better description selector

fix list index out of range error

calibre-plugin/__init__.py

@@ -7,15 +7,21 @@ __license__   = 'GPL v3'
 __copyright__ = '2016, Jim Miller'
 __docformat__ = 'restructuredtext en'
 
-import sys
+import sys, os
 if sys.version_info >= (2, 7):
     import logging
     logger = logging.getLogger(__name__)
     loghandler=logging.StreamHandler()
     loghandler.setFormatter(logging.Formatter("FFF: %(levelname)s: %(asctime)s: %(filename)s(%(lineno)d): %(message)s"))
     logger.addHandler(loghandler)
-    loghandler.setLevel(logging.DEBUG)
+
-    logger.setLevel(logging.DEBUG)
+    from calibre.constants import DEBUG
+    if os.environ.get('CALIBRE_WORKER', None) is not None or DEBUG:
+        loghandler.setLevel(logging.DEBUG)
+        logger.setLevel(logging.DEBUG)
+    else:
+        loghandler.setLevel(logging.CRITICAL)
+        logger.setLevel(logging.CRITICAL)
 
 # pulls in translation files for _() strings
 try:
@@ -42,7 +48,7 @@ class FanFicFareBase(InterfaceActionBase):
     description         = _('UI plugin to download FanFiction stories from various sites.')
     supported_platforms = ['windows', 'osx', 'linux']
     author              = 'Jim Miller'
-    version             = (2, 3, 1)
+    version             = (2, 5, 3)
     minimum_calibre_version = (1, 48, 0)
 
     #: This field defines the GUI plugin class that contains all the code
@@ -110,22 +116,23 @@ class FanFicFareBase(InterfaceActionBase):
             from calibre_plugins.fanficfare_plugin.fanficfare.cli import main as fff_main
             from calibre_plugins.fanficfare_plugin.prefs import PrefsFacade
             from calibre.utils.config import prefs as calibre_prefs
-            from optparse import OptionParser      
+            from optparse import OptionParser
-    
+
             parser = OptionParser('%prog --run-plugin '+self.name+' -- [options] <storyurl>')
             parser.add_option('--library-path', '--with-library', default=None, help=_('Path to the calibre library. Default is to use the path stored in the settings.'))
             # parser.add_option('--dont-notify-gui', default=False, action='store_true',
             #               help=_('Do not notify the running calibre GUI (if any) that the database has'
             #                      ' changed. Use with care, as it can lead to database corruption!'))
-    
+
             pargs = [x for x in argv if x.startswith('--with-library') or x.startswith('--library-path')
                      or not x.startswith('-')]
             opts, args = parser.parse_args(pargs)
-    
+
             fff_prefs = PrefsFacade(db(path=opts.library_path,
                                         read_only=True))
 
             fff_main(argv[1:],
-                      parser=parser,
+                     parser=parser,
-                      passed_defaultsini=StringIO(get_resources("fanficfare/defaults.ini")),
+                     passed_defaultsini=StringIO(get_resources("fanficfare/defaults.ini")),
-                      passed_personalini=StringIO(fff_prefs["personal.ini"]))
+                     passed_personalini=StringIO(fff_prefs["personal.ini"]),
+                     )

calibre-plugin/config.py

@@ -14,11 +14,13 @@ import traceback, copy, threading, re
 from collections import OrderedDict
 
 try:
+    from PyQt5 import QtWidgets as QtGui
     from PyQt5.Qt import (QDialog, QWidget, QVBoxLayout, QHBoxLayout, QGridLayout,
                           QLabel, QLineEdit, QFont, QWidget, QTextEdit, QComboBox,
                           QCheckBox, QPushButton, QTabWidget, QScrollArea,
                           QDialogButtonBox, QGroupBox, QButtonGroup, QRadioButton, Qt)
 except ImportError as e:
+    from PyQt4 import QtGui
     from PyQt4.Qt import (QDialog, QWidget, QVBoxLayout, QHBoxLayout, QGridLayout,
                           QLabel, QLineEdit, QFont, QWidget, QTextEdit, QComboBox,
                           QCheckBox, QPushButton, QTabWidget, QScrollArea,
@@ -87,7 +89,7 @@ from calibre_plugins.fanficfare_plugin.prefs \
 from calibre_plugins.fanficfare_plugin.dialogs \
     import (UPDATE, UPDATEALWAYS, collision_order, save_collisions, RejectListDialog,
             EditTextDialog, IniTextDialog, RejectUrlEntry)
-    
+
 from calibre_plugins.fanficfare_plugin.fanficfare.adapters \
     import getSiteSections
 
@@ -112,7 +114,7 @@ class RejectURLList:
             #print("rue.url:%s"%rue.url)
             if rue.valid:
                 cache[rue.url] = rue
-        return cache        
+        return cache
 
     def _get_listcache(self):
         if self.listcache == None:
@@ -124,7 +126,7 @@ class RejectURLList:
         self.prefs['rejecturls'] = '\n'.join([x.to_line() for x in listcache.values()])
         self.prefs.save_to_db()
         self.listcache = None
-        
+
     def clear_cache(self):
         self.listcache = None
 
@@ -133,7 +135,7 @@ class RejectURLList:
         with self.sync_lock:
             listcache = self._get_listcache()
             return url in listcache
-        
+
     def get_note(self,url):
         with self.sync_lock:
             listcache = self._get_listcache()
@@ -159,7 +161,7 @@ class RejectURLList:
 
     def add_text(self,rejecttext,addreasontext):
         self.add(self._read_list_from_text(rejecttext,addreasontext).values())
-            
+
     def add(self,rejectlist,clear=False):
         with self.sync_lock:
             if clear:
@@ -172,7 +174,7 @@ class RejectURLList:
 
     def get_list(self):
         return self._get_listcache().values()
-            
+
     def get_reject_reasons(self):
         return self.prefs['rejectreasons'].splitlines()
 
@@ -183,7 +185,7 @@ class ConfigWidget(QWidget):
     def __init__(self, plugin_action):
         QWidget.__init__(self)
         self.plugin_action = plugin_action
-        
+
         self.l = QVBoxLayout()
         self.setLayout(self.l)
 
@@ -192,7 +194,7 @@ class ConfigWidget(QWidget):
                            +_('List of Supported Sites')+'</a> -- <a href="'\
                            +'https://github.com/JimmXinu/FanFicFare/wiki/FAQs">'\
                            +_('FAQs')+'</a>')
-        
+
         label.setOpenExternalLinks(True)
         self.l.addWidget(label)
 
@@ -204,13 +206,13 @@ class ConfigWidget(QWidget):
 
         tab_widget = QTabWidget(self)
         self.scroll_area.setWidget(tab_widget)
-        
+
         self.basic_tab = BasicTab(self, plugin_action)
         tab_widget.addTab(self.basic_tab, _('Basic'))
 
         self.personalini_tab = PersonalIniTab(self, plugin_action)
         tab_widget.addTab(self.personalini_tab, 'personal.ini')
-        
+
         self.readinglist_tab = ReadingListTab(self, plugin_action)
         tab_widget.addTab(self.readinglist_tab, 'Reading Lists')
         if 'Reading List' not in plugin_action.gui.iactions:
@@ -258,6 +260,7 @@ class ConfigWidget(QWidget):
         prefs['adddialogstaysontop'] = self.basic_tab.adddialogstaysontop.isChecked()
         prefs['lookforurlinhtml'] = self.basic_tab.lookforurlinhtml.isChecked()
         prefs['checkforseriesurlid'] = self.basic_tab.checkforseriesurlid.isChecked()
+        prefs['auto_reject_seriesurlid'] = self.basic_tab.auto_reject_seriesurlid.isChecked()
         prefs['checkforurlchange'] = self.basic_tab.checkforurlchange.isChecked()
         prefs['injectseries'] = self.basic_tab.injectseries.isChecked()
         prefs['matchtitleauth'] = self.basic_tab.matchtitleauth.isChecked()
@@ -285,7 +288,7 @@ class ConfigWidget(QWidget):
             prefs['personal.ini'] = get_resources('plugin-example.ini')
 
         prefs['cal_cols_pass_in'] = self.personalini_tab.cal_cols_pass_in.isChecked()
-            
+
         # Covers tab
         prefs['updatecalcover'] = prefs_save_options[unicode(self.calibrecover_tab.updatecalcover.currentText())]
         # for backward compatibility:
@@ -306,7 +309,7 @@ class ConfigWidget(QWidget):
 
