Update CLI download zip.

maplebook using base_efiction.

app.yaml

@@ -1,6 +1,6 @@
 # ffd-retief-hrd fanfictiondownloader
 application: fanfictiondownloader
-version: 4-5-06
+version: 2-0-09
 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, 25)
-    minimum_calibre_version = (1, 13, 0)
+    version             = (2, 0, 9)
+    minimum_calibre_version = (1, 48, 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
@@ -60,7 +81,7 @@ from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.adapters \
 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):
@@ -220,6 +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
@@ -243,7 +265,7 @@ 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]))
@@ -275,12 +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]))
@@ -482,6 +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()
@@ -649,7 +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'])
@@ -665,7 +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'])
@@ -727,17 +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))
+                dropdown.addItem(setting,setting)
             if site == _("Default"):
                 self.gc_dropdowns["Default"] = dropdown
                 if 'Default' in prefs['gc_site_settings']:
-                    dropdown.setCurrentIndex(dropdown.findData(QVariant(prefs['gc_site_settings']['Default'])))
+                    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)
@@ -966,12 +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:
@@ -1007,11 +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
@@ -146,19 +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
@@ -196,9 +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):
@@ -559,7 +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
@@ -829,11 +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'])))
@@ -848,7 +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
@@ -914,15 +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)
@@ -992,10 +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)
@@ -1037,7 +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()
@@ -1047,7 +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
@@ -1089,11 +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
@@ -19,10 +19,12 @@ 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
 
@@ -207,7 +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,
@@ -385,6 +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]
@@ -417,7 +420,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         
     def list_story_urls(self):
         '''Get list of URLs from existing books.'''
-        if self.gui.current_view().selectionModel().selectedRows() == 0 :
+        if not self.gui.current_view().selectionModel().selectedRows() :
             self.gui.status_bar.show_message(_('No Selected Books to Get URLs From'),
                                              3000)
             return
@@ -712,6 +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.'''
 
@@ -724,6 +732,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
 
         options['version'] = self.version
         logger.debug(self.version)
+        options['personal.ini'] = get_ffdl_personalini()
         
         #print("prep_downloads:%s"%books)
 
@@ -764,7 +773,7 @@ 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>
@@ -817,8 +826,16 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         
         skip_date_update = False
         
-        options['personal.ini'] = get_ffdl_personalini()
         adapter = get_ffdl_adapter(url,fileform)
+        ## save and share cookiejar and pagecache between all
+        ## downloads.
+        if 'pagecache' not in options:
+            options['pagecache'] = adapter.get_empty_pagecache()
+        adapter.set_pagecache(options['pagecache'])
+        if 'cookiejar' not in options:
+            options['cookiejar'] = adapter.get_empty_cookiejar()
+        adapter.set_cookiejar(options['cookiejar'])
+            
         # reduce foreground sleep time for ffnet when few books.
         if 'ffnetcount' in options and \
                 adapter.getConfig('tweak_fg_sleep') and \
@@ -836,7 +853,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         ## or a couple tries of one or the other
         for x in range(0,2):
             try:
-                adapter.getStoryMetadataOnly()
+                adapter.getStoryMetadataOnly(get_cover=False)
             except exceptions.FailedToLogin, f:
                 logger.warn("Login Failed, Need Username/Password.")
                 userpass = UserPassDialog(self.gui,url,f)
@@ -852,12 +869,12 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                     adapter.is_adult=True
 
         # let other exceptions percolate up.
-        story = adapter.getStoryMetadataOnly()
+        story = adapter.getStoryMetadataOnly(get_cover=False)
 
         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$"'%re.sub(r'https?\\:','https?(\:|\|)',re.escape(story.getMetadata('seriesUrl')))
+            searchstr = self.make_id_searchstr(story.getMetadata('seriesUrl'))
             identicalbooks = db.search_getting_ids(searchstr, None)
             # print("searchstr:%s"%searchstr)
             # print("identicalbooks:%s"%identicalbooks)
@@ -934,7 +951,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                 logger.debug("from URL(%s)"%url)
     
                 # try to find by identifier url or uri first.
-                searchstr = 'identifiers:"~ur(i|l):~^%s$"'%re.sub(r'https?\:','https?(\:|\|)',url)
+                searchstr = self.make_id_searchstr(url)
                 identicalbooks = db.search_getting_ids(searchstr, None)
                 # print("searchstr:%s"%searchstr)
                 # print("identicalbooks:%s"%identicalbooks)
@@ -1080,7 +1097,18 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                                           dir=options['tdir'])
             logger.debug("title:"+book['title'])
             logger.debug("outfile:"+tmp.name)
-            book['outfile'] = tmp.name            
+            book['outfile'] = tmp.name
+            
+            # cookiejar = PersistentTemporaryFile(prefix=story.formatFileName("${title}-${author}-",allowunsafefilename=False)[:100],
+            #                                     suffix='.cookiejar',
+            #                                     dir=options['tdir'])
+            # adapter.save_cookiejar(cookiejar.name)
+            # book['cookiejar'] = cookiejar.name
+            # pagecache = PersistentTemporaryFile(prefix=story.formatFileName("${title}-${author}-",allowunsafefilename=False)[:100],
+            #                                     suffix='.pagecache',
+            #                                     dir=options['tdir'])
+            # adapter.save_pagecache(pagecache.name)
+            # book['pagecache'] = pagecache.name
                 
         return
         
@@ -1137,7 +1165,15 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                                       _('FFDL log'), _('FFDL download ended'), msg,
                                       show_copy_button=False)
             return
-            
+
+        cookiejarfile = PersistentTemporaryFile(suffix='.cookiejar',
+                                                dir=options['tdir'])
+        options['cookiejar'].save(cookiejarfile.name,
+                                  ignore_discard=True,
+                                  ignore_expires=True)
+        options['cookiejarfile']=cookiejarfile.name
+        del options['cookiejar'] ## can't be pickled.
+        
         func = 'arbitrary_n'
         cpus = self.gui.job_manager.server.pool_size
         args = ['calibre_plugins.fanfictiondownloader_plugin.jobs', 'do_download_worker',
@@ -1797,6 +1833,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         book['url'] = ''
         book['site'] = ''
         book['added'] = False
+        book['pubdate'] = None
         return book
     
     def convert_urls_to_books(self, urls):
@@ -1962,9 +1999,9 @@ 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.
@@ -2013,8 +2050,12 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             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

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'
 
@@ -19,6 +19,11 @@ from calibre.utils.ipc.server import Server
 from calibre.utils.ipc.job import ParallelJob
 from calibre.constants import numeric_version as calibre_version
 
+# for smarten punc
+from calibre.ebooks.oeb.polish.main import polish, ALL_OPTS
+from calibre.utils.logging import Log
+from collections import namedtuple
+
 from calibre_plugins.fanfictiondownloader_plugin.dialogs import (NotGoingToDownload,
     OVERWRITE, OVERWRITEALWAYS, UPDATE, UPDATEALWAYS, ADDNEW, SKIP, CALIBREONLY)
 from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader import adapters, writers, exceptions
@@ -58,10 +63,6 @@ def do_download_worker(book_list, options,
                               done=None,
                               args=args)
             job._book = book
-            # job._book_id = book_id
-            # job._title = title
-            # job._modified_date = modified_date
-            # job._existing_isbn = existing_isbn
             server.add_job(job)
         else:
             # was already bad before the subprocess ever started.
@@ -69,7 +70,7 @@ def do_download_worker(book_list, options,
     
     # This server is an arbitrary_n job, so there is a notifier available.
     # Set the % complete to a small number to avoid the 'unavailable' indicator
-    notification(0.01, 'Downloading FanFiction Stories')
+    notification(0.01, _('Downloading FanFiction Stories'))
 
     # dequeue the job results as they arrive, saving the results
     count = 0
@@ -81,24 +82,19 @@ def do_download_worker(book_list, options,
         if not job.is_finished:
             continue
         # A job really finished. Get the information.
-        output_book = job.result
-        #print("output_book:%s"%output_book)
         book_list.remove(job._book)
         book_list.append(job.result)
         book_id = job._book['calibre_id']
-        #title = job._title
         count = count + 1
         notification(float(count)/total, '%d of %d stories finished downloading'%(count,total))
         # Add this job's output to the current log
         logger.info('Logfile for book ID %s (%s)'%(book_id, job._book['title']))
         logger.info(job.details)
 
-
-
         if count >= total:
-            logger.info("\nSuccessful:\n%s\n"%("\n".join([book['url'] for book in 
+            logger.info("\n"+_("Successful:")+"\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 
+            logger.info("\n"+_("Unsuccessful:")+"\n%s\n"%("\n".join([book['url'] for book in 
                                                         filter(lambda x: not x['good'], book_list) ] ) ) )
             break
 
@@ -109,11 +105,10 @@ def do_download_worker(book_list, options,
 
 def do_download_for_worker(book,options,notification=lambda x,y:x):
     '''
-    Child job, to extract isbn from formats for this specific book,
-    when run as a worker job
+    Child job, to download story when run as a worker job
     '''
     try:
-        book['comment'] = 'Download started...'
+        book['comment'] = _('Download started...')
 
         configuration = get_ffdl_config(book['url'],
                                         options['fileform'],
@@ -122,8 +117,8 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
         if not options['updateepubcover'] and 'epub_for_update' in book and options['collision'] in (UPDATE, UPDATEALWAYS):
             configuration.set("overrides","never_make_cover","true")
 
-        # images only for epub, even if the user mistakenly turned it
-        # on else where.
+        # images only for epub, html, even if the user mistakenly
+        # turned it on else where.
         if options['fileform'] not in ("epub","html"):
             configuration.set("overrides","include_images","false")
         
@@ -133,6 +128,10 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
         adapter.password = book['password']
         adapter.setChaptersRange(book['begin'],book['end'])
         
+        adapter.load_cookiejar(options['cookiejarfile'])
+        logger.debug("cookiejar:%s"%adapter.cookiejar)
+        adapter.set_pagecache(options['pagecache'])
+        
         story = adapter.getStoryMetadataOnly()
         if 'calibre_series' in book:
             adapter.setSeries(book['calibre_series'][0],book['calibre_series'][1])
@@ -191,13 +190,13 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
             # dup handling from ffdl_plugin needed for anthology updates.
             if options['collision'] == UPDATE:
                 if chaptercount == urlchaptercount:
-                    book['comment']="Already contains %d chapters.  Reuse as is."%chaptercount
+                    book['comment']=_("Already contains %d chapters.  Reuse as is.")%chaptercount
                     book['outfile'] = book['epub_for_update'] # for anthology merge ops.
                     return book
 
             # dup handling from ffdl_plugin needed for anthology updates.
             if chaptercount > urlchaptercount:
-                raise NotGoingToDownload("Existing epub contains %d chapters, web site only has %d. Use Overwrite to force update." % (chaptercount,urlchaptercount),'dialog_error.png')
+                raise NotGoingToDownload(_("Existing epub contains %d chapters, web site only has %d. Use Overwrite to force update.") % (chaptercount,urlchaptercount),'dialog_error.png')
 
             if not (options['collision'] == UPDATEALWAYS and chaptercount == urlchaptercount) \
                     and adapter.getConfig("do_update_hook"):
@@ -208,16 +207,12 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
 
             writer.writeStory(outfilename=outfile, forceOverwrite=True)
             
-            book['comment'] = 'Update %s completed, added %s chapters for %s total.'%\
+            book['comment'] = _('Update %s completed, added %s chapters for %s total.')%\
                 (options['fileform'],(urlchaptercount-chaptercount),urlchaptercount)
         
         if options['smarten_punctuation'] and options['fileform'] == "epub" \
                 and calibre_version >= (0, 9, 39):
             # do smarten_punctuation 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
-        
             data = {'smarten_punctuation':True}
             opts = ALL_OPTS.copy()
             opts.update(data)

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

defaults.ini

@@ -321,7 +321,7 @@ sort_ships:false
 #keep_in_order_author:true
 
 ## User-agent
-user_agent:FFDL/1.7
+user_agent:FFDL/2.0
 
 ## Each output format has a section that overrides [defaults]
 [html]
@@ -626,6 +626,18 @@ extracategories:The Sentinel
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+[bdsm-geschichten.net]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
+## This site offers no index page so we can either guess the chapter URLs
+## by dec/incrementing numbers ('guess') or walk all the chapters in the metadata
+## parsing state ('parse'). Since guessing can lead to errors for non-standard
+## story URLs, the default is to parse
+#find_chapters:guess 
+
 [bloodshedverse.com]
 ## website encoding(s) In theory, each website reports the character
 ## encoding they use for each page.  In practice, some sites report it
@@ -634,7 +646,7 @@ extracategories:The Sentinel
 ## explicitly set the encoding and order if you need to.  The special
 ## value 'auto' will call chardet and use the encoding it reports if
 ## it has +90% confidence.  'auto' is not reliable.
-website_encodings:ISO-8859-1,auto
+website_encodings:Windows-1252,ISO-8859-1,auto
 
 ## Extra metadata that this adapter knows about.  See [dramione.org]
 ## for examples of how to use them.
@@ -700,6 +712,20 @@ extracategories:Castle
 ## cover image.  This lets you exclude them.
 cover_exclusion_regexp:/images/.*?ribbon.gif
 
+[csi-forensics.com]
+## Some sites also require the user to confirm they are adult for
+## adult content.  In commandline version, this should go in your
+## personal.ini, not defaults.ini.
+#is_adult:true
+
+## Virtually all eFiction-based sites allow downloading the whole story in
+## bulk using the 'Print' feature. If 'bulk_load' is set to 'true', both
+## metadata and chapters can be loaded in one step
+bulk_load:true
+
+extra_valid_entries: readings
+readings_label: Readings
+
 [dark-solace.org]
 ## Site dedicated to these categories/characters/ships
 ## Some sites require login (or login for some rated stories) The
@@ -872,6 +898,24 @@ extraships:Harry Potter/Hermione Granger
 #username:YourName
 #password:yourpassword
 
+[fannation.shades-of-moonlight.com]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Virtually all eFiction-based sites allow downloading the whole story in
+## bulk using the 'Print' feature. If 'bulk_load' is set to 'true', both
+## metadata and chapters can be loaded in one step
+bulk_load:true
+
+extra_valid_entries: readings,romance
+extra_titlepage_entries: readings,romance
+readings_label: Readings
+romance_label: Romance
+
 [ficwad.com]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -999,7 +1043,19 @@ extraships:Kirk/Spock
 [literotica.com]
 extra_valid_entries:eroticatags
 eroticatags_label:Erotica Tags
-#extra_titlepage_entries: eroticatags
+extra_titlepage_entries: eroticatags
+
+[lotrfanfiction.com]
+## Virtually all eFiction-based sites allow downloading the whole story in
+## bulk using the 'Print' feature. If 'bulk_load' is set to 'true', both
+## metadata and chapters can be loaded in one step
+bulk_load:true
+
+extra_valid_entries: readings
+readings_label: Readings
+
+## Site dedicated to these categories/characters/ships
+extracategories:Lord of the Rings
 
