+
+        print("book['url']:%s"%book['url'])
+        configuration = get_ffdl_config(book['url'],fileform)
         if existingbook:
             book['title'] = deftitle = existingbook['title']
             book['comments'] = existingbook['comments']
         else:
             book['title'] = deftitle = book_list[0]['title']
-            book['comments'] = _("Anthology containing:")+"\n" + \
-                "\n".join([ _("%s by %s")%(b['title'],', '.join(b['author'])) for b in book_list ])
+            if len(book['author']) > 1:
+                book['comments'] = _("Anthology containing:")+"\n" + \
+                    "\n".join([ _("%s by %s")%(b['title'],', '.join(b['author'])) for b in book_list ])
+            else:
+                book['comments'] = _("Anthology containing:")+"\n" + \
+                    "\n".join([ b['title'] for b in book_list ])
             # book['all_metadata']['description']
         
             # if all same series, use series for name.  But only if all and not previous named
@@ -1954,7 +2039,6 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                         book['title'] = deftitle
                         break
             
-            configuration = get_ffdl_config(book['url'],fileform)
             logger.debug("anthology_title_pattern:%s"%configuration.getConfig('anthology_title_pattern'))
             if configuration.getConfig('anthology_title_pattern'):
                 tmplt = Template(configuration.getConfig('anthology_title_pattern'))
@@ -1970,7 +2054,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         for v in ['Completed','In-Progress']:
             if v in book['tags']:
                 book['tags'].remove(v)
-        book['tags'].append('Anthology')
+        book['tags'].extend(configuration.getConfigList('anthology_tags'))
         book['all_metadata']['anthology'] = "true"
         
         return book

calibre-plugin/jobs.py

@@ -4,7 +4,7 @@ from __future__ import (unicode_literals, division, absolute_import,
                         print_function)
 
 __license__   = 'GPL v3'
-__copyright__ = '2012, Jim Miller'
+__copyright__ = '2014, Jim Miller'
 __copyright__ = '2011, Grant Drake <grant.drake@gmail.com>'
 __docformat__ = 'restructuredtext en'
 
@@ -93,16 +93,13 @@ def do_download_worker(book_list, options,
         logger.info('Logfile for book ID %s (%s)'%(book_id, job._book['title']))
         logger.info(job.details)
 
+
+
         if count >= total:
-            # All done!  Output some lists for convenience of some users.
-            logger.info("Successfully downloaded:")
-            for book in book_list:
-                if book['good']:
-                    logger.info("%s %s"%(book['title'],book['url']))
-            logger.info("\nUnsuccessful:")
-            for book in book_list:
-                if not book['good']:
-                    logger.info("%s %s"%(book['title'],book['url']))
+            logger.info("\nSuccessful:\n%s\n"%("\n".join([book['url'] for book in 
+                                                      filter(lambda x: x['good'], book_list) ] ) ) )
+            logger.info("\nUnsuccessful:\n%s\n"%("\n".join([book['url'] for book in 
+                                                        filter(lambda x: not x['good'], book_list) ] ) ) )
             break
 
     server.close()
@@ -182,7 +179,7 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
 
             # update now handled by pre-populating the old images and
             # chapters in the adapter rather than merging epubs.
-            urlchaptercount = int(story.getMetadata('numChapters'))
+            urlchaptercount = int(story.getMetadata('numChapters').replace(',',''))
             (url,
              chaptercount,
              adapter.oldchapters,

calibre-plugin/prefs.py

@@ -25,6 +25,7 @@ default_prefs['rejecturls'] = ''
 default_prefs['rejectreasons'] = '''Sucked
 Boring
 Dup from another site'''
+default_prefs['reject_always'] = False
 
 default_prefs['updatemeta'] = True
 default_prefs['updatecover'] = False
@@ -34,6 +35,7 @@ default_prefs['suppressauthorsort'] = False
 default_prefs['suppresstitlesort'] = False
 default_prefs['mark'] = False
 default_prefs['showmarked'] = False
+default_prefs['autoconvert'] = False
 default_prefs['urlsfromclip'] = True
 default_prefs['updatedefault'] = True
 default_prefs['fileform'] = 'epub'
@@ -56,6 +58,7 @@ default_prefs['addtolistsonread'] = False
 default_prefs['gcnewonly'] = False
 default_prefs['gc_site_settings'] = {}
 default_prefs['allow_gc_from_ini'] = True
+default_prefs['gc_polish_cover'] = False
 
 default_prefs['countpagesstats'] = []
 

downloader.py

@@ -23,6 +23,7 @@ import getpass
 import string
 import ConfigParser
 from subprocess import call
+import pprint
 
 import logging
 if sys.version_info >= (2, 7):
@@ -226,9 +227,9 @@ def main(argv,
            except:
                options.update = False
                pass
-       
-       ## Check for include_images and absence of PIL, give warning.
-       if adapter.getConfig('include_images'):
+
+       ## Check for include_images without no_image_processing. In absence of PIL, give warning.
+       if adapter.getConfig('include_images') and not adapter.getConfig('no_image_processing'):
            try:
                from calibre.utils.magick import Image
                logging.debug("Using calibre.utils.magick")
@@ -270,31 +271,29 @@ def main(argv,
            elif chaptercount == 0:
                print "%s doesn't contain any recognizable chapters, probably from a different source.  Not updating." % (output_filename)
            else:
-               if not options.metaonly:
+               # update now handled by pre-populating the old
+               # images and chapters in the adapter rather than
+               # merging epubs.
+               (url,
+                chaptercount,
+                adapter.oldchapters,
+                adapter.oldimgs,
+                adapter.oldcover,
+                adapter.calibrebookmark,
+                adapter.logfile) = get_update_data(output_filename)
 
-                   # update now handled by pre-populating the old
-                   # images and chapters in the adapter rather than
-                   # merging epubs.
-                   (url,
-                    chaptercount,
-                    adapter.oldchapters,
-                    adapter.oldimgs,
-                    adapter.oldcover,
-                    adapter.calibrebookmark,
-                    adapter.logfile) = get_update_data(output_filename)
+               print "Do update - epub(%d) vs url(%d)" % (chaptercount, urlchaptercount)
 
-                   print "Do update - epub(%d) vs url(%d)" % (chaptercount, urlchaptercount)
+               if not (options.update and chaptercount == urlchaptercount) \
+                       and adapter.getConfig("do_update_hook"):
+                   chaptercount = adapter.hookForUpdates(chaptercount)
 
-                   if not (options.update and chaptercount == urlchaptercount) \
-                           and adapter.getConfig("do_update_hook"):
-                       chaptercount = adapter.hookForUpdates(chaptercount)
-
-                   writeStory(configuration,adapter,"epub")
+               writeStory(configuration,adapter,"epub")
                    
        else:
            # regular download
            if options.metaonly:
-               print adapter.getStoryMetadataOnly()
+               pprint.pprint(adapter.getStoryMetadataOnly().getAllMetadata())
            
            output_filename=writeStory(configuration,adapter,options.format,options.metaonly)
        

fanficdownloader/HtmlTagStack.py

@@ -0,0 +1,57 @@
+# coding: utf-8
+
+import re
+import codecs
+
+stack = []
+
+def get_end_tag(tag):
+    if len(tag) > 0 and tag.find(u'<') > -1 and tag.rfind(u'>') > -1:
+        return re.sub(r'.*<([^\ >]+).*', r'</\1>', tag)
+    return u''
+
+def get_tag_name(tag):
+    if len(tag) > 0 and tag.find(u'<') > -1 and tag.rfind(u'>') > -1:
+        return re.sub(r'</*([^\ >]+).*', r'\1', tag)
+    return u''
+
+def push(tag):
+    if len(tag) > 0 and tag.find(u'<') > -1 and tag.rfind(u'>') > -1:
+        stack.append(tag)
+
+def pop():
+    if len(stack) > 0:
+        return stack.pop()
+    return u''
+
+def pop_end_tag():
+    return unicode(get_end_tag(pop()))
+
+def spool_end():
+    html = u''
+    for tag in reversed(stack):
+        html += get_end_tag(tag)
+    return html
+
+def spool_start():
+    html = u''
+    for item in stack:
+        html += item
+    return html
+
+def has_elements():
+    return len(stack) > 0
+
+def get_last():
+    # t = pop()
+    # push(t)
+    # return t
+    if len(stack) > 0:
+        return stack[len(stack)-1]
+    return u''
+
+def flush():
+    del stack[:]
+
+def get_stack():
+    return stack

fanficdownloader/adapters/__init__.py

@@ -121,11 +121,23 @@ import adapter_simplyundeniablecom
 import adapter_scarheadnet
 import adapter_fictionpadcom
 import adapter_storiesonlinenet
+import adapter_trekiverseorg
+import adapter_literotica
+import adapter_voracity2eficcom
+import adapter_spikeluvercom
+import adapter_bloodshedversecom
+import adapter_nocturnallightnet
+import adapter_fanfichu
+import adapter_fanfictioncsodaidokhu
+import adapter_fictionmaniatv
+import adapter_bdsmgeschichten
+import adapter_tolkienfanfiction
+import adapter_themaplebookshelf
 
 ## This bit of complexity allows adapters to be added by just adding
 ## importing.  It eliminates the long if/else clauses we used to need
 ## to pick out the adapter.
-    
+
 ## List of registered site adapters.
 __class_list = []
 __domain_map = {}
@@ -144,6 +156,13 @@ for x in imports():
             __domain_map[site]=cls
 
 def getNormalStoryURL(url):
+    r = getNormalStoryURLSite(url)
+    if r:
+        return r[0]
+    else:
+        return None
+
+def getNormalStoryURLSite(url):
     if not getNormalStoryURL.__dummyconfig:
         getNormalStoryURL.__dummyconfig = Configuration("test1.com","EPUB")
     # pulling up an adapter is pretty low over-head.  If
@@ -151,10 +170,11 @@ def getNormalStoryURL(url):
     try:
         adapter = getAdapter(getNormalStoryURL.__dummyconfig,url)
         url = adapter.url
+        site = adapter.getSiteDomain()
         del adapter
-        return url
+        return (url,site)
     except:
-        return None;
+        return None
 
 # kludgey function static/singleton
 getNormalStoryURL.__dummyconfig = None
@@ -185,18 +205,20 @@ def getConfigSectionFor(url):
     (cls,fixedurl) = getClassFor(url)
     if cls:
         return cls.getConfigSection()
-    
+
     # No adapter found.
     raise exceptions.UnknownSite( url, [cls.getSiteDomain() for cls in __class_list] )
 
 def getClassFor(url):
     ## fix up leading protocol.
-    fixedurl = re.sub(r"(?i)^[htps]+[:/]+","http://",url.strip())
+    fixedurl = re.sub(r"(?i)^[htp]+(s?)[:/]+",r"http\1://",url.strip())
+    if fixedurl.startswith("//"):
+        fixedurl = "http:%s"%url
     if not fixedurl.startswith("http"):
         fixedurl = "http://%s"%url
     ## remove any trailing '#' locations.
     fixedurl = re.sub(r"#.*$","",fixedurl)
-    
+
     parsedUrl = up.urlparse(fixedurl)
     domain = parsedUrl.netloc.lower()
     if( domain != parsedUrl.netloc ):
@@ -207,17 +229,17 @@ def getClassFor(url):
         domain = domain.replace("www.","")
         #logger.debug("trying site:without www: "+domain)
         cls = getClassFromList(domain)
-        fixedurl = fixedurl.replace("http://www.","http://")
+        fixedurl = re.sub(r"^http(s?)://www\.",r"http\1://",fixedurl)
     if not cls:
         #logger.debug("trying site:www."+domain)
         cls = getClassFromList("www."+domain)
-        fixedurl = fixedurl.replace("http://","http://www.")
+        fixedurl = re.sub(r"^http(s?)://",r"http\1://www.",fixedurl)
 
     if cls:
         fixedurl = cls.stripURLParameters(fixedurl)
-    
+
     return (cls,fixedurl)
-    
+
 def getClassFromList(domain):
     try:
         return __domain_map[domain]

fanficdownloader/adapters/adapter_archiveofourownorg.py

@@ -77,14 +77,14 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
         # The site domain.  Does have www here, if it uses it.
         return 'archiveofourown.org'
 
-    @classmethod
+    @classmethod
     def getSiteExampleURLs(self):
         return "http://"+self.getSiteDomain()+"/works/123456 http://"+self.getSiteDomain()+"/collections/Some_Archive/works/123456 http://"+self.getSiteDomain()+"/works/123456/chapters/78901"
 
     def getSiteURLPattern(self):
         # 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 re.escape("http://")+re.escape(self.getSiteDomain())+r"(/collections/[^/]+)?/works/0*(?P<id>\d+)"
+        return r"https?://"+re.escape(self.getSiteDomain())+r"(/collections/[^/]+)?/works/0*(?P<id>\d+)"
         
     ## Login
     def needToLoginCheck(self, data):
@@ -145,10 +145,13 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
             
         except urllib2.HTTPError, e:
             if e.code == 404:
-                raise exceptions.StoryDoesNotExist(self.meta)
+                raise exceptions.StoryDoesNotExist(self.url)
             else:
                 raise e
-                
+
+        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)
@@ -162,34 +165,43 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
         # Now go hunting for all the meta data and the chapter list.
         
         ## Title
-        a = soup.find('a', href=re.compile(r"^/works/\d+$"))
+        a = soup.find('a', href=re.compile(r"/works/\d+$"))
         self.story.setMetadata('title',stripHTML(a))
 		
         # Find authorid and URL from... author url.
-        alist = soup.findAll('a', href=re.compile(r"^/users/\w+/pseuds/\w+"))
+        alist = soup.findAll('a', href=re.compile(r"/users/\w+/pseuds/\w+"))
         if len(alist) < 1: # ao3 allows for author 'Anonymous' with no author link.
             self.story.setMetadata('author','Anonymous')
             self.story.setMetadata('authorUrl','http://archiveofourown.org/')
             self.story.setMetadata('authorId','0')
         else:
             for a in alist:
-                self.story.addToList('authorId',a['href'].split('/')[2])
-                self.story.addToList('authorUrl','http://'+self.host+a['href'])
+                self.story.addToList('authorId',a['href'].split('/')[-1])
+                self.story.addToList('authorUrl',a['href'])
                 self.story.addToList('author',a.text)
 
+        newestChapter = None
+        self.newestChapterNum = None # save for comparing during update.
+        # Scan all chapters to find the oldest and newest, on AO3 it's
+        # possible for authors to insert new chapters out-of-order or
+        # change the dates of earlier ones by editing them--That WILL
+        # break epub update.
         # Find the chapters:
         chapters=soup.findAll('a', href=re.compile(r'/works/'+self.story.getMetadata('storyId')+"/chapters/\d+$"))
         self.story.setMetadata('numChapters',len(chapters))
         logger.debug("numChapters: (%s)"%self.story.getMetadata('numChapters'))
-        for x in range(0,len(chapters)):
-            # just in case there's tags, like <i> in chapter titles.
-            chapter=chapters[x]
-            if len(chapters)==1:
-                self.chapterUrls.append((self.story.getMetadata('title'),'http://'+self.host+chapter['href']+addurl))
-            else:
+        if len(chapters)==1:
+            self.chapterUrls.append((self.story.getMetadata('title'),'http://'+self.host+chapters[0]['href']+addurl))
+        else:
+            for index, chapter in enumerate(chapters):
+                # strip just in case there's tags, like <i> in chapter titles.
                 self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+chapter['href']+addurl))
-
-
+                # (2013-09-21)
+                date = stripHTML(chapter.findNext('span'))[1:-1]
+                chapterDate = makeDate(date,self.dateformat)
+                if newestChapter == None or chapterDate > newestChapter:
+                    newestChapter = chapterDate
+                    self.newestChapterNum = index
 
         a = metasoup.find('blockquote',{'class':'userstuff'})
         if a != None:
@@ -299,6 +311,12 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
                     self.setSeries(series_name, series_index)
                     self.story.setMetadata('seriesUrl',series_url)
 
+    def hookForUpdates(self,chaptercount):
+        if self.oldchapters and len(self.oldchapters) > self.newestChapterNum:
+            print("Existing epub has %s chapters\nNewest chapter is %s.  Discarding old chapters from there on."%(len(self.oldchapters), self.newestChapterNum+1))
+            self.oldchapters = self.oldchapters[:self.newestChapterNum]
+        return len(self.oldchapters)
+            
     # grab the text for an individual chapter.
     def getChapterText(self, url):
         logger.debug('Getting chapter text from: %s' % url)
@@ -306,25 +324,31 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
         chapter=bs.BeautifulSoup('<div class="story"></div>').find('div')
         data = self._fetchUrl(url)
         soup = bs.BeautifulSoup(data,selfClosingTags=('br','hr'))
-		
-        headnotes = soup.find('div', {'class' : "preface group"}).find('div', {'class' : "notes module"})
-        if headnotes != None:
-            headnotes = headnotes.find('blockquote', {'class' : "userstuff"})
+
+        exclude_notes=self.getConfigList('exclude_notes')
+
+        if 'authorheadnotes' not in exclude_notes:
+            headnotes = soup.find('div', {'class' : "preface group"}).find('div', {'class' : "notes module"})
             if headnotes != None:
-                chapter.append("<b>Author's Note:</b>")
-                chapter.append(headnotes)
+                headnotes = headnotes.find('blockquote', {'class' : "userstuff"})
+                if headnotes != None:
+                    chapter.append("<b>Author's Note:</b>")
+                    chapter.append(headnotes)
         
-        chapsumm = soup.find('div', {'id' : "summary"})
-        if chapsumm != None:
-            chapsumm = chapsumm.find('blockquote')
-            chapter.append("<b>Summary for the Chapter:</b>")
-            chapter.append(chapsumm)
-        chapnotes = soup.find('div', {'id' : "notes"})
-        if chapnotes != None:
-            chapnotes = chapnotes.find('blockquote')
+        if 'chaptersummary' not in exclude_notes:
+            chapsumm = soup.find('div', {'id' : "summary"})
+            if chapsumm != None:
+                chapsumm = chapsumm.find('blockquote')
+                chapter.append("<b>Summary for the Chapter:</b>")
+                chapter.append(chapsumm)
+                
+        if 'chapterheadnotes' not in exclude_notes:
+            chapnotes = soup.find('div', {'id' : "notes"})
             if chapnotes != None:
-                chapter.append("<b>Notes for the Chapter:</b>")
-                chapter.append(chapnotes)
+                chapnotes = chapnotes.find('blockquote')
+                if chapnotes != None:
+                    chapter.append("<b>Notes for the Chapter:</b>")
+                    chapter.append(chapnotes)
 		
         text = soup.find('div', {'class' : "userstuff module"})
         chtext = text.find('h3', {'class' : "landmark heading"})
@@ -332,17 +356,19 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
             chtext.extract()
         chapter.append(text)
 		
-        chapfoot = soup.find('div', {'class' : "end notes module", 'role' : "complementary"})
-        if chapfoot != None:
-            chapfoot = chapfoot.find('blockquote')
-            chapter.append("<b>Notes for the Chapter:</b>")
-            chapter.append(chapfoot)
+        if 'chapterfootnotes' not in exclude_notes:
+            chapfoot = soup.find('div', {'class' : "end notes module", 'role' : "complementary"})
+            if chapfoot != None:
+                chapfoot = chapfoot.find('blockquote')
+                chapter.append("<b>Notes for the Chapter:</b>")
+                chapter.append(chapfoot)
 		