         # Count Pages tab
         countpagesstats = []
-        
+
         if self.countpages_tab.pagecount.isChecked():
             countpagesstats.append('PageCount')
         if self.countpages_tab.wordcount.isChecked():
@@ -317,10 +320,10 @@ class ConfigWidget(QWidget):
             countpagesstats.append('FleschGrade')
         if self.countpages_tab.gunningfog.isChecked():
             countpagesstats.append('GunningFog')
-            
+
         prefs['countpagesstats'] = countpagesstats
         prefs['wordcountmissing'] = self.countpages_tab.wordcount.isChecked() and self.countpages_tab.wordcountmissing.isChecked()
-        
+
         # Standard Columns tab
         colsnewonly = {}
         for (col,checkbox) in self.std_columns_tab.stdcol_newonlycheck.iteritems():
@@ -328,6 +331,8 @@ class ConfigWidget(QWidget):
         prefs['std_cols_newonly'] = colsnewonly
 
         prefs['set_author_url'] =self.std_columns_tab.set_author_url.isChecked()
+        prefs['includecomments'] =self.std_columns_tab.includecomments.isChecked()
+        prefs['anth_comments_newonly'] =self.std_columns_tab.anth_comments_newonly.isChecked()
 
         # Custom Columns tab
         # error column
@@ -350,7 +355,7 @@ class ConfigWidget(QWidget):
         for (col,checkbox) in self.cust_columns_tab.custcol_newonlycheck.iteritems():
             colsnewonly[col] = checkbox.isChecked()
         prefs['custom_cols_newonly'] = colsnewonly
-        
+
         prefs['allow_custcol_from_ini'] = self.cust_columns_tab.allow_custcol_from_ini.isChecked()
 
         prefs['imapserver'] = unicode(self.imap_tab.imapserver.text()).strip()
@@ -360,8 +365,9 @@ class ConfigWidget(QWidget):
         prefs['imapmarkread'] = self.imap_tab.imapmarkread.isChecked()
         prefs['imapsessionpass'] = self.imap_tab.imapsessionpass.isChecked()
         prefs['auto_reject_from_email'] = self.imap_tab.auto_reject_from_email.isChecked()
+        prefs['update_existing_only_from_email'] = self.imap_tab.update_existing_only_from_email.isChecked()
         prefs['download_from_email_immediately'] = self.imap_tab.download_from_email_immediately.isChecked()
-        
+
         prefs.save_to_db()
 
     def edit_shortcuts(self):
@@ -378,7 +384,7 @@ class BasicTab(QWidget):
         self.parent_dialog = parent_dialog
         self.plugin_action = plugin_action
         QWidget.__init__(self)
-        
+
         topl = QVBoxLayout()
         self.setLayout(topl)
 
@@ -433,7 +439,7 @@ class BasicTab(QWidget):
         self.updateepubcover.setToolTip(_("On each download, FanFicFare offers an option to update the book cover image <i>inside</i> the EPUB from the web site when the EPUB is updated.<br />This sets whether that will default to on or off."))
         self.updateepubcover.setChecked(prefs['updateepubcover'])
         horz.addWidget(self.updateepubcover)
-        
+
         self.bgmeta = QCheckBox(_('Default Background Metadata?'),self)
         self.bgmeta.setToolTip(_("On each download, FanFicFare offers an option to Collect Metadata from sites in a Background process.<br />This returns control to you quicker while updating, but you won't be asked for username/passwords or if you are an adult--stories that need those will just fail.<br />Only available for Update/Overwrite of existing books in case URL given isn't canonical or matches to existing book by Title/Author."))
         self.bgmeta.setChecked(prefs['bgmeta'])
@@ -449,7 +455,7 @@ class BasicTab(QWidget):
         self.deleteotherforms.setToolTip(_('Check this to automatically delete all other ebook formats when updating an existing book.\nHandy if you have both a Nook(epub) and Kindle(mobi), for example.'))
         self.deleteotherforms.setChecked(prefs['deleteotherforms'])
         self.l.addWidget(self.deleteotherforms)
-        
+
         self.keeptags = QCheckBox(_('Keep Existing Tags when Updating Metadata?'),self)
         self.keeptags.setToolTip(_("Existing tags will be kept and any new tags added.\n%(cmplt)s and %(inprog)s tags will be still be updated, if known.\n%(lul)s tags will be updated if %(lus)s in %(is)s.\n(If Tags is set to 'New Only' in the Standard Columns tab, this has no effect.)")%no_trans)
         self.keeptags.setChecked(prefs['keeptags'])
@@ -466,10 +472,18 @@ class BasicTab(QWidget):
         self.l.addWidget(self.suppresstitlesort)
 
         self.checkforseriesurlid = QCheckBox(_("Check for existing Series Anthology books?"),self)
-        self.checkforseriesurlid.setToolTip(_("Check for existings Series Anthology books using each new story's series URL before downloading.\nOffer to skip downloading if a Series Anthology is found.\nDoesn't work when Collect Metadata in Background is selected."))
+        self.checkforseriesurlid.setToolTip(_("Check for existing Series Anthology books using each new story's series URL before downloading.\nOffer to skip downloading if a Series Anthology is found.\nDoesn't work when Collect Metadata in Background is selected."))
         self.checkforseriesurlid.setChecked(prefs['checkforseriesurlid'])
         self.l.addWidget(self.checkforseriesurlid)
 
+        self.auto_reject_seriesurlid = QCheckBox(_("Reject Without Confirmation?"),self)
+        self.auto_reject_seriesurlid.setToolTip(_("Automatically reject storys with existing Series Anthology books.\nOnly works if 'Check for existing Series Anthology books' is on.\nDoesn't work when Collect Metadata in Background is selected."))
+        self.auto_reject_seriesurlid.setChecked(prefs['auto_reject_seriesurlid'])
+        horz = QHBoxLayout()
+        horz.addItem(QtGui.QSpacerItem(20, 1))
+        horz.addWidget(self.auto_reject_seriesurlid)
+        self.l.addLayout(horz)
+
         self.checkforurlchange = QCheckBox(_("Check for changed Story URL?"),self)
         self.checkforurlchange.setToolTip(_("Warn you if an update will change the URL of an existing book.\nfanfiction.net URLs will change from http to https silently."))
         self.checkforurlchange.setChecked(prefs['checkforurlchange'])
@@ -499,7 +513,7 @@ class BasicTab(QWidget):
         self.smarten_punctuation.setChecked(prefs['smarten_punctuation'])
         self.l.addWidget(self.smarten_punctuation)
 
-        
+
         tooltip = _("Calculate Word Counts using Calibre internal methods.\n"
                     "Many sites include Word Count, but many do not.\n"
                     "This will count the words in each book and include it as if it came from the site.")
@@ -516,7 +530,7 @@ class BasicTab(QWidget):
         horz.addWidget(self.do_wordcount)
         self.l.addLayout(horz)
 