 [lumos.sycophanthex.com]
 ## Some sites do not require a login, but do require the user to
@@ -1123,6 +1179,24 @@ extracategories:My Little Pony: Friendship is Magic
 ## Site dedicated to these categories/characters/ships
 extracategories:The Pretender
 
+[samandjack.net]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Some sites also require the user to confirm they are adult for
+## adult content.  In commandline version, this should go in your
+## personal.ini, not defaults.ini.
+#is_adult:true
+
+## Site dedicated to these categories/characters/ships
+extracategories:Stargate: SG-1
+extracharacters:Sam,Jack
+extraships:Sam/Jack
+
 [samdean.archive.nu]
 ## Site dedicated to these categories/characters/ships
 extracategories:Supernatural
@@ -1151,6 +1225,24 @@ extracategories:Harry Potter
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+[sheppardweir.com]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Some sites also require the user to confirm they are adult for
+## adult content.  In commandline version, this should go in your
+## personal.ini, not defaults.ini.
+#is_adult:true
+
+## Site dedicated to these categories/characters/ships
+extracategories:Stargate: Atlantis
+extracharacters:John Sheppard,Elizabeth Weir
+extraships:John Sheppard/Elizabeth Weir
+
 [spikeluver.com]
 ## Extra metadata that this adapter knows about.  See [dramione.org]
 ## for examples of how to use them.
@@ -1230,6 +1322,22 @@ extraships:Harry Potter/Draco Malfoy
 ## Site dedicated to these categories/characters/ships
 extracategories:Criminal Minds
 
+[themaplebookshelf.com]
+## Some sites also require the user to confirm they are adult for
+## adult content.  In commandline version, this should go in your
+## personal.ini, not defaults.ini.
+#is_adult:true
+
+## Virtually all eFiction-based sites allow downloading the whole story in
+## bulk using the 'Print' feature. If 'bulk_load' is set to 'true', both
+## metadata and chapters can be loaded in one step
+bulk_load:true
+
+extra_valid_entries: readings,challenge
+extra_titlepage_entries: readings,challenge
+challenge_label: Challenge
+readings_label: Readings
+
 [themasque.net]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -1268,6 +1376,10 @@ extracategories:Harry Potter
 ## Site dedicated to these categories/characters/ships
 extracategories:Stargate: SG-1
 
+[tolkienfanfiction.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Lord of the Rings
+
 [trekiverse.org]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -1276,6 +1388,11 @@ extracategories:Stargate: SG-1
 #username:YourName
 #password:yourpassword
 
+## Virtually all eFiction-based sites allow downloading the whole story in
+## bulk using the 'Print' feature. If 'bulk_load' is set to 'true', both
+## metadata and chapters can be loaded in one step
+bulk_load:true
+
 ## Some sites also require the user to confirm they are adult for
 ## adult content.  In commandline version, this should go in your
 ## personal.ini, not defaults.ini.
@@ -1284,8 +1401,10 @@ extracategories:Stargate: SG-1
 ## Site dedicated to these categories/characters/ships
 extracategories:Star Trek
 
-extra_valid_entries:awards
+extra_valid_entries:readings,awards
+extra_titlepage_entries:readings,awards
 awards_label:Awards
+readings_label:Readings
 
 cover_exclusion_regexp:art/.*Awards.jpg
 
@@ -1383,8 +1502,11 @@ type_label:Type of Couple
 [www.fanfiction.net]
 user_agent:
 ## fanfiction.net's 'cover' images are really just tiny thumbnails.
-## Change this to false to use them anyway.
-never_make_cover: true
+## Set this to true to never use them.
+#never_make_cover: false
+
+## fanfiction.net shows the user's 
+cover_exclusion_regexp:/imageu/
 
 ## fanfiction.net is blocking people more aggressively.  If you
 ## download fewer stories less often you can likely get by with
@@ -1476,7 +1598,7 @@ extracategories:My Little Pony: Friendship is Magic
 
 ## Extra metadata that this adapter knows about.  See [dramione.org]
 ## for examples of how to use them.
-extra_valid_entries:likes,dislikes,views,total_views,short_description,groups,groupsUrl,groupsHTML,prequel,prequelUrl,prequelHTML,sequels,sequelsUrl,sequelsHTML
+extra_valid_entries:likes,dislikes,views,total_views,short_description,groups,groupsUrl,groupsHTML,prequel,prequelUrl,prequelHTML,sequels,sequelsUrl,sequelsHTML,comment_count,coverSource,coverSourceUrl,coverSourceHTML
 likes_label:Likes
 dislikes_label:Dislikes
 views_label:Highest Single Chapter Views
@@ -1491,6 +1613,10 @@ prequelHTML_label:Prequel
 sequels_label:Sequels
 sequelsUrl_label:Sequel URLs
 sequelsHTML_label:Sequels
+comment_count_label:Comment Count
+coverSource_label:Cover Source
+coverSourceUrl_label:Cover Source URL
+coverSourceHTML_label:Cover Source
 
 keep_in_order_sequels:true
 keep_in_order_sequelsUrl:true
@@ -1499,7 +1625,7 @@ keep_in_order_groupsUrl:true
 
 ## Assume entryUrl, apply to "<a class='%slink' href='%s'>%s</a>" to
 ## make entryHTML.
-make_linkhtml_entries:prequel,sequels,groups
+make_linkhtml_entries:prequel,sequels,groups,coverSource
 
 [www.harrypotterfanfiction.com]
 ## Some sites do not require a login, but do require the user to
@@ -1707,7 +1833,7 @@ extracategories:Lord of the Rings
 #username:YourName
 #password:yourpassword
 
-[www.thewriterscoffeeshop.com]
+[www.twcslibrary.net]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
 ## commandline version, this should go in your personal.ini, not
@@ -1720,7 +1846,7 @@ extracategories:Lord of the Rings
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
-## thewriterscoffeeshop.com (ab)uses series as personal reading lists.
+## twcslibrary.net (ab)uses series as personal reading lists.
 collect_series: false
 
 [www.tthfanfic.org]
@@ -1808,6 +1934,9 @@ extracharacters:Wolverine,Rogue
 ## Site dedicated to these categories/characters/ships
 extracategories:Stargate: Atlantis
 
+extra_valid_entries:reviews
+reviews_label:Reviews
+
 [overrides]
 ## It may sometimes be useful to override all of the specific format,
 ## site and site:format sections in your private configuration.  For

downloader.py

@@ -227,9 +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")

fanficdownloader/adapters/__init__.py

@@ -39,7 +39,7 @@ import adapter_mediaminerorg
 import adapter_potionsandsnitchesnet
 import adapter_tenhawkpresentscom
 import adapter_adastrafanficcom
-import adapter_thewriterscoffeeshopcom
+import adapter_twcslibrarynet
 import adapter_tthfanficorg
 import adapter_twilightednet
 import adapter_twiwritenet
@@ -130,11 +130,19 @@ import adapter_nocturnallightnet
 import adapter_fanfichu
 import adapter_fanfictioncsodaidokhu
 import adapter_fictionmaniatv
+import adapter_bdsmgeschichten
+import adapter_tolkienfanfiction
+import adapter_themaplebookshelf
+import adapter_fannation
+import adapter_sheppardweircom
+import adapter_samandjacknet
+import adapter_csiforensicscom
+import adapter_lotrfanfictioncom
 
 ## 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 = {}
@@ -202,7 +210,7 @@ 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] )
 
@@ -234,9 +242,9 @@ def getClassFor(url):
 
     if cls:
         fixedurl = cls.stripURLParameters(fixedurl)
-    
+
     return (cls,fixedurl)
-    
+
 def getClassFromList(domain):
     try:
         return __domain_map[domain]

fanficdownloader/adapters/adapter_adastrafanficcom.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -53,12 +54,19 @@ class AdAstraFanficComSiteAdapter(BaseSiteAdapter):
         return 'www.adastrafanfic.com'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
 
+    def use_pagecache(self):
+        '''
+        adapters that will work with the page cache need to implement
+        this and change it to True.
+        '''
+        return True
+    
     def extractChapterUrlsAndMetadata(self):
 
         if self.is_adult or self.getConfig("is_adult"):

fanficdownloader/adapters/adapter_archiveofourownorg.py

@@ -78,8 +78,8 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
         return 'archiveofourown.org'
 
     @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 getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/works/123456 http://"+cls.getSiteDomain()+"/collections/Some_Archive/works/123456 http://"+cls.getSiteDomain()+"/works/123456/chapters/78901"
 
     def getSiteURLPattern(self):
         # http://archiveofourown.org/collections/Smallville_Slash_Archive/works/159770
@@ -123,6 +123,13 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
         else:
             return True
 
+    def use_pagecache(self):
+        '''
+        adapters that will work with the page cache need to implement
+        this and change it to True.
+        '''
+        return True
+
     ## Getting the chapter list and the meta data, plus 'is adult' checking.
     def extractChapterUrlsAndMetadata(self):
 
@@ -155,29 +162,33 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
         if self.needToLoginCheck(data):
             # need to log in for this one.
             self.performLogin(url,data)
-            data = self._fetchUrl(url)
-            meta = self._fetchUrl(metaurl)
+            data = self._fetchUrl(url,usecache=False)
+            meta = self._fetchUrl(metaurl,usecache=False)
             
         # use BeautifulSoup HTML parser to make everything easier to find.
         soup = bs.BeautifulSoup(data)
+        for tag in soup.findAll('div',id='admin-banner'):
+            tag.extract()
         metasoup = bs.BeautifulSoup(meta)
+        for tag in metasoup.findAll('div',id='admin-banner'):
+            tag.extract()
 
         # Now go hunting for all the meta data and the chapter list.
         
         ## Title
-        a = soup.find('a', href=re.compile(r"^/works/\d+$"))
+        a = soup.find('a', href=re.compile(r"/works/\d+$"))
         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

fanficdownloader/adapters/adapter_archiveskyehawkecom.py

@@ -71,7 +71,7 @@ class ArchiveSkyeHawkeComAdapter(BaseSiteAdapter):
         return ['archive.skyehawke.com','www.skyehawke.com']
 
     @classmethod
-    def getSiteExampleURLs(self):
+    def getSiteExampleURLs(cls):
         return "http://archive.skyehawke.com/story.php?no=1234 http://www.skyehawke.com/archive/story.php?no=1234  http://skyehawke.com/archive/story.php?no=1234"
 
     def getSiteURLPattern(self):
@@ -91,8 +91,6 @@ class ArchiveSkyeHawkeComAdapter(BaseSiteAdapter):
             else:
                 raise e
 
-        data = self._fetchUrl(url)
-            
         # use BeautifulSoup HTML parser to make everything easier to find.
         soup = bs.BeautifulSoup(data)
         # print data

fanficdownloader/adapters/adapter_ashwindersycophanthexcom.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -67,8 +68,8 @@ class AshwinderSycophantHexComAdapter(BaseSiteAdapter):
         return 'ashwinder.sycophanthex.com'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_asr3slashzoneorg.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -64,8 +65,8 @@ class Asr3SlashzoneOrgAdapter(BaseSiteAdapter):
         return 'asr3.slashzone.org'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/archive/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/archive/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/archive/viewstory.php?sid=")+r"\d+$"