-        footnotes = soup.find('div', {'id' : "work_endnotes"})
-        if footnotes != None:
-            footnotes = footnotes.find('blockquote')
-            chapter.append("<b>Author's Note:</b>")
-            chapter.append(footnotes)
+        if 'authorfootnotes' not in exclude_notes:
+            footnotes = soup.find('div', {'id' : "work_endnotes"})
+            if footnotes != None:
+                footnotes = footnotes.find('blockquote')
+                chapter.append("<b>Author's Note:</b>")
+                chapter.append(footnotes)
 			
         if None == soup:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)

fanficdownloader/adapters/adapter_bdsmgeschichten.py

@@ -0,0 +1,346 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2014 Fanficdownloader 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(self):
+        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

fanficdownloader/adapters/adapter_bloodshedversecom.py

@@ -0,0 +1,193 @@
+from datetime import timedelta
+import re
+import urllib2
+import urlparse
+
+from .. import BeautifulSoup
+from ..htmlcleanup import stripHTML
+
+from base_adapter import BaseSiteAdapter, makeDate
+from .. import exceptions
+
+
+def getClass():
+    return BloodshedverseComAdapter
+
+
+def _get_query_data(url):
+    components = urlparse.urlparse(url)
+    query_data = urlparse.parse_qs(components.query)
+    return dict((key, data[0]) for key, data in query_data.items())
+
+
+class BloodshedverseComAdapter(BaseSiteAdapter):
+    SITE_ABBREVIATION = 'bvc'
+    SITE_DOMAIN = 'bloodshedverse.com'
+
+    BASE_URL = 'http://' + SITE_DOMAIN + '/'
+    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'
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        query_data = urlparse.parse_qs(self.parsedUrl.query)
+        story_no = query_data['no'][0]
+
+        self.story.setMetadata('storyId', story_no)
+        self._setURL(self.READ_URL_TEMPLATE % story_no)
+        self.story.setMetadata('siteabbrev', self.SITE_ABBREVIATION)
+
+    def _customized_fetch_url(self, url, exception=None, parameters=None):
+        if exception:
+            try:
+                data = self._fetchUrl(url, parameters)
+            except urllib2.HTTPError:
+                raise exception(self.url)
+        # Just let self._fetchUrl throw the exception, don't catch and
+        # customize it.
+        else:
+            data = self._fetchUrl(url, parameters)
+
+        return BeautifulSoup.BeautifulSoup(data)
+
+    @staticmethod
+    def getSiteDomain():
+        return BloodshedverseComAdapter.SITE_DOMAIN
+
+    @classmethod
+    def getSiteExampleURLs(cls):
+        return cls.READ_URL_TEMPLATE % 1234
+
+    def getSiteURLPattern(self):
+        return re.escape(self.BASE_URL + 'stories.php?go=') + r'(read|chapters)\&no=\d+$'
+
+    # Override stripURLParameters so the "no" parameter won't get stripped
+    @classmethod
+    def stripURLParameters(cls, url):
+        return url
+
+    def extractChapterUrlsAndMetadata(self):
+        soup = self._customized_fetch_url(self.url)
+
+        # Since no 404 error code we have to raise the exception ourselves.
+        # A title that is just 'by' indicates that there is no author name
+        # and no story title available.
+        if stripHTML(soup.title) == 'by':
+            raise exceptions.StoryDoesNotExist(self.url)
+
+        for option in soup.find('select', {'name': 'chapter'}):
+            title = stripHTML(option)
+            url = self.READ_URL_TEMPLATE % option['value']
+            self.chapterUrls.append((title, url))
+
+        # Get the URL to the author's page and find the correct story entry to
+        # scrape the metadata
+        author_url = urlparse.urljoin(self.url, soup.find('a', {'class': 'headline'})['href'])
+        soup = self._customized_fetch_url(author_url)
+
+        story_no = self.story.getMetadata('storyId')
+        # Ignore first list_box div, it only contains the author information
+        for list_box in soup('div', {'class': 'list_box'})[1:]:
+            url = list_box.find('a', {'class': 'fictitle'})['href']
+            query_data = _get_query_data(url)
+
+            # Found the div containing the story's metadata; break the loop and
+            # parse the element
+            if query_data['no'] == story_no:
+                break
+        else:
+            raise exceptions.FailedToDownload(self.url)
+
+        title_anchor = list_box.find('a', {'class': 'fictitle'})
+        self.story.setMetadata('title', stripHTML(title_anchor))
+
+        author_anchor = title_anchor.findNextSibling('a')
+        self.story.setMetadata('author', stripHTML(author_anchor))
+        self.story.setMetadata('authorId', _get_query_data(author_anchor['href'])['who'])
+        self.story.setMetadata('authorUrl', urlparse.urljoin(self.url, author_anchor['href']))
+
+        list_review = list_box.find('div', {'class': 'list_review'})
+        reviews = stripHTML(list_review.a).split(' ', 1)[0]
+        self.story.setMetadata('reviews', reviews)
+
+        summary_div = list_box.find('div', {'class': 'list_summary'})
+        if not self.getConfig('keep_summary_html'):
+            summary = ''.join(summary_div(text=True))
+        else:
+            summary = self.utf8FromSoup(author_url, summary_div)
+
+        self.story.setMetadata('description', summary)
+
+        # I'm assuming this to be the category, not sure what else it could be
+        first_listinfo = list_box.find('div', {'class': 'list_info'})
+        self.story.addToList('category', stripHTML(first_listinfo.a))
+
+        for list_info in first_listinfo.findNextSiblings('div', {'class': 'list_info'}):
+            for b_tag in list_info('b'):
+                key = b_tag.string.strip(': ')
+                # Strip colons from the beginning, superfluous spaces and minus
+                # characters from the end, and possibly trailing commas from
+                # the warnings if only one is present
+                value = b_tag.nextSibling.string.strip(': -,')
+
+                if key == 'Genre':
+                    for genre in value.split(', '):
+                        # Ignore the "none" genre
+                        if not genre == 'none':
+                            self.story.addToList('genre', genre)
+
+                elif key == 'Rating':
+                    self.story.setMetadata('rating', value)
+
+                elif key == 'Complete':
+                    self.story.setMetadata('status', 'Completed' if value == 'Yes' else 'In-Progress')
+
+                elif key == 'Warning':
+                    for warning in value.split(', '):
+                        # The string here starts with ", " before the actual list
+                        # of values sometimes, so check for an empty warning
+                        # and ignore the "none" warning.
+                        if not warning or warning == 'none':
+                            continue
+
+                        self.story.addToList('warnings', warning)
+
+                elif key == 'Chapters':
+                    self.story.setMetadata('numChapters', int(value))
+
+                elif key == 'Words':
+                    # Apparently only numChapters need to be an integer for
+                    # some strange reason. Remove possible ',' characters as to
+                    # not confuse the codebase down the line
+                    self.story.setMetadata('numWords', value.replace(',', ''))
+
+                elif key == 'Started':
+                    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)
+                    self.story.setMetadata('dateUpdated', date)
+
+        if self.story.getMetadata('rating') == 'NC-17' and not (self.is_adult or self.getConfig('is_adult')):
+            raise exceptions.AdultCheckRequired(self.url)
+
+    def getChapterText(self, url):
+        soup = self._customized_fetch_url(url)
+        storytext_div = soup.find('div', {'class': 'storytext'})
+
+        if self.getConfig('strip_text_links'):
+            for anchor in storytext_div('a', {'class': 'FAtxtL'}):
+                navigable_string = BeautifulSoup.NavigableString(anchor.string)
+                anchor.replaceWith(navigable_string)
+
+        return self.utf8FromSoup(url, storytext_div)

fanficdownloader/adapters/adapter_buffynfaithnet.py

@@ -87,7 +87,7 @@ class BuffyNFaithNetAdapter(BaseSiteAdapter):
     
     def setHeader(self):
         "buffynfaith.net wants a Referer for images.  Used both above and below(after cookieproc added)"
-        self.opener.addheaders = [('Referer', 'http://'+self.getSiteDomain()+'/')]
+        self.opener.addheaders.append(('Referer', 'http://'+self.getSiteDomain()+'/'))
         
     @classmethod
     def getSiteExampleURLs(self):

fanficdownloader/adapters/adapter_darksolaceorg.py

@@ -182,6 +182,11 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
 
         # 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+')):
@@ -234,31 +239,28 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
                 self.setDescription(url,svalue)
                 #self.story.setMetadata('description',stripHTML(svalue))
 
-            if 'Rated' in label:
-                self.story.setMetadata('rating', value[:len(value)-2])
-
             if 'Word count' in label:
                 self.story.setMetadata('numWords', value)
 
             if 'Categories' in label:
-                cats = labelspan.parent.findAll('a',href=re.compile(r'categories.php\?catid=\d+'))
+                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:
-                for char in value.string.split(', '):
-                    if not 'None' in char:
-                        self.story.addToList('characters',char)
+                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:
-                for genre in value.string.split(', '):
-                    if not 'None' in genre:
-                        self.story.addToList('genre',genre)
+                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:
-                for warning in value.string.split(', '):
-                    if not 'None' in warning:
-                        self.story.addToList('warnings',warning)
+                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:

fanficdownloader/adapters/adapter_efpfanficnet.py

@@ -74,7 +74,8 @@ class EFPFanFicNet(BaseSiteAdapter):
 
     ## Login seems to be reasonably standard across eFiction sites.
     def needToLoginCheck(self, data):
-        if 'Fai il login e leggi la storia!' in data:
+        if( 'Fai il login e leggi la storia!' in data or
+            'Questa storia presenta contenuti non adatti ai minori' in data ):
             return True
         else:
             return False

fanficdownloader/adapters/adapter_fanfichu.py

@@ -0,0 +1,185 @@
+# coding=utf-8
+
+import re
+import urllib2
+import urlparse
+
+from .. import BeautifulSoup
+
+from base_adapter import BaseSiteAdapter, makeDate
+from .. import exceptions
+
+
+_SOURCE_CODE_ENCODING = 'utf-8'
+
+
+def getClass():
+    return FanficHuAdapter
+
+
+def _get_query_data(url):
+    components = urlparse.urlparse(url)
+    query_data = urlparse.parse_qs(components.query)
+    return dict((key, data[0]) for key, data in query_data.items())
+
+
+class FanficHuAdapter(BaseSiteAdapter):
+    SITE_ABBREVIATION = 'ffh'
+    SITE_DOMAIN = 'fanfic.hu'
+    SITE_LANGUAGE = 'Hungarian'
+
+    BASE_URL = 'http://' + SITE_DOMAIN + '/merengo/'
+    VIEW_STORY_URL_TEMPLATE = BASE_URL + 'viewstory.php?sid=%s'
+
+    DATE_FORMAT = '%m/%d/%Y'
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        query_data = urlparse.parse_qs(self.parsedUrl.query)
+        story_id = query_data['sid'][0]
+
+        self.story.setMetadata('storyId', story_id)
+        self._setURL(self.VIEW_STORY_URL_TEMPLATE % story_id)
+        self.story.setMetadata('siteabbrev', self.SITE_ABBREVIATION)
+        self.story.setMetadata('language', self.SITE_LANGUAGE)
+
+    def _customized_fetch_url(self, url, exception=None, parameters=None):
+        if exception:
+            try:
+                data = self._fetchUrl(url, parameters)
+            except urllib2.HTTPError:
+                raise exception(self.url)
+        # Just let self._fetchUrl throw the exception, don't catch and
+        # customize it.
+        else:
+            data = self._fetchUrl(url, parameters)
+
+        return BeautifulSoup.BeautifulSoup(data)
+
+    @staticmethod
+    def getSiteDomain():
+        return FanficHuAdapter.SITE_DOMAIN
+
+    @classmethod
+    def getSiteExampleURLs(cls):
+        return cls.VIEW_STORY_URL_TEMPLATE % 1234
+
+    def getSiteURLPattern(self):
+        return re.escape(self.VIEW_STORY_URL_TEMPLATE[:-2]) + r'\d+$'
+
+    def extractChapterUrlsAndMetadata(self):
+        soup = self._customized_fetch_url(self.url + '&i=1')
+
+        if soup.title.string.encode(_SOURCE_CODE_ENCODING).strip(' :') == 'írta':
+            raise exceptions.StoryDoesNotExist(self.url)
+
+        chapter_options = soup.find('form', action='viewstory.php').select('option')
+        # Remove redundant "Fejezetek" option
+        chapter_options.pop(0)
+
+        # If there is still more than one entry remove chapter overview entry
+        if len(chapter_options) > 1:
+            chapter_options.pop(0)
+
+        for option in chapter_options:
+            url = urlparse.urljoin(self.url, option['value'])
+            self.chapterUrls.append((option.string, url))
+
+        author_url = urlparse.urljoin(self.BASE_URL, soup.find('a', href=lambda href: href and href.startswith('viewuser.php?uid='))['href'])
+        soup = self._customized_fetch_url(author_url)
+
+        story_id = self.story.getMetadata('storyId')
+        for table in soup('table', {'class': 'mainnav'}):
+            title_anchor = table.find('span', {'class': 'storytitle'}).a
+            href = title_anchor['href']
+            if href.startswith('javascript:'):
+                href = href.rsplit(' ', 1)[1].strip("'")
+            query_data = _get_query_data(href)
+
+            if query_data['sid'] == story_id:
+                break
+        else:
+            # This should never happen, the story must be found on the author's
+            # page.
+            raise exceptions.FailedToDownload(self.url)
+
+        self.story.setMetadata('title', title_anchor.string)
+
+        rows = table('tr')
+
+        anchors = rows[0].div('a')
+        author_anchor = anchors[1]
+        query_data = _get_query_data(author_anchor['href'])
+        self.story.setMetadata('author', author_anchor.string)
+        self.story.setMetadata('authorId', query_data['uid'])
+        self.story.setMetadata('authorUrl', urlparse.urljoin(self.BASE_URL, author_anchor['href']))
+        self.story.setMetadata('reviews', anchors[3].string)
+
+        if self.getConfig('keep_summary_html'):
+            self.story.setMetadata('description', self.utf8FromSoup(author_url, rows[1].td))
+        else:
+            self.story.setMetadata('description', ''.join(rows[1].td(text=True)))
+
+        for row in rows[3:]:
+            index = 0
+            cells = row('td')
+
+            while index < len(cells):
+                cell = cells[index]
+                key = cell.b.string.encode(_SOURCE_CODE_ENCODING).strip(':')
+                try:
+                    value = cells[index+1].string.encode(_SOURCE_CODE_ENCODING)
+                except AttributeError:
+                    value = None
+
+                if key == 'Kategória':
+                    for anchor in cells[index+1]('a'):
+                        self.story.addToList('category', anchor.string)
+
+                elif key == 'Szereplõk':
+                    if cells[index+1].string:
+                        for name in cells[index+1].string.split(', '):
+                            self.story.addToList('character', name)
+
+                elif key == 'Korhatár':
+                    if value != 'nem korhatáros':
+                        self.story.setMetadata('rating', value)
+
+                elif key == 'Figyelmeztetések':
+                    for b_tag in cells[index+1]('b'):
+                        self.story.addToList('warnings', b_tag.string)
+
+                elif key == 'Jellemzõk':
+                    for genre in cells[index+1].string.split(', '):
+                        self.story.addToList('genre', genre)
+
+                elif key == 'Fejezetek':
+                    self.story.setMetadata('numChapters', int(value))
+
+                elif key == 'Megjelenés':
+                    self.story.setMetadata('datePublished', makeDate(value, self.DATE_FORMAT))
+
+                elif key == 'Frissítés':
+                    self.story.setMetadata('dateUpdated', makeDate(value, self.DATE_FORMAT))
+
+                elif key == 'Szavak':
+                    self.story.setMetadata('numWords', value)
+
+                elif key == 'Befejezett':
+                    self.story.setMetadata('status', 'Completed' if value == 'Nem' else 'In-Progress')
+
+                index += 2
+
+        if self.story.getMetadata('rating') == '18':
+            if not (self.is_adult or self.getConfig('is_adult')):
+                raise exceptions.AdultCheckRequired(self.url)
+
+    def getChapterText(self, url):
+        soup = self._customized_fetch_url(url)
+        story_cell = soup.find('form', action='viewstory.php').parent.parent
+
+        for div in story_cell('div'):
+            div.extract()
+
+        return self.utf8FromSoup(url, story_cell)

fanficdownloader/adapters/adapter_fanfictioncsodaidokhu.py

@@ -0,0 +1,218 @@
+# coding=utf-8
+
+import re
+import urllib2
+import urlparse
+
+from .. import BeautifulSoup
+
+from base_adapter import BaseSiteAdapter, makeDate
+from .. import exceptions
+
+
+_SOURCE_CODE_ENCODING = 'utf-8'
+
+
+def getClass():
+    return FanfictionCsodaidokHuAdapter
+
+
+def _get_query_data(url):
+    components = urlparse.urlparse(url)
+    query_data = urlparse.parse_qs(components.query)
+    return dict((key, data[0]) for key, data in query_data.items())
+
+
+# yields Tag _and_ NavigableString siblings from the given tag. The
+# BeautifulSoup findNextSiblings() method for some reasons only returns either
+# NavigableStrings _or_ Tag objects, not both.
+def _yield_next_siblings(tag):
+    sibling = tag.nextSibling
+    while sibling:
+        yield sibling
+        sibling = sibling.nextSibling
+
+
+class FanfictionCsodaidokHuAdapter(BaseSiteAdapter):
+    _SITE_DOMAIN = 'fanfiction.csodaidok.hu'
+    _BASE_URL = 'http://' + _SITE_DOMAIN + '/'
+    _VIEW_STORY_URL_TEMPLATE = _BASE_URL + 'viewstory.php?sid=%s'
+    _VIEW_CHAPTER_URL_TEMPLATE = _VIEW_STORY_URL_TEMPLATE + '&chapter=%s'
+
+    _STORY_DOES_NOT_EXIST_PAGE_TITLE = 'Cím:  Szerző:'
+    _DATE_FORMAT = '%Y.%m.%d'
+    _SITE_LANGUAGE = 'Hungarian'
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        query_data = urlparse.parse_qs(self.parsedUrl.query)
+        story_id = query_data['sid'][0]
+
+        self.story.setMetadata('storyId', story_id)
+        self._setURL(self._VIEW_STORY_URL_TEMPLATE % story_id)
+        self.story.setMetadata('siteabbrev', self._SITE_DOMAIN)
+        self.story.setMetadata('language', self._SITE_LANGUAGE)
+
+    def _customized_fetch_url(self, url, exception=None, parameters=None):
+        if exception:
+            try:
+                data = self._fetchUrl(url, parameters)
+            except urllib2.HTTPError:
+                raise exception(self.url)
+        # Just let self._fetchUrl throw the exception, don't catch and
+        # customize it.
+        else:
+            data = self._fetchUrl(url, parameters)
+
+        return BeautifulSoup.BeautifulSoup(data)
+
+    @staticmethod
+    def getSiteDomain():
+        return FanfictionCsodaidokHuAdapter._SITE_DOMAIN
+
+    @classmethod
+    def getSiteExampleURLs(cls):
+        return cls._VIEW_STORY_URL_TEMPLATE % 1234
+
+    def getSiteURLPattern(self):
+        return re.escape(self._VIEW_STORY_URL_TEMPLATE[:-2]) + r'\d+$'
+
+    def extractChapterUrlsAndMetadata(self):
+        soup = self._customized_fetch_url(self.url + '&chapter=1')
+
+        element = soup.find('div', id='pagetitle')
+        page_title = ''.join(element(text=True)).encode(_SOURCE_CODE_ENCODING)
+        if page_title == self._STORY_DOES_NOT_EXIST_PAGE_TITLE:
+            raise exceptions.StoryDoesNotExist(self.url)
+
+        author_url = urlparse.urljoin(self.url, element.a['href'])
+
+        story_id = self.story.getMetadata('storyId')
+        element = soup.find('select', {'name': 'chapter'})
+        if element:
+            for option in element('option'):
+                title = option.string
+                url = self._VIEW_CHAPTER_URL_TEMPLATE % (story_id, option['value'])
+                self.chapterUrls.append((title, url))
+
+        soup = self._customized_fetch_url(author_url)
+        story_id = self.story.getMetadata('storyId')
+
+        for listbox_div in soup('div', {'class': lambda klass: klass and 'listbox' in klass}):
+            a = listbox_div.div.a
+            if not a['href'].startswith('viewstory.php?sid='):
+                continue
+
+            query_data = _get_query_data(a['href'])
+            if query_data['sid'] == story_id:
+                break
+        else:
+            raise exceptions.FailedToDownload(self.url)
+
+        title = ''.join(a(text=True))
+        self.story.setMetadata('title', title)
+        if not self.chapterUrls:
+            self.chapterUrls.append((title, self.url))
+
+        element = a.findNextSibling('a')
+        self.story.setMetadata('author', element.string)
+        query_data = _get_query_data(element['href'])
+        self.story.setMetadata('authorId', query_data['uid'])
+        self.story.setMetadata('authorUrl', author_url)
+
+        element = element.findNextSibling('span')
+        rating = element.nextSibling.strip(' [')
+
+        if rating.encode(_SOURCE_CODE_ENCODING) != 'Korhatár nélkül':
+            self.story.setMetadata('rating', rating)
+
+        if rating == '18':
+            raise exceptions.AdultCheckRequired(self.url)
+
+        element = element.findNextSiblings('a')[1]
+        self.story.setMetadata('reviews', element.string)
+
+        sections = listbox_div('div', {'class': lambda klass: klass and klass in ['content', 'tail']})
+        for section in sections:
+            for element in section('span', {'class': 'classification'}):
+                key = element.string.encode(_SOURCE_CODE_ENCODING).strip(' :')
+                try:
+                    value = element.nextSibling.string.encode(_SOURCE_CODE_ENCODING).strip()
+                except AttributeError:
+                    value = None
+
+                if key == 'Tartalom':
+                    contents = []
+                    keep_summary_html = self.getConfig('keep_summary_html')
+
+                    for sibling in _yield_next_siblings(element):
+                        if isinstance(sibling, BeautifulSoup.Tag):
+                            if sibling.name == 'span' and sibling.get('class', None) == 'classification':
+                                break
+
+                            if keep_summary_html:
+                                contents.append(self.utf8FromSoup(author_url, sibling))
+                            else:
+                                contents.append(''.join(sibling(text=True)))
+                        else:
+                            contents.append(sibling)
+                    self.story.setMetadata('description', ''.join(contents))
+
+                elif key == 'Kategória':
+                    for sibling in element.findNextSiblings(['a', 'span']):
+                        if sibling.name == 'span':
+                            break
+
+                        self.story.addToList('category', sibling.string)
+
+                elif key == 'Szereplők':
+                    for name in value.split(', '):
+                        self.story.addToList('characters', name)
+
+                elif key == 'Műfaj':
+                    if value != 'Nincs':
+                        self.story.setMetadata('genre', value)
+
+                elif key == 'Figyelmeztetés':
+                    if value != 'Nincs':
+                        for warning in value.split(', '):
+                            self.story.addToList('warnings', warning)
+
+                elif key == 'Kihívás':
+                    if value != 'Nincs':
+                        self.story.setMetadata('challenge', value)
+
+                elif key == 'Sorozat':
+                    if value != 'Nincs':
+                        self.story.setMetadata('series', value)
+
+                elif key == 'Fejezetek':
+                    self.story.setMetadata('numChapters', int(value))
+
+                elif key == 'Befejezett':
+                    self.story.setMetadata('status', 'Completed' if value == 'Nem' else 'In-Progress')
+
+                elif key == 'Szavak száma':
+                    self.story.setMetadata('numWords', value)
+
+                elif key == 'Feltöltve':
+                    self.story.setMetadata('datePublished', makeDate(value, self._DATE_FORMAT))
+
+                elif key == 'Frissítve':
+                    self.story.setMetadata('dateUpdated', makeDate(value, self._DATE_FORMAT))
+
+    def getChapterText(self, url):
+        soup = self._customized_fetch_url(url)
+        contents = []
+
+        notes_div = soup.find('div', id='notes')
+        if notes_div:
+            contents.append(self.utf8FromSoup(url, notes_div))
+            story_div = notes_div.findNextSibling('div')
+        else:
+            element = soup.find('div', {'class': 'jumpmenu'})
+            story_div = element.findNextSibling('div')
+
+        contents.append(self.utf8FromSoup(url, story_div.span))
+        return ''.join(contents)

fanficdownloader/adapters/adapter_fanfictionnet.py

@@ -57,6 +57,8 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
             ## accept m(mobile)url, but use www.
             self.origurl = self.origurl.replace("https://m.","https://www.")
 