-        
+
         self.autoconvert = QCheckBox(_("Automatically Convert new/update books?"),self)
         self.autoconvert.setToolTip(_("Automatically call calibre's Convert for new/update books.\nConverts to the current output format as chosen in calibre's\nPreferences->Behavior settings."))
         self.autoconvert.setChecked(prefs['autoconvert'])
@@ -568,12 +582,12 @@ class BasicTab(QWidget):
         self.rejectlist.setToolTip(_("Edit list of URLs FanFicFare will automatically Reject."))
         self.rejectlist.clicked.connect(self.show_rejectlist)
         self.l.addWidget(self.rejectlist)
-        
+
         self.reject_urls = QPushButton(_('Add Reject URLs'), self)
         self.reject_urls.setToolTip(_("Add additional URLs to Reject as text."))
         self.reject_urls.clicked.connect(self.add_reject_urls)
         self.l.addWidget(self.reject_urls)
-        
+
         self.reject_reasons = QPushButton(_('Edit Reject Reasons List'), self)
         self.reject_reasons.setToolTip(_("Customize the Reasons presented when Rejecting URLs"))
         self.reject_reasons.clicked.connect(self.show_reject_reasons)
@@ -596,13 +610,13 @@ class BasicTab(QWidget):
         vertright.addWidget(gui_gb)
         vertright.addWidget(misc_gb)
         vertright.addWidget(rej_gb)
-        
+
         horz.addLayout(vertleft)
         horz.addLayout(vertright)
-        
+
         topl.addLayout(horz)
         topl.insertStretch(-1)
-        
+
     def set_collisions(self):
         prev=self.collision.currentText()
         self.collision.clear()
@@ -612,7 +626,7 @@ class BasicTab(QWidget):
         i = self.collision.findText(prev)
         if i > -1:
             self.collision.setCurrentIndex(i)
-        
+
     def show_rejectlist(self):
         d = RejectListDialog(self,
                              rejecturllist.get_list(),
@@ -621,12 +635,12 @@ class BasicTab(QWidget):
                              show_delete=False,
                              show_all_reasons=False)
         d.exec_()
-        
+
         if d.result() != d.Accepted:
             return
-        
+
         rejecturllist.add(d.get_reject_list(),clear=True)
-        
+
     def show_reject_reasons(self):
         d = EditTextDialog(self,
                            prefs['rejectreasons'],
@@ -638,7 +652,7 @@ class BasicTab(QWidget):
         d.exec_()
         if d.result() == d.Accepted:
             prefs['rejectreasons'] = d.get_plain_text()
-                
+
     def add_reject_urls(self):
         d = EditTextDialog(self,
                            "http://example.com/story.php?sid=5,"+_("Reason why I rejected it")+"\nhttp://example.com/story.php?sid=6,"+_("Title by Author")+" - "+_("Reason why I rejected it"),
@@ -652,14 +666,14 @@ class BasicTab(QWidget):
         d.exec_()
         if d.result() == d.Accepted:
             rejecturllist.add_text(d.get_plain_text(),d.get_reason_text())
-                
+
 class PersonalIniTab(QWidget):
 
     def __init__(self, parent_dialog, plugin_action):
         self.parent_dialog = parent_dialog
         self.plugin_action = plugin_action
         QWidget.__init__(self)
-        
+
         self.l = QVBoxLayout()
         self.setLayout(self.l)
 
@@ -676,16 +690,16 @@ class PersonalIniTab(QWidget):
         self.l.addWidget(groupbox)
 
         horz = QHBoxLayout()
-        vert.addLayout(horz)        
+        vert.addLayout(horz)
         self.ini_button = QPushButton(_('Edit personal.ini'), self)
         #self.ini_button.setToolTip(_("Edit personal.ini file."))
         self.ini_button.clicked.connect(self.add_ini_button)
         horz.addWidget(self.ini_button)
-        
+
         label = QLabel(_("FanFicFare now includes find, color coding, and error checking for personal.ini editing.  Red generally indicates errors."))
         label.setWordWrap(True)
         horz.addWidget(label)
-        
+
         vert.addSpacing(5)
 
         horz = QHBoxLayout()
@@ -694,18 +708,18 @@ class PersonalIniTab(QWidget):
         #self.ini_button.setToolTip(_("Edit personal.ini file."))
         self.ini_button.clicked.connect(self.safe_ini_button)
         horz.addWidget(self.ini_button)
-        
+
         label = QLabel(_("View your personal.ini with usernames and passwords removed.  For safely sharing your personal.ini settings with others."))
         label.setWordWrap(True)
         horz.addWidget(label)
-        
+
         self.l.addSpacing(5)
-        
+
         groupbox = QGroupBox(_("defaults.ini"))
         horz = QHBoxLayout()
         groupbox.setLayout(horz)
         self.l.addWidget(groupbox)
-        
+
         view_label = _("View all of the plugin's configurable settings\nand their default settings.")
         self.defaults = QPushButton(_('View Defaults')+' (plugin-defaults.ini)', self)
         self.defaults.setToolTip(view_label)
@@ -715,7 +729,7 @@ class PersonalIniTab(QWidget):
         label = QLabel(view_label)
         label.setWordWrap(True)
         horz.addWidget(label)
-        
+
         self.l.addSpacing(5)
 
         groupbox = QGroupBox(_("Calibre Columns"))
@@ -730,13 +744,13 @@ class PersonalIniTab(QWidget):
         self.cal_cols_pass_in.setToolTip(pass_label)
         self.cal_cols_pass_in.setChecked(prefs['cal_cols_pass_in'])
         horz.addWidget(self.cal_cols_pass_in)
-        
+
         label = QLabel(pass_label)
         label.setWordWrap(True)
         horz.addWidget(label)
 
         vert.addSpacing(5)
-        
+
         horz = QHBoxLayout()
         vert.addLayout(horz)
         col_label = _("FanFicFare can pass the Calibre Columns into the download/update process.<br>This will show you the columns available by name.")
@@ -754,7 +768,7 @@ class PersonalIniTab(QWidget):
         self.l.addWidget(label)
 
         self.l.insertStretch(-1)
-        
+
     def show_defaults(self):
         IniTextDialog(self,
                        get_resources('plugin-defaults.ini'),
@@ -764,10 +778,10 @@ class PersonalIniTab(QWidget):
                        use_find=True,
                        read_only=True,
                        save_size_name='fff:defaults.ini').exec_()
-        
+
     def safe_ini_button(self):
         personalini = re.sub(r'((username|password) *[=:]).*$',r'\1XXXXXXXX',self.personalini,flags=re.MULTILINE)
-        
+
         d = EditTextDialog(self,
                            personalini,
                            icon=self.windowIcon(),
@@ -776,7 +790,7 @@ class PersonalIniTab(QWidget):
                            save_size_name='fff:safe personal.ini',
                            read_only=True)
         d.exec_()
-        
+
     def add_ini_button(self):
         d = IniTextDialog(self,
                            self.personalini,
@@ -788,13 +802,13 @@ class PersonalIniTab(QWidget):
         d.exec_()
         if d.result() == d.Accepted:
             self.personalini = d.get_plain_text()
-                
+
     def show_showcalcols(self):
         lines=[]#[('calibre_std_user_categories',_('User Categories'))]
         for k,f in field_metadata.iteritems():
             if f['name'] and k not in STD_COLS_SKIP: # only if it has a human readable name.
                 lines.append(('calibre_std_'+k,f['name']))
-            
+
         for k, column in self.plugin_action.gui.library_view.model().custom_columns.iteritems():
             if k != prefs['savemetacol']:
                 # custom always have name.
@@ -809,14 +823,14 @@ class PersonalIniTab(QWidget):
                        label=_('Label (entry_name)'),
                        read_only=True,
                        save_size_name='fff:showcalcols').exec_()
-        
+
 class ReadingListTab(QWidget):
 
     def __init__(self, parent_dialog, plugin_action):
         self.parent_dialog = parent_dialog
         self.plugin_action = plugin_action
         QWidget.__init__(self)
-        
+
         self.l = QVBoxLayout()
         self.setLayout(self.l)
 