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(cls):
+        return "http://www.bdsm-geschichten.net/title-of-story-1 http://bdsm-geschichten.net/title-of-story-1"
+
+    def getSiteURLPattern(self):
+        return r"http://(www\.)?bdsm-geschichten.net/(?P<storyId>[a-zA-Z0-9_-]+)"
+
+    def extractChapterUrlsAndMetadata(self):
+
+        if not (self.is_adult or self.getConfig("is_adult")):
+            raise exceptions.AdultCheckRequired(self.url)
+
+        try:
+            data1 = self._fetchUrl(self.url)
+            soup = bs.BeautifulSoup(data1)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        #strip comments from soup
+        [comment.extract() for comment in soup.findAll(text=lambda text:isinstance(text, bs.Comment))]
+
+        # Cache the soups so we won't have to redownload in getChapterText later
+        self.soupsCache = {}
+        self.soupsCache[self.url] = soup
+
+        # author
+        authorDiv = soup.find("div", "author-pane-line author-name")
+        authorId = authorDiv.string.strip()
+        self.story.setMetadata('authorId', authorId)
+        self.story.setMetadata('author', authorId)
+        # TODO not really true need to be loggedin for this to work or fetch userid
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+authorId)
+
+        # TODO better metadata
+        date = soup.find("div", {"class": "submitted"}).string.strip()
+        date = re.sub(" &#151;.*", "", date)
+        date = _translate_date_german_english(date)
+        self.story.setMetadata('datePublished', makeDate(date, self.dateformat))
+        title1 = soup.find("h1", {'class': 'title'}).string
+
+
+        for tagLink in soup.find("ul", "taxonomy").findAll("a"):
+            self.story.addToList('category', tagLink.string)
+
+        ## Retrieve chapter soups
+        if self.getConfig('find_chapters') == 'guess':
+            self.chapterUrls = []
+            self._find_chapters_by_guessing(title1)
+        else:
+            self._find_chapters_by_parsing(soup)
+
+        firstChapterUrl = self.chapterUrls[0][1]
+        if firstChapterUrl in self.soupsCache:
+            firstChapterSoup = self.soupsCache[firstChapterUrl]
+            h1 = firstChapterSoup.find("h1").text
+        else:
+            h1 = soup.find("h1").text
+
+        h1 = re.sub(_REGEX_CHAPTER_TITLE, "", h1)
+        self.story.setMetadata('title', h1)
+        self.story.setMetadata('numChapters', len(self.chapterUrls))
+        return
+
+    def _find_chapters_by_parsing(self, soup):
+
+        # store original soup
+        origSoup = soup
+
+        #
+        # find first chapter
+        #
+        firstLink = None
+        firstLinkDiv = soup.find("div", "field-field-erster-teil")
+        if firstLinkDiv is not None:
+            firstLink = "http://%s%s" % (self.getSiteDomain(), firstLinkDiv.findNext("a")['href'])
+            logger.debug("Found first chapter right away <%s>" % firstLink)
+            try:
+                soup = bs.BeautifulSoup(self._fetchUrl(firstLink))
+                self.soupsCache[firstLink] = soup
+                self.chapterUrls.insert(0, (soup.find("h1").text, firstLink))
+            except urllib2.HTTPError, e:
+                if e.code == 404:
+                    raise exceptions.StoryDoesNotExist(self.url)
+                else:
+                    raise exceptions.StoryDoesNotExist(firstLink)
+        else:
+            logger.debug("DIDN'T find first chapter right away")
+            # parse previous Link until first
+            while True:
+                prevLink = None
+                prevLinkDiv = soup.find("div", "field-field-vorheriger-teil")
+                if prevLinkDiv is not None:
+                    prevLink = prevLinkDiv.find("a")
+                if prevLink is None:
+                    prevLink = soup.find("a", text=re.compile("&lt;&lt;&lt;")) # <<<
+                if prevLink is None:
+                    logger.debug("Couldn't find prev part")
+                    break
+                else:
+                    logger.debug("Previous Chapter <%s>" % prevLink)
+                    if type(prevLink) != bs.Tag or prevLink.name != "a":
+                        prevLink = prevLink.findParent("a")
+                    if prevLink is None or '#' in prevLink['href']:
+                        logger.debug("Couldn't find prev part (false positive) <%s>" % prevLink)
+                        break
+                    prevLink = prevLink['href']
+                try:
+                    soup = bs.BeautifulSoup(self._fetchUrl(prevLink))
+                    self.soupsCache[prevLink] = soup
+                    prevTtitle = soup.find("h1", {'class': 'title'}).string
+                    self.chapterUrls.insert(0, (prevTtitle, prevLink))
+                except urllib2.HTTPError, e:
+                    if e.code == 404:
+                        raise exceptions.StoryDoesNotExist(nextLink)
+                    else:
+                        raise e
+                firstLink = prevLink
+
+        # if first chapter couldn't be determined, assume the URL originally
+        # passed is the first chapter
+        if firstLink is None:
+            logger.debug("Couldn't set first chapter")
+            firstLink = self.url
+            self.chapterUrls.insert(0, (soup.find("h1").text, firstLink))
+
+        # set first URL
+        logger.debug("Set first link: %s" % firstLink)
+        self._setURL(firstLink)
+        self.story.setMetadata('storyId', re.compile(self.getSiteURLPattern()).match(firstLink).group('storyId'))
+
+        #
+        # Parse next chapters
+        #
+        while True:
+            nextLink = None
+            nextLinkDiv = soup.find("div", "field-field-naechster-teil")
+            if nextLinkDiv is not None:
+                nextLink = nextLinkDiv.find("a")
+            if nextLink is None:
+                nextLink = soup.find("a", text=re.compile("&gt;&gt;&gt;"))
+            if nextLink is None:
+                nextLink = soup.find("a", text=re.compile("Fortsetzung"))
+
+            if nextLink is None:
+                logger.debug("Couldn't find next part")
+                break
+            else:
+                if type(nextLink) != bs.Tag or nextLink.name != "a":
+                    nextLink = nextLink.findParent("a")
+                if nextLink is None or '#' in nextLink['href']:
+                    logger.debug("Couldn't find next part (false positive) <%s>" % nextLink)
+                    break
+                nextLink = nextLink['href']
+
+            if not nextLink.startswith('http:'):
+                nextLink = 'http://' + self.getSiteDomain() + nextLink
+
+            for loadedChapter in self.chapterUrls:
+                if loadedChapter[0] == nextLink:
+                    logger.debug("ERROR: Repeating chapter <%s> Try to fix it" % nextLink)
+                    nextLinkMatch = _REGEX_TRAILING_DIGIT.match(nextLink)
+                    if nextLinkMatch is not None:
+                        curChap = nextLinkMatch.group(1)
+                        nextLink = re.sub(_REGEX_TRAILING_DIGIT, str(int(curChap) + 1), nextLink)
+                    else:
+                        break
+            try:
+                data = self._fetchUrl(nextLink)
+                soup = bs.BeautifulSoup(data)
+            except urllib2.HTTPError, e:
+                if e.code == 404:
+                    raise exceptions.StoryDoesNotExist(nextLink)
+                else:
+                    raise e
+            title2 = soup.find("h1", {'class': 'title'}).string
+            self.chapterUrls.append((title2, nextLink))
+            logger.debug("Grabbing next chapter URL " + nextLink)
+            self.soupsCache[nextLink] = soup
+            # [comment.extract() for comment in soup.findAll(text=lambda text:isinstance(text, bs.Comment))]
+        logger.debug("Chapters: %s" % self.chapterUrls)
+
+
+    def _find_chapters_by_guessing(self, title1):
+        step = _INITIAL_STEP
+        curMax = self.maxChapter + step
+        lastHit = True
+        while True:
+            nextChapterUrl = re.sub(_REGEX_TRAILING_DIGIT, str(curMax), self.url) 
+            if nextChapterUrl == self.url:
+                logger.debug("Unable to guess next chapter because URL doesn't end in numbers")
+                break;
+            try:
+                logger.debug("Trying chapter URL " + nextChapterUrl)
+                data = self._fetchUrl(nextChapterUrl)
+                hit = True
+            except urllib2.HTTPError, e:
+                if e.code == 404:
+                    hit = False
+                else:
+                    raise e
+            if hit:
+                logger.debug("Found chapter URL " + nextChapterUrl)
+                self.maxChapter = curMax
+                self.soupsCache[nextChapterUrl] = bs.BeautifulSoup(data)
+                if not lastHit:
+                    break
+                lastHit = curMax
+                curMax += step
+            else:
+                lastHit = False
+                curMax -= 1
+            logger.debug(curMax)
+
+        for i in xrange(1, self.maxChapter):
+            nextChapterUrl = re.sub(_REGEX_TRAILING_DIGIT, str(i), self.url)
+            nextChapterTitle = re.sub("1", str(i), title1)
+            self.chapterUrls.append((nextChapterTitle, nextChapterUrl))
+
+    def getChapterText(self, url):
+
+        if url in self.soupsCache:
+            logger.debug('Getting chapter <%s> from cache' % url)
+            soup = self.soupsCache[url]
+        else:
+            logger.debug('Downloading chapter <%s>' % url)
+            data1 = self._fetchUrl(url)
+            soup = bs.BeautifulSoup(data1)
+            #strip comments from soup
+            [comment.extract() for comment in soup.findAll(text=lambda text:isinstance(text, bs.Comment))]
+
+        # get story text
+        storyDiv1 = bs.Tag(soup, "div")
+        for para in soup.find("div", "full-node").find('div', 'content').findAll("p"):
+            storyDiv1.append(para)
+        storyDiv1.append('<br />')
+        storytext = self.utf8FromSoup(url,storyDiv1)
+
+        return storytext
+
+
+def getClass():
+    return BdsmGeschichtenAdapter

fanficdownloader/adapters/adapter_bloodshedversecom.py

@@ -4,6 +4,7 @@ import urllib2
 import urlparse
 
 from .. import BeautifulSoup
+from ..htmlcleanup import stripHTML
 
 from base_adapter import BaseSiteAdapter, makeDate
 from .. import exceptions
@@ -74,11 +75,11 @@ class BloodshedverseComAdapter(BaseSiteAdapter):
         # 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':
+        if stripHTML(soup.title) == 'by':
             raise exceptions.StoryDoesNotExist(self.url)
 
         for option in soup.find('select', {'name': 'chapter'}):
-            title = option.string.strip()
+            title = stripHTML(option)
             url = self.READ_URL_TEMPLATE % option['value']
             self.chapterUrls.append((title, url))
 
@@ -101,15 +102,15 @@ class BloodshedverseComAdapter(BaseSiteAdapter):
             raise exceptions.FailedToDownload(self.url)
 
         title_anchor = list_box.find('a', {'class': 'fictitle'})
-        self.story.setMetadata('title', title_anchor.string.strip())
+        self.story.setMetadata('title', stripHTML(title_anchor))
 
         author_anchor = title_anchor.findNextSibling('a')
-        self.story.setMetadata('author', author_anchor.string.strip())
+        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 = list_review.a.string.strip().split(' ', 1)[0]
+        reviews = stripHTML(list_review.a).split(' ', 1)[0]
         self.story.setMetadata('reviews', reviews)
 
         summary_div = list_box.find('div', {'class': 'list_summary'})
@@ -122,7 +123,7 @@ class BloodshedverseComAdapter(BaseSiteAdapter):
 
         # 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', first_listinfo.a.string.strip())
+        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'):

fanficdownloader/adapters/adapter_bloodtiesfancom.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -89,8 +90,8 @@ class BloodTiesFansComAdapter(BaseSiteAdapter): # XXX
         return 'bloodties-fans.com' # XXX
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/fiction/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/fiction/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/fiction/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_buffynfaithnet.py

@@ -90,8 +90,8 @@ class BuffyNFaithNetAdapter(BaseSiteAdapter):
         self.opener.addheaders.append(('Referer', 'http://'+self.getSiteDomain()+'/'))
         
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/fanfictions/index.php?act=vie&id=1234 http://buffynfaith.net/fanfictions/index.php?act=ovr&id=1234 http://buffynfaith.net/fanfictions/index.php?act=vie&id=1234&ch=2"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/fanfictions/index.php?act=vie&id=1234 http://"+cls.getSiteDomain()+"/fanfictions/index.php?act=ovr&id=1234 http://"+cls.getSiteDomain()+"/fanfictions/index.php?act=vie&id=1234&ch=2"
 
     def getSiteURLPattern(self):
         #http://buffynfaith.net/fanfictions/index.php?act=vie&id=963
@@ -101,6 +101,13 @@ class BuffyNFaithNetAdapter(BaseSiteAdapter):
             r"(vie|ovr)&id=(?P<id>\d+)(&ch=(?P<ch>\d+))?$"
         return p
 
+    def use_pagecache(self):
+        '''
+        adapters that will work with the page cache need to implement
+        this and change it to True.
+        '''
+        return True
+    
     def extractChapterUrlsAndMetadata(self):
 
         dateformat = "%d %B %Y"
@@ -109,7 +116,6 @@ class BuffyNFaithNetAdapter(BaseSiteAdapter):
         
         #set a cookie to get past adult check
         if self.is_adult or self.getConfig("is_adult"):
-            cookieproc = urllib2.HTTPCookieProcessor()
             cookie = cl.Cookie(version=0, name='my_age', value='yes',
                                port=None, port_specified=False,
                                domain=self.getSiteDomain(), domain_specified=False, domain_initial_dot=False,
@@ -121,8 +127,7 @@ class BuffyNFaithNetAdapter(BaseSiteAdapter):
                                comment_url=None,
                                rest={'HttpOnly': None},
                                rfc2109=False)
-            cookieproc.cookiejar.set_cookie(cookie)
-            self.opener = urllib2.build_opener(cookieproc)        
+            self.cookiejar.set_cookie(cookie)
             self.setHeader()
 
         try:

fanficdownloader/adapters/adapter_castlefansorg.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -91,8 +92,8 @@ class CastleFansOrgAdapter(BaseSiteAdapter): # XXX
         return 'castlefans.org' # XXX
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/fanfic/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/fanfic/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/fanfic/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_chaossycophanthexcom.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -67,8 +68,8 @@ class ChaosSycophantHexComAdapter(BaseSiteAdapter):
         return 'chaos.sycophanthex.com'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_checkmatedcom.py

@@ -65,8 +65,8 @@ class CheckmatedComAdapter(BaseSiteAdapter):
         return 'www.checkmated.com'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/story.php?story=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/story.php?story=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/story.php?story=")+r"\d+$"

fanficdownloader/adapters/adapter_csiforensicscom.py

@@ -0,0 +1,56 @@
+# -*- 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.
+#
+
+# Software: eFiction
+import re
+from base_efiction_adapter import BaseEfictionAdapter
+
+class CSIForensicsComAdapter(BaseEfictionAdapter):
+
+    @staticmethod
+    def getSiteDomain():
+        return 'csi-forensics.com'
+
+    @classmethod
+    def getPathToArchive(self):
+        return ''
+
+    @classmethod
+    def getSiteAbbrev(self):
+        return 'csiforensics'
+        
+    @classmethod
+    def getDateFormat(self):
+        return "%d %b %Y" 
+   
+    def handleMetadataPair(self, key, value):
+        if key == 'Warnings':
+            for val in re.split("\s*,\s*", value):
+                if value == 'None':
+                    return
+                else:
+                    self.story.addToList('warnings', val)
+     
+        elif 'Categories' in key:
+            for val in re.split("\s*>\s*", value):
+                self.story.addToList('category', val)
+        else:
+            super(CSIForensicsComAdapter, self).handleMetadataPair(key, value) 
+                           
+def getClass():
+    return CSIForensicsComAdapter
+    

fanficdownloader/adapters/adapter_darksolaceorg.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -70,8 +71,8 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
         return ['www.dark-solace.org','dark-solace.org']
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/elysian/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/elysian/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://")+"(www\.)?"+re.escape(self.getSiteDomain()+"/elysian/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_destinysgatewaycom.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -66,8 +67,8 @@ class DestinysGatewayComAdapter(BaseSiteAdapter):
         return 'www.destinysgateway.com'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_dokugacom.py

@@ -76,8 +76,8 @@ class DokugaComAdapter(BaseSiteAdapter):
         return 'www.dokuga.com'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/fanfiction/story/1234/1 http://"+self.getSiteDomain()+"/spark/story/1234/1"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/fanfiction/story/1234/1 http://"+cls.getSiteDomain()+"/spark/story/1234/1"
 
     def getSiteURLPattern(self):
         return r"http://"+self.getSiteDomain()+"/(fanfiction|spark)?/story/\d+/?\d+?$"

fanficdownloader/adapters/adapter_dotmoonnet.py

@@ -66,8 +66,8 @@ class DotMoonNetAdapter(BaseSiteAdapter):
         return 'www.dotmoon.net'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/library_view.php?storyid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/library_view.php?storyid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/library_view.php?storyid=")+r"\d+$"

fanficdownloader/adapters/adapter_dracoandginnycom.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -66,8 +67,8 @@ class DracoAndGinnyComAdapter(BaseSiteAdapter):
         return 'www.dracoandginny.com'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_dramioneorg.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -66,8 +67,8 @@ class DramioneOrgAdapter(BaseSiteAdapter):
         return 'dramione.org'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_efictionestelielde.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -66,8 +67,8 @@ class EfictionEstelielDeAdapter(BaseSiteAdapter):
         return 'efiction.esteliel.de'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_efpfanficnet.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -66,15 +67,16 @@ class EFPFanFicNet(BaseSiteAdapter):
         return 'www.efpfanfic.net'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
 