+        self.opener.addheaders.append(('Referer',self.origurl))
+
     @staticmethod
     def getSiteDomain():
         return 'www.fanfiction.net'
@@ -72,6 +74,13 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
     def getSiteURLPattern(self):
         return r"https?://(www|m)?\.fanfiction\.net/s/\d+(/\d+)?(/|/[^/]+)?/?$"
 
+    def _fetchUrl(self,url):
+        time.sleep(1.0) ## ffnet(and, I assume, fpcom) tends to fail
+                        ## more if hit too fast.  This is in
+                        ## additional to what ever the
+                        ## slow_down_sleep_time setting is.
+        return BaseSiteAdapter._fetchUrl(self,url)
+
     def extractChapterUrlsAndMetadata(self):
 
         # fetch the chapter.  From that we will get almost all the
@@ -98,28 +107,31 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         if "not found. Please check to see you are not using an outdated url." in data:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  'Chapter not found. Please check to see you are not using an outdated url.'" % url)
 
-        try:
-            # rather nasty way to check for a newer chapter.  ffnet has a
-            # tendency to send out update notices in email before all
-            # their servers are showing the update on the first chapter.
+        if self.getConfig('check_next_chapter'):
             try:
-                chapcount = len(soup.find('select', { 'name' : 'chapter' } ).findAll('option'))
-            # get chapter part of url.
+                ## ffnet used to have a tendency to send out update
+                ## notices in email before all their servers were
+                ## showing the update on the first chapter.  It
+                ## generates another server request and doesn't seem
+                ## to be needed lately, so now default it to off.
+                try:
+                    chapcount = len(soup.find('select', { 'name' : 'chapter' } ).findAll('option'))
+                # get chapter part of url.
+                except:
+                    chapcount = 1
+                chapter = url.split('/',)[5]
+                tryurl = "https://%s/s/%s/%d/"%(self.getSiteDomain(),
+                                                self.story.getMetadata('storyId'),
+                                                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:
+                    logger.debug('=======Found newer chapter: %s' % tryurl)
+                    soup = bs.BeautifulSoup(newdata)
             except:
-                chapcount = 1
-            chapter = url.split('/',)[5]
-            tryurl = "https://%s/s/%s/%d/"%(self.getSiteDomain(),
-                                            self.story.getMetadata('storyId'),
-                                            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:
-                logger.debug('=======Found newer chapter: %s' % tryurl)
-                soup = bs.BeautifulSoup(newdata)
-        except:
-            pass
-        
+                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])
@@ -157,7 +169,7 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
                 
                 
             
-        a = soup.find('a', href='http://www.fictionratings.com/')
+        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:]
@@ -275,7 +287,7 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         return
 
     def getChapterText(self, url):
-        time.sleep(5.0) ## ffnet(and, I assume, fpcom) tends to fail
+        time.sleep(4.0) ## ffnet(and, I assume, fpcom) tends to fail
                         ## more if hit too fast.  This is in
                         ## additional to what ever the
                         ## slow_down_sleep_time setting is.

fanficdownloader/adapters/adapter_fictionmaniatv.py

@@ -0,0 +1,178 @@
+import re
+import urllib2
+import urlparse
+
+from .. import BeautifulSoup
+from ..BeautifulSoup import NavigableString
+
+from base_adapter import BaseSiteAdapter, makeDate
+from .. import exceptions
+
+
+def getClass():
+    return FictionManiaTVAdapter
+
+
+def _get_query_data(url):
+    components = urlparse.urlparse(url)
+    query_data = urlparse.parse_qs(components.query)
+    return dict((key, data[0]) for key, data in query_data.items())
+
+# yields Tag _and_ NavigableString siblings from the given tag. The
+# BeautifulSoup findNextSiblings() method for some reasons only returns either
+# NavigableStrings _or_ Tag objects, not both.
+def _yield_next_siblings(tag):
+    sibling = tag.nextSibling
+    while sibling:
+        yield sibling
+        sibling = sibling.nextSibling
+
+
+class FictionManiaTVAdapter(BaseSiteAdapter):
+    SITE_ABBREVIATION = 'fmt'
+    SITE_DOMAIN = 'fictionmania.tv'
+
+    BASE_URL = 'http://' + SITE_DOMAIN + '/stories/'
+    READ_TEXT_STORY_URL_TEMPLATE = BASE_URL + 'readtextstory.html?storyID=%s'
+    DETAILS_URL_TEMPLATE = BASE_URL + 'details.html?storyID=%s'
+
+    DATETIME_FORMAT = '%m/%d/%Y'
+    ALTERNATIVE_DATETIME_FORMAT = '%m/%d/%y'
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        query_data = urlparse.parse_qs(self.parsedUrl.query)
+        story_id = query_data['storyID'][0]
+
+        self.story.setMetadata('storyId', story_id)
+        self._setURL(self.READ_TEXT_STORY_URL_TEMPLATE % story_id)
+        self.story.setMetadata('siteabbrev', self.SITE_ABBREVIATION)
+
+        # Always single chapters, probably should use the Anthology feature to
+        # merge chapters of a story
+        self.story.setMetadata('numChapters', 1)
+
+    def _customized_fetch_url(self, url, exception=None, parameters=None):
+        if exception:
+            try:
+                data = self._fetchUrl(url, parameters)
+            except urllib2.HTTPError:
+                raise exception(self.url)
+        # Just let self._fetchUrl throw the exception, don't catch and
+        # customize it.
+        else:
+            data = self._fetchUrl(url, parameters)
+
+        return BeautifulSoup.BeautifulSoup(data)
+
+    @staticmethod
+    def getSiteDomain():
+        return FictionManiaTVAdapter.SITE_DOMAIN
+
+    @classmethod
+    def getSiteExampleURLs(cls):
+        return cls.READ_TEXT_STORY_URL_TEMPLATE % 1234
+
+    def getSiteURLPattern(self):
+        return re.escape(self.BASE_URL) + '(readtextstory|details)\.html\?storyID=\d+$'
+
+    def extractChapterUrlsAndMetadata(self):
+        url = self.DETAILS_URL_TEMPLATE % self.story.getMetadata('storyId')
+        soup = self._customized_fetch_url(url)
+
+        keep_summary_html = self.getConfig('keep_summary_html')
+        for row in soup.find('table')('tr'):
+            cells = row('td')
+            key = cells[0].b.string.strip(':')
+            try:
+                value = cells[1].string
+            except AttributeError:
+                value = None
+
+            if key == 'Story Name-Title':
+                self.story.setMetadata('title', value)
+                self.chapterUrls.append((value, self.url))
+
+            elif key == 'File Name':
+                self.story.setMetadata('fileName', value)
+
+            elif key == 'File Size':
+                self.story.setMetadata('fileSize', value)
+
+            elif key == 'Author':
+                element = cells[1].a
+                self.story.setMetadata('author', element.string)
+                query_data = _get_query_data(element['href'])
+                self.story.setMetadata('authorId', query_data['word'])
+                self.story.setMetadata('authorUrl', urlparse.urljoin(url, element['href']))
+
+            elif key == 'Date Added':
+                try:
+                    date = makeDate(value, self.DATETIME_FORMAT)
+                except ValueError:
+                    date = makeDate(value, self.ALTERNATIVE_DATETIME_FORMAT)
+                self.story.setMetadata('datePublished', date)
+
+            elif key == 'Old Name':
+                self.story.setMetadata('oldName', value)
+
+            elif key == 'New Name':
+                self.story.setMetadata('newName', value)
+
+            elif key == 'Other Key Names':
+                for name in value.split(', '):
+                    self.story.addToList('characters', name)
+
+            # I have no clue how the rating system works, if you are reading
+            # transgender fanfiction, you are probably an adult.
+            elif key == 'Rating':
+                self.story.setMetadata('rating', value)
+
+            elif key == 'Complete':
+                self.story.setMetadata('status', 'Complete' if value == 'Complete' else 'In-Progress')
+
+            elif key == 'Categories':
+                for element in cells[1]('a'):
+                    self.story.addToList('category', element.string)
+
+            elif key == 'Key Words':
+                for element in cells[1]('a'):
+                    self.story.addToList('keyWords', element.string)
+
+            elif key == 'Main Characters Age':
+                element = cells[1].a
+                self.story.setMetadata('mainCharactersAge', element.string)
+
+            elif key == 'Synopsis':
+                element = cells[1]
+
+                # Replace td with div to avoid possible strange formatting in
+                # the ebook later on
+                element.name = 'div'
+
+                if keep_summary_html:
+                    self.story.setMetadata('description', unicode(element))
+                else:
+                    self.story.setMetadata('description', ''.join(element(text=True)))
+
+            elif key == 'Reads':
+                self.story.setMetadata('readings', value)
+
+    def getChapterText(self, url):
+        soup = self._customized_fetch_url(url)
+        element = soup.find('pre')
+        element.name = 'div'
+
+        # The story's content is contained in a <pre> tag, probably taken 1:1
+        # from the source text file. A simple replacement of all newline
+        # characters with a break line tag should take care of formatting.
+
+        # 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 />')
+
+        if self.getConfig('non_breaking_spaces'):
+            content = content.replace(' ', '&nbsp;')
+        return content

fanficdownloader/adapters/adapter_fictionpadcom.py

@@ -133,6 +133,7 @@ class FictionPadSiteAdapter(BaseSiteAdapter):
         author = tables['users'][0]
         story = tables['stories'][0]
         story_ver = tables['story_versions'][0]
+        print("story:%s"%story)
         
         self.story.setMetadata('authorId',author['id'])
         self.story.setMetadata('author',author['display_name'])
@@ -151,7 +152,8 @@ class FictionPadSiteAdapter(BaseSiteAdapter):
         self.story.setMetadata('comments',story['comments_count'])
         self.story.setMetadata('views',story['views_count'])
         self.story.setMetadata('likes',int(story['likes'])) # no idea why they floated these.
-        self.story.setMetadata('dislikes',int(story['dislikes']))
+        if 'dislikes' in story:
+            self.story.setMetadata('dislikes',int(story['dislikes']))
 
         if story_ver['is_complete']:
             self.story.setMetadata('status', 'Completed')

fanficdownloader/adapters/adapter_fictionpresscom.py

@@ -41,10 +41,10 @@ class FictionPressComSiteAdapter(FanFictionNetSiteAdapter):
 
     @classmethod
     def getSiteExampleURLs(self):
-        return "http://www.fictionpress.com/s/1234/1/ http://www.fictionpress.com/s/1234/12/ http://www.fictionpress.com/s/1234/1/Story_Title http://m.fictionpress.com/s/1234/1/"
+        return "https://www.fictionpress.com/s/1234/1/ https://www.fictionpress.com/s/1234/12/ http://www.fictionpress.com/s/1234/1/Story_Title http://m.fictionpress.com/s/1234/1/"
 
     def getSiteURLPattern(self):
-        return r"http://(www|m)?\.fictionpress\.com/s/\d+(/\d+)?(/|/[a-zA-Z0-9_-]+)?/?$"
+        return r"https?://(www|m)?\.fictionpress\.com/s/\d+(/\d+)?(/|/[a-zA-Z0-9_-]+)?/?$"
 
 def getClass():
     return FictionPressComSiteAdapter

fanficdownloader/adapters/adapter_fimfictionnet.py

@@ -59,7 +59,7 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
         return "http://www.fimfiction.net/story/1234/story-title-here http://www.fimfiction.net/story/1234/ http://www.fimfiction.com/story/1234/1/ http://mobile.fimfiction.net/story/1234/1/story-title-here/chapter-title-here"
 
     def getSiteURLPattern(self):
-        return r"http://(www|mobile)\.fimfiction\.(net|com)/story/\d+/?.*"
+        return r"https?://(www|mobile)\.fimfiction\.(net|com)/story/\d+/?.*"
         
     def extractChapterUrlsAndMetadata(self):
         
@@ -85,7 +85,7 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
             
             # Unfortunately, we still need to load the story index
             # page to parse the characters.  And chapters, now, too.
-            data = self._fetchUrl(self.url)
+            data = self.do_fix_blockquotes(self._fetchUrl(self.url))
             soup = bs.BeautifulSoup(data)
         except urllib2.HTTPError, e:
             if e.code == 404:
@@ -101,7 +101,7 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
         # if "/images/missing_story.png" in data:
         #     raise exceptions.StoryDoesNotExist(self.url)
         
-        if "This story has been marked as having adult content." in data:
+        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:
@@ -186,9 +186,9 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
             self.setCoverImage(self.url,coverurl)
 
         # fimf has started including extra stuff inside the description div.
-        descdivstr = "%s"%soup.find("div", {"class":"description"})
-        hrstr="<hr />"
-        descdivstr = '<div class="description">'+descdivstr[descdivstr.index(hrstr)+len(hrstr):]
+        descdivstr = u"%s"%soup.find("div", {"class":"description"})
+        hrstr=u"<hr />"
+        descdivstr = u'<div class="description">'+descdivstr[descdivstr.index(hrstr)+len(hrstr):]
         self.setDescription(self.url,descdivstr)
 
         # Can't trust dates from API anymore I'm told.
@@ -249,22 +249,55 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
                     value = unicode(value)
                 self.story.setMetadata(metakey, value)
 
-        rawGroupList = soup.find('ul', {'id':'story_group_list'})
-        if rawGroupList is not None:
-            for groupName in rawGroupList.findAll('a', {'href':re.compile('^/group/')}):
+        ## Groups and sequels code from FaceDeer
+        allGroupLists = soup.findAll('ul', {'id':'story_group_list'})
+        for groupList in allGroupLists:
+            for groupName in groupList.findAll('a', {'href':re.compile('^/group/')}):
+                self.story.addToList("groupsUrl", 'http://'+self.host+groupName["href"]) 
                 self.story.addToList("groups",stripHTML(groupName).replace(',', ';'))
-            
+
+        sequelStoryHeader = soup.find('h1', {'class':'header-stories'}, text="Sequels")
+        if not sequelStoryHeader == None:
+            sequelContainer = sequelStoryHeader.parent.parent
+            for sequel in sequelContainer.findAll('a', {'class':'story_link'}):
+                self.story.addToList("sequelsUrl", 'http://'+self.host+sequel["href"]) 
+                self.story.addToList("sequels", stripHTML(sequel).replace(',', ';'))
+                
+        #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.
+        try:
+            description = soup.find('div', {'class':'description'})
+            firstHR = description.find("hr")
+            nextSib = firstHR.nextSibling
+            if "This story is a sequel to" in nextSib.string:
+                link = nextSib.nextSibling
+                if link.name == "a":
+                    self.story.setMetadata("prequelUrl", 'http://'+self.host+link["href"])
+                    self.story.setMetadata("prequel", stripHTML(link))
+        except:
+            pass
+        
     def hookForUpdates(self,chaptercount):
         if self.oldchapters and len(self.oldchapters) > self.newestChapterNum:
             print("Existing epub has %s chapters\nNewest chapter is %s.  Discarding old chapters from there on."%(len(self.oldchapters), self.newestChapterNum+1))
             self.oldchapters = self.oldchapters[:self.newestChapterNum]
         return len(self.oldchapters)
-            
+
+    def do_fix_blockquotes(self,data):
+        if self.getConfig('fix_fimf_blockquotes'):
+            # <p class="double"><blockquote>
+            # </blockquote></p>
+            # include > in re groups so there's always something in the group.
+            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)
-        
-        soup = bs.BeautifulSoup(self._fetchUrl(url),selfClosingTags=('br','hr')).find('div', {'class' : 'chapter_content'})
+
+        data = self.do_fix_blockquotes(self._fetchUrl(url))
+        soup = bs.BeautifulSoup(data,selfClosingTags=('br','hr')).find('div', {'class' : 'chapter_content'})
         if soup == None:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
         return self.utf8FromSoup(url,soup)

fanficdownloader/adapters/adapter_finestoriescom.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2012 Fanficdownloader team
+# Copyright 2013 Fanficdownloader team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -37,11 +37,6 @@ class FineStoriesComAdapter(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
@@ -51,7 +46,6 @@ class FineStoriesComAdapter(BaseSiteAdapter):
         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'))
         

fanficdownloader/adapters/adapter_hpfanficarchivecom.py

@@ -128,23 +128,22 @@ class HPFanficArchiveComAdapter(BaseSiteAdapter):
         # <span class="label">Rated:</span> NC-17<br /> etc
         labels = soup.findAll('span',{'class':'label'})
         for labelspan in labels:
-            value = labelspan.nextSibling
+            val = labelspan.nextSibling
+            value = unicode('')
+            while val and not defaultGetattr(val,'class') == 'label':
+                value += unicode(val)
+                val = val.nextSibling
             label = labelspan.string
+            #print("label:%s\nvalue:%s"%(label,value))
 
             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))
+                self.setDescription(url,value)
 
             if 'Rated' in label:
-                self.story.setMetadata('rating', value)
+                self.story.setMetadata('rating', stripHTML(value))
 
             if 'Word count' in label:
-                self.story.setMetadata('numWords', value)
+                self.story.setMetadata('numWords', stripHTML(value))
 
             if 'Categories' in label:
                 cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
@@ -161,13 +160,18 @@ class HPFanficArchiveComAdapter(BaseSiteAdapter):
                 for genre in genres:
                     self.story.addToList('genre',genre.string)
 