@@ -825,21 +839,21 @@ class ReadingListTab(QWidget):
             reading_lists = rl_plugin.get_list_names()
         except KeyError:
             reading_lists= []
-            
+
         label = QLabel(_('These settings provide integration with the %(rl)s Plugin.  %(rl)s can automatically send to devices and change custom columns.  You have to create and configure the lists in %(rl)s to be useful.')%no_trans)
         label.setWordWrap(True)
         self.l.addWidget(label)
         self.l.addSpacing(5)
-        
+
         self.addtolists = QCheckBox(_('Add new/updated stories to "Send to Device" Reading List(s).'),self)
         self.addtolists.setToolTip(_('Automatically add new/updated stories to these lists in the %(rl)s plugin.')%no_trans)
         self.addtolists.setChecked(prefs['addtolists'])
         self.l.addWidget(self.addtolists)
-            
+
         horz = QHBoxLayout()
         label = QLabel(_('"Send to Device" Reading Lists'))
         label.setToolTip(_("When enabled, new/updated stories will be automatically added to these lists."))
-        horz.addWidget(label)        
+        horz.addWidget(label)
         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)
@@ -847,16 +861,16 @@ class ReadingListTab(QWidget):
         horz.addWidget(self.send_lists_box)
         self.send_lists_box.setCursorPosition(0)
         self.l.addLayout(horz)
-        
+
         self.addtoreadlists = QCheckBox(_('Add new/updated stories to "To Read" Reading List(s).'),self)
         self.addtoreadlists.setToolTip(_('Automatically add new/updated stories to these lists in the %(rl)s plugin.\nAlso offers menu option to remove stories from the "To Read" lists.')%no_trans)
         self.addtoreadlists.setChecked(prefs['addtoreadlists'])
         self.l.addWidget(self.addtoreadlists)
-            
+
         horz = QHBoxLayout()
         label = QLabel(_('"To Read" Reading Lists'))
         label.setToolTip(_("When enabled, new/updated stories will be automatically added to these lists."))
-        horz.addWidget(label)        
+        horz.addWidget(label)
         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)
@@ -864,31 +878,31 @@ class ReadingListTab(QWidget):
         horz.addWidget(self.read_lists_box)
         self.read_lists_box.setCursorPosition(0)
         self.l.addLayout(horz)
-        
+
         self.addtolistsonread = QCheckBox(_('Add stories back to "Send to Device" Reading List(s) when marked "Read".'),self)
         self.addtolistsonread.setToolTip(_('Menu option to remove from "To Read" lists will also add stories back to "Send to Device" Reading List(s)'))
         self.addtolistsonread.setChecked(prefs['addtolistsonread'])
         self.l.addWidget(self.addtolistsonread)
-            
+
         self.autounnew = QCheckBox(_('Automatically run Remove "New" Chapter Marks when marking books "Read".'),self)
         self.autounnew.setToolTip(_('Menu option to remove from "To Read" lists will also remove "(new)" chapter marks created by personal.ini <i>mark_new_chapters</i> setting.'))
         self.autounnew.setChecked(prefs['autounnew'])
         self.l.addWidget(self.autounnew)
-            
+
         self.l.insertStretch(-1)
-        
+
 class CalibreCoverTab(QWidget):
 
     def __init__(self, parent_dialog, plugin_action):
         self.parent_dialog = parent_dialog
         self.plugin_action = plugin_action
         QWidget.__init__(self)
-        
+
         self.gencov_elements=[] ## used to disable/enable when gen
                                 ## cover is off/on.  This is more
                                 ## about being a visual que than real
                                 ## necessary function.
-        
+
         topl = self.l = QVBoxLayout()
         self.setLayout(self.l)
 
@@ -898,7 +912,7 @@ class CalibreCoverTab(QWidget):
         except KeyError:
             gc_settings= []
 
-            
+
         label = QLabel(_("The Calibre cover image for a downloaded book can come"
                          " from the story site(if EPUB and images are enabled), or"
                          " from either Calibre's built-in random cover generator or"
@@ -906,7 +920,7 @@ class CalibreCoverTab(QWidget):
         label.setWordWrap(True)
         self.l.addWidget(label)
         self.l.addSpacing(5)
-        
+
         tooltip = _("Update Calibre book cover image from EPUB when Calibre metadata is updated.\n"
                     "Doesn't go looking for new images on 'Update Calibre Metadata Only'.\n"
                     "Cover in EPUB could be from site or previously injected into the EPUB.\n"
@@ -947,7 +961,7 @@ class CalibreCoverTab(QWidget):
         #     self.gencalcover.setCurrentIndex(self.gencalcover.findText(prefs_save_options[SAVE_YES]))
         # else: # doesn't have own value, old value not set, NO.
         #     self.gencalcover.setCurrentIndex(self.gencalcover.findText(prefs_save_options[SAVE_NO]))
-            
+
         self.gencalcover.setToolTip(tooltip)
         label.setBuddy(self.gencalcover)
         horz.addWidget(self.gencalcover)
@@ -960,7 +974,7 @@ class CalibreCoverTab(QWidget):
         self.gencov_gb = QGroupBox()
         horz = QHBoxLayout()
         self.gencov_gb.setLayout(horz)
-        
+
         self.plugin_gen_cover = QRadioButton(_('Plugin %(gc)s')%no_trans,self)
         self.plugin_gen_cover.setToolTip(_("Use plugin to create covers.  Additional settings are below."))
         self.gencov_rdgrp.addButton(self.plugin_gen_cover)
@@ -1005,7 +1019,7 @@ class CalibreCoverTab(QWidget):
         self.gencov_elements.append(self.gcp_gb)
 
         self.gencov_rdgrp.buttonClicked.connect(self.endisable_elements)
-            
+
         label = QLabel(_('The %(gc)s plugin can create cover images for books using various metadata (including existing cover image).  If you have %(gc)s installed, FanFicFare can run %(gc)s on new downloads and metadata updates.  Pick a %(gc)s setting by site and/or one to use by Default.')%no_trans)
         label.setWordWrap(True)
         self.l.addWidget(label)
@@ -1019,7 +1033,7 @@ class CalibreCoverTab(QWidget):
 
         self.sl = QVBoxLayout()
         scrollcontent.setLayout(self.sl)
-        
+
         self.gc_dropdowns = {}
 
         sitelist = getSiteSections()
@@ -1052,9 +1066,9 @@ class CalibreCoverTab(QWidget):
 
             horz.addWidget(dropdown)
             self.sl.addLayout(horz)
-        
+
         self.sl.insertStretch(-1)
-        
+
         self.allow_gc_from_ini = QCheckBox(_('Allow %(gcset)s from %(pini)s to override')%no_trans,self)
         self.allow_gc_from_ini.setToolTip(_("The %(pini)s parameter %(gcset)s allows you to choose a %(gc)s setting based on metadata"
                                             " rather than site, but it's much more complex.<br \>%(gcset)s is ignored when this is off.")%no_trans)
@@ -1068,7 +1082,7 @@ class CalibreCoverTab(QWidget):
         "Clearing house function for setting elements of Calibre"
         "Cover tab enabled/disabled depending on all factors."
 
-        ## First, cover gen on/off 
+        ## First, cover gen on/off
         for e in self.gencov_elements:
             e.setEnabled(prefs_save_options[unicode(self.gencalcover.currentText())] != SAVE_NO)
 
@@ -1082,15 +1096,15 @@ class CalibreCoverTab(QWidget):
         if not 'Generate Cover' in self.plugin_action.gui.iactions:
             self.plugin_gen_cover.setEnabled(False)
             self.gcp_gb.setEnabled(False)
-        
+
-            
+
 class CountPagesTab(QWidget):
 
     def __init__(self, parent_dialog, plugin_action):
         self.parent_dialog = parent_dialog
         self.plugin_action = plugin_action
         QWidget.__init__(self)
-        
+
         self.l = QVBoxLayout()
         self.setLayout(self.l)
 
@@ -1113,7 +1127,7 @@ class CountPagesTab(QWidget):
         self.l.addWidget(self.pagecount)
 
         horz = QHBoxLayout()
-        
+
         self.wordcount = QCheckBox('Word Count',self)
         self.wordcount.setToolTip(tooltip+"\n"+_('Will overwrite word count from FanFicFare metadata if set to update the same custom column.'))
         self.wordcount.setChecked('WordCount' in prefs['countpagesstats'])
@@ -1126,33 +1140,33 @@ class CountPagesTab(QWidget):
         horz.addWidget(self.wordcountmissing)
 
         self.wordcount.stateChanged.connect(lambda x : self.wordcountmissing.setEnabled(self.wordcount.isChecked()))
-        
+
         self.l.addLayout(horz)
 
         self.fleschreading = QCheckBox('Flesch Reading Ease',self)
         self.fleschreading.setToolTip(tooltip)
         self.fleschreading.setChecked('FleschReading' in prefs['countpagesstats'])
         self.l.addWidget(self.fleschreading)
-        
+
         self.fleschgrade = QCheckBox('Flesch-Kincaid Grade Level',self)
         self.fleschgrade.setToolTip(tooltip)
         self.fleschgrade.setChecked('FleschGrade' in prefs['countpagesstats'])
         self.l.addWidget(self.fleschgrade)
-        
+
         self.gunningfog = QCheckBox('Gunning Fog Index',self)
         self.gunningfog.setToolTip(tooltip)
         self.gunningfog.setChecked('GunningFog' in prefs['countpagesstats'])
         self.l.addWidget(self.gunningfog)
-        
+
         self.l.insertStretch(-1)
-        
+
 class OtherTab(QWidget):
 
     def __init__(self, parent_dialog, plugin_action):
         self.parent_dialog = parent_dialog
         self.plugin_action = plugin_action
         QWidget.__init__(self)
-        
+
         self.l = QVBoxLayout()
         self.setLayout(self.l)
 