     ## 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
@@ -203,8 +205,8 @@ class EFPFanFicNet(BaseSiteAdapter):
         noteblock = storyblock.find('div', {'class':'notebloc'})
         #print("%s"%noteblock)
         notetext = ("%s" % noteblock).replace("<br />"," |")
-        # <div class="notebloc">Autore: <a href="viewuser.php?uid=243036">Cendrillon89</a> | Pubblicata: 23/10/12 | Aggiornata: 30/10/12 | Rating: Arancione | Genere: Drammatico, Sentimentale | Capitoli: 10 | Completa<br />␍
-        # Tipo di coppia: Het |  Personaggi: Akasuna no Sasori , Akatsuki, Nuovo Personaggio |   Note: OOC | Avvertimenti: Tematiche delicate<br />␍
+        # <div class="notebloc">Autore: <a href="viewuser.php?uid=243036">Cendrillon89</a> | Pubblicata: 23/10/12 | Aggiornata: 30/10/12 | Rating: Arancione | Genere: Drammatico, Sentimentale | Capitoli: 10 | Completa<br />
+        # Tipo di coppia: Het |  Personaggi: Akasuna no Sasori , Akatsuki, Nuovo Personaggio |   Note: OOC | Avvertimenti: Tematiche delicate<br />
         # Categoria: <a href="categories.php?catid=1&amp;parentcatid=1">Anime & Manga</a> > <a href="categories.php?catid=108&amp;parentcatid=108">Naruto</a> | Contesto: Naruto Shippuuden | Leggi le <a href="reviews.php?sid=1331275&amp;a=">3</a> recensioni</div>
 
         cats = noteblock.findAll('a',href=re.compile(r'browse.php\?type=categories'))

fanficdownloader/adapters/adapter_erosnsapphosycophanthexcom.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -67,8 +68,8 @@ class ErosnSapphoSycophantHexComAdapter(BaseSiteAdapter):
         return 'erosnsappho.sycophanthex.com'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_fanfictionnet.py

@@ -52,6 +52,8 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         # latest chapter yet and going back to chapter 1 to pull the
         # chapter list doesn't get the latest.  So save and use the
         # original URL given to pull chapter list & metadata.
+        # Not used by plugin because URL gets normalized first for
+        # eliminating duplicate story urls.
         self.origurl = url
         if "https://m." in self.origurl:
             ## accept m(mobile)url, but use www.
@@ -68,20 +70,29 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         return ['www.fanfiction.net','m.fanfiction.net']
 
     @classmethod
-    def getSiteExampleURLs(self):
+    def getSiteExampleURLs(cls):
         return "https://www.fanfiction.net/s/1234/1/ https://www.fanfiction.net/s/1234/12/ http://www.fanfiction.net/s/1234/1/Story_Title http://m.fanfiction.net/s/1234/1/"
 
     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 _fetchUrl(self,url,parameters=None,extrasleep=1.0):
+        # 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,
+                                         parameters=parameters,
+                                         extrasleep=extrasleep)
 
-    def extractChapterUrlsAndMetadata(self):
+    def use_pagecache(self):
+        '''
+        adapters that will work with the page cache need to implement
+        this and change it to True.
+        '''
+        return True
+    
+    def doExtractChapterUrlsAndMetadata(self,get_cover=True):
 
         # fetch the chapter.  From that we will get almost all the
         # metadata and chapter list
@@ -256,14 +267,15 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         else:
             self.story.setMetadata('status', 'In-Progress')
 
-        # Try the larger image first.
-        try:
-            img = soup.find('img',{'class':'lazy cimage'})
-            self.setCoverImage(url,img['data-original'])
-        except:
-            img = soup.find('img',{'class':'cimage'})
-            if img:
-                self.setCoverImage(url,img['src'])
+        if get_cover:
+            # Try the larger image first.
+            try:
+                img = soup.find('img',{'class':'lazy cimage'})
+                self.setCoverImage(url,img['data-original'])
+            except:
+                img = soup.find('img',{'class':'cimage'})
+                if img:
+                    self.setCoverImage(url,img['src'])
             
         # Find the chapter selector 
         select = soup.find('select', { 'name' : 'chapter' } )
@@ -287,12 +299,12 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         return
 
     def getChapterText(self, url):
-        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.
+        # 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.
         logger.debug('Getting chapter text from: %s' % url)
-        data = self._fetchUrl(url)
+        data = self._fetchUrl(url,extrasleep=4.0)
 
         if "Please email this error message in full to <a href='mailto:support@fanfiction.com'>support@fanfiction.com</a>" in data:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  FanFiction.net Site Error!" % url)

fanficdownloader/adapters/adapter_fanfiktionde.py

@@ -68,12 +68,19 @@ class FanFiktionDeAdapter(BaseSiteAdapter):
         return 'www.fanfiktion.de'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/s/46ccbef30000616306614050 http://"+self.getSiteDomain()+"/s/46ccbef30000616306614050/1 http://"+self.getSiteDomain()+"/s/46ccbef30000616306614050/1/story-name"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/s/46ccbef30000616306614050 http://"+cls.getSiteDomain()+"/s/46ccbef30000616306614050/1 http://"+cls.getSiteDomain()+"/s/46ccbef30000616306614050/1/story-name"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/s/")+r"\w+(/\d+)?"
         
+    def use_pagecache(self):
+        '''
+        adapters that will work with the page cache need to implement
+        this and change it to True.
+        '''
+        return True
+    
         ## Login seems to be reasonably standard across eFiction sites.
     def needToLoginCheck(self, data):
         if 'Diese Geschichte wurde als entwicklungsbeeintr' in data \
@@ -99,9 +106,8 @@ class FanFiktionDeAdapter(BaseSiteAdapter):
         loginUrl = 'https://ssl.fanfiktion.de/'
         logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
                                                               params['nickname']))
-        d = self._postUrl(loginUrl,params)
-    
-        if "Login erfolgreich" not in d : #Member Account
+        soup = bs.BeautifulSoup(self._postUrl(loginUrl,params))
+        if not soup.find('a', title='Logout'):
             logger.info("Failed to login to URL %s as %s" % (loginUrl,
                                                               params['nickname']))
             raise exceptions.FailedToLogin(url,params['nickname'])
@@ -126,7 +132,7 @@ class FanFiktionDeAdapter(BaseSiteAdapter):
         if self.needToLoginCheck(data):
             # need to log in for this one.
             self.performLogin(url)
-            data = self._fetchUrl(url)
+            data = self._fetchUrl(url,usecache=False)
             
         if "Uhr ist diese Geschichte nur nach einer" in data:
             raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Auserhalb der Zeit von 23:00 Uhr bis 04:00 Uhr ist diese Geschichte nur nach einer erfolgreichen Altersverifikation zuganglich.")
@@ -142,7 +148,7 @@ class FanFiktionDeAdapter(BaseSiteAdapter):
         self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
-        head = soup.find('div', {'class' : 'story-metadata-left-top'})
+        head = soup.find('div', {'class' : 'story-left'})
         a = head.find('a')
         self.story.setMetadata('authorId',a['href'].split('/')[2])
         self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
@@ -156,14 +162,18 @@ class FanFiktionDeAdapter(BaseSiteAdapter):
         self.story.setMetadata('language','German')
 
         #find metadata on the story page
-        self.story.setMetadata('datePublished', makeDate(head.text.split('erstellt: ')[1].split('\n')[0], self.dateformat))
+        headtext = stripHTML(head)
+        self.story.setMetadata('datePublished', makeDate(headtext.split('erstellt: ')[1].split('\n')[0], self.dateformat))
         
-        self.story.setMetadata('dateUpdated', makeDate(head.text.split('letztes Update: ')[1].split('\n')[0], self.dateformat))
-        
-        for genre in head.text.split('   ')[3].split('/')[0].split(', '):
-            self.story.addToList('genre',genre)
+        self.story.setMetadata('dateUpdated', makeDate(headtext.split('aktualisiert: ')[1].split('\n')[0], self.dateformat))
+
+        # second colspan=3 td in head.
+        genres=stripHTML(head.findAll('td',{'colspan':'3'})[1])
+        self.story.extendList('genre',genres[:genres.index('(')].split(', '))
+        # for genre in head.text.split('   ')[3].split('/')[0].split(', '):
+        #     self.story.addToList('genre',genre)
             
-        if 'fertiggestellt' in head.text:
+        if 'fertiggestellt' in headtext:
             self.story.setMetadata('status', 'Completed')
         else:
             self.story.setMetadata('status', 'In Progress')
@@ -178,9 +188,9 @@ class FanFiktionDeAdapter(BaseSiteAdapter):
         self.setDescription(url,a['onmouseover'].split("', '")[1])
         
         td = tr[i].findAll('td')
-        self.story.addToList('category',stripHTML(td[1]))
-        self.story.setMetadata('rating', stripHTML(td[4]))
-        self.story.setMetadata('numWords', stripHTML(td[5]))
+        self.story.addToList('category',stripHTML(td[2]))
+        self.story.setMetadata('rating', stripHTML(td[5]))
+        self.story.setMetadata('numWords', stripHTML(td[6]))
  
             
     # grab the text for an individual chapter.

fanficdownloader/adapters/adapter_fannation.py

@@ -0,0 +1,44 @@
+# -*- 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.
+#
+
+# Software: eFiction
+import re
+from base_efiction_adapter import BaseEfictionAdapter
+
+class FanNationAdapter(BaseEfictionAdapter):
+
+    @staticmethod
+    def getSiteDomain():
+        return 'fannation.shades-of-moonlight.com'
+
+    @classmethod
+    def getPathToArchive(self):
+        return '/archive'
+
+    @classmethod
+    def getSiteAbbrev(self):
+        return 'fannation'
+
+    def handleMetadataPair(self, key, value):
+        if key == 'Romance':
+            for val in re.split("\s*,\s*", value):
+                self.story.addToList('romance', val)
+        else:
+            super(FanNationAdapter, self).handleMetadataPair(key, value)
+
+def getClass():
+    return FanNationAdapter

fanficdownloader/adapters/adapter_ficbooknet.py

@@ -70,8 +70,8 @@ class FicBookNetAdapter(BaseSiteAdapter):
         return 'www.ficbook.net'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/readfic/12345 http://"+self.getSiteDomain()+"/readfic/93626/246417#part_content"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/readfic/12345 http://"+cls.getSiteDomain()+"/readfic/93626/246417#part_content"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/readfic/")+r"\d+"

fanficdownloader/adapters/adapter_fictionalleyorg.py

@@ -58,8 +58,8 @@ class FictionAlleyOrgSiteAdapter(BaseSiteAdapter):
         return 'www.fictionalley.org'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/authors/drt/DA.html http://"+self.getSiteDomain()+"/authors/drt/JOTP01a.html"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/authors/drt/DA.html http://"+cls.getSiteDomain()+"/authors/drt/JOTP01a.html"
 
     def getSiteURLPattern(self):
         # http://www.fictionalley.org/authors/drt/DA.html

fanficdownloader/adapters/adapter_fictionpadcom.py

@@ -57,7 +57,7 @@ class FictionPadSiteAdapter(BaseSiteAdapter):
         return 'fictionpad.com'
 
     @classmethod
-    def getSiteExampleURLs(self):
+    def getSiteExampleURLs(cls):
         return "https://fictionpad.com/author/Author/stories/1234/Some-Title"
     
     def getSiteURLPattern(self):

fanficdownloader/adapters/adapter_fictionpresscom.py

@@ -40,7 +40,7 @@ class FictionPressComSiteAdapter(FanFictionNetSiteAdapter):
         return ['www.fictionpress.com','m.fictionpress.com']
 
     @classmethod
-    def getSiteExampleURLs(self):
+    def getSiteExampleURLs(cls):
         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):

fanficdownloader/adapters/adapter_ficwadcom.py

@@ -46,7 +46,7 @@ class FicwadComSiteAdapter(BaseSiteAdapter):
         return 'ficwad.com'
 
     @classmethod
-    def getSiteExampleURLs(self):
+    def getSiteExampleURLs(cls):
         return "http://ficwad.com/story/1234"
 
     def getSiteURLPattern(self):
@@ -65,7 +65,7 @@ class FicwadComSiteAdapter(BaseSiteAdapter):
         loginUrl = 'http://' + self.getSiteDomain() + '/account/login'
         logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
                                                               params['username']))
-        d = self._postUrl(loginUrl,params)
+        d = self._postUrl(loginUrl,params,usecache=False)
 
         if "Login attempt failed..." in d:
             logger.info("Failed to login to URL %s as %s" % (loginUrl,
@@ -75,6 +75,13 @@ class FicwadComSiteAdapter(BaseSiteAdapter):
         else:
             return True        
     
+    def use_pagecache(self):
+        '''
+        adapters that will work with the page cache need to implement
+        this and change it to True.
+        '''
+        return True
+
     def extractChapterUrlsAndMetadata(self):
 
         # fetch the chapter.  From that we will get almost all the
@@ -96,9 +103,15 @@ class FicwadComSiteAdapter(BaseSiteAdapter):
             else:
                 raise e
             
-        h3 = soup.find('h3')
-        storya = h3.find('a',href=re.compile("^/story/\d+$"))
-        if storya : # if there's a story link in the h3 header, this is a chapter page.
+        # if blocked, attempt login.
+        if soup.find("div",{"class":"blocked"}):
+            if self.performLogin(url): # performLogin raises
+                                       # FailedToLogin if it fails.
+                soup = bs.BeautifulSoup(self._fetchUrl(url,usecache=False))
+
+        divstory = soup.find('div',id='story')
+        storya = divstory.find('a',href=re.compile("^/story/\d+$"))
+        if storya : # if there's a story link in the divstory header, this is a chapter page.
             # normalize story URL on chapter list.
             self.story.setMetadata('storyId',storya['href'].split('/',)[2])
             url = "http://"+self.getSiteDomain()+storya['href']
@@ -113,17 +126,17 @@ class FicwadComSiteAdapter(BaseSiteAdapter):
                     raise e
 
         # if blocked, attempt login.
-        if soup.find("li",{"class":"blocked"}):
+        if soup.find("div",{"class":"blocked"}):
             if self.performLogin(url): # performLogin raises
                                        # FailedToLogin if it fails.
-                soup = bs.BeautifulSoup(self._fetchUrl(url))
+                soup = bs.BeautifulSoup(self._fetchUrl(url,usecache=False))
 
         # title - first h4 tag will be title.
-        titleh4 = soup.find('h4')
+        titleh4 = soup.find('div',{'class':'storylist'}).find('h4')
         self.story.setMetadata('title', stripHTML(titleh4.a))
 
         # Find authorid and URL from... author url.
-        a = soup.find('a', href=re.compile(r"^/author/\d+"))
+        a = soup.find('span',{'class':'author'}).find('a', href=re.compile(r"^/author/\d+"))
         self.story.setMetadata('authorId',a['href'].split('/')[2])
         self.story.setMetadata('authorUrl','http://'+self.host+a['href'])
         self.story.setMetadata('author',a.string)
@@ -139,7 +152,7 @@ class FicwadComSiteAdapter(BaseSiteAdapter):
 
         # warnings
         # <span class="req"><a href="/help/38" title="Medium Spoilers">[!!] </a> <a href="/help/38" title="Rape/Sexual Violence">[R] </a> <a href="/help/38" title="Violence">[V] </a> <a href="/help/38" title="Child/Underage Sex">[Y] </a></span>
-        spanreq = metap.find("span",{"class":"req"})
+        spanreq = metap.find("span",{"class":"story-warnings"})
         if spanreq: # can be no warnings.
             for a in spanreq.findAll("a"):
                 self.story.addToList('warnings',a['title'])
@@ -165,16 +178,16 @@ class FicwadComSiteAdapter(BaseSiteAdapter):
                 if g:
                     self.story.addToList('characters',g)
         