+            if 'Pairing' in label:
+                ships = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=4'))
+                for ship in ships:
+                    self.story.addToList('ships',ship.string)
+
             if 'Warnings' in label:
                 warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')) # XXX
                 for warning in warnings:
                     self.story.addToList('warnings',warning.string)
 
             if 'Completed' in label:
-                if 'Yes' in value:
+                if 'Yes' in stripHTML(value):
                     self.story.setMetadata('status', 'Completed')
                 else:
                     self.story.setMetadata('status', 'In-Progress')

fanficdownloader/adapters/adapter_literotica.py

@@ -0,0 +1,257 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2013 Fanficdownloader 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 ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter, makeDate
+
+class LiteroticaSiteAdapter(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','litero')
+
+        # normalize to first chapter.  Not sure if they ever have more than 2 digits.
+        storyId = self.parsedUrl.path.split('/',)[2]
+        # replace later chapters with first chapter but don't remove numbers
+        # from the URL that disambiguate stories with the same title.
+        storyId = re.sub("-ch-?\d\d", "", storyId)
+        self.story.setMetadata('storyId', storyId)
+
+        ## accept m(mobile)url, but use www.
+        url = re.sub("^(www|german|spanish|french|dutch|italian|romanian|portuguese|other)\.i",
+                              "\1",
+                              url)
+
+        ## strip ?page=...
+        url = re.sub("\?page=.*$", "", url)
+
+        ## 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 = '%m/%d/%y'
+
+    @staticmethod
+    def getSiteDomain():
+        return 'literotica.com'
+
+    @classmethod
+    def getAcceptDomains(cls):
+        return ['www.literotica.com',
+                'www.i.literotica.com',
+                'german.literotica.com',
+                'german.i.literotica.com',
+                'spanish.literotica.com',
+                'spanish.i.literotica.com',
+                'french.literotica.com',
+                'french.i.literotica.com',
+                'dutch.literotica.com',
+                'dutch.i.literotica.com',
+                'italian.literotica.com',
+                'italian.i.literotica.com',
+                'romanian.literotica.com',
+                'romanian.i.literotica.com',
+                'portuguese.literotica.com',
+                'portuguese.i.literotica.com',
+                'other.literotica.com',
+                'other.i.literotica.com']
+
+    @classmethod
+    def getSiteExampleURLs(self):
+        return "http://www.literotica.com/s/story-title https://www.literotica.com/s/story-title http://portuguese.literotica.com/s/story-title http://german.literotica.com/s/story-title"
+
+    def getSiteURLPattern(self):
+        return r"https?://(www|german|spanish|french|dutch|italian|romanian|portuguese|other)(\.i)?\.literotica\.com/s/([a-zA-Z0-9_-]+)"
+
+    def extractChapterUrlsAndMetadata(self):
+        """
+        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
+        Strategy:
+            * Go to author's page, search for the current story link,
+            * If it's in a tr.root-story => One-part story
+                * , get metadata and be done
+            * If it's in a tr.sl => Chapter in series
+                * Search up from there until we find a tr.ser-ttl (this is the
+                story)
+                * Gather metadata
+                * Search down from there for all tr.sl until the next
+                tr.ser-ttl, foreach
+                    * Chapter link is there
+        """
+
+        if not (self.is_adult or self.getConfig("is_adult")):
+            raise exceptions.AdultCheckRequired(self.url)
+
+        logger.debug("Chapter/Story URL: <%s> " % self.url)
+        try:
+            data1 = self._fetchUrl(self.url)
+            soup1 = bs.BeautifulSoup(data1)
+            #strip comments from soup
+            [comment.extract() for comment in soup1.findAll(text=lambda text:isinstance(text, bs.Comment))]
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        # author
+        a = soup1.find("span", "b-story-user-y")
+        self.story.setMetadata('authorId', urlparse.parse_qs(a.a['href'].split('?')[1])['uid'][0])
+        authorurl = a.a['href']
+        if authorurl.startswith('//'):
+            authorurl = self.parsedUrl.scheme+':'+authorurl
+        self.story.setMetadata('authorUrl', authorurl)
+        self.story.setMetadata('author', a.text)
+
+        # get the author page
+        try:
+            dataAuth = self._fetchUrl(authorurl)
+            soupAuth = bs.BeautifulSoup(dataAuth)
+            #strip comments from soup
+            [comment.extract() for comment in soupAuth.findAll(text=lambda text:isinstance(text, bs.Comment))]
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(authorurl)
+            else:
+                raise e
+
+        ## Find link to url in author's page
+        ## site has started using //domain.name/asdf urls remove https?: from front
+        storyLink = soupAuth.find('a', href=self.url[self.url.index(':')+1:])
+
+        if storyLink is not None:
+            urlTr = storyLink.parent.parent
+            if urlTr['class'] == "sl":
+                isSingleStory = False
+            else:
+                isSingleStory = True
+        else:
+            raise exceptions.FailedToDownload("Couldn't find story <%s> on author's page <%s>" % (url, authorurl))
+
+        if isSingleStory:
+            self.story.setMetadata('title', storyLink.text)
+            self.story.setMetadata('description', urlTr.findAll("td")[1].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)]
+        else:
+            seriesTr = urlTr.previousSibling
+            while seriesTr['class'] != 'ser-ttl':
+                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'))
+            self.story.setMetadata('numChapters', int(m.group('numChapters')))
+
+            ## 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)
+                chapterLink = chapterTr.find("td", "fc").find("a")
+                self.chapterUrls.append((chapterLink.text, "http:" + chapterLink["href"]))
+                self.story.addToList('eroticatags', chapterTr.findAll("td")[2].text)
+                dates.append(makeDate(chapterTr.findAll('td')[-1].text, self.dateformat))
+                chapterTr = chapterTr.nextSibling
+
+            ## Set description to joint chapter descriptions
+            self.story.setMetadata('description', " / ".join(descriptions))
+
+            ## 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])
+
+            # normalize on first chapter URL.
+            self._setURL(self.chapterUrls[0][1])
+
+        # 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()))
+
+        return
+
+    def getChapterText(self, url):
+        logger.debug('Getting chapter text from <%s>' % url)
+        data1 = self._fetchUrl(url)
+        soup1 = bs.BeautifulSoup(data1)
+
+        #strip comments from soup
+        [comment.extract() for comment in soup1.findAll(text=lambda text:isinstance(text, bs.Comment))]
+
+        # get story text
+        story1 = soup1.find('div', 'b-story-body-x').p
+        story1.name='div'
+        story1.append('<br />')
+        storytext = self.utf8FromSoup(url,story1)
+
+        # find num pages
+        pgs = int(soup1.find("span", "b-pager-caption-t r-d45").string.split(' ')[0])
+        logger.debug("pages: "+str(pgs))
+
+        # 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})
+                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').p
+                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
+
+
+def getClass():
+    return LiteroticaSiteAdapter
+
+
+

fanficdownloader/adapters/adapter_nocturnallightnet.py

@@ -0,0 +1,177 @@
+import re
+import urllib2
+import urlparse
+
+from .. import BeautifulSoup
+
+from base_adapter import BaseSiteAdapter, makeDate
+from .. import exceptions
+
+
+def getClass():
+    return NocturnalLightNetAdapter
+
+
+# yields Tag _and_ NavigableString siblings from the given tag. The
+# BeautifulSoup findNextSiblings() method for some reasons only returns either
+# NavigableStrings _or_ Tag objects, not both.
+def _yield_next_siblings(tag):
+    sibling = tag.nextSibling
+    while sibling:
+        yield sibling
+        sibling = sibling.nextSibling
+
+
+class NocturnalLightNetAdapter(BaseSiteAdapter):
+    SITE_ABBREVIATION = 'nln'
+    SITE_DOMAIN = 'nocturnal-light.net'
+    BASE_URL = 'http://' + SITE_DOMAIN + '/fanfiction/'
+    STORY_URL_TEMPLATE = BASE_URL + 'story/%s'
+    AUTHORS_URL_TEMPLATE = BASE_URL + 'authors/%s'
+
+    DATETIME_FORMAT = '%m-%d-%y'
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        url_tokens = self.parsedUrl.path.split('/')
+        story_id = url_tokens[url_tokens.index('story') + 1]
+
+        self.story.setMetadata('storyId', story_id)
+        self._setURL(self.STORY_URL_TEMPLATE % story_id)
+        self.story.setMetadata('siteabbrev', self.SITE_ABBREVIATION)
+
+    def _customized_fetch_url(self, url, exception=None, parameters=None):
+        if exception:
+            try:
+                data = self._fetchUrl(url, parameters)
+            except urllib2.HTTPError:
+                raise exception(self.url)
+        # Just let self._fetchUrl throw the exception, don't catch and
+        # customize it.
+        else:
+            data = self._fetchUrl(url, parameters)
+
+        return BeautifulSoup.BeautifulSoup(data)
+
+    @staticmethod
+    def getSiteDomain():
+        return NocturnalLightNetAdapter.SITE_DOMAIN
+
+    @classmethod
+    def getSiteExampleURLs(cls):
+        return cls.STORY_URL_TEMPLATE % 1234
+
+    def getSiteURLPattern(self):
+        return re.escape(self.STORY_URL_TEMPLATE[:-2]) + r'\d+.*$'
+
+    def extractChapterUrlsAndMetadata(self):
+        soup = self._customized_fetch_url(self.url)
+
+        # Since no 404 error code we have to raise the exception ourselves.
+        # A title that is just 'by' indicates that there is no author name
+        # and no story title available.
+        if soup.title.string.strip() == 'by':
+            raise exceptions.StoryDoesNotExist(self.url)
+
+        # "storycontent" is found in a single-chapter story
+        author_anchor = soup.find('div', id=lambda id: id in ('main', 'storycontent')).h1.a
+        self.story.setMetadata('author', author_anchor.string)
+
+        url_tokens = author_anchor['href'].split('/')
+        author_id = url_tokens[url_tokens.index('authors')+1]
+        self.story.setMetadata('authorId', author_id)
+        self.story.setMetadata('authorUrl', self.AUTHORS_URL_TEMPLATE % author_id)
+
+        chapter_anchors = soup('a', href=lambda href: href and href.startswith('/fanfiction/story/'))
+        for chapter_anchor in chapter_anchors:
+            url = urlparse.urljoin(self.BASE_URL, chapter_anchor['href'])
+            self.chapterUrls.append((chapter_anchor.string, url))
+
+        author_url = urlparse.urljoin(self.BASE_URL, author_anchor['href'])
+        soup = self._customized_fetch_url(author_url)
+        story_id = self.story.getMetadata('storyId')
+        for listbox in soup('div', {'class': 'listbox'}):
+            url_tokens = listbox.a['href'].split('/')
+            # Found the div containing the story's metadata; break the loop and
+            # parse the element
+            if story_id == url_tokens[url_tokens.index('story')+1]:
+                break
+        else:
+            raise exceptions.FailedToDownload(self.url)
+
+        title = listbox.a.string
+        self.story.setMetadata('title', title)
+
+        # No chapter anchors found in the original story URL, so the story has
+        # only a single chapter.
+        if not chapter_anchors:
+            self.chapterUrls.append((title, self.url))
+
+        for b_tag in listbox('b'):
+            key = b_tag.string.strip(':')
+            try:
+                value = b_tag.nextSibling.string.replace('•', '').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
+            except AttributeError:
+                value = None
+
+            if key == 'Summary':
+                contents = []
+                keep_summary_html = self.getConfig('keep_summary_html')
+
+                for sibling in _yield_next_siblings(b_tag):
+                    if isinstance(sibling, BeautifulSoup.Tag):
+                        if sibling.name == 'b' and sibling.findPreviousSibling().name == 'br':
+                            break
+
+                        if keep_summary_html:
+                            contents.append(self.utf8FromSoup(author_url, sibling))
+                        else:
+                            contents.append(''.join(sibling(text=True)))
+                    else:
+                        contents.append(sibling)
+
+                # Pop last break line tag
+                contents.pop()
+                self.story.setMetadata('description', ''.join(contents))
+
+            elif key == 'Category':
+                for sibling in b_tag.findNextSiblings(['a', 'b']):
+                    if sibling.name == 'b':
+                        break
+
+                    self.story.addToList('category', sibling.string)
+
+            elif key == 'Rating':
+                self.story.setMetadata('rating', value)
+
+            elif key == 'Chapters':
+                self.story.setMetadata('numChapters', int(value))
+
+                # Also parse reviews number which lies right after the chapters
+                # section
+                reviews_anchor = b_tag.findNextSibling('a')
+                reviews = reviews_anchor.string.split(' ')[1].strip('()')
+                self.story.setMetadata('reviews', reviews)
+
+            elif key == 'Completed':
+                self.story.setMetadata('status', 'Completed' if value == 'Yes' else 'In-Progress')
+
+            elif key == 'Date Added':
+                self.story.setMetadata('datePublished', makeDate(value, self.DATETIME_FORMAT))
+
+            elif key == 'Last Updated':
+                self.story.setMetadata('dateUpdated', makeDate(value, self.DATETIME_FORMAT))
+
+            elif key == 'Read':
+                self.story.setMetadata('readings', value.split()[0])
+
+        if self.story.getMetadata('rating') == 'NC-17' and not (self.is_adult or self.getConfig('is_adult')):
+            raise exceptions.AdultCheckRequired(self.url)
+
+    def getChapterText(self, url):
+        soup = self._customized_fetch_url(url)
+        return self.utf8FromSoup(url, soup.find('div', id='storytext'))

fanficdownloader/adapters/adapter_onedirectionfanfictioncom.py

@@ -192,7 +192,7 @@ class OneDirectionFanfictionComAdapter(BaseSiteAdapter):
             if 'Summary' in label:
                 ## Everything until the next span class='label'
                 svalue = ""
-                while not defaultGetattr(value,'class') == 'label':
+                while value and not defaultGetattr(value,'class') == 'label':
                     svalue += str(value)
                     value = value.nextSibling
                 self.setDescription(url,svalue)

fanficdownloader/adapters/adapter_potionsandsnitchesnet.py

@@ -163,12 +163,11 @@ class PotionsAndSnitchesNetSiteAdapter(BaseSiteAdapter):
                     self.story.setMetadata('status', 'In-Progress')
 
             if 'Published' in label:
-                self.story.setMetadata('datePublished', makeDate(stripHTML(value), "%d %b %Y"))
+                # limit date values, there's some extra chars.
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value[:12]), "%d %b %Y"))
             
             if 'Updated' in label:
-                # there's a stray [ at the end.
-                #value = value[0:-1]
-                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), "%d %b %Y"))
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value[:12]), "%d %b %Y"))
 
         try:
             # Find Series name from series URL.

fanficdownloader/adapters/adapter_spikeluvercom.py

@@ -0,0 +1,207 @@
+import re
+import urllib2
+import urlparse
+
+from .. import BeautifulSoup
+from ..htmlcleanup import stripHTML
+
+from base_adapter import BaseSiteAdapter, makeDate
+from .. import exceptions
+
+
+def getClass():
+    return SpikeluverComAdapter
+
+
+# yields Tag _and_ NavigableString siblings from the given tag. The
+# BeautifulSoup findNextSiblings() method for some reasons only returns either
+# NavigableStrings _or_ Tag objects, not both.
+def _yield_next_siblings(tag):
+    sibling = tag.nextSibling
+    while sibling:
+        yield sibling
+        sibling = sibling.nextSibling
+
+
+class SpikeluverComAdapter(BaseSiteAdapter):
+    SITE_ABBREVIATION = 'slc'
+    SITE_DOMAIN = 'spikeluver.com'
+
+    BASE_URL = 'http://' + SITE_DOMAIN + '/SpuffyRealm/'
+    LOGIN_URL = BASE_URL + 'user.php?action=login'
+    VIEW_STORY_URL_TEMPLATE = BASE_URL + 'viewstory.php?sid=%d'
+    METADATA_URL_SUFFIX = '&index=1'
+    AGE_CONSENT_URL_SUFFIX = '&ageconsent=ok&warning=5'
+
+    DATETIME_FORMAT = '%m/%d/%Y'
+    STORY_DOES_NOT_EXIST_ERROR_TEXT = 'That story does not exist on this archive.  You may search for it or return to the home page.'
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        query_data = urlparse.parse_qs(self.parsedUrl.query)
+        story_id = query_data['sid'][0]
+
+        self.story.setMetadata('storyId', story_id)
+        self._setURL(self.VIEW_STORY_URL_TEMPLATE % int(story_id))
+        self.story.setMetadata('siteabbrev', self.SITE_ABBREVIATION)
+
+    def _customized_fetch_url(self, url, exception=None, parameters=None):
+        if exception:
+            try:
+                data = self._fetchUrl(url, parameters)
+            except urllib2.HTTPError:
+                raise exception(self.url)
+        # Just let self._fetchUrl throw the exception, don't catch and
+        # customize it.
+        else:
+            data = self._fetchUrl(url, parameters)
+
+        return BeautifulSoup.BeautifulSoup(data)
+
+    @staticmethod
+    def getSiteDomain():
+        return SpikeluverComAdapter.SITE_DOMAIN
+
+    @classmethod
+    def getSiteExampleURLs(cls):
+        return cls.VIEW_STORY_URL_TEMPLATE % 1234
+
+    def getSiteURLPattern(self):
+        return re.escape(self.VIEW_STORY_URL_TEMPLATE[:-2]) + r'\d+$'
+
+    def extractChapterUrlsAndMetadata(self):
+        soup = self._customized_fetch_url(self.url + self.METADATA_URL_SUFFIX)
+
+        errortext_div = soup.find('div', {'class': 'errortext'})
+        if errortext_div:
+            error_text = ''.join(errortext_div(text=True)).strip()
+            if error_text == self.STORY_DOES_NOT_EXIST_ERROR_TEXT:
+                raise exceptions.StoryDoesNotExist(self.url)
+
+        # No additional login is required, just check for adult
+        pagetitle_div = soup.find('div', id='pagetitle')
+        if pagetitle_div.a['href'].startswith('javascript:'):
+            if not(self.is_adult or self.getConfig('is_adult')):
+                raise exceptions.AdultCheckRequired(self.url)
+
+        url = ''.join([self.url, self.METADATA_URL_SUFFIX, self.AGE_CONSENT_URL_SUFFIX])
+        soup = self._customized_fetch_url(url)
+
+        pagetitle_div = soup.find('div', id='pagetitle')
+        self.story.setMetadata('title', stripHTML(pagetitle_div.a))
+
+        author_anchor = pagetitle_div.a.findNextSibling('a')
+        url = urlparse.urljoin(self.BASE_URL, author_anchor['href'])
+        components = urlparse.urlparse(url)
+        query_data = urlparse.parse_qs(components.query)
+
+        self.story.setMetadata('author', stripHTML(author_anchor))
+        self.story.setMetadata('authorId', query_data['uid'])
+        self.story.setMetadata('authorUrl', url)
+
+        sort_div = soup.find('div', id='sort')
+        self.story.setMetadata('reviews', stripHTML(sort_div('a')[1]))
+
+        listbox_tag = soup.find('div', {'class': 'listbox'})
+        for span_tag in listbox_tag('span'):
+            key = span_tag.string.strip(' :')
+            try:
+                value = stripHTML(span_tag.nextSibling)
+            # 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
+            except AttributeError:
+                value = None
+
+            if key == 'Summary':
+                contents = []
+                keep_summary_html = self.getConfig('keep_summary_html')
+
+                for sibling in _yield_next_siblings(span_tag):
+                    if isinstance(sibling, BeautifulSoup.Tag):
+                        # Encountered next label, break. Not as bad as other
+                        # e-fiction sites, let's hope this is enough for proper
+                        # parsing.
+                        if sibling.name == 'span' and sibling.get('class', None) == 'label':
+                            break
+
+                        if keep_summary_html:
+                            contents.append(self.utf8FromSoup(self.url, sibling))
+                        else:
+                            contents.append(''.join(sibling(text=True)))
+                    else:
+                        contents.append(sibling)
+
+                # Remove the preceding break line tag and other crud
+                contents.pop()
+                contents.pop()
+                self.story.setMetadata('description', ''.join(contents))
+
+            elif key == 'Rated':
+                self.story.setMetadata('rating', value)
+
+            elif key == 'Categories':
+                for sibling in span_tag.findNextSiblings(['a', 'br']):
+                    if sibling.name == 'br':
+                        break
+
+                    self.story.addToList('category', stripHTML(sibling))
+
+            # Seems to be always "None" for some reason
+            elif key == 'Characters':
+                for sibling in span_tag.findNextSiblings(['a', 'br']):
+                    if sibling.name == 'br':
+                        break
+                    self.story.addToList('characters', stripHTML(sibling))
+
+            elif key == 'Genres':
+                for sibling in span_tag.findNextSiblings(['a', 'br']):
+                    if sibling.name == 'br':
+                        break
+
+                    self.story.addToList('genre', stripHTML(sibling))
+
+            elif key == 'Warnings':
+                for sibling in span_tag.findNextSiblings(['a', 'br']):
+                    if sibling.name == 'br':
+                        break
+                    self.story.addToList('warnings', stripHTML(sibling))
+
+            # Challenges
+
+            elif key == 'Series':
+                a = span_tag.findNextSibling('a')
+                if not a:
+                    continue
+                self.story.setMetadata('series', stripHTML(a))
+                self.story.setMetadata('seriesUrl', urlparse.urljoin(self.BASE_URL, a['href']))
+
+            elif key == 'Chapters':
+                self.story.setMetadata('numChapters', int(value))
+
+            elif key == 'Completed':
+                self.story.setMetadata('status', 'Completed' if value == 'Yes' else 'In-Progress')
+
+            elif key == 'Word count':
+                self.story.setMetadata('numWords', value)
+
+            elif key == 'Published':
+                self.story.setMetadata('datePublished', makeDate(value, self.DATETIME_FORMAT))
+
+            elif key == 'Updated':
+                self.story.setMetadata('dateUpdated', makeDate(value, self.DATETIME_FORMAT))
+
+        for p_tag in listbox_tag.findNextSiblings('p'):
+            chapter_anchor = p_tag.find('a', href=lambda href: href and href.startswith('viewstory.php?sid='))
+            if not chapter_anchor:
+                continue
+
+            title = stripHTML(chapter_anchor)
+            url = urlparse.urljoin(self.BASE_URL, chapter_anchor['href'])
+            self.chapterUrls.append((title, url))
+
+    def getChapterText(self, url):
+        url += self.AGE_CONSENT_URL_SUFFIX
+        soup = self._customized_fetch_url(url)
+        return self.utf8FromSoup(url, soup.find('div', id='story'))

fanficdownloader/adapters/adapter_squidgeorgpeja.py

@@ -62,7 +62,7 @@ class SquidgeOrgPejaAdapter(BaseSiteAdapter):
         
         
         # normalized story URL.
-        self._setURL('http://' + self.getSiteDomain() + '/peja/cgi-bin/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        self._setURL('https://' + self.getSiteDomain() + '/peja/cgi-bin/viewstory.php?sid='+self.story.getMetadata('storyId'))
         
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','wwomb')
@@ -83,10 +83,10 @@ class SquidgeOrgPejaAdapter(BaseSiteAdapter):
     
     @classmethod
     def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/peja/cgi-bin/viewstory.php?sid=1234"
+        return "https://"+self.getSiteDomain()+"/peja/cgi-bin/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
-        return re.escape("http://"+self.getSiteDomain()+"/")+"~?"+re.escape("peja/cgi-bin/viewstory.php?sid=")+r"\d+$"        
+        return r"https?"+re.escape("://"+self.getSiteDomain()+"/")+r"~?"+re.escape("peja/cgi-bin/viewstory.php?sid=")+r"\d+$"        
 
     ## Getting the chapter list and the meta data, plus 'is adult' checking.
     def extractChapterUrlsAndMetadata(self):
@@ -116,7 +116,7 @@ class SquidgeOrgPejaAdapter(BaseSiteAdapter):
         # Find authorid and URL from... author url.
         author = soup.find('div', {'id':"pagetitle"}).find('a')
         self.story.setMetadata('authorId',author['href'].split('=')[1])
-        self.story.setMetadata('authorUrl','http://'+self.host+'/peja/cgi-bin/'+author['href'])
+        self.story.setMetadata('authorUrl','https://'+self.host+'/peja/cgi-bin/'+author['href'])
         self.story.setMetadata('author',author.string)
 		
         authorSoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
@@ -131,7 +131,7 @@ class SquidgeOrgPejaAdapter(BaseSiteAdapter):
         chapterselect=soup.find('select',{'name':'chapter'})
         if chapterselect:
             for ch in chapterselect.findAll('option'):
-                self.chapterUrls.append((stripHTML(ch),'http://'+self.host+'/peja/cgi-bin/viewstory.php?sid='+self.story.getMetadata('storyId')+'&chapter='+ch['value']))
+                self.chapterUrls.append((stripHTML(ch),'https://'+self.host+'/peja/cgi-bin/viewstory.php?sid='+self.story.getMetadata('storyId')+'&chapter='+ch['value']))
         else:
             self.chapterUrls.append((title,url))
 		
@@ -207,7 +207,7 @@ class SquidgeOrgPejaAdapter(BaseSiteAdapter):
             # http://www.squidge.org/peja/cgi-bin/series.php?seriesid=254
             a = titleblock.find('a', href=re.compile(r"series.php\?seriesid=\d+"))
             series_name = a.string
-            series_url = 'http://'+self.host+'/peja/cgi-bin/'+a['href']
+            series_url = 'https://'+self.host+'/peja/cgi-bin/'+a['href']
     
             # use BeautifulSoup HTML parser to make everything easier to find.
             seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))

fanficdownloader/adapters/adapter_storiesonlinenet.py

@@ -37,11 +37,6 @@ class StoriesOnlineNetAdapter(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
@@ -71,18 +66,18 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
         return "http://"+self.getSiteDomain()+"/s/1234 http://"+self.getSiteDomain()+"/s/1234:4010"
 
     def getSiteURLPattern(self):
-        return re.escape("http://"+self.getSiteDomain())+r"/s/\d+((:\d+)?(;\d+)?$|(:i)?$)"
+        return re.escape("http://"+self.getSiteDomain())+r"/s/\d+((:\d+)?(;\d+)?$|(:i)?$)?"
 