@@ -1160,7 +1174,7 @@ class OtherTab(QWidget):
         label.setWordWrap(True)
         self.l.addWidget(label)
         self.l.addSpacing(5)
-        
+
         keyboard_shortcuts_button = QPushButton(_('Keyboard shortcuts...'), self)
         keyboard_shortcuts_button.setToolTip(_('Edit the keyboard shortcuts associated with this plugin'))
         keyboard_shortcuts_button.clicked.connect(parent_dialog.edit_shortcuts)
@@ -1170,14 +1184,14 @@ class OtherTab(QWidget):
         reset_confirmation_button.setToolTip(_('Reset all show me again dialogs for the FanFicFare plugin'))
         reset_confirmation_button.clicked.connect(self.reset_dialogs)
         self.l.addWidget(reset_confirmation_button)
-        
+
         view_prefs_button = QPushButton(_('&View library preferences...'), self)
         view_prefs_button.setToolTip(_('View data stored in the library database for this plugin'))
         view_prefs_button.clicked.connect(self.view_prefs)
         self.l.addWidget(view_prefs_button)
-        
+
         self.l.insertStretch(-1)
-        
+
     def reset_dialogs(self):
         for key in dynamic.keys():
             if key.startswith('fanfictiondownloader_') and key.endswith('_again') \
@@ -1187,7 +1201,7 @@ class OtherTab(QWidget):
                     _('Confirmation dialogs have all been reset'),
                     show=True,
                     show_copy_button=False)
-        
+
     def view_prefs(self):
         d = PrefsViewerDialog(self.plugin_action.gui, PREFS_NAMESPACE)
         d.exec_()
@@ -1269,7 +1283,7 @@ class CustomColumnsTab(QWidget):
         self.parent_dialog = parent_dialog
         self.plugin_action = plugin_action
         QWidget.__init__(self)
-        
+
         custom_columns = self.plugin_action.gui.library_view.model().custom_columns
 
         self.l = QVBoxLayout()
@@ -1279,7 +1293,7 @@ class CustomColumnsTab(QWidget):
         label.setWordWrap(True)
         self.l.addWidget(label)
         self.l.addSpacing(5)
-        
+
         self.custcol_dropdowns = {}
         self.custcol_newonlycheck = {}
 
@@ -1291,7 +1305,7 @@ class CustomColumnsTab(QWidget):
 
         self.sl = QVBoxLayout()
         scrollcontent.setLayout(self.sl)
-        
+
         for key, column in custom_columns.iteritems():
 
             if column['datatype'] in permitted_values:
@@ -1321,9 +1335,9 @@ class CustomColumnsTab(QWidget):
                 if key in prefs['custom_cols_newonly']:
                     newonlycheck.setChecked(prefs['custom_cols_newonly'][key])
                 horz.addWidget(newonlycheck)
-                
+
                 self.sl.addLayout(horz)
-        
+
         self.sl.insertStretch(-1)
 
         self.l.addSpacing(5)
@@ -1331,11 +1345,11 @@ class CustomColumnsTab(QWidget):
         self.allow_custcol_from_ini.setToolTip(_("The %(pini)s parameter %(ccset)s allows you to set custom columns to site specific values that aren't common to all sites.<br />%(ccset)s is ignored when this is off.")%no_trans)
         self.allow_custcol_from_ini.setChecked(prefs['allow_custcol_from_ini'])
         self.l.addWidget(self.allow_custcol_from_ini)
-        
+
         label = QLabel(_("Special column:"))
         label.setWordWrap(True)
         self.l.addWidget(label)
-        
+
         horz = QHBoxLayout()
         label = QLabel(_("Update/Overwrite Error Column:"))
         tooltip=_("When an update or overwrite of an existing story fails, record the reason in this column.\n(Text and Long Text columns only.)")
@@ -1350,7 +1364,7 @@ class CustomColumnsTab(QWidget):
                 self.errorcol.addItem(column['name'],key)
         self.errorcol.setCurrentIndex(self.errorcol.findData(prefs['errorcol']))
         horz.addWidget(self.errorcol)
-        
+
         self.save_all_errors = QCheckBox(_('Save All Errors'),self)
         self.save_all_errors.setToolTip(_('If unchecked, these errors will not be saved:%s')%(
                 '\n'+
@@ -1358,9 +1372,9 @@ class CustomColumnsTab(QWidget):
                            _("Already contains %d chapters.").replace('%d','X')))))
         self.save_all_errors.setChecked(prefs['save_all_errors'])
         horz.addWidget(self.save_all_errors)
-        
+
         self.l.addLayout(horz)
-        
+
         horz = QHBoxLayout()
         label = QLabel(_("Saved Metadata Column:"))
         tooltip=_("If set, FanFicFare will save a copy of all its metadata in this column when the book is downloaded or updated.<br/>The metadata from this column can later be used to update custom columns without having to request the metadata from the server again.<br/>(Long Text columns only.)")
@@ -1377,7 +1391,7 @@ class CustomColumnsTab(QWidget):
 
         label = QLabel('')
         horz.addWidget(label) # empty spacer for alignment with error column line.
-        
+
         self.l.addLayout(horz)
 
         #print("prefs['custom_cols'] %s"%prefs['custom_cols'])
@@ -1391,7 +1405,7 @@ class StandardColumnsTab(QWidget):
         QWidget.__init__(self)
 
         columns=OrderedDict()
-        
+
         columns["title"]=_("Title")
         columns["authors"]=_("Author(s)")
         columns["publisher"]=_("Publisher")
@@ -1410,7 +1424,7 @@ class StandardColumnsTab(QWidget):
         label.setWordWrap(True)
         self.l.addWidget(label)
         self.l.addSpacing(5)
-        
+
         self.stdcol_newonlycheck = {}
 
         for key, column in columns.iteritems():
@@ -1425,9 +1439,9 @@ class StandardColumnsTab(QWidget):
             if key in prefs['std_cols_newonly']:
                 newonlycheck.setChecked(prefs['std_cols_newonly'][key])
             horz.addWidget(newonlycheck)
-            
+
             self.l.addLayout(horz)
-            
+
         self.l.addSpacing(5)
         label = QLabel(_("Other Standard Column Options"))
         label.setWordWrap(True)
@@ -1438,7 +1452,18 @@ class StandardColumnsTab(QWidget):
         self.set_author_url.setToolTip(_("Set Calibre Author URL to Author's URL on story site."))
         self.set_author_url.setChecked(prefs['set_author_url'])
         self.l.addWidget(self.set_author_url)
-        
+
+        self.includecomments = QCheckBox(_("Include Books' Comments in Anthology Comments?"),self)
+        self.includecomments.setToolTip(_('''Include all the merged books' comments in the new book's comments.
+Default is a list of included titles only.'''))
+        self.includecomments.setChecked(prefs['includecomments'])
+        self.l.addWidget(self.includecomments)
+
+        self.anth_comments_newonly = QCheckBox(_("Set Anthology Comments only for new books"),self)
+        self.anth_comments_newonly.setToolTip(_("Comments will only be set for New Anthologies, not updates.\nThat way comments you set manually are retained."))
+        self.anth_comments_newonly.setChecked(prefs['anth_comments_newonly'])
+        self.l.addWidget(self.anth_comments_newonly)
+
         self.l.insertStretch(-1)
 