-        m = re.match(r".*?Published: ([0-9/]+?) -.*?",metastr)
+        m = re.match(r".*?Published: ([0-9-]+?) -.*?",metastr)
         if m:
-            self.story.setMetadata('datePublished',makeDate(m.group(1), "%Y/%m/%d"))
+            self.story.setMetadata('datePublished',makeDate(m.group(1), "%Y-%m-%d"))
 
         # Updated can have more than one space after it. <shrug>
-        m = re.match(r".*?Updated: ([0-9/]+?) +-.*?",metastr) 
+        m = re.match(r".*?Updated: ([0-9-]+?) +-.*?",metastr) 
         if m:
-            self.story.setMetadata('dateUpdated',makeDate(m.group(1), "%Y/%m/%d"))
+            self.story.setMetadata('dateUpdated',makeDate(m.group(1), "%Y-%m-%d"))
 
-        m = re.match(r".*? - ([0-9/]+?) words.*?",metastr)
+        m = re.match(r".*? - ([0-9,]+?) words.*?",metastr)
         if m:
             self.story.setMetadata('numWords',m.group(1))
 
@@ -185,7 +198,7 @@ class FicwadComSiteAdapter(BaseSiteAdapter):
 
         # get the chapter list first this time because that's how we
         # detect the need to login.
-        storylistul = soup.find('ul',{'id':'storylist'})
+        storylistul = soup.find('ul',{'class':'storylist'})
         if not storylistul:
             # no list found, so it's a one-chapter story.
             self.chapterUrls.append((self.story.getMetadata('title'),url))

fanficdownloader/adapters/adapter_fimfictionnet.py

@@ -55,16 +55,22 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
         return ['www.fimfiction.net','mobile.fimfiction.net', 'www.fimfiction.com', 'mobile.fimfiction.com']
 
     @classmethod
-    def getSiteExampleURLs(self):
+    def getSiteExampleURLs(cls):
         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"https?://(www|mobile)\.fimfiction\.(net|com)/story/\d+/?.*"
         
-    def extractChapterUrlsAndMetadata(self):
+    def use_pagecache(self):
+        '''
+        adapters that will work with the page cache need to implement
+        this and change it to True.
+        '''
+        return True
+    
+    def doExtractChapterUrlsAndMetadata(self,get_cover=True):
         
         if self.is_adult or self.getConfig("is_adult"):
-            cookieproc = urllib2.HTTPCookieProcessor()
             cookie = cl.Cookie(version=0, name='view_mature', value='true',
                                port=None, port_specified=False,
                                domain=self.getSiteDomain(), domain_specified=False, domain_initial_dot=False,
@@ -76,15 +82,12 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
                                comment_url=None,
                                rest={'HttpOnly': None},
                                rfc2109=False)
-            cookieproc.cookiejar.set_cookie(cookie)
-            self.opener = urllib2.build_opener(cookieproc)
-        
+            self.cookiejar.set_cookie(cookie)
+
+        ##---------------------------------------------------------------------------------------------------
+        ## Get the story's title page. Check if it exists.
+
         try:
-            apiResponse = urllib2.urlopen("http://www.fimfiction.net/api/story.php?story=%s" % (self.story.getMetadata("storyId"))).read()
-            apiData = json.loads(apiResponse)
-            
-            # Unfortunately, we still need to load the story index
-            # page to parse the characters.  And chapters, now, too.
             data = self.do_fix_blockquotes(self._fetchUrl(self.url))
             soup = bs.BeautifulSoup(data)
         except urllib2.HTTPError, e:
@@ -96,109 +99,97 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
         if "Warning: mysql_fetch_array(): supplied argument is not a valid MySQL result resource" in data:
             raise exceptions.StoryDoesNotExist(self.url)
 
-        # Can cause problems if a missing story is referenced in a comment.
-        # Shouldn't be needed anyway.
-        # if "/images/missing_story.png" in data:
-        #     raise exceptions.StoryDoesNotExist(self.url)
-        
         if "This story has been marked as having adult content. Please click below to confirm you are of legal age to view adult material in your country." in data:
             raise exceptions.AdultCheckRequired(self.url)
         
         if self.password:
             params = {}
             params['password'] = self.password
-            data = self._postUrl(self.url,params)
+            data = self._postUrl(self.url, params)
+            soup = bs.BeautifulSoup(data)
 
-        if "Enter the password the author set for this story to view it." in data:
+        if not (soup.find('form', {'id' : 'password_form'}) == None):
             if self.getConfig('fail_on_password'):
                 raise exceptions.FailedToDownload("%s requires story password and fail_on_password is true."%self.url)
             else:
                 raise exceptions.FailedToLogin(self.url,"Story requires individual password",passwdonly=True)
-         
-        if "Invalid story id" in apiData.values():
-            raise exceptions.StoryDoesNotExist(self.url)
-        
-        storyMetadata = apiData["story"]    
-            
-        ## Title
-        a = soup.find('a', href=re.compile(r'^/story/'+self.story.getMetadata('storyId')))
-        self.story.setMetadata('title',stripHTML(a))
-        
-        # self.story.setMetadata("title", storyMetadata["title"])
-        # if not storyMetadata["title"]:
-        #     raise exceptions.FailedToDownload("%s doesn't have a title in the API.  This is a known fimfiction.net bug with titles containing ."%self.url)
-        
-        self.story.setMetadata("author", storyMetadata["author"]["name"])
-        self.story.setMetadata("authorId", storyMetadata["author"]["id"])
-        self.story.setMetadata("authorUrl", "http://%s/user/%s" % (self.getSiteDomain(), storyMetadata["author"]["name"]))
 
-        # chapters = [{"chapterTitle": chapter["title"], "chapterURL": chapter["link"]} for chapter in storyMetadata["chapters"]]
-        
-        # ## this is bit of a kludge based on the assumption all the
-        # ## 'bad' chapters will be at the end.
-        # ## limit down to the number of chapters reported by chapter_count.
-        # chapters = chapters[:storyMetadata["chapter_count"]] 
-        
-        # for chapter in chapters:
-        #     self.chapterUrls.append((chapter["chapterTitle"], chapter["chapterURL"]))
-        # self.story.setMetadata("numChapters", len(self.chapterUrls))
+        ##----------------------------------------------------------------------------------------------------
+        ## Extract metadata
 
-        for chapter in soup.findAll('a',{'class':'chapter_link'}):
+        storyContentBox = soup.find('div', {'class':'story_content_box'})
+
+        # Title
+        title = storyContentBox.find('a', {'class':re.compile(r'.*\bstory_name\b.*')})
+        self.story.setMetadata('title',stripHTML(title))
+
+        # Author
+        author = storyContentBox.find('span', {'class':'author'})
+        self.story.setMetadata("author", stripHTML(author))
+        #No longer seems to be a way to access Fimfiction's internal author ID
+        self.story.setMetadata("authorId", self.story.getMetadata("author"))
+        self.story.setMetadata("authorUrl", "http://%s/user/%s" % (self.getSiteDomain(), stripHTML(author)))
+
+        #Rating text is replaced with full words for historical compatibility after the site changed
+        #on 2014-10-27
+        rating = stripHTML(storyContentBox.find('a', {'class':re.compile(r'.*\bcontent-rating-.*')}))
+        rating = rating.replace("E", "Everyone").replace("T", "Teen").replace("M", "Mature")
+        self.story.setMetadata("rating", rating)
+
+        # Chapters
+        for chapter in storyContentBox.findAll('a',{'class':'chapter_link'}):
             self.chapterUrls.append((stripHTML(chapter), 'http://'+self.host+chapter['href']))
 
         self.story.setMetadata('numChapters',len(self.chapterUrls))
-            
-        # In the case of fimfiction.net, possible statuses are 'Completed', 'Incomplete', 'On Hiatus' and 'Cancelled'
+
+        # Status
+        # In the case of Fimfiction, possible statuses are 'Completed', 'Incomplete', 'On Hiatus' and 'Cancelled'
         # For the sake of bringing it in line with the other adapters, 'Incomplete' becomes 'In-Progress'
-        # and 'Complete' beomes 'Completed'. 'Cancelled' seems an important enough (not to mention more strictly true) 
-        # status to leave unchanged.
-        # Nov2012 - 'On Hiatus' is now passed, too.  It's easy now for users to change/remove if they want
-        # with replace_metadata
-        status = storyMetadata["status"].replace("Incomplete", "In-Progress").replace("Complete", "Completed")
+        # and 'Complete' becomes 'Completed'. 'Cancelled' and 'On Hiatus' are passed through, it's easy now for users
+        # to change/remove if they want with replace_metadata
+        status = stripHTML(storyContentBox.find('span', {'class':re.compile(r'.*\bcompleted-status-.*')}))
+        status = status.replace("Incomplete", "In-Progress").replace("Complete", "Completed")
         self.story.setMetadata("status", status)
-        self.story.setMetadata("rating", storyMetadata["content_rating_text"])
 
-        ## Warnings aren't included in the API.
-        bottomli = soup.find('li',{'class':'bottom'})
-        if bottomli:
-            bottomspans = bottomli.findAll('span')
-            # the first span in bottom is the rating, obtained above.
-            if bottomspans and len(bottomspans) > 1:
-                for warning in bottomspans[1:]:
-                    self.story.addToList('warnings',warning.string)
-                
-        
-        for category in storyMetadata["categories"]:
-            if storyMetadata["categories"][category]:
-                self.story.addToList("genre", category) 
-
-        self.story.setMetadata("numWords", str(storyMetadata["words"]))
-        
-        # fimfic is the first site with an explicit cover image.
-        if "image" in storyMetadata.keys():
-            if "full_image" in storyMetadata:
-                coverurl = storyMetadata["full_image"]
+        # Genres and Warnings
+        # warnings were folded into general categories in the 2014-10-27 site update
+        categories = storyContentBox.findAll('a', {'class':re.compile(r'.*\bstory_category\b.*')})
+        for category in categories:
+            category = stripHTML(category)
+            if category == "Gore" or category == "Sex":
+                self.story.addToList('warnings', category)
             else:
-                coverurl = storyMetadata["image"]
+                self.story.addToList('genre', category)
+
+        # Word count
+        wordCountText = stripHTML(storyContentBox.find('li', {'class':'bottom'}).find('div', {'class':'word_count'}))
+        self.story.setMetadata("numWords", re.sub(r'[^0-9]', '', wordCountText))
+
+        # Cover image
+        storyImage = storyContentBox.find('div', {'class':'story_image'})
+        if storyImage:
+            coverurl = storyImage.find('a')['href']
             if coverurl.startswith('//'): # fix for img urls missing 'http:'
                 coverurl = "http:"+coverurl
+            if get_cover:
+                self.setCoverImage(self.url,coverurl)
 
-            self.setCoverImage(self.url,coverurl)
+            coverSource = storyImage.find('a', {'class':'source'})
+            if coverSource:
+                self.story.setMetadata('coverSourceUrl', coverSource['href'])
+                #There's no text associated with the cover source link, so just
+                #reuse the URL. Makes it clear it's an external link leading
+                #outside of the fanfic site, at least.
+                self.story.setMetadata('coverSource', coverSource['href'])
 
         # fimf has started including extra stuff inside the description div.
-        descdivstr = u"%s"%soup.find("div", {"class":"description"})
+        descdivstr = u"%s"%storyContentBox.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.
-        # Dates are in Unix time
-        # Take the publish date from the first chapter posted
-        # rawDatePublished = storyMetadata["chapters"][0]["date_modified"]
-        # self.story.setMetadata("datePublished", datetime.fromtimestamp(rawDatePublished))
-        # rawDateUpdated = storyMetadata["date_modified"]
-        # self.story.setMetadata("dateUpdated", datetime.fromtimestamp(rawDateUpdated))
-        
+        # Find the newest and oldest chapter dates
+        storyData = storyContentBox.find('div', {'class':'story_data'})
         oldestChapter = None
         newestChapter = None
         self.newestChapterNum = None # save for comparing during update.
@@ -206,18 +197,21 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
         # FiMFiction 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.
-        for index, chapterDate in enumerate(soup.findAll('span', {'class':'date'})):
-            date=re.sub(r"(\d+)(st|nd|rd|th)",r"\1",chapterDate.contents[1].strip())
-            chapterDate = makeDate(date,self.dateformat)
+        for index, chapterDate in enumerate(storyData.findAll('span', {'class':'date'})):
+            dateString=re.sub(r"(\d+)(st|nd|rd|th)",r"\1",chapterDate.contents[1].strip())
+            chapterDate = makeDate(dateString,self.dateformat)
             if oldestChapter == None or chapterDate < oldestChapter:
                 oldestChapter = chapterDate
             if newestChapter == None or chapterDate > newestChapter:
                 newestChapter = chapterDate
                 self.newestChapterNum = index
 
+        # Date updated
         self.story.setMetadata("dateUpdated", newestChapter)
-        
-        pubdatetag = soup.find('span', {'class':'date_approved'})
+
+        # Date published
+        # falls back to oldest chapter date for stories that haven't been officially published yet
+        pubdatetag = storyContentBox.find('span', {'class':'date_approved'})
         if pubdatetag is None:
             self.story.setMetadata("datePublished", oldestChapter)            
         else:
@@ -225,37 +219,48 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
             datestripped=re.sub(r"(\d+)(st|nd|rd|th)",r"\1",pubdateraw.strip())
             pubDate = makeDate(datestripped,self.dateformat)
             self.story.setMetadata("datePublished", pubDate)
-            
-        chars = soup.find("div", {"class":"inner_data"})
-        # fimfic stopped putting the char name on or around the char
-        # icon now for some reason.  Pull it from the image name with
-        # some heuristics.
-        for character in [character_icon["src"] for character_icon in chars.findAll("img", {"class":"character_icon"})]:
-            # //static.fimfiction.net/images/characters/twilight_sparkle.png
-            # 5th split /, remove last four, replace _, capitolize every word(title())
-            char = character.split('/')[5][:-4].replace('_',' ').title()
-            if char == 'Oc':
-                char = "OC"
-            if char == 'Cmc':
-                char = "Cutie Mark Crusaders"
-            self.story.addToList("characters", char)
-            
-        # extra site specific metadata
-        extralist = ["likes","dislikes","views","total_views","short_description"]
-        for metakey in extralist:
-            if metakey in storyMetadata:
-                value = storyMetadata[metakey]
-                if not isinstance(value,basestring):
-                    value = unicode(value)
-                self.story.setMetadata(metakey, value)
 