     ## Login seems to be reasonably standard across eFiction sites.
     def needToLoginCheck(self, data):
-        if 'Free Registration' in data \
+        if self.needToLogin \
+                or 'Free Registration' in data \
                 or "Invalid Password!" in data \
                 or "Invalid User Name!" in data \
                 or "Log In" in data \
                 or "Access to unlinked chapters requires" in data:
-            return True
-        else:
-            return False
+            self.needToLogin = True
+        return self.needToLogin
         
     def performLogin(self, url):
         params = {}
@@ -119,11 +114,15 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
         url = self.url
         logger.debug("URL: "+url)
 
+        self.needToLogin = False
         try:
             data = self._fetchUrl(url+":i")
         except urllib2.HTTPError, e:
             if e.code == 404:
                 raise exceptions.StoryDoesNotExist(self.url)
+            elif e.code == 401:
+                self.needToLogin = True
+                data = ''
             else:
                 raise e
 
@@ -147,6 +146,10 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
         a = soup.find('h1')
         self.story.setMetadata('title',stripHTML(a))
         
+        notice = soup.find('div', {'class' : 'notice'})
+        if notice:
+            self.story.setMetadata('notice',unicode(notice))
+
         # 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])
@@ -172,7 +175,7 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
 
             a = asoup.findAll('td', {'class' : 'lc2'})
             for lc2 in a:
-                if lc2.find('a')['href'] == '/s/'+self.story.getMetadata('storyId'):
+                if lc2.find('a', href=re.compile(r'^/s/'+self.story.getMetadata('storyId'))):
                     i=1
                     break
                 if a[len(a)-1] == lc2:
@@ -185,23 +188,74 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
         self.story.setMetadata('size', lc2.findNext('td', {'class' : 'num'}).text)
         
         lc4 = lc2.findNext('td', {'class' : 'lc4'})        
-        
+        desc = lc4.contents[0]
+
         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(stripHTML(a), i)
-            self.story.setMetadata('seriesUrl','http://'+self.host+a['href'])
+            if a:
+                # if there's a number after the series name, series_contents is a two element list:
+                # [<a href="...">Title</a>, u' (2)']
+                series_contents = a.parent.contents
+                i = 0 if len(series_contents) == 1 else series_contents[1].strip(' ()')
+                seriesUrl = 'http://'+self.host+a['href']
+                self.story.setMetadata('seriesUrl',seriesUrl)
+                series_name = stripHTML(a)
+                logger.debug("Series name= %s" % series_name)
+                series_soup = bs.BeautifulSoup(self._fetchUrl(seriesUrl))
+                if series_soup:
+                    logger.debug("Retrieving Series - looking for name")
+                    series_name = series_soup.find('span', {'id' : 'ptitle'}).text.partition(' — ')[0]
+                    logger.debug("Series name: '{0}'".format(series_name))
+                self.setSeries(series_name, i)
+                desc = lc4.contents[2]
+                # Check if series is in a universe
+                universes_soup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')  + "&type=uni")) 
+#                logger.debug("Universe page=", universes_soup)
+                if universes_soup:
+                    universes = universes_soup.findAll('div', {'class' : 'ser-box'})
+                    logger.debug("Number of Universes: %d" % len(universes))
+                    for universe in universes:
+                        logger.debug("universe.find('a')={0}".format(universe.find('a')))
+                        # The universe id is in an "a" tag that has an id but nothing else. It is the first tag.
+                        # The id is prefixed with the letter "u".
+                        universe_id = universe.find('a')['id'][1:]
+                        logger.debug("universe_id='%s'" % universe_id)
+                        universe_name = universe.find('div', {'class' : 'ser-name'}).text.partition(' ')[2]
+                        logger.debug("universe_name='%s'" % universe_name)
+                        # If there is link to the story, we have the right universe
+                        story_a = universe.find('a', {'href' : '/s/'+self.story.getMetadata('storyId')})
+                        if story_a:
+                            logger.debug("Story is in a series that is in a universe! The universe is '%s'" % universe_name)
+                            self.story.setMetadata("universe", universe_name)
+                            self.story.setMetadata('universeUrl','http://'+self.host+ '/library/universe.php?id=' + universe_id)
+                            break
         except:
             pass
         try:
             a = lc4.find('a', href=re.compile(r"/library/universe.php\?id=\d+"))
             if a:
                 self.story.setMetadata("universe",stripHTML(a))
+                desc = lc4.contents[2]
+                # Assumed only one universe, but it does have a URL--use universeHTML
+                universe_name = stripHTML(a)
+                universeUrl = 'http://'+self.host+a['href']
+                logger.debug("Retrieving Universe - about to get page")
+                universe_soup = bs.BeautifulSoup(self._fetchUrl(universeUrl))
+                logger.debug("Retrieving Universe - have page")
+                if universe_soup:
+                    logger.debug("Retrieving Universe - looking for name")
+                    universe_name = universe_soup.find('span', {'id' : 'ptitle'}).text.partition(' &mdash;')[0]
+                    logger.debug("Universes name: '{0}'".format(universe_name))
+
+                self.story.setMetadata('universeUrl',universeUrl)
+                logger.debug("Setting universe name: '{0}'".format(universe_name))
+                self.story.setMetadata('universe',universe_name)
+                if self.getConfig("universe_as_series"):
+                    self.setSeries(universe_name, 0)
+                    self.story.setMetadata('seriesUrl',universeUrl)
         except:
             pass
-            
 
-        desc = lc4.contents[0]
         self.setDescription('http://'+self.host+'/s/'+self.story.getMetadata('storyId'),desc)
             
         for b in lc4.findAll('b'):
@@ -255,8 +309,18 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
         # some big chapters are split over several pages
         pager = div.find('span', {'class' : 'pager'})
         if pager != None:
+            a = pager.previousSibling
+            while a != None:
+                logger.debug("before pager: {0}".format(a))
+                b = a.previousSibling
+                a.extract()
+                a = b
+
             urls=pager.findAll('a')
             urls=urls[:len(urls)-1]
+            pager.extract()
+            div.contents = div.contents[2:]
+#            logger.debug(div)
                         
             for ur in urls:
                 soup = bs.BeautifulSoup(self._fetchUrl("http://"+self.getSiteDomain()+ur['href']),
@@ -264,38 +328,76 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
         
                 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:
+                # Find the "Continues" marker on the current page and remove everything after that. 
+                continues = div.find('span', {'class' : 'conTag'})
+                if continues != None:
+                    while continues != None:
+#                        logger.debug("removing end: {0}".format(continues))
+                        b = continues.nextSibling
+                        continues.extract()
+                        continues = b
+
+                # Find the "Continued" marker and delete everything before that
+                continued = div1.find('span', {'class' : 'conTag'})
+                if continued != None:
+                    a = continued.previousSibling
+                    while a != None:
+#                        logger.debug("before conTag: {0}".format(a))
+                        b = a.previousSibling
+                        a.extract()
+                        a = b
+                # Remove the pager from the end if this is the last page
+                endPager = div1.find('span', {'class' : 'pager'})
+                if endPager != None:
+                    b = endPager.nextSibling
+                    while endPager != None:
+                        logger.debug("removing end: {0}".format(endPager))
+                        b = endPager.nextSibling
+                        endPager.extract()
+                        endPager = b
+                    div1.contents = div1.contents[:len(div1) - 2]
+#                logger.debug("after removing pager: {0}".format(div1))
+                for tag in div1.contents[2:]:
+                    div.append(tag)
+
+        # If it is a chapter, there are dates at the start for when it was posted or modified. These plus 
+        # everything before them can be discarded. 
+        postedDates = div.findAll('div', {'class' : 'date'})
+        if postedDates:
+            a = postedDates[0].previousSibling
+            while a != None:
+#                logger.debug("before dates: {0}".format(a))
+                b = a.previousSibling
                 a.extract()
-                a=b
-                b=b.nextSibling
-        
+                a = b
+            for a in div.findAll('div', {'class' : 'date'}):
+                a.extract()
+
+        # For single chapter stories, there is a copyright statement. Remove this and everything
+        # before it.
+        copy = div.find('h4', {'class': 'copy'})
+        while copy != None:
+#            logger.debug("before copyright: {0}".format(copy))
+            b = copy.previousSibling
+            copy.extract()
+            copy = b
+
+        # For a story or the last chapter, remove voting form and the in library box
+        a = div.find('div', {'id' : 'vote-form'})
+        if a != None:
+            a.extract()
+        a = div.find('div', {'id' : 'b-man-div'})
+        if a != None:
+            a.extract()
+
+        # Kill the "The End" header and everything after it.
+        a = div.find(['h2', 'h3'], {'class' : 'end'})
+        logger.debug("Chapter end= '{0}'".format(a))
+        while a != None:
+            b = a.nextSibling
+            a.extract()
+            a=b
+
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)

fanficdownloader/adapters/adapter_test1.py

@@ -50,6 +50,7 @@ class TestSiteAdapter(BaseSiteAdapter):
     def extractChapterUrlsAndMetadata(self):
         idstr = self.story.getMetadata('storyId')
         idnum = int(idstr)
+        self.do_sleep()
 
         if idnum >= 1000:
             logger.warn("storyId:%s - Custom INI data will be used."%idstr)
@@ -218,15 +219,18 @@ Some more longer description.  "I suck at summaries!"  "Better than it sounds!"
         elif idstr == '81':
             self.story.addToList('category',u'Pitch Perfect')
             self.story.addToList('characters','Chloe B.')
+        elif idstr == '82':
+            self.story.addToList('characters','Henry (Once Upon a Time)')        
+            self.story.addToList('category',u'Once Upon a Time (TV)')
         elif idstr == '83':
             self.story.addToList('category',u'Rizzoli & Isles')
             self.story.addToList('characters','J. Rizzoli')
             self.story.addToList('category',u'Pitch Perfect')
             self.story.addToList('characters','Chloe B.')
             self.story.addToList('ships','Chloe B. & J. Rizzoli')
-        elif idstr == '82':
-            self.story.addToList('characters','Henry (Once Upon a Time)')        
-            self.story.addToList('category',u'Once Upon a Time (TV)')
+        elif idstr == '90':
+            self.story.setMetadata('characters','Henry (Once Upon a Time)')        
+            self.story.setMetadata('category',u'Once Upon a Time (TV)')
         else:
             self.story.addToList('category','Harry Potter')
             self.story.addToList('category','Furbie')
@@ -296,6 +300,7 @@ Some more longer description.  "I suck at summaries!"  "Better than it sounds!"
 
     def getChapterText(self, url):
         logger.debug('Getting chapter text from: %s' % url)
+        self.do_sleep()
         if self.story.getMetadata('storyId').startswith('670') or \
                 self.story.getMetadata('storyId').startswith('672'):
             time.sleep(1.0)

fanficdownloader/adapters/adapter_themaplebookshelf.py

@@ -0,0 +1,130 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2014 Fanficdownloader 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 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
+
+
+class TheMapleBookshelfComSiteAdapter(BaseSiteAdapter):
+    """
+    Use Printable version which is easier to parse and has everything in one
+    page and cache between extractChapterUrlsAndMetadata and getChapterText
+    """
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+        self.story.setMetadata('siteabbrev','maplebook')
+        self.decode = ["Windows-1252", "utf8"]
+        self.story.setMetadata('storyId', re.compile(self.getSiteURLPattern()).match(url).group('storyId'))
+        self._setURL("http://%s/Literati/viewstory.php?sid=%s" % (self.getSiteDomain(), self.story.getMetadata('storyId')))
+        self.dateformat = "%b %d, %Y"
+
+    @staticmethod
+    def getSiteDomain():
+        return 'themaplebookshelf.com'
+
+    @classmethod
+    def getSiteExampleURLs(self):
+        return "http://www.themaplebookshelf.com/Literati/viewstory.php?sid=227 http://themaplebookshelf.com/Literati/viewstory.php?sid=227&chapter=2"
+
+    def getSiteURLPattern(self):
+        return r"http://themaplebookshelf.com/Literati/viewstory.php\?sid=(?P<storyId>\d+)"
+
+    def extractChapterUrlsAndMetadata(self):
+        logger.debug(self.url)
+        self._setURL(self.url + "&action=printable")
+        try:
+            html = self._fetchUrl(self.url)
+            soup = bs.BeautifulSoup(html)
+            # #strip comments from soup
+            # [comment.extract() for comment in soup1.findAll(text=lambda text:isinstance(text, bs.Comment))]
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+        ## title + author
+        pagetitleDiv = soup.find("div", {"id": "pagetitle"})
+        self.story.setMetadata('title', pagetitleDiv.find("a").text)
+        authorLink = pagetitleDiv.findAll("a")[1]
+        self.story.setMetadata('author', authorLink.text)
+        self.story.setMetadata('authorUrl', "http://" + self.getSiteDomain() + "/" + authorLink['href'])
+        self.story.setMetadata('authorId', re.search("\d+", authorLink['href']).group(0))
+
+        ## Description
+        description = ""
+        summaryEnd = soup.find("div", "content").find("span", "label").nextSibling
+        while summaryEnd is not None:
+            description += stripHTML(summaryEnd)
+            summaryEnd = summaryEnd.nextSibling
+            if type(summaryEnd) != bs.NavigableString and summaryEnd.name == 'br':
+                break
+        self.story.setMetadata('description', description)
+
+        ## General Metadata
+        for kSpan in soup.findAll("span", "label"):
+            k = kSpan.text.strip().replace(':', '')
+            vSpan = kSpan.nextSibling
+            if k == 'Summary:' or not vSpan or not vSpan.string:
+                continue
+            v = vSpan.string.strip()
+            if v == 'None':
+                continue
+            logger.debug("%s '%s'" %(k, v))
+            if k == 'Genre':
+                for genre in v.split(", "):
+                    self.story.addToList('genre', genre)
+            elif k == 'Chapters':
+                self.story.setMetadata('numChapters', int(v))
+            elif k == 'Word count':
+                self.story.setMetadata('numWords', v)
+            elif k == 'Published':
+                self.story.setMetadata('datePublished', makeDate(v, self.dateformat))
+            elif k == 'Updated':
+                self.story.setMetadata('dateUpdated', makeDate(v, self.dateformat))
+            # TODO: Series, Warnings
+
+        ## Chapter URLs (fragment identifiers in the document, so we don' need to fetch so much)
+        for chapterNumB in soup.findAll("b", text=re.compile("^\d+\.$")):
+            self.chapterUrls.append((
+                chapterNumB.parent.parent.find("a").text,
+                self.url + chapterNumB.parent.parent.find("a")["href"]
+                ))
+
+        ## fix all local image 'src' to absolute
+        for img in soup.findAll("img", {"src": re.compile("^(?!http)")}):
+            img['src'] = re.sub("viewstory.php\?.*", "", self.url) + img['src']
+
+        self.html = soup
+
+    def getChapterText(self, url):
+        logger.debug('Getting chapter text from <%s>' % url)
+        anchor = url.replace(self.url, "")
+        anchor = anchor.replace("#", "")
+        chapterDiv = self.html.find("a", {"name": anchor}).parent.findNext("div", "chapter")
+        return self.utf8FromSoup(self.url, chapterDiv)
+
+def getClass():
+    return TheMapleBookshelfComSiteAdapter

fanficdownloader/adapters/adapter_tolkienfanfiction.py

@@ -0,0 +1,238 @@
+# -*- coding: utf-8 -*-
+
+"""
+FFDL Adapter for TolkienFanFiction.com.
+
+Chapter URL: http://www.tolkienfanfiction.com/Story_Read_Chapter.php?CHid=1234
+    Metadata
+        Link to Story URL [Index]
+        chapterTitle
+        storyTitle
+Story URL: http://www.tolkienfanfiction.com/Story_Read_Head.php?STid=1034
+    Metadata
+        Links to Chapter URLs
+        storyTitle
+        chapterTitle[s]
+        author
+        authorId
+        authorUrl
+        numChapters
+        wordCount
+        description/summary
+        rating TODO
+        genre TODO
+        Characters
+        Ages (specific) TODO
+Search: http://www.tolkienfanfiction.com/Story_Chapter_Search.php?text=From+Wilderness+to+Cities+White&field=1&type=3&search=Search
+    Strategy
+        Search by exact phrase for styo
+    Metadata
+        dateUpdated
+    Parameters
+        field (field to search)
+            1: title
+            2: description
+            3: chapter text
+        type (any, all or exact phrase)
+            1: any
+            2: all
+            3: exact phrase
+
+"""
+# Copyright 2014 Fanficdownloader 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 urllib
+import urllib2
+import urlparse
+import string
+
+from .. import BeautifulSoup as bs
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter, makeDate
+
+def _is_story_url(url):
+    return "Story_Read_Head.php" in url
+
+def _latinize(text):
+    """
+    See http://stackoverflow.com/a/19114706/201318
+    """
+    src = u"áâäÉéêëíóôöúû"
+    tgt = u"aaaEeeeiooouu"
+    src_ord = [ord(char) for char in src]
+    translate_table = dict(zip(src_ord, tgt))
+    return text.translate(translate_table)
+
+def _fix_broken_markup(html):
+    """Replaces invalid comment tags"""
+    if html.startswith("<CENTER>"):
+        logger.error("TolkienFanFiction.com couldn't handle this request: '%s'" % html)
+    html = re.sub("<!-.+?->", "", html)
+    return html
+
+
+class TolkienFanfictionAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["ISO-8859-1", "Windows-1252"] 
+
+        self.story.setMetadata('siteabbrev','tolkien')
+
+        self.dateformat = '%B %d, %Y'
+
+        self._normalizeURL(url)
+
+    def _normalizeURL(self, url):
+        if _is_story_url(url):
+            self.story.setMetadata('storyId', re.compile(self.getSiteURLPattern()).match(url).group('storyId'))
+            self._setURL('http://' + self.getSiteDomain() + '/Story_Read_Head.php?STid=' + self.story.getMetadata('storyId'))
+
+    @staticmethod
+    def getSiteDomain():
+        return 'tolkienfanfiction.com'
+
+    @classmethod
+    def getAcceptDomains(cls):
+        return ['tolkienfanfiction.com', 'www.tolkienfanfiction.com']
+
+    @classmethod
+    def getSiteExampleURLs(self):
+        return 'http://www.tolkienfanfiction.com/Story_Read_Head.php?STid=1034 http://www.tolkienfanfiction.com/Story_Read_Chapter.php?CHid=4945'
+
+    def getSiteURLPattern(self):
+        return r"http://(?:www.)?tolkienfanfiction.com/(?:Story_Read_Chapter\.php\?CH|Story_Read_Head\.php\?ST)id=(?P<storyId>[0-9]+)"
+
+    def extractChapterUrlsAndMetadata(self):
+
+        if not _is_story_url(self.url):
+            # Get the link to the index page
+            try:
+                chapterHtml = _fix_broken_markup(self._fetchUrl(self.url))
+                chapterSoup = bs.BeautifulSoup(chapterHtml)
+                indexLink = chapterSoup.find("a", text="[Index]").parent
+                self._normalizeURL('http://' + self.getSiteDomain() + '/' + indexLink.get('href'))
+            except urllib2.HTTPError, e:
+                if e.code == 404:
+                    raise exceptions.StoryDoesNotExist(self.url)
+                else:
+                    raise e
+        logger.debug("Determined index page: <%s>" % self.url)
+
+        try:
+            indexHtml = _fix_broken_markup(self._fetchUrl(self.url))
+            soup = bs.BeautifulSoup(indexHtml)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        # chapterUrls
+        for pfLink in soup.findAll("a", text='[PF] '):
+            chapterLink = pfLink.parent.findNext("a")
+            chapterTitle = chapterLink.string
+            if self.getConfig('strip_chapter_numeral'):
+                chapterTitle = re.sub("^\d+:", "", chapterTitle)
+            chapterUrl = 'http://' + self.host + '/' + chapterLink['href']
+            self.chapterUrls.append((chapterTitle, chapterUrl))
+            numChapters = len(self.chapterUrls)
+            self.story.setMetadata('numChapters', numChapters)
+        logger.debug('Number of Chapters: %s' % numChapters)
+
+        # title
+        title = soup.find("table", "headertitle").find("tr").contents[1].string
+        logger.debug("Title: '%s'" % title)
+        self.story.setMetadata('title', title)
+
+        # author
+        authorLink = soup.find("a", {"href":lambda x: x.startswith("Author_Profile.php")})
+        authorName = authorLink.find("b").string
+        authorHref = authorLink['href']
+        authorUrl = 'http:' + self.host + '/' + authorHref
+        authorId = authorHref[authorHref.index('=')+1:]
+        self.story.setMetadata('author', authorName)
+        self.story.setMetadata('authorId', authorId)
+        self.story.setMetadata('authorUrl', authorUrl)
+        logger.debug("Author: %s [%s] @ <%s>" % (authorId, authorName, authorUrl))
+
+        # numWords
+        numWordsMatch = re.search("Word Count: (\d+)<BR>", indexHtml)
+        if numWordsMatch:
+            numWords = numWordsMatch.group(1)
+            logger.debug('Number of words: %s' % numWords)
+            self.story.setMetadata('numWords', numWords)
+
+        # description
+        description = soup.find("b", text="Description:").parent.nextSibling.nextSibling
+        self.story.setDescription(description)
+        logger.debug("Summary: '%s'" % description)
+
+        # characters
+        characters = soup.find("b", text="Characters").parent.nextSibling.nextSibling.nextSibling
+        for character in characters.split(", "):
+            self.story.addToList('characters', character)
+        logger.debug("Characters: %s" % self.story.getMetadata('characters'))
+
+        logger.debug('Title as `str`: ' + str(title))
+        # For publication date we need to search
+        try:
+            queryString = urllib.urlencode((
+                ('type', 3),
+                ('field', 1),
+                # need translate here for the weird accented letters
+                ('text', _latinize(title)),
+                ('search', 'Search'),
+            ))
+            searchUrl = 'http://%s/Story_Chapter_Search.php?%s' % (self.host, queryString)
+            logger.debug("Search URL: <%s>" % searchUrl)
+            searchHtml = _fix_broken_markup(self._fetchUrl(searchUrl))
+            searchSoup = bs.BeautifulSoup(searchHtml)
+            date = searchSoup.find(text="Updated:").nextSibling.string
+            logger.debug("Last Updated: '%s'" % date)
+            self.story.setMetadata('dateUpdated', makeDate(date, self.dateformat))
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+    def getChapterText(self, url):
+
+        logger.debug('Downloading chapter <%s>' % url)
+
+        time.sleep(0.5)
+        htmldata = _fix_broken_markup(self._fetchUrl(url))
+        soup = bs.BeautifulSoup(htmldata)
+
+        #strip comments from soup
+        [comment.extract() for comment in soup.findAll(text=lambda text:isinstance(text, bs.Comment))]
+
+        # Strip redundant headings
+        [font.parent.extract() for font in soup.findAll("font", {"size": "4"})]
+
+        # get story text
+        textDiv = soup.find("div", "text")
+        return self.utf8FromSoup(url, textDiv)
+
+def getClass():
+    return TolkienFanfictionAdapter