 class ImapTab(QWidget):
@@ -1447,11 +1472,11 @@ class ImapTab(QWidget):
         self.parent_dialog = parent_dialog
         self.plugin_action = plugin_action
         QWidget.__init__(self)
-        
+
         self.l = QGridLayout()
         self.setLayout(self.l)
         row=0
-            
+
         label = QLabel(_('These settings will allow FanFicFare to fetch story URLs from your email account.  It will only look for story URLs in unread emails in the folder specified below.'))
         label.setWordWrap(True)
         self.l.addWidget(label,row,0,1,-1)
@@ -1466,21 +1491,21 @@ class ImapTab(QWidget):
         self.imapserver.setText(prefs['imapserver'])
         self.l.addWidget(self.imapserver,row,1)
         row+=1
-        
+
         label = QLabel(_('IMAP User Name'))
         tooltip = _("Name of IMAP user.  Eg: yourname@gmail.com\nNote that Gmail accounts need to have IMAP enabled in Gmail Settings first.")
         label.setToolTip(tooltip)
-        self.l.addWidget(label,row,0)        
+        self.l.addWidget(label,row,0)
         self.imapuser = QLineEdit(self)
         self.imapuser.setToolTip(tooltip)
         self.imapuser.setText(prefs['imapuser'])
         self.l.addWidget(self.imapuser,row,1)
         row+=1
-        
+
         label = QLabel(_('IMAP User Password'))
         tooltip = _("IMAP password.  If left empty, FanFicFare will ask you for your password when you use the feature.")
         label.setToolTip(tooltip)
-        self.l.addWidget(label,row,0)        
+        self.l.addWidget(label,row,0)
         self.imappass = QLineEdit(self)
         self.imappass.setToolTip(tooltip)
         self.imappass.setEchoMode(QLineEdit.Password)
@@ -1493,35 +1518,41 @@ class ImapTab(QWidget):
         self.imapsessionpass.setChecked(prefs['imapsessionpass'])
         self.l.addWidget(self.imapsessionpass,row,0,1,-1)
         row+=1
-        
+
         label = QLabel(_('IMAP Folder Name'))
         tooltip = _("Name of IMAP folder to search for new emails.  The folder (or label) has to already exist.  Use INBOX for your default inbox.")
         label.setToolTip(tooltip)
-        self.l.addWidget(label,row,0)        
+        self.l.addWidget(label,row,0)
         self.imapfolder = QLineEdit(self)
         self.imapfolder.setToolTip(tooltip)
         self.imapfolder.setText(prefs['imapfolder'])
         self.l.addWidget(self.imapfolder,row,1)
         row+=1
-        
+
         self.imapmarkread = QCheckBox(_('Mark Emails Read'),self)
         self.imapmarkread.setToolTip(_('If checked, emails will be marked as having been read if they contain any story URLs.'))
         self.imapmarkread.setChecked(prefs['imapmarkread'])
         self.l.addWidget(self.imapmarkread,row,0,1,-1)
         row+=1
-            
+
         self.auto_reject_from_email = QCheckBox(_('Discard URLs on Reject List'),self)
         self.auto_reject_from_email.setToolTip(_('If checked, FanFicFare will silently discard story URLs from emails that are on your Reject URL List.<br>Otherwise they will appear and you will see the normal Reject URL dialog.<br>The Emails will still be marked Read if configured to.'))
         self.auto_reject_from_email.setChecked(prefs['auto_reject_from_email'])
         self.l.addWidget(self.auto_reject_from_email,row,0,1,-1)
         row+=1
-        
+
+        self.update_existing_only_from_email = QCheckBox(_('Update Existing Books Only'),self)
+        self.update_existing_only_from_email.setToolTip(_('If checked, FanFicFare will silently discard story URLs from emails that are not already in your library.<br>Otherwise all story URLs, new and existing, will be used.<br>The Emails will still be marked Read if configured to.'))
+        self.update_existing_only_from_email.setChecked(prefs['update_existing_only_from_email'])
+        self.l.addWidget(self.update_existing_only_from_email,row,0,1,-1)
+        row+=1
+
         self.download_from_email_immediately = QCheckBox(_('Download from Email Immediately'),self)
         self.download_from_email_immediately.setToolTip(_('If checked, FanFicFare will start downloading story URLs from emails immediately.<br>Otherwise the usual Download from URLs dialog will appear.'))
         self.download_from_email_immediately.setChecked(prefs['download_from_email_immediately'])
         self.l.addWidget(self.download_from_email_immediately,row,0,1,-1)
         row+=1
-        
+
         label = QLabel(_("<b>It's safest if you create a separate email account that you use only "
                          "for your story update notices.  FanFicFare and calibre cannot guarantee that "
                          "malicious code cannot get your email password once you've entered it. "
@@ -1530,5 +1561,5 @@ class ImapTab(QWidget):
         self.l.addWidget(label,row,0,1,-1,Qt.AlignTop)
         self.l.setRowStretch(row,1)
         row+=1
-        
+
-        
+

calibre-plugin/dialogs.py

@@ -21,19 +21,19 @@ from datetime import datetime
 try:
     from PyQt5 import QtWidgets as QtGui
     from PyQt5 import QtCore
-    from PyQt5.Qt import (QDialog, QTableWidget, QVBoxLayout, QHBoxLayout, QGridLayout,
+    from PyQt5.Qt import (QDialog, QWidget, QTableWidget, QVBoxLayout, QHBoxLayout,
-                          QPushButton, QFont, QLabel, QCheckBox, QIcon, QLineEdit,
+                          QGridLayout, QPushButton, QFont, QLabel, QCheckBox, QIcon,
-                          QComboBox, QProgressDialog, QTimer, QDialogButtonBox,
+                          QLineEdit, QComboBox, QProgressDialog, QTimer, QDialogButtonBox,
-                          QPixmap, Qt, QAbstractItemView, QTextEdit, pyqtSignal,
+                          QScrollArea, QPixmap, Qt, QAbstractItemView, QTextEdit,
-                          QGroupBox, QFrame, QTextBrowser, QSize, QAction)
+                          pyqtSignal, QGroupBox, QFrame, QTextBrowser, QSize, QAction)
 except ImportError as e:
     from PyQt4 import QtGui
     from PyQt4 import QtCore
-    from PyQt4.Qt import (QDialog, QTableWidget, QVBoxLayout, QHBoxLayout, QGridLayout,
+    from PyQt4.Qt import (QDialog, QWidget, QTableWidget, QVBoxLayout, QHBoxLayout,
-                          QPushButton, QFont, QLabel, QCheckBox, QIcon, QLineEdit,
+                          QGridLayout, QPushButton, QFont, QLabel, QCheckBox, QIcon,
-                          QComboBox, QProgressDialog, QTimer, QDialogButtonBox,
+                          QLineEdit, QComboBox, QProgressDialog, QTimer, QDialogButtonBox,
-                          QPixmap, Qt, QAbstractItemView, QTextEdit, pyqtSignal,
+                          QScrollArea, QPixmap, Qt, QAbstractItemView, QTextEdit,
-                          QGroupBox, QFrame, QTextBrowser, QSize, QAction)
+                          pyqtSignal, QGroupBox, QFrame, QTextBrowser, QSize, QAction)
 
 try:
     from calibre.gui2 import QVariant
@@ -581,14 +581,34 @@ class UserPassDialog(QDialog):
         self.status=False
         self.hide()
 
-class LoopProgressDialog(QProgressDialog):
+def LoopProgressDialog(gui,
+                       book_list,
+                       foreach_function,
+                       finish_function,
+                       init_label=_("Fetching metadata for stories..."),
+                       win_title=_("Downloading metadata for stories"),
+                       status_prefix=_("Fetched metadata for")):
+    ld = _LoopProgressDialog(gui,
+                             book_list,
+                             foreach_function,
+                             init_label,
+                             win_title,
+                             status_prefix)
+    
+    # Mac OS X gets upset if the finish_function is called from inside
+    # the real _LoopProgressDialog class.
+    
+    # reflect old behavior.
+    if not ld.wasCanceled():
+        finish_function(book_list)
+        
+class _LoopProgressDialog(QProgressDialog):
     '''
     ProgressDialog displayed while fetching metadata for each story.
     '''
     def __init__(self, gui,
                  book_list,
                  foreach_function,
-                 finish_function,
                  init_label=_("Fetching metadata for stories..."),
                  win_title=_("Downloading metadata for stories"),
                  status_prefix=_("Fetched metadata for")):
@@ -599,10 +619,10 @@ class LoopProgressDialog(QProgressDialog):
         self.setMinimumWidth(500)
         self.book_list = book_list
         self.foreach_function = foreach_function
-        self.finish_function = finish_function
         self.status_prefix = status_prefix
         self.i = 0
         self.start_time = datetime.now()
+        self.first = True
 