-        ## 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/')}):
+        # Characters
+        chars = storyContentBox.find("div", {"class":"extra_story_data"})
+        for character in chars.findAll("a", {"class":"character_icon"}):
+            self.story.addToList("characters", character['title'])
+
+        # Likes and dislikes
+        storyToolbar = soup.find('div', {'class':'story-toolbar'})
+        likes = storyToolbar.find('span', {'class':'likes'})
+        if not likes is None:
+            self.story.setMetadata("likes", stripHTML(likes))
+        dislikes = storyToolbar.find('span', {'class':'dislikes'})
+        if not dislikes is None:
+            self.story.setMetadata("dislikes", stripHTML(dislikes))
+
+        # Highest view for a chapter and total views
+        viewSpan = storyToolbar.find('span', {'title':re.compile(r'.*\btotal views\b.*')})
+        self.story.setMetadata("views", re.sub(r'[^0-9]', '', stripHTML(viewSpan)))
+        self.story.setMetadata("total_views", re.sub(r'[^0-9]', '', viewSpan['title']))
+
+        # Comment count
+        commentSpan = storyToolbar.find('span', {'title':re.compile(r'.*\bcomments\b.*')})
+        self.story.setMetadata("comment_count", re.sub(r'[^0-9]', '', stripHTML(commentSpan)))
+
+        # Short description
+        descriptionMeta = soup.find('meta', {'property':'og:description'})
+        self.story.setMetadata("short_description", stripHTML(descriptionMeta['content']))
+
+        #groups
+        if soup.find('button', {'id':'button-view-all-groups'}):
+            groupResponse = self._fetchUrl("http://www.fimfiction.net/ajax/groups/story_groups_list.php?story=%s" % (self.story.getMetadata("storyId")))
+            groupData = json.loads(groupResponse)
+            groupList = bs.BeautifulSoup(groupData["content"])
+        else:
+            groupList = soup.find('ul', {'id':'story-groups-list'})
+
+        if not (groupList == None):
+            for groupName in groupList.findAll('a'):
                 self.story.addToList("groupsUrl", 'http://'+self.host+groupName["href"]) 
                 self.story.addToList("groups",stripHTML(groupName).replace(',', ';'))
 
+        #sequels
         sequelStoryHeader = soup.find('h1', {'class':'header-stories'}, text="Sequels")
         if not sequelStoryHeader == None:
             sequelContainer = sequelStoryHeader.parent.parent
@@ -296,9 +301,27 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
     def getChapterText(self, url):
         logger.debug('Getting chapter text from: %s' % url)
 
-        data = self.do_fix_blockquotes(self._fetchUrl(url))
+        data = self._fetchUrl(url)
+
+        soup = bs.BeautifulSoup(data)
+        if not (soup.find('form', {'id' : 'password_form'}) == None):
+            if self.password:
+                params = {}
+                params['password'] = self.password
+                data = self._postUrl(url, params)
+            else:
+                print("Chapter %s needed password but no password was present" % url)
+
+        data = self.do_fix_blockquotes(data)
+
         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)
+
+        # fix for img urls missing 'http:'
+        images = soup.findAll('img')
+        for imagetag in images:
+            if 'src' in imagetag.attrs and imagetag['src'].startswith('//'):
+                imagetag['src'] = "http:"+imagetag['src']
+
         return self.utf8FromSoup(url,soup)
-        

fanficdownloader/adapters/adapter_finestoriescom.py

@@ -62,8 +62,8 @@ class FineStoriesComAdapter(BaseSiteAdapter):
         return 'finestories.com'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/s/1234 http://"+self.getSiteDomain()+"/s/1234:4010 http://"+self.getSiteDomain()+"/library/storyInfo.php?id=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/s/1234 http://"+cls.getSiteDomain()+"/s/1234:4010 http://"+cls.getSiteDomain()+"/library/storyInfo.php?id=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain())+r"/(s|library)?/(storyInfo.php\?id=)?\d+(:\d+)?(;\d+)?$"

fanficdownloader/adapters/adapter_grangerenchantedcom.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -75,7 +76,7 @@ class GrangerEnchantedCom(BaseSiteAdapter):
         return ['grangerenchanted.com','malfoymanor.grangerenchanted.com']
 
     @classmethod
-    def getSiteExampleURLs(self):
+    def getSiteExampleURLs(cls):
         return "http://grangerenchanted.com/enchant/viewstory.php?sid=1234 http://malfoymanor.grangerenchanted.com/themanor/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):

fanficdownloader/adapters/adapter_harrypotterfanfictioncom.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -57,7 +58,7 @@ class HarryPotterFanFictionComSiteAdapter(BaseSiteAdapter):
         return ['www.harrypotterfanfiction.com','harrypotterfanfiction.com']
 
     @classmethod
-    def getSiteExampleURLs(self):
+    def getSiteExampleURLs(cls):
         return "http://www.harrypotterfanfiction.com/viewstory.php?psid=1234"
 
     def getSiteURLPattern(self):

fanficdownloader/adapters/adapter_hennethannunnet.py

@@ -66,8 +66,8 @@ class HennethAnnunNetAdapter(BaseSiteAdapter):
         return 'www.henneth-annun.net'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/stories/chapter.cfm?stid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/stories/chapter.cfm?stid=1234"
 
     def getSiteURLPattern(self):
         return "http://"+self.getSiteDomain()+"/stories/chapter(_view)?.cfm\?stid="+r"\d+$"

fanficdownloader/adapters/adapter_hlfictionnet.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -66,8 +67,8 @@ class HLFictionNetAdapter(BaseSiteAdapter):
         return 'hlfiction.net'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_hpfandomnet.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -71,8 +72,8 @@ class HPFandomNetAdapterAdapter(BaseSiteAdapter): # XXX
         return 'www.hpfandom.net' # XXX
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/eff/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/eff/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/eff/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_hpfanficarchivecom.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -66,8 +67,8 @@ class HPFanficArchiveComAdapter(BaseSiteAdapter):
         return 'www.hpfanficarchive.com'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/stories/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/stories/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/stories/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_iketernalnet.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -66,8 +67,8 @@ class IkEternalNetAdapter(BaseSiteAdapter):
         return 'www.ik-eternal.net'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_imagineeficcom.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -66,8 +67,8 @@ class ImagineEFicComAdapter(BaseSiteAdapter):
         return 'imagine.e-fic.com'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_indeathnet.py

@@ -73,8 +73,8 @@ class InDeathNetAdapter(BaseSiteAdapter):
 
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/blog/archive/123-story-in-death/"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/blog/archive/123-story-in-death/"
 
     def getSiteURLPattern(self):
         # http://www.indeath.net/blog/archive/169-ransom-in-death/

fanficdownloader/adapters/adapter_ksarchivecom.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -75,8 +76,8 @@ class KSArchiveComAdapter(BaseSiteAdapter): # XXX
         return 'ksarchive.com' # XXX
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return "http://(www.)?"+re.escape(self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_libraryofmoriacom.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -67,8 +68,8 @@ class LibraryOfMoriaComAdapter(BaseSiteAdapter):
         return 'www.libraryofmoria.com'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/a/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/a/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/a/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_literotica.py

@@ -39,64 +39,97 @@ class LiteroticaSiteAdapter(BaseSiteAdapter):
                                # 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]
-        if re.match(r'-ch\d\d$',storyid):
-            storyid = storyid[:-2]+'01'
-        self.story.setMetadata('storyId',storyid)
-        
-        self.origurl = url
-        if "//www.i." in self.origurl:
-            ## accept m(mobile)url, but use www.
-            self.origurl = self.origurl.replace("//www.i.","//www.")
+        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)
 
-        # normalized story URL.
-        self._setURL(url[:url.index('//')+2]+self.getSiteDomain()\
-                         +"/s/"+self.story.getMetadata('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 'www.literotica.com'
+        return 'literotica.com'
 
     @classmethod
     def getAcceptDomains(cls):
-        return ['www.literotica.com', 'www.i.literotica.com']
+        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 http://www.literotica.com/stories/showstory.php?id=1234 http://www.i.literotica.com/stories/showstory.php?id=1234"
-        return "http://www.literotica.com/s/story-title https://www.literotica.com/s/story-title"
+    def getSiteExampleURLs(cls):
+        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(\.i)?\.literotica\.com/s/([a-zA-Z0-9_-]+)"
+        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)
-        
-        url1 = self.origurl
-        logger.debug("first page URL: "+url1)
 
+        logger.debug("Chapter/Story URL: <%s> " % self.url)
         try:
-            data1 = self._fetchUrl(url1)
+            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(url1)
+                raise exceptions.StoryDoesNotExist(self.url)
             else:
                 raise e
 
-        #strip comments from soup
-        [comment.extract() for comment in soup1.findAll(text=lambda text:isinstance(text, bs.Comment))]
-
         # author
         a = soup1.find("span", "b-story-user-y")
         self.story.setMetadata('authorId', urlparse.parse_qs(a.a['href'].split('?')[1])['uid'][0])
@@ -110,105 +143,78 @@ class LiteroticaSiteAdapter(BaseSiteAdapter):
         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=url1[url1.index(':')+1:])
+        storyLink = soupAuth.find('a', href=self.url[self.url.index(':')+1:])
 
         if storyLink is not None:
-            # pull the published date from the author page
-            # default values from single link.  Updated below if multiple chapter.
-            date = storyLink.parent.parent.findAll('td')[-1].text
+            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))
-
-        # find num of pages
-        # find a "3 Pages:" string on the page and parse it
-        pgs = soup1.find("span", "b-pager-caption-t r-d45").string.split(' ')[0]
-
-        # If there are multiple pages, find and request the last page
-        if "1" != pgs:
-            logger.debug("last page number: "+pgs)
-            try:
-                data2 = self._fetchUrl(url1, {'page': pgs})
-                soup2 = bs.BeautifulSoup(data2)
-                [comment.extract() for comment in soup2.findAll(text=lambda text:isinstance(text, bs.Comment))]
-            except urllib2.HTTPError, e:
-                if e.code == 404:
-                    # TODO: Probably should reformat this
-                    raise exceptions.StoryDoesNotExist(url1, {'page': pgs})
-                else:
-                    raise e
+            self.chapterUrls = [(storyLink.text, self.url)]
         else:
-            #If we're already on the last page, copy the soup
-            soup2 = soup1
+            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'))
 
-        # parse out the list of chapters
-        chaps = soup2.find('div', id='b-series')
-        if chaps:  # may be one post only
-            #self.chapterUrls = [(ch.a.text, ch.a['href']) for ch in chaps.findAll('li')]
-
-            # if there are chapters, lets pull them and title from the
-            # author page because *this* chapter is omitted from the
-            # list on the last page.
-            row = storyLink.parent.parent.previousSibling
-            while row['class'] != 'ser-ttl':
-                row = row.previousSibling
-
-            seriesTitle = stripHTML(row)
-            if seriesTitle:
-                # this regex is deliberately greedy. We want to get the biggest match before a ':'
-                self.story.setMetadata('title', re.match('(.*):[^:]*$', seriesTitle).group(1))
-            else:
-                self.story.setMetadata('title', soup1.h1.string)
-
-            # now chapter list.  Assumed oldest to newest.
+            ## Walk the chapters
+            chapterTr = seriesTr.nextSibling
             self.chapterUrls = []
-            row = row.nextSibling
-                
-            self.story.setMetadata('datePublished',makeDate(stripHTML(row.find('td',{'class':'dt'})), self.dateformat))
-            while row['class'] == 'sl':
-                # pages include full URLs.
-                chapurl = row.a['href']
-                if chapurl.startswith('//'):
-                    chapurl = self.parsedUrl.scheme+':'+chapurl
-                self.chapterUrls.append((row.a.string,chapurl))
-                if not row.nextSibling:
-                    break
-                row = row.nextSibling
+            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
 
-            row = row.previousSibling
-            self.story.setMetadata('dateUpdated',makeDate(stripHTML(row.find('td',{'class':'dt'})), self.dateformat))
-                
-        else:  # if one post only
-            self.chapterUrls = [(soup1.h1.string, url1)]
-            self.story.setMetadata('title', soup1.h1.string)
+            ## Set description to joint chapter descriptions
+            self.story.setMetadata('description', " / ".join(descriptions))
 
-        # normalize on first chapter URL.
-        self._setURL(self.chapterUrls[0][1])
+            ## 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])
 
-        # reset storyId to first chapter.
-        self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2])
+            # normalize on first chapter URL.
+            self._setURL(self.chapterUrls[0][1])
 
         self.story.setMetadata('numChapters', len(self.chapterUrls))
-
-        self.story.setMetadata('category', soup1.find('div', 'b-breadcrumbs').findAll('a')[1].string)
-        # deliberately not self.setDescription() because it's never HTML.
-        self.story.setMetadata('description', soup1.find('meta', {'name': 'description'})['content'])
-        
-        # li tags inside div class b-s-story-tag-list
-        for li in soup1.find('div', {'class':'b-s-story-tag-list'}).findAll('a'):
-            self.story.addToList('eroticatags',stripHTML(li))
+                
+        # 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)
-        time.sleep(0.5)
+        logger.debug('Getting chapter text from <%s>' % url)
         data1 = self._fetchUrl(url)
         soup1 = bs.BeautifulSoup(data1)
 

fanficdownloader/adapters/adapter_lotrfanfictioncom.py

@@ -0,0 +1,36 @@
+# -*- 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.
+#
+
+# Software: eFiction
+from base_efiction_adapter import BaseEfictionAdapter
+
+class TheLOTRFanFictionSiteAdapter(BaseEfictionAdapter):
+
+    @staticmethod
+    def getSiteDomain():
+        return 'lotrfanfiction.com'
+
+    @classmethod
+    def getSiteAbbrev(seluuf):
+        return 'lotrff'
+
+    @classmethod
+    def getDateFormat(self):
+        return "%d/%m/%y"
+
+def getClass():
+    return TheLOTRFanFictionSiteAdapter

fanficdownloader/adapters/adapter_lumossycophanthexcom.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -67,8 +68,8 @@ class LumosSycophantHexComAdapter(BaseSiteAdapter):
         return 'lumos.sycophanthex.com'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_mediaminerorg.py

@@ -56,8 +56,8 @@ class MediaMinerOrgSiteAdapter(BaseSiteAdapter):
         return 'www.mediaminer.org'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/fanfic/view_st.php/123456 http://"+self.getSiteDomain()+"/fanfic/view_ch.php/1234123/123444#fic_c"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/fanfic/view_st.php/123456 http://"+cls.getSiteDomain()+"/fanfic/view_ch.php/1234123/123444#fic_c"
 
     def getSiteURLPattern(self):
         ##  http://www.mediaminer.org/fanfic/view_st.php/76882

fanficdownloader/adapters/adapter_merlinficdtwinscouk.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -66,8 +67,8 @@ class MerlinFicDtwinsCoUk(BaseSiteAdapter):
         return 'merlinfic.dtwins.co.uk'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_midnightwhispersca.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -71,8 +72,8 @@ class MidnightwhispersCaAdapter(BaseSiteAdapter): # XXX
         return 'www.midnightwhispers.ca' # XXX
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_mugglenetcom.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -74,8 +75,8 @@ class MuggleNetComAdapter(BaseSiteAdapter): # XXX
         return ['fanfiction.mugglenet.com','fanfic.mugglenet.com']
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://")+r"fanfic(tion)?\.mugglenet\.com"+re.escape("/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_nationallibrarynet.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -69,9 +70,9 @@ class NationalLibraryNetAdapter(BaseSiteAdapter):
         return ['www.national-library.net','national-library.net']
 