fanficdownloader/adapters/adapter_trekiverseorg.py

@@ -0,0 +1,325 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2013 Fanficdownloader 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
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return TrekiverseOrgAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class TrekiverseOrgAdapter(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()\
+                         +"/efiction/viewstory.php?sid="+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','trkvs')
+
+        # 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.
+        return 'trekiverse.org'
+
+    @classmethod
+    def getAcceptDomains(cls):
+        return ['trekiverse.org','efiction.trekiverse.org']
+
+    @classmethod
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/efiction/viewstory.php?sid=1234 http://efiction."+self.getSiteDomain()+"/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return r'(http://trekiverse\.org/efiction/viewstory\.php\?sid=\d+|http://efiction\.trekiverse\.org/viewstory\.php\?sid=\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() + '/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']))
+            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 = "&index=1&ageconsent=ok&warning=5"
+        else:
+            addurl="&index=1"
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+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)
+
+        # 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="))
+        self.story.setMetadata('authorId',aut['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/efiction/'+aut['href'])
+        self.story.setMetadata('author',aut.string)
+        
+        ttl = a.find('a', href=re.compile(r'^viewstory.php\?sid=%s$'%self.story.getMetadata('storyId')))
+        self.story.setMetadata('title',ttl.string)
+
+        # Find the chapters:
+        outputdiv = soup.find('div', {'id':'output'})
+        # (amp;)? because it should be &, but is escaped to & in URL.
+        # viewstory.php?sid=35&chapter=3
+        chapters=outputdiv.findAll('a', href=re.compile(r'^viewstory.php\?sid=%s&(amp;)?chapter=\d+$'%self.story.getMetadata('storyId')))
+        if len(chapters)==0:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: No php/html chapters found.")
+        if len(chapters)==1:
+            self.chapterUrls.append((self.story.getMetadata('title'),'http://'+self.host+'/efiction/'+chapters[0]['href']))
+        else:
+            for chapter in chapters:
+                # just in case there's tags, like <i> in chapter titles.
+                self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/efiction/'+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.
+
+        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
+
+            if 'Summary' in label:
+                ## Everything until the next span class='label'
+                svalue = ''
+                while value and not defaultGetattr(value,'class') == 'label':
+                    svalue += str(value)
+                    value = value.nextSibling
+                # sometimes poorly formated desc (<p> w/o </p>) leads
+                # to all labels being included.
+                svalue=svalue[:svalue.find('<span class="label">')]
+                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)
+
+            if 'Genre' in label:
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=9'))
+                genrestext = [genre.string for genre in genres]
+                self.genre = ', '.join(genrestext)
+                for genre in genrestext:
+                    self.story.addToList('genre',genre.string)
+
+            if 'Awards' in label:
+                awards = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=12'))
+                awardstext = [award.string for award in awards]
+                self.award = ', '.join(awardstext)
+                for award in awardstext:
+                    self.story.addToList('awards',award.string)
+
+            if 'Pairing' in label:
+                ships = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=10'))
+                shipstext = [ship.string for ship in ships]
+                self.ship = ', '.join(shipstext)
+                for ship in shipstext:
+                    self.story.addToList('ships',ship.string)
+
+            if 'Warnings' in label:
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=11'))
+                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(value.strip(), "%d %b %Y"))
+            
+            if 'Updated' in label:
+                self.story.setMetadata('dateUpdated', makeDate(value.strip(), "%d %b %Y"))
+                    
+        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+'/efiction/'+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:
+                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.BeautifulSoup(self._fetchUrl(url)) # 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)
+
+        notesdiv = soup.find('div', {'class':'noteinfo'})
+        if notesdiv != None:
+            div.insert(0,"<hr>")
+            div.insert(0,notesdiv)
+            div.insert(0,"<hr>")
+        
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_tthfanficorg.py

@@ -134,18 +134,18 @@ class TwistingTheHellmouthSiteAdapter(BaseSiteAdapter):
         if "<h2>Story Not Found</h2>" in data:
             raise exceptions.StoryDoesNotExist(url)
         
+        if self.is_adult or self.getConfig("is_adult"):
+            form = soup.find('form', {'id':'sitemaxratingform'})
+            params={'ctkn':form.find('input', {'name':'ctkn'})['value'],
+                    'sitemaxrating':'5'}
+            logger.info("Attempting to get rating cookie for %s" % url)
+            data = self._postUrl("http://"+self.getSiteDomain()+'/setmaxrating.php',params)
+            # refetch story page.
+            data = self._fetchUrl(url)
+            soup = bs.BeautifulSoup(data)
+
         if "NOTE: This story is rated FR21 which is above your chosen filter level." in data:
-            if self.is_adult or self.getConfig("is_adult"):
-                form = soup.find('form', {'id':'sitemaxratingform'})
-                params={'ctkn':form.find('input', {'name':'ctkn'})['value'],
-                        'sitemaxrating':'5'}
-                logger.info("Attempting to get rating cookie for %s" % url)
-                data = self._postUrl("http://"+self.getSiteDomain()+'/setmaxrating.php',params)
-                # refetch story page.
-                data = self._fetchUrl(url)
-                soup = bs.BeautifulSoup(data)
-            else:
-                raise exceptions.AdultCheckRequired(self.url)
+            raise exceptions.AdultCheckRequired(self.url)
 
         # http://www.tthfanfic.org/AuthorStories-3449/Greywizard.htm
         # Find authorid and URL from... author url.
@@ -163,7 +163,14 @@ class TwistingTheHellmouthSiteAdapter(BaseSiteAdapter):
             authorsoup = bs.BeautifulSoup(authordata)
             # author can have several pages, scan until we find it.
             while( not authorsoup.find('a', href=re.compile(r"^/Story-"+self.story.getMetadata('storyId'))) ):
-                nextpage = 'http://'+self.host+authorsoup.find('a', {'class':'arrowf'})['href']
+                nextarrow = authorsoup.find('a', {'class':'arrowf'})
+                if not nextarrow:
+                    ## if rating is set lower than story, it won't be
+                    ## visible on author lists unless.  The *story* is
+                    ## visible via the url, just not the entry on
+                    ## author list.
+                    raise exceptions.AdultCheckRequired(self.url)
+                nextpage = 'http://'+self.host+nextarrow['href']
                 logger.debug("**AUTHOR** nextpage URL: "+nextpage)
                 authordata = self._fetchUrl(nextpage)
                 descurl=nextpage

fanficdownloader/adapters/adapter_voracity2eficcom.py

@@ -0,0 +1,232 @@
+import re
+import urllib2
+import urlparse
+
+from .. import BeautifulSoup
+
+from base_adapter import BaseSiteAdapter, makeDate
+from .. import exceptions
+
+
+def getClass():
+    return Voracity2EficComAdapter
+
+
+# yields Tag _and_ NavigableString siblings from the given tag. The
+# BeautifulSoup findNextSiblings() method for some reasons only returns either
+# NavigableStrings _or_ Tag objects, not both.
+def _yield_next_siblings(tag):
+    sibling = tag.nextSibling
+    while sibling:
+        yield sibling
+        sibling = sibling.nextSibling
+
+
+class Voracity2EficComAdapter(BaseSiteAdapter):
+    SITE_ABBREVIATION = 'voe'
+    SITE_DOMAIN = 'voracity2.e-fic.com'
+
+    BASE_URL = 'http://' + SITE_DOMAIN + '/'
+    LOGIN_URL = BASE_URL + 'user.php?action=login'
+    VIEW_STORY_URL_TEMPLATE = BASE_URL + 'viewstory.php?sid=%d'
+    METADATA_URL_SUFFIX = '&index=1'
+    AGE_CONSENT_URL_SUFFIX = '&ageconsent=ok&warning=4'
+
+    DATETIME_FORMAT = '%m/%d/%Y'
+    REQUIRED_SKIN = 'Simple Elegance'
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        query_data = urlparse.parse_qs(self.parsedUrl.query)
+        story_id = query_data['sid'][0]
+
+        self.story.setMetadata('storyId', story_id)
+        self._setURL(self.VIEW_STORY_URL_TEMPLATE % int(story_id))
+        self.story.setMetadata('siteabbrev', self.SITE_ABBREVIATION)
+
+        self.is_logged_in = False
+
+    def _login(self):
+        # Apparently self.password is only set when login fails, i.e.
+        # the FailedToLogin exception is raised, so the adapter gets new
+        # login data and tries again
+        if self.password:
+            password = self.password
+            username = self.username
+        else:
+            username = self.getConfig('username')
+            password = self.getConfig('password')
+
+        parameters = {
+            'penname': username,
+            'password': password,
+            'submit': 'Submit'}
+
+        class CustomizedFailedToLogin(exceptions.FailedToLogin):
+            def __init__(self, url, passwdonly=False):
+                # Use username variable from outer scope
+                exceptions.FailedToLogin.__init__(self, url, username, passwdonly)
+
+        soup = self._customized_fetch_url(self.LOGIN_URL, CustomizedFailedToLogin, parameters)
+        div = soup.find('div', id='useropts')
+        if not div:
+            raise CustomizedFailedToLogin(self.LOGIN_URL)
+
+        self.is_logged_in = True
+
+    def _customized_fetch_url(self, url, exception=None, parameters=None):
+        if exception:
+            try:
+                data = self._fetchUrl(url, parameters)
+            except urllib2.HTTPError:
+                raise exception(self.url)
+        # Just let self._fetchUrl throw the exception, don't catch and
+        # customize it.
+        else:
+            data = self._fetchUrl(url, parameters)
+
+        return BeautifulSoup.BeautifulSoup(data)
+
+    @staticmethod
+    def getSiteDomain():
+        return Voracity2EficComAdapter.SITE_DOMAIN
+
+    @classmethod
+    def getSiteExampleURLs(cls):
+        return cls.VIEW_STORY_URL_TEMPLATE % 1234
+
+    def getSiteURLPattern(self):
+        return re.escape(self.VIEW_STORY_URL_TEMPLATE[:-2]) + r'\d+$'
+
+    def extractChapterUrlsAndMetadata(self):
+        soup = self._customized_fetch_url(self.url + self.METADATA_URL_SUFFIX)
+
+        # Check if the story is for "Registered Users Only", i.e. has adult
+        # content. Based on the "is_adult" attributes either login or raise an
+        # error.
+        errortext_div = soup.find('div', {'class': 'errortext'})
+        if errortext_div:
+            error_text = ''.join(errortext_div(text=True)).strip()
+            if error_text == 'Registered Users Only':
+                if not (self.is_adult or self.getConfig('is_adult')):
+                    raise exceptions.AdultCheckRequired(self.url)
+                self._login()
+            else:
+                # This case usually occurs when the story doesn't exist, but
+                # might potentially be something else, so just raise
+                # FailedToDownload exception with the found error text.
+                raise exceptions.FailedToDownload(error_text)
+
+        url = ''.join([self.url, self.METADATA_URL_SUFFIX, self.AGE_CONSENT_URL_SUFFIX])
+        soup = self._customized_fetch_url(url)
+
+        # If logged in and the skin doesn't match the required skin throw an
+        # error
+        if self.is_logged_in:
+            skin = soup.find('select', {'name': 'skin'}).find('option', selected=True)['value']
+            if skin != self.REQUIRED_SKIN:
+                raise exceptions.FailedToDownload('Required skin "%s" must be set in preferences' % self.REQUIRED_SKIN)
+
+        pagetitle_div = soup.find('div', id='pagetitle')
+        self.story.setMetadata('title', pagetitle_div.a.string)
+
+        author_anchor = pagetitle_div.a.findNextSibling('a')
+        url = urlparse.urljoin(self.BASE_URL, author_anchor['href'])
+        components = urlparse.urlparse(url)
+        query_data = urlparse.parse_qs(components.query)
+
+        self.story.setMetadata('author', author_anchor.string)
+        self.story.setMetadata('authorId', query_data['uid'])
+        self.story.setMetadata('authorUrl', url)
+
+        sort_div = soup.find('div', id='sort')
+        self.story.setMetadata('reviews', sort_div('a')[1].string)
+
+        for b_tag in soup.find('div', {'class': 'listbox'})('b'):
+            key = b_tag.string.strip(' :')
+            try:
+                value = b_tag.nextSibling.string.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
+            except AttributeError:
+                value = None
+
+            if key == 'Summary':
+                contents = []
+                keep_summary_html = self.getConfig('keep_summary_html')
+
+                for sibling in _yield_next_siblings(b_tag):
+                    if isinstance(sibling, BeautifulSoup.Tag):
+                        # Encountered next label, break. This method is the
+                        # safest and most reliable I could think of. Blame
+                        # e-fiction sites that allow their users to include
+                        # arbitrary markup into their summaries and the
+                        # horrible HTML markup.
+                        if sibling.name == 'b' and sibling.findPreviousSibling().name == 'br':
+                            break
+
+                        if keep_summary_html:
+                            contents.append(self.utf8FromSoup(self.url, sibling))
+                        else:
+                            contents.append(''.join(sibling(text=True)))
+                    else:
+                        contents.append(sibling)
+
+                # Remove the preceding break line tag and other crud
+                contents.pop()
+                contents.pop()
+                self.story.setMetadata('description', ''.join(contents))
+
+            elif key == 'Rating':
+                self.story.setMetadata('rating', value)
+
+            elif key == 'Category':
+                for sibling in b_tag.findNextSiblings(['a', 'br']):
+                    if sibling.name == 'br':
+                        break
+                    self.story.addToList('category', sibling.string)
+
+            # Seems to be always "None" for some reason
+            elif key == 'Characters':
+                for sibling in b_tag.findNextSiblings(['a', 'br']):
+                    if sibling.name == 'br':
+                        break
+                    self.story.addToList('characters', sibling.string)
+
+            elif key == 'Series':
+                a = b_tag.findNextSibling('a')
+                if not a:
+                    continue
+                self.story.setMetadata('series', a.string)
+                self.story.setMetadata('seriesUrl', urlparse.urljoin(self.BASE_URL, a['href']))
+
+            elif key == 'Chapter':
+                self.story.setMetadata('numChapters', int(value))
+
+            elif key == 'Completed':
+                self.story.setMetadata('status', 'Completed' if value == 'Yes' else 'In-Progress')
+
+            elif key == 'Words':
+                self.story.setMetadata('numWords', value)
+
+            elif key == 'Read':
+                self.story.setMetadata('readings', value)
+
+            elif key == 'Published':
+                self.story.setMetadata('datePublished', makeDate(value, self.DATETIME_FORMAT))
+
+            elif key == 'Updated':
+                self.story.setMetadata('dateUpdated', makeDate(value, self.DATETIME_FORMAT))
+
+        for b_tag in soup.find('div', id='output').findNextSiblings('b'):
+            chapter_anchor = b_tag.a
+            title = chapter_anchor.string
+            url = urlparse.urljoin(self.BASE_URL, chapter_anchor['href'])
+            self.chapterUrls.append((title, url))
+
+    def getChapterText(self, url):
+        url += self.AGE_CONSENT_URL_SUFFIX
+        soup = self._customized_fetch_url(url)
+        return self.utf8FromSoup(url, soup.find('div', id='story'))

fanficdownloader/adapters/adapter_wraithbaitcom.py

@@ -125,6 +125,10 @@ class WraithBaitComAdapter(BaseSiteAdapter):
         rating=pt.text.split('[')[1].split(']')[0]
         self.story.setMetadata('rating', rating)
 
+        st = soup.find('div', {'class' : 'storytitle'})
+        a = st.findAll('a', href=re.compile(r'reviews.php\?type=ST&item='+self.story.getMetadata('storyId')+"$"))[1] # second one.
+        self.story.setMetadata('reviews',stripHTML(a))
+        
         # Find the chapters:
         for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
             # include author on chapters if multiple authors.

fanficdownloader/adapters/base_adapter.py

@@ -76,6 +76,8 @@ class BaseSiteAdapter(Configurable):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
+
+        self.override_sleep = None
         
         self.opener = u2.build_opener(u2.HTTPCookieProcessor(),GZipProcessor())
         ## Specific UA because too many sites are blocking the default python UA.
@@ -147,8 +149,7 @@ class BaseSiteAdapter(Configurable):
 
     # Assumes application/x-www-form-urlencoded.  parameters, headers are dict()s
     def _postUrl(self, url, parameters={}, headers={}):
-        if self.getConfig('slow_down_sleep_time'):
-            time.sleep(float(self.getConfig('slow_down_sleep_time')))
+        self.do_sleep()
 
         ## u2.Request assumes POST when data!=None.  Also assumes data
         ## is application/x-www-form-urlencoded.
@@ -159,24 +160,38 @@ class BaseSiteAdapter(Configurable):
         req = u2.Request(url,
                          data=urllib.urlencode(parameters),
                          headers=headers)
-        return self._decode(self.opener.open(req).read())
+        return self._decode(self.opener.open(req,None,float(self.getConfig('connect_timeout',30.0))).read())
 
     def _fetchUrlRaw(self, url, parameters=None):
         if parameters != None:
-            return self.opener.open(url.replace(' ','%20'),urllib.urlencode(parameters)).read()
+            return self.opener.open(url.replace(' ','%20'),urllib.urlencode(parameters),float(self.getConfig('connect_timeout',30.0))).read()
         else:
-            return self.opener.open(url.replace(' ','%20')).read()
+            return self.opener.open(url.replace(' ','%20'),None,float(self.getConfig('connect_timeout',30.0))).read()
+
+    def set_sleep(self,val):
+        print("\n===========\n set sleep time %s\n==========="%val)
+        self.override_sleep = val
     