         # can't import at file load.
         from calibre_plugins.fanficfare_plugin.prefs import prefs
@@ -629,8 +649,14 @@ class LoopProgressDialog(QProgressDialog):
 
     def do_loop(self):
 
-        if self.i == 0:
+        if self.first:
-            self.setValue(0)
+            ## Windows 10 doesn't want to show the prog dialog content
+            ## until after the timer's been called again.  Something to
+            ## do with cooperative multi threading maybe?
+            ## So this just trips the timer loop an extra time at the start.
+            self.first = False
+            QTimer.singleShot(0, self.do_loop)
+            return
 
         book = self.book_list[self.i]
         try:
@@ -639,6 +665,7 @@ class LoopProgressDialog(QProgressDialog):
             self.foreach_function(book)
 
         except NotGoingToDownload as d:
+            book['status']=_('Skipped')
             book['good']=False
             book['showerror']=d.showerror
             book['comment']=unicode(d)
@@ -647,8 +674,7 @@ class LoopProgressDialog(QProgressDialog):
         except Exception as e:
             book['good']=False
             book['comment']=unicode(e)
-            logger.error("Exception: %s:%s"%(book,unicode(e)))
+            logger.error("Exception: %s:%s"%(book,unicode(e)),exc_info=True)
-            traceback.print_exc()
 
         self.updateStatus()
         self.i += 1
@@ -660,8 +686,6 @@ class LoopProgressDialog(QProgressDialog):
 
     def do_when_finished(self):
         self.hide()
-        # Queues a job to process these books in the background.
-        self.finish_function(self.book_list)
 
 def time_duration_format(seconds):
     """
@@ -1433,6 +1457,15 @@ class ViewLog(SizePersistedDialog):
 
         self.lineno = None
 
+        scrollable = QScrollArea()
+        scrollcontent = QWidget()
+        scrollable.setWidget(scrollcontent)
+        scrollable.setWidgetResizable(True)
+        self.l.addWidget(scrollable)
+
+        self.sl = QVBoxLayout()
+        scrollcontent.setLayout(self.sl)
+
         ## error = (lineno, msg)
         for (lineno, error_msg) in errors:
             # print('adding label for error:%s: %s'%(lineno, error_msg))
@@ -1443,7 +1476,7 @@ class ViewLog(SizePersistedDialog):
             label.setStyleSheet("QLabel { margin-left: 2em; color : blue; } QLabel:hover { color: red; }");
             label.setToolTip(_('Click to go to line %s')%lineno)
             label.mouseReleaseEvent = partial(self.label_clicked, lineno=lineno)
-            self.l.addWidget(label)
+            self.sl.addWidget(label)
 
         # html='<p>'+'</p><p>'.join([ '(lineno: %s) %s'%e for e in errors ])+'</p>'
 
@@ -1453,7 +1486,7 @@ class ViewLog(SizePersistedDialog):
         # self.tb.setHtml(html)
         # l.addWidget(self.tb)
 
-        self.l.insertStretch(-1)
+        self.sl.insertStretch(-1)
 
         horz = QHBoxLayout()
 

calibre-plugin/fff_plugin.py

@@ -73,7 +73,7 @@ except:
 
 from calibre.library.field_metadata import FieldMetadata
 field_metadata = FieldMetadata()
-    
+
 from calibre_plugins.fanficfare_plugin.common_utils import (
     set_plugin_icon_resources, get_icon, create_menu_action_unique,
     get_library_uuid)
@@ -83,7 +83,7 @@ from calibre_plugins.fanficfare_plugin.fanficfare import (
 
 from calibre_plugins.fanficfare_plugin.fanficfare.epubutils import (
     get_dcsource, get_dcsource_chaptercount, get_story_url_from_html,
-    reset_orig_chapters_epub)
+    reset_orig_chapters_epub, get_cover_data)
 
 from calibre_plugins.fanficfare_plugin.fanficfare.geturls import (
     get_urls_from_page, get_urls_from_html,get_urls_from_text,
@@ -116,6 +116,13 @@ formmapping = {
     'txt':'TXT'
     }
 
+imagetypes = {
+    'image/jpeg':'jpg',
+    'image/png':'png',
+    'image/gif':'gif',
+    'image/svg+xml':'svg',
+    }
+
 PLUGIN_ICONS = ['images/icon.png']
 
 class FanFicFarePlugin(InterfaceAction):
@@ -477,9 +484,16 @@ class FanFicFarePlugin(InterfaceAction):
         reject_list=set()
         if prefs['auto_reject_from_email']:
             # need to normalize for reject list.
-            reject_list = set([x for x in url_list if rejecturllist.check(adapters.getNormalStoryURLSite(x)[0])])
+            reject_list = set([x for x in url_list if rejecturllist.check(adapters.getNormalStoryURL(x))])
         url_list = url_list - reject_list
 
+        ## feature for update-only - check url_list with
+        ## self.do_id_search(url)
+        notupdate_list = set()
+        if prefs['update_existing_only_from_email']:
+            notupdate_list = set([x for x in url_list if not self.do_id_search(adapters.getNormalStoryURL(x))])
+        url_list = url_list - notupdate_list
+
         self.gui.status_bar.show_message(_('No Valid Story URLs Found in Unread Emails.'),3000)
         self.restore_cursor()
 
@@ -497,19 +511,21 @@ class FanFicFarePlugin(InterfaceAction):
                         },"\n".join(url_list))
             else:
                 self.gui.status_bar.show_message(_('Finished Fetching Story URLs from Email.'),3000)
-                
+
         else:
             if url_list:
                 self.add_dialog("\n".join(url_list),merge=False)
-            else:            
+            else:
                 msg = _('No Valid Story URLs Found in Unread Emails.')
                 if reject_list:
                     msg = msg + '<p>'+(_('(%d Story URLs Skipped, on Rejected URL List)')%len(reject_list))+'</p>'
+                if notupdate_list:
+                    msg = msg + '<p>'+(_("(%d Story URLs Skipped, no Existing Book in Library)")%len(notupdate_list))+'</p>'
                 info_dialog(self.gui, _('Get Story URLs from Email'),
                             msg,
                             show=True,
                             show_copy_button=False)
-    
+
     def get_urls_from_page_menu(self,anthology=False):
 
         urltxt = ""
@@ -534,7 +550,7 @@ class FanFicFarePlugin(InterfaceAction):
 
         self.gui.status_bar.show_message(_('Finished Fetching Story URLs from Page.'),3000)
         self.restore_cursor()
-        
+
         if url_list:
             self.add_dialog("\n".join(url_list),merge=d.anthology,anthology_url=url)
         else:
@@ -606,7 +622,7 @@ class FanFicFarePlugin(InterfaceAction):
             self.gui.status_bar.show_message(_('Can only UnNew books in library'),
                                              3000)
             return
-        
+
         if not self.gui.current_view().selectionModel().selectedRows() :
             self.gui.status_bar.show_message(_('No Selected Books to Get URLs From'),
                                              3000)
@@ -632,7 +648,7 @@ class FanFicFarePlugin(InterfaceAction):
                                           suffix='.epub',
                                           dir=tdir)
             db.copy_format_to(book['calibre_id'],'EPUB',tmp,index_is_id=True)
-            
+
             unnewtmp = PersistentTemporaryFile(prefix='unnew-%s-'%book['calibre_id'],
                                                suffix='.epub',
                                                dir=tdir)
@@ -656,7 +672,7 @@ class FanFicFarePlugin(InterfaceAction):
                     if fmt.lower() != 'epub' and db.has_format(book['calibre_id'],fmt,index_is_id=True):
                         logger.debug("autoconvert remove f:"+fmt)
                         db.remove_format(book['calibre_id'], fmt, index_is_id=True)#, notify=False
-                
+
     def get_unnew_books_finish(self, book_list, tdir=None):
         remove_dir(tdir)
         if prefs['autoconvert']:
@@ -787,7 +803,7 @@ class FanFicFarePlugin(InterfaceAction):
 
         self.busy_cursor()
         self.gui.status_bar.show_message(_('Fetching Story URLs for Series...'))
-        
+
         # get list from identifiers:url/uri if present, but only if
         # it's *not* a valid story URL.
         mergeurl = self.get_story_url(db,book_id)
@@ -798,7 +814,7 @@ class FanFicFarePlugin(InterfaceAction):
 
         self.gui.status_bar.show_message(_('Finished Fetching Story URLs for Series.'),3000)
         self.restore_cursor()
-        
+
         #print("urlmapfile:%s"%urlmapfile)
 