     @classmethod
-    def getSiteExampleURLs(self):
+    def getSiteExampleURLs(cls):
         # ONLY the stories archived on or after June 17, 2006 and that are hosted on the website: 
-        return "http://"+self.getSiteDomain()+"/viewstory.php?storyid=1234"
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?storyid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://")+"(www\.)?"+re.escape(self.getSiteDomain()+"/viewstory.php?storyid=")+r"\d+$"

fanficdownloader/adapters/adapter_ncisficcom.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -69,8 +70,8 @@ class NCISFicComAdapter(BaseSiteAdapter):
         return ['www.ncisfic.com','ncisfic.com']
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/viewstory.php?storyid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?storyid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://")+"(www\.)?"+re.escape(self.getSiteDomain()+"/viewstory.php?storyid=")+r"\d+$"

fanficdownloader/adapters/adapter_ncisfictionnet.py

@@ -75,8 +75,8 @@ class NCISFictionNetAdapter(BaseSiteAdapter):
         return ['www.ncisfiction.net','www.ncisfiction.com']
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/story.php?stid=01234 http://"+self.getSiteDomain()+"/chapters.php?stid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/story.php?stid=01234 http://"+cls.getSiteDomain()+"/chapters.php?stid=1234"
 
     def getSiteURLPattern(self):
         return r'http://www\.ncisfiction\.(net|com)/(chapters|story)?.php\?stid=\d+'

fanficdownloader/adapters/adapter_netraptororg.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -64,8 +65,8 @@ class NetRaptorOrgAdapter(BaseSiteAdapter):
         return 'netraptor.org'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/fanfiction/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/fanfiction/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/fanfiction/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_nfacommunitycom.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -75,8 +76,8 @@ class NfaCommunityComAdapter(BaseSiteAdapter): # XXX
         return 'nfacommunity.com' # XXX
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return "http://(www.)?"+re.escape(self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_nhamagicalworldsus.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -59,7 +60,7 @@ class NHAMagicalWorldsUsAdapter(BaseSiteAdapter):
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = " %m/%d/%y"
+        self.dateformat = " %d/%m/%y"
             
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
@@ -67,8 +68,8 @@ class NHAMagicalWorldsUsAdapter(BaseSiteAdapter):
         return 'nha.magical-worlds.us'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
@@ -86,6 +87,28 @@ class NHAMagicalWorldsUsAdapter(BaseSiteAdapter):
             else:
                 raise e
             
+        m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
+        if m != None:
+            if self.is_adult or self.getConfig("is_adult"):
+                # We tried the default and still got a warning, so
+                # let's pull the warning number from the 'continue'
+                # link and reload data.
+                addurl = m.group(1)
+                # correct stupid & error in url.
+                addurl = addurl.replace("&","&")
+                url = self.url+'&index=1'+addurl
+                logger.debug("URL 2nd try: "+url)
+
+                try:
+                    data = self._fetchUrl(url)
+                except urllib2.HTTPError, e:
+                    if e.code == 404:
+                        raise exceptions.StoryDoesNotExist(self.url)
+                    else:
+                        raise e    
+            else:
+                raise exceptions.AdultCheckRequired(self.url)
+            
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
             raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
             

fanficdownloader/adapters/adapter_nickandgregnet.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -67,8 +68,8 @@ class NickAndGregNetAdapter(BaseSiteAdapter):
         return 'www.nickandgreg.net'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/desert_archive/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/desert_archive/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/desert_archive/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_occlumencysycophanthexcom.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -67,8 +68,8 @@ class OcclumencySycophantHexComAdapter(BaseSiteAdapter):
         return 'occlumency.sycophanthex.com'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_onedirectionfanfictioncom.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -71,8 +72,8 @@ class OneDirectionFanfictionComAdapter(BaseSiteAdapter):
 
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://")+"(www\.)?"+re.escape(self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_phoenixsongnet.py

@@ -66,8 +66,8 @@ class PhoenixSongNetAdapter(BaseSiteAdapter):
         return 'www.phoenixsong.net'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/fanfiction/story/1234/"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/fanfiction/story/1234/"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/fanfiction/story/")+r"\d+/?$"

fanficdownloader/adapters/adapter_pommedesangcom.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -76,8 +77,8 @@ class PommeDeSangComAdapter(BaseSiteAdapter):
         return 'pommedesang.com'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/efiction/viewstory.php?sid=1234 http://"+self.getSiteDomain()+"/sds/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/efiction/viewstory.php?sid=1234 http://"+cls.getSiteDomain()+"/sds/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return r"http://"+self.getSiteDomain()+"/(efiction|sds)?/viewstory.php\?sid=\d+$"

fanficdownloader/adapters/adapter_ponyfictionarchivenet.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -70,8 +71,8 @@ class PonyFictionArchiveNetAdapter(BaseSiteAdapter):
         return ['www.ponyfictionarchive.net','ponyfictionarchive.net','explicit.ponyfictionarchive.net']
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234 http://explicit."+self.getSiteDomain()+"/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234 http://explicit."+cls.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://")+"(www\.|explicit\.)?"+re.escape(self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_portkeyorg.py

@@ -73,12 +73,19 @@ class PortkeyOrgAdapter(BaseSiteAdapter): # XXX
         return 'fanfiction.portkey.org' # XXX
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/story/1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/story/1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/story/")+r"\d+(/\d+)?$"
 
+    def use_pagecache(self):
+        '''
+        adapters that will work with the page cache need to implement
+        this and change it to True.
+        '''
+        return True
+    
     ## Getting the chapter list and the meta data, plus 'is adult' checking.
     def extractChapterUrlsAndMetadata(self):
 
@@ -88,7 +95,6 @@ class PortkeyOrgAdapter(BaseSiteAdapter): # XXX
         # portkey screws around with using a different URL to set the
         # cookie and it's a pain.  So... cheat!
         if self.is_adult or self.getConfig("is_adult"):
-            cookieproc = urllib2.HTTPCookieProcessor()
             cookie = cl.Cookie(version=0, name='verify17', value='1',
                                port=None, port_specified=False,
                                domain=self.getSiteDomain(), domain_specified=False, domain_initial_dot=False,
@@ -99,9 +105,8 @@ class PortkeyOrgAdapter(BaseSiteAdapter): # XXX
                                comment=None,
                                comment_url=None,
                                rest={'HttpOnly': None},
-                               rfc2109=False)
-            cookieproc.cookiejar.set_cookie(cookie)
-            self.opener = urllib2.build_opener(cookieproc)        
+                               rfc2109=False) 
+            self.cookiejar.set_cookie(cookie)
 
         try:
             data = self._fetchUrl(url)

fanficdownloader/adapters/adapter_potionsandsnitchesnet.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -56,7 +57,7 @@ class PotionsAndSnitchesNetSiteAdapter(BaseSiteAdapter):
         return ['www.potionsandsnitches.net','potionsandsnitches.net']
 
     @classmethod
-    def getSiteExampleURLs(self):
+    def getSiteExampleURLs(cls):
         return "http://www.potionsandsnitches.net/fanfiction/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):

fanficdownloader/adapters/adapter_potterficscom.py

@@ -73,7 +73,7 @@ class PotterFicsComAdapter(BaseSiteAdapter):
         return 'www.potterfics.com'
 
     @classmethod
-    def getSiteExampleURLs(self):
+    def getSiteExampleURLs(cls):
         return "http://www.potterfics.com/historias/12345 http://www.potterfics.com/historias/12345/capitulo-1 "
 
     def getSiteURLPattern(self):
@@ -86,6 +86,40 @@ class PotterFicsComAdapter(BaseSiteAdapter):
             r"(?P<id>\d+)(/capitulo-(?P<ch>\d+))?/?$"
         return p
 
+    def needToLoginCheck(self, data):
+        # partials used to avoid having to figure out what was wrong
+        # with included utf8 higher chars.
+        if 'Para ver esta historia, por favor inicia tu sesi' in data \
+                or '<script>alert("El nombre de usuario o contrase' in data:
+            return True
+        else:
+            return False
+        
+    def performLogin(self,url):
+        params = {}
+
+        if self.password:
+            params['login_usuario'] = self.username
+            params['login_password'] = self.password
+        else:
+            params['login_usuario'] = self.getConfig("username")
+            params['login_password'] = self.getConfig("password")
+        params['login_ck'] = '1'
+
+        loginUrl = 'http://www.potterfics.com/secciones/usuarios/login.php'
+        logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
+                                                              params['login_usuario']))
+        d = self._postUrl(loginUrl,params)
+
+        #print("d:%s"%d)
+        if '<script>alert("El nombre de usuario o contrase' in d:
+            logger.info("Failed to login to URL %s as %s" % (loginUrl,
+                                                              params['login_usuario']))
+            raise exceptions.FailedToLogin(url,params['login_usuario'])
+            return False
+        else:
+            return True
+
     def extractChapterUrlsAndMetadata(self):
 
         #this converts '/historias/12345' to 'http://www.potterfics.com/historias/12345'
@@ -123,8 +157,12 @@ class PotterFicsComAdapter(BaseSiteAdapter):
 
         #print data
 
-        #deal with adult content warnings - doesn't seem to apply to this site
-
+        #deal with adult content login
+        if self.needToLoginCheck(data):
+            # need to log in for this one.
+            self.performLogin(url)
+            data = self._fetchUrl(url,usecache=False)
+            
         #set constant meta for this site:
         #Set Language = Spanish
         self.story.setMetadata('language', 'Spanish')
@@ -144,8 +182,8 @@ class PotterFicsComAdapter(BaseSiteAdapter):
         #within that, we want the second row, first cell
         cell = table.tr.findNextSibling('tr').td
 
-        #find first metadata block
-        mb = cell.div.findNextSibling('div')
+        #find first metadata block--isn't first if logged in
+        mb = cell.div.findNextSibling('div',{'align':'left'})
         #Get meta...
         self.story.setMetadata('title', stripHTML(mb.b))
         #strip out brackets on rating

fanficdownloader/adapters/adapter_potterheadsanonymouscom.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -66,8 +67,8 @@ class PotterHeadsAnonymousComAdapter(BaseSiteAdapter):
         return 'fanfic.potterheadsanonymous.com'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_pretendercentrecom.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -70,8 +71,8 @@ class PretenderCenterComAdapter(BaseSiteAdapter):
         return ['www.pretendercentre.com','pretendercentre.com']
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/missingpieces/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/missingpieces/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://")+"(www\.)?"+re.escape(self.getSiteDomain()+"/missingpieces/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_psychficcom.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -66,8 +67,8 @@ class PsychFicComAdapter(BaseSiteAdapter):
         return 'www.psychfic.com'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_qafficcom.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -66,8 +67,8 @@ class QafFicComAdapter(BaseSiteAdapter):
         return 'www.qaf-fic.com'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/atp/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/atp/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/atp/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_restrictedsectionorg.py

@@ -69,8 +69,8 @@ class RestrictedSectionOrgSiteAdapter(BaseSiteAdapter):
         return 'www.restrictedsection.org'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/story.php?story=1234 http://"+self.getSiteDomain()+"/file.php?file=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/story.php?story=1234 http://"+cls.getSiteDomain()+"/file.php?file=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain())+r"/(?P<filestory>file|story).php\?(file|story)=(?P<id>\d+)$"