+    def do_sleep(self):
+        if self.override_sleep:
+            time.sleep(float(self.override_sleep))
+        elif self.getConfig('slow_down_sleep_time'):
+            time.sleep(float(self.getConfig('slow_down_sleep_time')))
+        
     # parameters is a dict()
     def _fetchUrl(self, url, parameters=None):
-        if self.getConfig('slow_down_sleep_time'):
-            time.sleep(float(self.getConfig('slow_down_sleep_time')))
+        self.do_sleep()
 
         excpt=None
         for sleeptime in [0, 0.5, 4, 9]:
             time.sleep(sleeptime)	
             try:
                 return self._decode(self._fetchUrlRaw(url,parameters))
+            except u2.HTTPError, he:
+                excpt=he
+                if he.code == 404:
+                    logger.warn("Caught an exception reading URL: %s  Exception %s."%(unicode(url),unicode(he)))
+                    break # break out on 404
             except Exception, e:
                 excpt=e
                 logger.warn("Caught an exception reading URL: %s  Exception %s."%(unicode(url),unicode(e)))
@@ -282,9 +297,10 @@ class BaseSiteAdapter(Configurable):
     @classmethod
     def getSiteExampleURLs(self):
         """
+        Return a string of space separated example URLs.
         Needs to be overriden in each adapter class.  It's the adapter
         writer's responsibility to make sure the example(s) pass the
-        URL validate.
+        validateURL method.
         """
         return 'no such example'
     
@@ -313,7 +329,8 @@ class BaseSiteAdapter(Configurable):
 
     def setCoverImage(self,storyurl,imgurl):
         if self.getConfig('include_images'):
-            self.story.addImgUrl(storyurl,imgurl,self._fetchUrlRaw,cover=True)
+            self.story.addImgUrl(storyurl,imgurl,self._fetchUrlRaw,cover=True,
+                                 coverexclusion=self.getConfig('cover_exclusion_regexp'))
 
     # This gives us a unicode object, not just a string containing bytes.
     # (I gave soup a unicode string, you'd think it could give it back...)
@@ -358,7 +375,7 @@ class BaseSiteAdapter(Configurable):
 
         retval = soup.__str__('utf8').decode('utf-8')
 
-        if self.getConfig('nook_img_fix'):
+        if self.getConfig('nook_img_fix') and not self.getConfig('replace_br_with_p'):
             # if the <img> tag doesn't have a div or a p around it,
             # nook gets confused and displays it on every page after
             # that under the text for the rest of the chapter.
@@ -367,7 +384,7 @@ class BaseSiteAdapter(Configurable):
             
         # Don't want body tags in chapter html--writers add them.
         # This is primarily for epub updates.
-        retval = re.sub(r"</?body>\r?\n?","",retval)
+        retval = re.sub(r"</?body[^>]*>\r?\n?","",retval)
         
         if self.getConfig("replace_br_with_p"):
             # Apply heuristic processing to replace <br> paragraph

fanficdownloader/configurable.py

@@ -53,46 +53,52 @@ class Configuration(ConfigParser.SafeConfigParser):
             self.addConfigSection(sitewithout+":"+fileform)
         self.addConfigSection("overrides")
         
-        self.validEntries = [
+        self.listTypeEntries = [
             'category',
             'genre',
-            'language',
             'characters',
             'ships',
+            'warnings',
+            'extratags',
+            'author',
+            'authorId',
+            'authorUrl',
+            'lastupdate',
+            ]
+        
+        self.validEntries = self.listTypeEntries + [
             'series',
             'seriesUrl',
+            'language',
             'status',
             'datePublished',
             'dateUpdated',
             'dateCreated',
             'rating',
-            'warnings',
             'numChapters',
             'numWords',
             'site',
             'storyId',
-            'authorId',
-            'extratags',
             'title',
             'storyUrl',
             'description',
-            'author',
-            'authorUrl',
             'formatname',
             'formatext',
             'siteabbrev',
             'version',
             # internal stuff.
-            'langcode',
-            'output_css',
             'authorHTML',
             'seriesHTML',
-            'lastupdate'
+            'langcode',
+            'output_css',
             ]
 
     def addConfigSection(self,section):
         self.sectionslist.insert(0,section)
 
+    def isListType(self,key):
+        return key in self.listTypeEntries or self.hasConfig("include_in_"+key)
+        
     def isValidMetaEntry(self, key):
         return key in self.getValidMetaList()
 
@@ -162,6 +168,9 @@ class Configurable(object):
     def __init__(self, configuration):
         self.configuration = configuration
 
+    def isListType(self,key):
+        return self.configuration.isListType(key)
+
     def isValidMetaEntry(self, key):
         return self.configuration.isValidMetaEntry(key)
 

fanficdownloader/epubutils.py

@@ -4,7 +4,7 @@ from __future__ import (unicode_literals, division, absolute_import,
                         print_function)
 
 __license__   = 'GPL v3'
-__copyright__ = '2012, Jim Miller'
+__copyright__ = '2014, Jim Miller'
 __docformat__ = 'restructuredtext en'
 
 import logging

fanficdownloader/htmlheuristics.py

@@ -18,7 +18,9 @@
 import logging
 logger = logging.getLogger(__name__)
 import re
+import codecs
 import BeautifulSoup as bs
+import HtmlTagStack as stack
 
 from . import exceptions as exceptions
 
@@ -28,7 +30,7 @@ def replace_br_with_p(body):
     # However, Python Regex does not recognize it as a whitespace, so we'll be changing it to a reagular space.
     body = body.replace(u'\xa0', u' ')
 
-    if body.find('>') == -1 or body.rfind("<") == -1:
+    if body.find('>') == -1 or body.rfind('<') == -1:
         return body
 
     # logger.debug(u'BODY start.: ' + body[:250])
@@ -42,11 +44,11 @@ def replace_br_with_p(body):
     # tag in all cases now should be div, to just strip the first and
     # last tags.
     if is_valid_block(body) and body.find('<div') == 0:
-        body = body[body.index('>')+1:body.rindex("<")]
+        body = body[body.index('>')+1:body.rindex('<')]
 
     body = soup_up_div(u'<div>' + body + u'</div>')
 
-    body = body[body.index('>')+1:body.rindex("<")]
+    body = body[body.index('>')+1:body.rindex('<')]
 
     # Find all bexisting blocks with p, pre and blockquote tags, we need to shields break tags inside those.
     # This is for "lenient" mode, however it is also used to clear break tags before and after the block elements.
@@ -135,32 +137,35 @@ def replace_br_with_p(body):
             contentLinesSum += lineLen
             if lineLen > longestLineLength:
                 longestLineLength = lineLen
+                
+    if contentLines == 0:
+        contentLines = 1
 
     averageLineLength = contentLinesSum/contentLines
 
     logger.debug(u'---')
-    logger.debug(u'Lines.............: ' + str(len(lines)))
-    logger.debug(u'contentLines......: ' + str(contentLines))
-    logger.debug(u'contentLinesSum...: ' + str(contentLinesSum))
-    logger.debug(u'longestLineLength.: ' + str(longestLineLength))
-    logger.debug(u'averageLineLength.: ' + str(averageLineLength))
+    logger.debug(u'Lines.............: ' + unicode(len(lines)))
+    logger.debug(u'contentLines......: ' + unicode(contentLines))
+    logger.debug(u'contentLinesSum...: ' + unicode(contentLinesSum))
+    logger.debug(u'longestLineLength.: ' + unicode(longestLineLength))
+    logger.debug(u'averageLineLength.: ' + unicode(averageLineLength))
 
     if breaksMaxIndex == len(breaksCount)-1 and breaksMax < 2:
         breaksMaxIndex = 0
         breaksMax = breaksCount[0]
 
     logger.debug(u'---')
-    logger.debug(u'breaks 1: ' + str(breaksCount[0]))
-    logger.debug(u'breaks 2: ' + str(breaksCount[1]))
-    logger.debug(u'breaks 3: ' + str(breaksCount[2]))
-    logger.debug(u'breaks 4: ' + str(breaksCount[3]))
-    logger.debug(u'breaks 5: ' + str(breaksCount[4]))
-    logger.debug(u'breaks 6: ' + str(breaksCount[5]))
-    logger.debug(u'breaks 7: ' + str(breaksCount[6]))
-    logger.debug(u'breaks 8: ' + str(breaksCount[7]))
+    logger.debug(u'breaks 1: ' + unicode(breaksCount[0]))
+    logger.debug(u'breaks 2: ' + unicode(breaksCount[1]))
+    logger.debug(u'breaks 3: ' + unicode(breaksCount[2]))
+    logger.debug(u'breaks 4: ' + unicode(breaksCount[3]))
+    logger.debug(u'breaks 5: ' + unicode(breaksCount[4]))
+    logger.debug(u'breaks 6: ' + unicode(breaksCount[5]))
+    logger.debug(u'breaks 7: ' + unicode(breaksCount[6]))
+    logger.debug(u'breaks 8: ' + unicode(breaksCount[7]))
     logger.debug(u'----')
-    logger.debug(u'max found: ' + str(breaksMax))
-    logger.debug(u'max Index: ' + str(breaksMaxIndex))
+    logger.debug(u'max found: ' + unicode(breaksMax))
+    logger.debug(u'max Index: ' + unicode(breaksMaxIndex))
     logger.debug(u'----')
 
     if breaksMaxIndex > 0 and breaksCount[0] > breaksMax and averageLineLength < 90:
@@ -169,14 +174,15 @@ def replace_br_with_p(body):
     # Find all instances of consecutive breaks less than otr equal to the max count use most often
     #  replase those tags to inverted p tag pairs, those with more connsecutive breaks are replaced them with a horisontal line
     for i in range(len(breaksCount)):
+        # if i > 0 or breaksMaxIndex == 0:
         if i <= breaksMaxIndex:
-            logger.debug(str(i) + u' <= breaksMaxIndex (' + str(breaksMaxIndex) + u')')
+            logger.debug(unicode(i) + u' <= breaksMaxIndex (' + unicode(breaksMaxIndex) + u')')
             body = breaksRegexp[i].sub(r'\1</p>\n<p>\3', body)
         elif i == breaksMaxIndex+1:
-            logger.debug(str(i) + u' == breaksMaxIndex+1 (' + str(breaksMaxIndex+1) + u')')
+            logger.debug(unicode(i) + u' == breaksMaxIndex+1 (' + unicode(breaksMaxIndex+1) + u')')
             body = breaksRegexp[i].sub(r'\1</p>\n<p><br/></p>\n<p>\3', body)
         else:
-            logger.debug(str(i) + u' > breaksMaxIndex+1 (' + str(breaksMaxIndex+1) + u')')
+            logger.debug(unicode(i) + u' > breaksMaxIndex+1 (' + unicode(breaksMaxIndex+1) + u')')
             body = breaksRegexp[i].sub(r'\1</p>\n<hr />\n<p>\3', body)
 
     body = breaksRegexp[8].sub(r'</p>\n<hr />\n<p>', body)
@@ -223,10 +229,11 @@ def replace_br_with_p(body):
     # re-wrap in div tag.
     body = u'<div>\n' + body + u'</div>\n'
 
-    return body
+    # return body
+    return tag_sanitizer(body)
 
 def is_valid_block(block):
-    return str(block).find('<') == 0 and str(block).find('<!') != 0
+    return unicode(block).find('<') == 0 and unicode(block).find('<!') != 0
 
 def soup_up_div(body):
     blockTags = ['address', 'blockquote', 'del', 'div', 'dl', 'fieldset', 'form', 'ins', 'noscript', 'ol', 'p', 'pre', 'table', 'ul']
@@ -243,8 +250,8 @@ def soup_up_div(body):
     lastElement = 1 # 1 = block, 2 = nested, 3 = invalid
 
     for i in soup.contents[0]:
-        if str(i).strip().__len__() > 0:
-            s = str(i)
+        if unicode(i).strip().__len__() > 0:
+            s = unicode(i)
             if  type(i) == bs.Tag:
                 if  i.name in blockTags:
                     if lastElement > 1:
@@ -281,3 +288,61 @@ def soup_up_div(body):
     body = body.replace(u'[br /]', u'<br />')
 
     return tag + body + tagend
+
+
+def is_end_tag(tag):
+    return re.match(r'</([^\ >]+)>', tag) != None
+
+def is_comment_tag(tag):
+    return re.match(r'<\!\-\-([^>]+)>', tag) != None
+
+def is_closed_tag(tag):
+    return re.match(r'<(.+?)/>', tag) != None
+
+def tag_sanitizer(html):
+    blockTags = ['address', 'blockquote', 'del', 'div', 'dl', 'fieldset', 'form', 'ins', 'noscript', 'ol', 'pre', 'table', 'ul']
+
+    body = u''
+    tags = re.findall(r'(<[^>]+>)([^<]*)', html)
+
+    for rTag in tags:
+        name = stack.get_tag_name(rTag[0])
+        is_end = is_end_tag(rTag[0])
+        is_closed = is_closed_tag(rTag[0]) or is_comment_tag(rTag[0])
+
+        # is_comment = is_comment_tag(rTag[0])
+        # logger.debug(u'%s >  isEnd: %s >  isClosed: %s >  isComment: %s'%(name, unicode(is_end), unicode(is_closed), unicode(is_comment)))
+        # logger.debug(u'> %s%s\n'%(rTag[0], rTag[1]))
+
+        if name in blockTags:
+            body += rTag[0]
+            body += rTag[1]
+        elif name == u'p':
+            if is_end:
+                body += stack.spool_end()
+                body += rTag[0]
+                body += rTag[1]
+            elif is_closed:
+                body += rTag[0]
+                body += rTag[1]
+            else:
+                body += rTag[0]
+                body += stack.spool_start()
+                body += rTag[1]
+        else:
+            if is_end:
+                t = stack.get_last()
+                tn = stack.get_tag_name(t)
+                rTn = stack.get_tag_name(rTag[0])
+                if tn == rTn:
+                    body += rTag[0]
+                    stack.pop()
+            elif not is_closed:
+                stack.push(rTag[0])
+                body += rTag[0]
+            else:
+                body += rTag[0]
+
+            body += rTag[1]
+    stack.flush()
+    return body

fanficdownloader/story.py

@@ -28,9 +28,12 @@ import exceptions
 from htmlcleanup import conditionalRemoveEntities, removeAllEntities
 from configurable import Configurable
 
+SPACE_REPLACE=u'\s'
+SPLIT_META=u'\,'
+
 # Create convert_image method depending on which graphics lib we can
 # load.  Preferred: calibre, PIL, none
-        
+
 imagetypes = {
     'jpg':'image/jpeg',
     'jpeg':'image/jpeg',
@@ -48,14 +51,14 @@ try:
         export = False
         img = Image()
         img.load(data)
-        
+
         owidth, oheight = img.size
         nwidth, nheight = sizes
         scaled, nwidth, nheight = fit_image(owidth, oheight, nwidth, nheight)
         if scaled:
             img.size = (nwidth, nheight)
             export = True
-            
+
         if normalize_format_name(img.format) != imgtype:
             export = True
 
@@ -65,7 +68,7 @@ try:
             canvas.compose(img)
             img = canvas
             export = True
-            
+
         if grayscale and img.type != "GrayscaleType":
             img.type = "GrayscaleType"
             export = True
@@ -75,7 +78,7 @@ try:
         else:
             logger.debug("image used unchanged")
             return (data,imgtype,imagetypes[imgtype])
-        
+
 except:
 
     # No calibre routines, try for PIL for CLI.
@@ -87,14 +90,14 @@ except:
                           removetrans,imgtype="jpg",background='#ffffff'):
             export = False
             img = Image.open(StringIO(data))
-            
+
             owidth, oheight = img.size
             nwidth, nheight = sizes
             scaled, nwidth, nheight = fit_image(owidth, oheight, nwidth, nheight)
             if scaled:
                 img = img.resize((nwidth, nheight),Image.ANTIALIAS)
                 export = True
-                
+
             if normalize_format_name(img.format) != imgtype:
                 if img.mode == "P":
                     # convert pallete gifs to RGB so jpg save doesn't fail.
@@ -119,7 +122,7 @@ except:
             else:
                 logger.debug("image used unchanged")
                 return (data,imgtype,imagetypes[imgtype])
-        
+
     except:
         # No calibre or PIL, simple pass through with mimetype.
         def convert_image(url,data,sizes,grayscale,
@@ -129,16 +132,16 @@ except:
 ## also used for explicit no image processing.
 def no_convert_image(url,data):
     parsedUrl = up.urlparse(url)
-    
+
     ext=parsedUrl.path[parsedUrl.path.rfind('.')+1:].lower()
-    
+
     if ext not in imagetypes:
         logger.debug("no_convert_image url:%s - no known extension"%url)
         # doesn't have extension? use jpg.
         ext='jpg'
-        
+
     return (data,ext,imagetypes[ext])
-        
+
 def normalize_format_name(fmt):
     if fmt:
         fmt = fmt.lower()
@@ -221,8 +224,67 @@ langs = {
     "Devanagari":"hi",
     }
 
+class InExMatch:
+    keys = []
+    regex = None
+    match = None
+    negate = False
+
+    def  __init__(self,line):
+        if "=~" in line:
+            (self.keys,self.match) = line.split("=~")
+            self.match = self.match.replace(SPACE_REPLACE,' ')
+            self.regex = re.compile(self.match)
+        elif "!~" in line:
+            (self.keys,self.match) = line.split("!~")
+            self.match = self.match.replace(SPACE_REPLACE,' ')
+            self.regex = re.compile(self.match)
+            self.negate = True
+        elif "==" in line:
+            (self.keys,self.match) = line.split("==")
+            self.match = self.match.replace(SPACE_REPLACE,' ')
+        elif "!=" in line:
+            (self.keys,self.match) = line.split("!=")
+            self.match = self.match.replace(SPACE_REPLACE,' ')
+            self.negate = True
+        self.keys = map( lambda x: x.strip(), self.keys.split(",") )
+
+    # For conditional, only one key
+    def is_key(self,key):
+        return key == self.keys[0]
+
+    # For conditional, only one key
+    def key(self):
+        return self.keys[0]
+
+    def in_keys(self,key):
+        return key in self.keys
+
+    def is_match(self,value):
+        retval = False
+        if self.regex:
+            if self.regex.search(value):
+                retval = True
+            #print(">>>>>>>>>>>>>%s=~%s r: %s,%s=%s"%(self.match,value,self.negate,retval,self.negate != retval))
+        else:
+            retval = self.match == value
+            #print(">>>>>>>>>>>>>%s==%s r: %s,%s=%s"%(self.match,value,self.negate,retval, self.negate != retval))
+            
+        return self.negate != retval
+
+    def __str__(self):
+        if self.negate:
+            f='!'
+        else:
+            f='='
+        if self.regex:
+            s='~'
+        else:
+            s='='
+        return u'InExMatch(%s %s%s %s)'%(self.keys,f,s,self.match)
+
 class Story(Configurable):
-    
+
     def __init__(self, configuration):
         Configurable.__init__(self, configuration)
         try:
@@ -231,18 +293,18 @@ class Story(Configurable):
         except:
             self.metadata = {'version':'4.4'}
         self.replacements = []
+        self.in_ex_cludes = {}
         self.chapters = [] # chapters will be tuples of (title,html)
         self.imgurls = []
         self.imgtuples = []
-        
+
         self.cover=None # *href* of new cover image--need to create html.
         self.oldcover=None # (oldcoverhtmlhref,oldcoverhtmltype,oldcoverhtmldata,oldcoverimghref,oldcoverimgtype,oldcoverimgdata)
         self.calibrebookmark=None # cheesy way to carry calibre bookmark file forward across update.
         self.logfile=None # cheesy way to carry log file forward across update.
 
         ## Look for config parameter, split and add each to metadata field.
-        for (config,metadata) in [("extratags","extratags"),
-                                  ("extracategories","category"),
+        for (config,metadata) in [("extracategories","category"),
                                   ("extragenres","genre"),
                                   ("extracharacters","characters"),
                                   ("extraships","ships"),
@@ -251,24 +313,93 @@ class Story(Configurable):
                 self.addToList(metadata,val)
 
         self.setReplace(self.getConfig('replace_metadata'))
-        
+
+        in_ex_clude_list = ['include_metadata_pre','exclude_metadata_pre',
+                            'include_metadata_post','exclude_metadata_post']
+        for ie in in_ex_clude_list:
+            ies = self.getConfig(ie)
+            # print("%s %s"%(ie,ies))
+            if ies:
+                iel = []
+                self.in_ex_cludes[ie] = self.set_in_ex_clude(ies)
+
+    def join_list(self, key, vallist):
+        return self.getConfig("join_string_"+key,u", ").replace(SPACE_REPLACE,' ').join(map(unicode, vallist))
+                
     def setMetadata(self, key, value, condremoveentities=True):
-        ## still keeps < < and &
-        if condremoveentities:
-            self.metadata[key]=conditionalRemoveEntities(value)
+
+        # keep as list type, but set as only value.
+        if self.isList(key):
+            self.addToList(key,value,condremoveentities=condremoveentities,clear=True)
         else:
-            self.metadata[key]=value
+            ## still keeps < < and &
+            if condremoveentities:
+                self.metadata[key]=conditionalRemoveEntities(value)
+            else:
+                self.metadata[key]=value
+                
         if key == "language":
             try:
                 # getMetadata not just self.metadata[] to do replace_metadata.
-                self.metadata['langcode'] = langs[self.getMetadata(key)]
+                self.setMetadata('langcode',langs[self.getMetadata(key)])
             except:
-                self.metadata['langcode'] = 'en'
-        if key == 'dateUpdated':
+                self.setMetadata('langcode','en')
+                
+        if key == 'dateUpdated' and value:
             # Last Update tags for Bill.
             self.addToList('lastupdate',value.strftime("Last Update Year/Month: %Y/%m"))
             self.addToList('lastupdate',value.strftime("Last Update: %Y/%m/%d"))
 
+        
+    ## metakey[,metakey]=~pattern
+    ## metakey[,metakey]==string
+    ## *for* part lines.  Effect only when trailing conditional key=~regexp matches
+    ## metakey[,metakey]=~pattern[&&metakey=~regexp]
+    ## metakey[,metakey]==string[&&metakey=~regexp]
+    ## metakey[,metakey]=~pattern[&&metakey==string]
+    ## metakey[,metakey]==string[&&metakey==string]
+    def set_in_ex_clude(self,setting):
+        dest = []
+        # print("set_in_ex_clude:"+setting)
+        for line in setting.splitlines():
+            if line:
+                (match,condmatch)=(None,None)
+                if "&&" in line:
+                    (line,conditional) = line.split("&&")
+                    condmatch = InExMatch(conditional)
+                match = InExMatch(line)
+                dest.append([match,condmatch])
+        return dest
+              
+    def do_in_ex_clude(self,which,value,key):
+        if value and which in self.in_ex_cludes:
+            include = 'include' in which
+            keyfound = False
+            found = False
+            for (match,condmatch) in self.in_ex_cludes[which]:
+                keyfndnow = False
+                if match.in_keys(key):
+                    # key in keys and either no conditional, or conditional matched
+                    if condmatch == None or condmatch.is_key(key):
+                        keyfndnow = True
+                    else:
+                        condval = self.getMetadata(condmatch.key())
+                        keyfndnow = condmatch.is_match(condval)
+                    keyfound |= keyfndnow
+                        # print("match:%s %s\ncondmatch:%s %s\n\tkeyfound:%s\n\tfound:%s"%(
+                        #         match,value,condmatch,condval,keyfound,found))
+                    if keyfndnow:
+                        found = isinstance(value,basestring) and match.is_match(value)
+                    if found:
+                        # print("match:%s %s\n\tkeyfndnow:%s\n\tfound:%s"%(
+                        #         match,value,keyfndnow,found))
+                        if not include:
+                            value = None
+                        break
+            if include and keyfound and not found:
+                value = None
+        return value
+        
 
     ## Two or three part lines.  Two part effect everything.
     ## Three part effect only those key(s) lists.
@@ -278,6 +409,7 @@ class Story(Configurable):
     ## metakey[,metakey]=>pattern=>replacement[&&metakey=>regexp]
     def setReplace(self,replace):
         for line in replace.splitlines():
+            # print("replacement line:%s"%line)
             (metakeys,regexp,replacement,condkey,condregexp)=(None,None,None,None,None)
             if "&&" in line:
                 (line,conditional) = line.split("&&")
@@ -297,11 +429,20 @@ class Story(Configurable):
                 # A way to explicitly include spaces in the
                 # replacement string.  The .ini parser eats any
                 # trailing spaces.
-                replacement=replacement.replace('\s',' ') 
+                replacement=replacement.replace(SPACE_REPLACE,' ')
                 self.replacements.append([metakeys,regexp,replacement,condkey,condregexp])
-    
-    def doReplacements(self,value,key):
-        for (metakeys,regexp,replacement,condkey,condregexp) in self.replacements:
+
+    def doReplacements(self,value,key,return_list=False,seen_list=[]):
+        value = self.do_in_ex_clude('include_metadata_pre',value,key)
+        value = self.do_in_ex_clude('exclude_metadata_pre',value,key)
+
+        retlist = [value]
+        for replaceline in self.replacements:
+            if replaceline in seen_list: # recursion on pattern, bail
+                # print("bailing on %s"%replaceline)
+                continue
+            #print("replacement tuple:%s"%replaceline)
+            (metakeys,regexp,replacement,condkey,condregexp) = replaceline
             if (metakeys == None or key in metakeys) \
                     and isinstance(value,basestring) \
                     and regexp.search(value):
@@ -309,11 +450,37 @@ class Story(Configurable):
                 if condkey and condkey != key: # prevent infinite recursion.
                     condval = self.getMetadata(condkey)
                     doreplace = condval != None and condregexp.search(condval)
-                    
+
                 if doreplace:
-                    value = regexp.sub(replacement,value)
-        return value
-        
+                    # split into more than one list entry if
+                    # SPLIT_META present in replacement string.  Split
+                    # first, then regex sub, then recurse call replace
+                    # on each.  Break out of loop, each split element
+                    # handled individually by recursion call.
+                    if SPLIT_META in replacement:
+                        retlist = []
+                        for splitrepl in replacement.split(SPLIT_META):
+                            retlist.extend(self.doReplacements(regexp.sub(splitrepl,value),
+                                                               key,
+                                                               return_list=True,
+                                                               seen_list=seen_list+[replaceline]))
+                        break
+                    else:
+                        # print("replacement,value:%s,%s->%s"%(replacement,value,regexp.sub(replacement,value)))
+                        value = regexp.sub(replacement,value)
+                        retlist = [value]
+                    
+        for val in retlist:
+            retlist = map(partial(self.do_in_ex_clude,'include_metadata_post',key=key),retlist)
+            retlist = map(partial(self.do_in_ex_clude,'exclude_metadata_post',key=key),retlist)
+        # value = self.do_in_ex_clude('include_metadata_post',value,key)
+        # value = self.do_in_ex_clude('exclude_metadata_post',value,key)
+
+        if return_list:
+            return retlist
+        else:
+            return self.join_list(key,retlist)
+
     def getMetadataRaw(self,key):
         if self.isValidMetaEntry(key) and self.metadata.has_key(key):
             return self.metadata[key]
@@ -326,8 +493,9 @@ class Story(Configurable):
             return value
 
         if self.isList(key):
-            join_string = self.getConfig("join_string_"+key,u", ").replace('\s',' ') 
-            value = join_string.join(self.getList(key, removeallentities, doreplacements=True))
+            # join_string = self.getConfig("join_string_"+key,u", ").replace(SPACE_REPLACE,' ')
+            # value = join_string.join(self.getList(key, removeallentities, doreplacements=True))
+            value = self.join_list(key,self.getList(key, removeallentities, doreplacements=True))
             if doreplacements:
                 value = self.doReplacements(value,key+"_LIST")
             return value
@@ -351,22 +519,23 @@ class Story(Configurable):
                 return value
         else: #if self.getConfig("default_value_"+key):
             return self.getConfig("default_value_"+key)
-        
+
     def getAllMetadata(self,
                        removeallentities=False,
                        doreplacements=True,
                        keeplists=False):
         '''
-        All single value *and* list value metadata as strings (unless keeplists=True, then keep lists).
+        All single value *and* list value metadata as strings (unless
+        keeplists=True, then keep lists).
         '''
         allmetadata = {}
-        
+
         # special handling for authors/authorUrls
         linkhtml="<a class='%slink' href='%s'>%s</a>"
         if self.isList('author'): # more than one author, assume multiple authorUrl too.
             htmllist=[]
             for i, v in enumerate(self.getList('author')):
-                aurl = self.getList('authorUrl')[i]                    
+                aurl = self.getList('authorUrl')[i]
                 auth = v
                 # make sure doreplacements & removeallentities are honored.
                 if doreplacements:
@@ -375,38 +544,62 @@ class Story(Configurable):
                 if removeallentities:
                     aurl=removeAllEntities(aurl)
                     auth=removeAllEntities(auth)
-                
+
                 htmllist.append(linkhtml%('author',aurl,auth))
-            join_string = self.getConfig("join_string_authorHTML",u", ").replace('\s',' ') 
-            self.setMetadata('authorHTML',join_string.join(htmllist))
+            # join_string = self.getConfig("join_string_authorHTML",u", ").replace(SPACE_REPLACE,' ')
+            self.setMetadata('authorHTML',self.join_list("join_string_authorHTML",htmllist))
         else:
             self.setMetadata('authorHTML',linkhtml%('author',self.getMetadata('authorUrl', removeallentities, doreplacements),
                                                     self.getMetadata('author', removeallentities, doreplacements)))
 
-        if self.getMetadataRaw('seriesUrl') != None:
+        if self.getMetadataRaw('seriesUrl'):
             self.setMetadata('seriesHTML',linkhtml%('series',self.getMetadata('seriesUrl', removeallentities, doreplacements),
                                                     self.getMetadata('series', removeallentities, doreplacements)))
-        elif self.getMetadataRaw('series') != None:
+        elif self.getMetadataRaw('series'):
             self.setMetadata('seriesHTML',self.getMetadataRaw('series'))
-            
+
+        # logger.debug("make_linkhtml_entries:%s"%self.getConfig('make_linkhtml_entries'))
+        for k in self.getConfigList('make_linkhtml_entries'):
+            # Assuming list, because it has to be site specific and
+            # they are all lists.  Bail if kUrl list not the same
+            # length.
+            # logger.debug("\nk:%s\nlist:%s\nlistURL:%s"%(k,self.getList(k),self.getList(k+'Url')))
+            if len(self.getList(k+'Url')) != len(self.getList(k)):
+                continue
+            htmllist=[]
+            for i, v in enumerate(self.getList(k)):
+                url = self.getList(k+'Url')[i]
+                # make sure doreplacements & removeallentities are honored.
+                if doreplacements:
+                    url=self.doReplacements(url,k+'Url')
+                    v=self.doReplacements(v,k)
+                if removeallentities:
+                    url=removeAllEntities(url)
+                    v=removeAllEntities(v)
+
+                htmllist.append(linkhtml%(k,url,v))
+            # join_string = self.getConfig("join_string_"+k+"HTML",u", ").replace(SPACE_REPLACE,' ')
+            self.setMetadata(k+'HTML',self.join_list("join_string_"+k+"HTML",htmllist))
+
         for k in self.getValidMetaList():
             if self.isList(k) and keeplists:
                 allmetadata[k] = self.getList(k, removeallentities, doreplacements)
             else:
                 allmetadata[k] = self.getMetadata(k, removeallentities, doreplacements)
-                
+
         return allmetadata
 
     # just for less clutter in adapters.
     def extendList(self,listname,l):
         for v in l:
             self.addToList(listname,v.strip())
-    
-    def addToList(self,listname,value):
+
+    def addToList(self,listname,value,condremoveentities=True,clear=False):
         if value==None:
             return
-        value = conditionalRemoveEntities(value)
-        if not self.isList(listname) or not listname in self.metadata:
+        if condremoveentities:
+            value = conditionalRemoveEntities(value)
+        if clear or not self.isList(listname) or not listname in self.metadata:
             # Calling addToList to a non-list meta will overwrite it.
             self.metadata[listname]=[]
         # prevent duplicates.
@@ -418,27 +611,27 @@ class Story(Configurable):
 
     def isList(self,listname):
         'Everything set with an include_in_* is considered a list.'
-        return self.hasConfig("include_in_"+listname) or \
+        return self.isListType(listname) or \
             ( self.isValidMetaEntry(listname) and self.metadata.has_key(listname) \
                   and isinstance(self.metadata[listname],list) )
-    
+
     def getList(self,listname,
                 removeallentities=False,
                 doreplacements=True,
                 includelist=[]):
         #print("getList(%s,%s)"%(listname,includelist))
         retlist = []
-        
+
         if not self.isValidMetaEntry(listname):
             return retlist
-        
+
         # includelist prevents infinite recursion of include_in_'s
         if self.hasConfig("include_in_"+listname) and listname not in includelist:
             for k in self.getConfigList("include_in_"+listname):
                 retlist.extend(self.getList(k,removeallentities=False,
                                             doreplacements=doreplacements,includelist=includelist+[listname]))
         else:
-        
+
             if not self.isList(listname):
                 retlist = [self.getMetadata(listname,removeallentities=False,
                                             doreplacements=doreplacements)]
@@ -447,18 +640,22 @@ class Story(Configurable):
 
         if retlist:
             if doreplacements:
-                retlist = filter( lambda x : x!=None and x!='' ,
-                                  map(partial(self.doReplacements,key=listname),retlist) )
+                newretlist = []
+                for val in retlist:
+                    newretlist.extend(self.doReplacements(val,listname,return_list=True))
+                retlist = newretlist
+                
             if removeallentities:
-                retlist = filter( lambda x : x!=None and x!='' ,
-                                  map(removeAllEntities,retlist) )
+                retlist = map(removeAllEntities,retlist)
+                
+            retlist = filter( lambda x : x!=None and x!='' ,retlist)
 
         # reorder ships so b/a and c/b/a become a/b and a/b/c.  Only on '/',
         # use replace_metadata to change separator first if needed.
         # ships=>[ ]*(/|&amp;|&)[ ]*=>/
-        if listname == 'ships' and self.getConfig('sort_ships'):
+        if listname == 'ships' and self.getConfig('sort_ships') and retlist:
             retlist = [ '/'.join(sorted(x.split('/'))) for x in retlist ]
-                
+
         if retlist:
             if listname in ('author','authorUrl','authorId') or self.getConfig('keep_in_order_'+listname):
                 # need to retain order for author & authorUrl so the
@@ -473,9 +670,9 @@ class Story(Configurable):
     def getSubjectTags(self, removeallentities=False):
         # set to avoid duplicates subject tags.
         subjectset = set()
-        
+
         tags_list = self.getConfigList("include_subject_tags") + self.getConfigList("extra_subject_tags")
-            
+
         # metadata all go into dc:subject tags, but only if they are configured.
         for (name,value) in self.getAllMetadata(removeallentities=removeallentities,keeplists=True).iteritems():
             if name in tags_list:
@@ -491,7 +688,7 @@ class Story(Configurable):
             subjectset.remove('')
 
         return list(subjectset | set(self.getConfigList("extratags")))
-            
+
     def addChapter(self, url, title, html):
         if self.getConfig('strip_chapter_numbers') and \
                 self.getConfig('chapter_title_strip_pattern'):
@@ -512,7 +709,7 @@ class Story(Configurable):
                                 html) )
         else:
             retval = self.chapters
-            
+
         return retval
 
     def formatFileName(self,template,allowunsafefilename=True):
@@ -526,7 +723,7 @@ class Story(Configurable):
             pattern = re.compile(self.getConfig("output_filename_safepattern",r"[^a-zA-Z0-9_\. \[\]\(\)&'-]+"))
             for k in origvalues.keys():
                 values[k]=re.sub(pattern,'_', removeAllEntities(self.getMetadata(k)))
-    
+
         return string.Template(template).substitute(values).encode('utf8')
 
     # pass fetch in from adapter in case we need the cookies collected
@@ -537,7 +734,7 @@ class Story(Configurable):
         # isn't used anywhere.
         if cover and self.getConfig('never_make_cover'):
             return
-        
+
         url = url.strip() # ran across an image with a space in the
                           # src. Browser handled it, so we'd better, too.
 
@@ -545,12 +742,18 @@ class Story(Configurable):
         # gets too big too fast and breaks things.
         if is_appengine:
             return
-        
+
         if url.startswith("http") or url.startswith("file") or parenturl == None:
             imgurl = url
         else:
             parsedUrl = urlparse.urlparse(parenturl)
-            if url.startswith("/") :
+            if url.startswith("//") :
+                imgurl = urlparse.urlunparse(
+                    (parsedUrl.scheme,
+                     '',
+                     url,
+                     '','',''))
+            elif url.startswith("/") :
                 imgurl = urlparse.urlunparse(
                     (parsedUrl.scheme,
                      parsedUrl.netloc,
@@ -569,6 +772,10 @@ class Story(Configurable):
                      '','',''))
                 #print("\n===========\nparsedUrl.path:%s\ntoppath:%s\nimgurl:%s\n\n"%(parsedUrl.path,toppath,imgurl))
 
+        # apply coverexclusion to explicit covers, too.  Primarily for ffnet imageu.
+        if cover and coverexclusion and re.search(coverexclusion,imgurl):
+            return
+
         prefix='ffdl'
         if imgurl not in self.imgurls:
             parsedUrl = urlparse.urlparse(imgurl)
@@ -598,9 +805,9 @@ class Story(Configurable):
             except Exception, e:
                 logger.info("Failed to load or convert image, skipping:\n%s\nException: %s"%(imgurl,e))
                 return "failedtoload"
-            
+
             # explicit cover, make the first image.
-            if cover and not self.getConfig('never_make_cover'):
+            if cover:
                 if len(self.imgtuples) > 0 and 'cover' in self.imgtuples[0]['newsrc']:
                     # remove existing cover, if there is one.
                     del self.imgurls[0]
@@ -619,24 +826,24 @@ class Story(Configurable):
                 if self.cover == None and \
                         self.getConfig('make_firstimage_cover') and \
                         not self.getConfig('never_make_cover') and \
-                        (not coverexclusion or not re.search(coverexclusion,imgurl)):
+                        not (coverexclusion and re.search(coverexclusion,imgurl)):
                     newsrc = "images/cover.%s"%ext
                     self.cover=newsrc
                     self.imgtuples.append({'newsrc':newsrc,'mime':mime,'data':data})
                     self.imgurls.append(imgurl)
-            
+
                 newsrc = "images/%s-%s.%s"%(
                     prefix,
                     self.imgurls.index(imgurl),
                     ext)
                 self.imgtuples.append({'newsrc':newsrc,'mime':mime,'data':data})
-                
+
             #logger.debug("\nimgurl:%s\nnewsrc:%s\nimage size:%d\n"%(imgurl,newsrc,len(data)))
         else:
             newsrc = self.imgtuples[self.imgurls.index(imgurl)]['newsrc']
-            
+
         #print("===============\n%s\nimg url:%s\n============"%(newsrc,self.imgurls[-1]))
-        
+
         return newsrc
 
     def getImgUrls(self):
@@ -645,9 +852,9 @@ class Story(Configurable):
             #parsedUrl = urlparse.urlparse(url)
             retlist.append(self.imgtuples[i])
         return retlist
-    
+
     def __str__(self):
-        return "Metadata: " +str(self.metadata) 
+        return "Metadata: " +str(self.metadata)
 
 def commaGroups(s):
     groups = []

fanficdownloader/writers/writer_epub.py

@@ -361,7 +361,7 @@ div { margin: 0pt; padding: 0pt; }
 
         metadata.appendChild(newTag(contentdom,"dc:contributor",text="fanficdownloader [http://fanficdownloader.googlecode.com]",attrs={"opf:role":"bkp"}))
         metadata.appendChild(newTag(contentdom,"dc:rights",text=""))
-        if self.story.getMetadata('langcode') != None:
+        if self.story.getMetadata('langcode'):
             metadata.appendChild(newTag(contentdom,"dc:language",text=self.story.getMetadata('langcode')))
         else:
             metadata.appendChild(newTag(contentdom,"dc:language",text='en'))

index.html

@@ -46,17 +46,6 @@
       {{yourfile}}
       <!--			</div> -->
 
-          <h3>fanfiction.net / fimfiction.net</h3>
-          <p>
-            Fanfiction.net appears to be blocking access from Google
-            App Engine, which prevents this web service.  There's
-            nothing I can do about it.  At the time of writing, the
-            latest CLI and calibre plugin versions worked.
-          </p>
-          <p>It appears that FimFiction.net is also blocking access from Google
-            App Engine now.
-          </p>
-	  
       {% if authorized %}
       <form action="/fdown" method="post">
 	<div id='urlbox'>
@@ -66,12 +55,16 @@
 	  </div>
 	  <!-- put announcements here, h3 is a good title size. -->
 	  <h3>Changes:</h3>
+	  <p>
+            Now supporting over 100 different sites!  Thanks, cryzed, for pushing us over the top.
+	  </p>
 	  <p>
 	    <ul>
-              <li>Additional fixes/enhancements for replace_br_with_p heuristic processing feature.  Turn on in personal User Config.  Thanks, Asbjørn Grandt.</li>
+              <li>Fix for AO3 authors all coming out as Anonymous.</li>
+              <li>Known issue: Password protected FimFiction.net stories aren't working.  FimF changed API access.</li>
+              <li>Known issue: Specific metadata 'eroticatags' for literotica.com doesn't work on all stories.</li>
 	    </ul>
 	  </p>
-          
 	  <p>
 	    Questions?  Check out our 
 	    <a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownloaderFAQs">FAQs</a>.
@@ -80,7 +73,7 @@
 	    If you have any problems with this application, please
 	    report them in
 	    the <a href="http://groups.google.com/group/fanfic-downloader">FanFictionDownLoader Google Group</a>.  The
-	    <a href="http://4-4-81.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
+	    <a href="http://2-0-01.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
 	  </p>
 	  <div id='error'>
 	    {{ error_message }}

makezip.py

@@ -1,9 +1,7 @@
 #!/usr/bin/python
 # -*- coding: utf-8 -*-
 
-# epubmerge.py 1.0
-
-# Copyright 2011, Jim Miller
+# Copyright 2014, Jim Miller
 
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

status.html

@@ -51,16 +51,6 @@
 	      by {{ fic.author }} ({{ fic.format }})
 	  {% endif %}
 	  {% if fic.failure %}
-          <h3>fanfiction.net / fimfiction.net</h3>
-          <p>
-            FYI, fanfiction.net appears to be blocking access from Google
-            App Engine, which prevents this web service.  There's
-            nothing I can do about it.  At the time of writing, the
-            latest CLI and calibre plugin versions worked.
-          </p>
-          <p>It appears that FimFiction.net is also blocking access from Google
-            App Engine now.
-          </p>
 	  <span id='error'>{{ fic.failure }}</span>
 	  {% endif %}
 	  {% if  not fic.completed and not fic.failure %}