fanficdownloader/adapters/adapter_samandjacknet.py

@@ -0,0 +1,342 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2011 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
+
+# By virtue of being recent and requiring both is_adult and user/pass,
+# adapter_fanficcastletvnet.py is the best choice for learning to
+# write adapters--especially for sites that use the eFiction system.
+# Most sites that have ".../viewstory.php?sid=123" in the story URL
+# are eFiction.
+
+# For non-eFiction sites, it can be considerably more complex, but
+# this is still a good starting point.
+
+# In general an 'adapter' needs to do these five things:
+
+# - 'Register' correctly with the downloader
+# - Site Login (if needed)
+# - 'Are you adult?' check (if needed--some do one, some the other, some both)
+# - Grab the chapter list
+# - Grab the story meta-data (some (non-eFiction) adapters have to get it from the author page)
+# - Grab the chapter texts
+
+# Search for XXX comments--that's where things are most likely to need changing.
+
+# This function is called by the downloader in all adapter_*.py files
+# in this dir to register the adapter class.  So it needs to be
+# updated to reflect the class below it.  That, plus getSiteDomain()
+# take care of 'Registering'.
+def getClass():
+    return SamAndJackNetAdapter # XXX
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class SamAndJackNetAdapter(BaseSiteAdapter): # XXX
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        
+        
+        # normalized story URL.
+        # XXX Most sites don't have the /fanfic part.  Replace all to remove it usually.
+        self._setURL('http://' + self.getSiteDomain() + '/fanfics/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','sjn') # XXX
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%b %d, %Y" # XXX
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'samandjack.net' # XXX
+
+    @classmethod
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/fanfics/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/fanfics/viewstory.php?sid=")+r"\d+$"
+
+    ## Login seems to be reasonably standard across eFiction sites.
+    def needToLoginCheck(self, data):
+        if 'Registered Users Only' in data \
+                or 'There is no such account on our website' in data \
+                or "That password doesn't match the one in our database" in data:
+            return True
+        else:
+            return False
+        
+    def performLogin(self, url):
+        params = {}
+
+        if self.password:
+            params['penname'] = self.username
+            params['password'] = self.password
+        else:
+            params['penname'] = self.getConfig("username")
+            params['password'] = self.getConfig("password")
+        params['cookiecheck'] = '1'
+        params['submit'] = 'Submit'
+    
+        loginUrl = 'http://' + self.getSiteDomain() + '/fanfics/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.
+
+            # Furthermore, there's a couple sites now with more than
+            # one warning level for different ratings.  And they're
+            # fussy about it.  midnightwhispers has three: 10, 3 & 5.
+            # we'll try 5 first.
+            addurl = "&ageconsent=ok&warning=5" # XXX
+        else:
+            addurl=""
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'+addurl
+        logger.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        # The actual text that is used to announce you need to be an
+        # adult varies from site to site.  Again, print data before
+        # the title search to troubleshoot.
+            
+        # Since the warning text can change by warning level, let's
+        # look for the warning pass url.  nfacommunity uses
+        # &warning= -- actually, so do other sites.  Must be an
+        # eFiction book.
+            
+        # viewstory.php?sid=1882&warning=4
+        # viewstory.php?sid=1654&ageconsent=ok&warning=5
+        #print data
+        #m = re.search(r"'viewstory.php\?sid=1882(&warning=4)'",data)
+        m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
+        if m != None:
+            if self.is_adult or self.getConfig("is_adult"):
+                # We tried the default and still got a warning, so
+                # let's pull the warning number from the 'continue'
+                # link and reload data.
+                addurl = m.group(1)
+                # correct stupid & error in url.
+                addurl = addurl.replace("&","&")
+                url = self.url+'&index=1'+addurl
+                logger.debug("URL 2nd try: "+url)
+
+                try:
+                    data = self._fetchUrl(url)
+                except urllib2.HTTPError, e:
+                    if e.code == 404:
+                        raise exceptions.StoryDoesNotExist(self.url)
+                    else:
+                        raise e    
+            else:
+                raise exceptions.AdultCheckRequired(self.url)
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+
+        pagetitle = soup.find('div',{'id':'pagetitle'})
+        ## Title
+        a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        self.story.setMetadata('title',stripHTML(a))
+             
+        # Find authorid and URL from... author url.
+        # (fetch multiple authors)
+        alist = soup.findAll('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        for a in alist:
+            self.story.addToList('authorId',a['href'].split('=')[1])
+            self.story.addToList('authorUrl','http://'+self.host+'/fanfics/'+a['href'])
+            self.story.addToList('author',a.string)
+                             
+        # Reviews
+        reviewdata = soup.find('div', {'id' : 'sort'})
+        a = reviewdata.findAll('a', href=re.compile(r'reviews.php\?type=ST&(amp;)?item='+self.story.getMetadata('storyId')+"$"))[1] # second one.
+        self.story.setMetadata('reviews',stripHTML(a))              
+        
+        # Find the chapters:
+        for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
+            # just in case there's tags, like <i> in chapter titles.
+            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/fanfics/'+chapter['href']+addurl))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+
+        # utility method
+        def defaultGetattr(d,k):
+            try:
+                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:
+                self.setDescription(url,value)                     
+
+            if 'Rated' in label:
+                self.story.setMetadata('rating', value)
+
+            if 'Word count' in label:
+                self.story.setMetadata('numWords', value)
+
+            if 'Categories' in label:
+                cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
+                catstext = [cat.string for cat in cats]
+                for cat in catstext:
+                    self.story.addToList('category',cat.string)
+
+            if 'Characters' in label:
+                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+                charstext = [char.string for char in chars]
+                for char in charstext:
+                    self.story.addToList('characters',char.string)
+
+            ## Not all sites use Genre, but there's no harm to
+            ## leaving it in.  Check to make sure the type_id number
+            ## is correct, though--it's site specific.
+            if 'Genre' in label:
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1')) # XXX
+                genrestext = [genre.string for genre in genres]
+                self.genre = ', '.join(genrestext)
+                for genre in genrestext:
+                    self.story.addToList('genre',genre.string)
+
+            ## Not all sites use Warnings, but there's no harm to
+            ## leaving it in.  Check to make sure the type_id number
+            ## is correct, though--it's site specific.
+            if 'Warnings' in label:
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')) # XXX
+                warningstext = [warning.string for warning in warnings]
+                self.warning = ', '.join(warningstext)
+                for warning in warningstext:
+                    self.story.addToList('warnings',warning.string)
+
+            if 'Completed' in label:
+                if 'Yes' in value:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+
+            if 'Published' in label:
+                value=value.replace(' | ','')
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            
+            if 'Updated' in label:
+                # there's a stray [ at the end.
+                #value = value[0:-1]
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+                         
+
+        try:
+            # Find Series name from series URL.
+            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/fanfics/'+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.BeautifulStoneSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('div', {'id' : 'story'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_samdeanarchivenu.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -70,8 +71,8 @@ class SamDeanArchiveNuAdapter(BaseSiteAdapter):
         return ['www.samdean.archive.nu','samdean.archive.nu']
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://")+r"(www\.)?"+re.escape(self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_scarheadnet.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -66,8 +67,8 @@ class ScarHeadNetAdapter(BaseSiteAdapter):
         return 'scarhead.net'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_scarvesandcoffeenet.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -66,8 +67,8 @@ class ScarvesAndCoffeeNetAdapter(BaseSiteAdapter):
         return 'www.scarvesandcoffee.net'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_sg1heliopoliscom.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -75,8 +76,8 @@ class SG1HeliopolisComAdapter(BaseSiteAdapter):
         return 'sg1-heliopolis.com'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/archive/viewstory.php?sid=1234 http://"+self.getSiteDomain()+"/adult/viewstory.php?sid=1234 http://"+self.getSiteDomain()+"/atlantis/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/archive/viewstory.php?sid=1234 http://"+cls.getSiteDomain()+"/adult/viewstory.php?sid=1234 http://"+cls.getSiteDomain()+"/atlantis/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return r"http://sg1-heliopolis.com/(archive|adult|atlantis)?/viewstory.php\?sid=\d+$"

fanficdownloader/adapters/adapter_sheppardweircom.py

@@ -0,0 +1,317 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2011 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
+
+# By virtue of being recent and requiring both is_adult and user/pass,
+# adapter_fanficcastletvnet.py is the best choice for learning to
+# write adapters--especially for sites that use the eFiction system.
+# Most sites that have ".../viewstory.php?sid=123" in the story URL
+# are eFiction.
+
+# For non-eFiction sites, it can be considerably more complex, but
+# this is still a good starting point.
+
+# In general an 'adapter' needs to do these five things:
+
+# - 'Register' correctly with the downloader
+# - Site Login (if needed)
+# - 'Are you adult?' check (if needed--some do one, some the other, some both)
+# - Grab the chapter list
+# - Grab the story meta-data (some (non-eFiction) adapters have to get it from the author page)
+# - Grab the chapter texts
+
+# Search for XXX comments--that's where things are most likely to need changing.
+
+# This function is called by the downloader in all adapter_*.py files
+# in this dir to register the adapter class.  So it needs to be
+# updated to reflect the class below it.  That, plus getSiteDomain()
+# take care of 'Registering'.
+def getClass():
+    return SheppardWeirComAdapter # XXX
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class SheppardWeirComAdapter(BaseSiteAdapter): # XXX
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        
+        
+        # normalized story URL.
+        # XXX Most sites don't have the /fanfic part.  Replace all to remove it usually.
+        self._setURL('http://' + self.getSiteDomain() + '/fanfics/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','swf') # XXX
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%B %d, %Y" # XXX
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'sheppardweir.com' # XXX
+
+    @classmethod
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/fanfics/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/fanfics/viewstory.php?sid=")+r"\d+$"
+
+    ## Login seems to be reasonably standard across eFiction sites.
+    def needToLoginCheck(self, data):
+        if 'Registered Users Only' in data \
+                or 'There is no such account on our website' in data \
+                or "That password doesn't match the one in our database" in data:
+            return True
+        else:
+            return False
+        
+    def performLogin(self, url):
+        params = {}
+
+        if self.password:
+            params['penname'] = self.username
+            params['password'] = self.password
+        else:
+            params['penname'] = self.getConfig("username")
+            params['password'] = self.getConfig("password")
+        params['cookiecheck'] = '1'
+        params['submit'] = 'Submit'
+    
+        loginUrl = 'http://' + self.getSiteDomain() + '/fanfics/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 = "&ageconsent=ok&warning=4" # XXX
+        else:
+            addurl=""
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'+addurl
+        logger.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        if self.needToLoginCheck(data):
+            # need to log in for this one.
+            self.performLogin(url)
+            data = self._fetchUrl(url)
+
+        # The actual text that is used to announce you need to be an
+        # adult varies from site to site.  Again, print data before
+        # the title search to troubleshoot.
+        if "Age Consent Required" in data: # XXX 
+            raise exceptions.AdultCheckRequired(self.url)
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+
+        pagetitle = soup.find('div',{'id':'pagetitle'})
+        ## Title
+        a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        self.story.setMetadata('title',stripHTML(a))
+        
+        # Find authorid and URL from... author url.
+        # (fetch multiple authors)
+        alist = soup.findAll('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        for a in alist:
+            self.story.addToList('authorId',a['href'].split('=')[1])
+            self.story.addToList('authorUrl','http://'+self.host+'/fanfics/'+a['href'])
+            self.story.addToList('author',a.string)
+        
+        
+        # Reviews
+        reviewdata = soup.find('div', {'id' : 'sort'})
+        a = reviewdata.findAll('a', href=re.compile(r'reviews.php\?type=ST&(amp;)?item='+self.story.getMetadata('storyId')+"$"))[1] # second one.
+        self.story.setMetadata('reviews',stripHTML(a))  
+
+
+        # Find the chapters:
+        for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
+            # just in case there's tags, like <i> in chapter titles.
+            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/fanfics/'+chapter['href']+addurl))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+
+        # utility method
+        def defaultGetattr(d,k):
+            try:
+                return d[k]
+            except:
+                return ""
+                
+        # Summary        
+        summarydata = unicode(soup.find('div',{'class':'content'}))
+        start='<span class="label">Summary: </span>'
+        end='</div>'
+        summarydata = summarydata[summarydata.index(start)+len(start):summarydata.rindex(end)]
+        self.setDescription(url,bs.BeautifulSoup(summarydata)) 
+        
+        # <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 'Rated' in label:
+                self.story.setMetadata('rating', value)
+
+            if 'Word count' in label:
+                self.story.setMetadata('numWords', value)
+
+            if 'Categories' in label:
+                cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
+                catstext = [cat.string for cat in cats]
+                for cat in catstext:
+                    self.story.addToList('category',cat.string)
+
+            if 'Characters' in label:
+                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+                charstext = [char.string for char in chars]
+                for char in charstext:
+                    self.story.addToList('characters',char.string)
+
+            ## Not all sites use Genre, but there's no harm to
+            ## leaving it in.  Check to make sure the type_id number
+            ## is correct, though--it's site specific.
+            if 'Genre' in label:
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1')) # XXX
+                genrestext = [genre.string for genre in genres]
+                self.genre = ', '.join(genrestext)
+                for genre in genrestext:
+                    self.story.addToList('genre',genre.string)
+
+            ## Not all sites use Warnings, but there's no harm to
+            ## leaving it in.  Check to make sure the type_id number
+            ## is correct, though--it's site specific.
+            if 'Warnings' in label:
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')) # XXX
+                warningstext = [warning.string for warning in warnings]
+                self.warning = ', '.join(warningstext)
+                for warning in warningstext:
+                    self.story.addToList('warnings',warning.string)
+
+            if 'Completed' in label:
+                if 'Yes' in value:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+
+            if 'Published' in label:
+                value=value.replace(' - ','')
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            
+            if 'Updated' in label:
+                # there's a stray [ at the end.
+                #value = value[0:-1]
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+
+        try:
+            # Find Series name from series URL.
+            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/fanfics/'+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.BeautifulStoneSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('div', {'id' : 'story'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_simplyundeniablecom.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -66,8 +67,8 @@ class SimplyUndeniableComAdapter(BaseSiteAdapter):
         return 'www.simplyundeniable.com'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_sinfuldesireorg.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -66,8 +67,8 @@ class SinfulDesireOrgAdapter(BaseSiteAdapter):
         return 'www.sinful-desire.org'
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/archive/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/archive/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/archive/viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_siyecouk.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -71,8 +72,8 @@ class SiyeCoUkAdapter(BaseSiteAdapter): # XXX
         return ['www.siye.co.uk','siye.co.uk']
 
     @classmethod
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/siye/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/siye/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
         return re.escape("http://")+r"(www\.)?siye\.co\.uk/(siye/)?"+re.escape("viewstory.php?sid=")+r"\d+$"

fanficdownloader/adapters/adapter_spikeluvercom.py

@@ -1,8 +1,10 @@
+# Software: eFiction
 import re
 import urllib2
 import urlparse
 
 from .. import BeautifulSoup
+from ..htmlcleanup import stripHTML
 
 from base_adapter import BaseSiteAdapter, makeDate
 from .. import exceptions
@@ -88,25 +90,25 @@ class SpikeluverComAdapter(BaseSiteAdapter):
         soup = self._customized_fetch_url(url)
 
         pagetitle_div = soup.find('div', id='pagetitle')
-        self.story.setMetadata('title', pagetitle_div.a.string.strip())
+        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', author_anchor.string.strip())
+        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', sort_div('a')[1].string.strip())
+        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 = span_tag.nextSibling.string.strip()
+                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
@@ -145,27 +147,27 @@ class SpikeluverComAdapter(BaseSiteAdapter):
                     if sibling.name == 'br':
                         break
 
-                    self.story.addToList('category', sibling.string.strip())
+                    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', sibling.string.strip())
+                    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', sibling.string.strip())
+                    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', sibling.string.strip())
+                    self.story.addToList('warnings', stripHTML(sibling))
 
             # Challenges
 
@@ -173,7 +175,7 @@ class SpikeluverComAdapter(BaseSiteAdapter):
                 a = span_tag.findNextSibling('a')
                 if not a:
                     continue
-                self.story.setMetadata('series', a.string.strip())
+                self.story.setMetadata('series', stripHTML(a))
                 self.story.setMetadata('seriesUrl', urlparse.urljoin(self.BASE_URL, a['href']))
 
             elif key == 'Chapters':
@@ -196,7 +198,7 @@ class SpikeluverComAdapter(BaseSiteAdapter):
             if not chapter_anchor:
                 continue
 
-            title = chapter_anchor.string.strip()
+            title = stripHTML(chapter_anchor)
             url = urlparse.urljoin(self.BASE_URL, chapter_anchor['href'])
             self.chapterUrls.append((title, url))
 

fanficdownloader/adapters/adapter_squidgeorgpeja.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+# Software: eFiction
 import time
 import logging
 logger = logging.getLogger(__name__)
@@ -82,11 +83,12 @@ class SquidgeOrgPejaAdapter(BaseSiteAdapter):
         return cls.getSiteDomain()+'/peja'
     
     @classmethod
-    def getSiteExampleURLs(self):
-        return "https://"+self.getSiteDomain()+"/peja/cgi-bin/viewstory.php?sid=1234"
+    def getSiteExampleURLs(cls):
+        return "https://"+cls.getSiteDomain()+"/peja/cgi-bin/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
-        return r"https?"+re.escape("://"+self.getSiteDomain()+"/")+r"~?"+re.escape("peja/cgi-bin/viewstory.php?sid=")+r"\d+$"        
+        # but not https://www.squidge.org/peja/cgi-bin/viewstory.php?sid=47746 -- that's the 'Site Map' negative look aead
+        return r"https?"+re.escape("://"+self.getSiteDomain()+"/")+r"~?"+re.escape("peja/cgi-bin/viewstory.php?sid=")+r"(?!47746)\d+$"
 
     ## Getting the chapter list and the meta data, plus 'is adult' checking.
     def extractChapterUrlsAndMetadata(self):
@@ -218,7 +220,9 @@ class SquidgeOrgPejaAdapter(BaseSiteAdapter):
                     self.setSeries(series_name, i)
                     self.story.setMetadata('seriesUrl',series_url)
                     break
-                i+=1
+                # don't count the 'site map' story.  See the url pattern method.
+                if '47746' not in a['href']:
+                    i+=1
                 
         except:
             # I find it hard to care if the series parsing fails