         # AddNewDialog collects URLs, format and presents buttons.
@@ -958,7 +974,7 @@ class FanFicFarePlugin(InterfaceAction):
                 init_label=_("Fetching metadata for stories...")
                 win_title=_("Downloading metadata for stories")
                 status_prefix=_("Fetched metadata for")
-                
+
             self.gui.status_bar.show_message(status_bar, 3000)
             LoopProgressDialog(self.gui,
                                books,
@@ -1072,7 +1088,7 @@ class FanFicFarePlugin(InterfaceAction):
             ## Getting metadata from configured column.
             custom_columns = self.gui.library_view.model().custom_columns
             if ( collision in (CALIBREONLYSAVECOL) and
-                 prefs['savemetacol'] != '' and 
+                 prefs['savemetacol'] != '' and
                  prefs['savemetacol'] in custom_columns ):
 
                 savedmeta_book_id = book['calibre_id']
@@ -1081,13 +1097,13 @@ class FanFicFarePlugin(InterfaceAction):
                     identicalbooks = self.do_id_search(url)
                     if len(identicalbooks) == 1:
                         savedmeta_book_id = identicalbooks.pop()
-                        
+
                 if savedmeta_book_id:
                     label = custom_columns[prefs['savemetacol']]['label']
                     savedmetadata = db.get_custom(savedmeta_book_id, label=label, index_is_id=True)
                 else:
                     savedmetadata = None
-                    
+
                 if savedmetadata:
                     # sets flag inside story so getStoryMetadataOnly won't hit server.
                     adapter.setStoryMetadata(savedmetadata)
@@ -1123,19 +1139,19 @@ class FanFicFarePlugin(InterfaceAction):
                         if userpass.status:
                             adapter.username = userpass.user.text()
                             adapter.password = userpass.passwd.text()
-        
+
                     except exceptions.AdultCheckRequired:
                         if question_dialog(self.gui, _('Are You an Adult?'), '<p>'+
                                            _("%s requires that you be an adult.  Please confirm you are an adult in your locale:")%url,
                                            show_copy_button=False):
                             adapter.is_adult=True
-        
+
                 # let other exceptions percolate up.
                 story = adapter.getStoryMetadataOnly(get_cover=False)
                 book['title'] = story.getMetadata('title')
                 book['author'] = [story.getMetadata('author')]
                 book['url'] = story.getMetadata('storyUrl')
-        
+
             ## Check reject list.  Redundant with below for when story
             ## URL changes, but also kept here to avoid network hit in
             ## most common case where given url is story url.
@@ -1148,7 +1164,8 @@ class FanFicFarePlugin(InterfaceAction):
                     # try to find *series anthology* by *seriesUrl* identifier url or uri first.
                     identicalbooks = self.do_id_search(story.getMetadata('seriesUrl'))
                     # print("identicalbooks:%s"%identicalbooks)
-                    if len(identicalbooks) > 0 and question_dialog(self.gui, _('Skip Story?'),'''
+                    if len(identicalbooks) > 0 and (prefs['auto_reject_seriesurlid'] or \
+                                                        question_dialog(self.gui, _('Skip Story?'),'''
                                                                       <h3>%s</h3>
                                                                       <p>%s</p>
                                                                       <p>%s</p>
@@ -1158,7 +1175,7 @@ class FanFicFarePlugin(InterfaceAction):
                                                                    _('"<b>%s</b>" is in series "<b><a href="%s">%s</a></b>" that you have an anthology book for.')%(story.getMetadata('title'),story.getMetadata('seriesUrl'),series[:series.index(' [')]),
                                                                    _("Click '<b>Yes</b>' to Skip."),
                                                                    _("Click '<b>No</b>' to download anyway.")),
-                                                                   show_copy_button=False):
+                                                                   show_copy_button=False)):
                         book['comment'] = _("Story in Series Anthology(%s).")%series
                         book['title'] = story.getMetadata('title')
                         book['author'] = [story.getMetadata('author')]
@@ -1167,7 +1184,7 @@ class FanFicFarePlugin(InterfaceAction):
                         book['icon']='rotate-right.png'
                         book['status'] = _('Skipped')
                         return
-    
+
         ################################################################################################################################################33
 
         book['is_adult'] = adapter.is_adult
@@ -1176,7 +1193,7 @@ class FanFicFarePlugin(InterfaceAction):
 
         book['icon'] = 'plus.png'
         book['status'] = _('Add')
-        
+
         if not bgmeta:
             # set PI version instead of default.
             if 'version' in options:
@@ -1187,7 +1204,7 @@ class FanFicFarePlugin(InterfaceAction):
             if prefs['savemetacol'] != '':
                 # get metadata to save in configured column.
                 book['savemetacol'] = story.dump_html_metadata()
-            
+
             book['title'] = story.getMetadata("title", removeallentities=True)
             book['author_sort'] = book['author'] = story.getList("author", removeallentities=True)
             book['publisher'] = story.getMetadata("site")
@@ -1198,7 +1215,7 @@ class FanFicFarePlugin(InterfaceAction):
             else:
                 book['comments']=''
             book['series'] = story.getMetadata("series", removeallentities=True)
-    
+
             if story.getMetadataRaw('datePublished'):
                 book['pubdate'] = story.getMetadataRaw('datePublished').replace(tzinfo=local_tz)
             if story.getMetadataRaw('dateUpdated'):
@@ -1207,7 +1224,7 @@ class FanFicFarePlugin(InterfaceAction):
                 book['timestamp'] = story.getMetadataRaw('dateCreated').replace(tzinfo=local_tz)
             else:
                 book['timestamp'] = None # need *something* there for calibre.
-    
+
         if not merge:# skip all the collision code when d/ling for merging.
             if collision in (CALIBREONLY, CALIBREONLYSAVECOL):
                 book['icon'] = 'metadata.png'
@@ -1334,7 +1351,7 @@ class FanFicFarePlugin(InterfaceAction):
                         # check make sure incoming is newer.
                         lastupdated=story.getMetadataRaw('dateUpdated')
                         logger.debug("OVERWRITE site updated: %s"%lastupdated)
-    
+
                         # updated doesn't have time (or is midnight), use dates only.
                         # updated does have time, use full timestamps.
                         if (lastupdated.time() == time.min and fileupdated.date() > lastupdated.date()) or \
@@ -1377,19 +1394,19 @@ class FanFicFarePlugin(InterfaceAction):
                     if not label and k in field_metadata:
                         label=field_metadata[k]['name']
                     key='calibre_std_'+k
-                    
+
                     # if k == 'user_categories':
                     #     value=u', '.join(mi.get(k))
                     #     label=_('User Categories')
-        
+
                     if label: # only if it has a human readable name.
                         if value is None or not book['calibre_id']:
                             ## if existing book, populate existing calibre column
                             ## values in metadata, else '' to hide.
-                            value=''                    
+                            value=''
                         book['calibre_columns'][key]={'val':value,'label':label}
                         #logger.debug("%s(%s): %s"%(label,key,value))
-        
+
                 # custom columns
                 for k, column in self.gui.library_view.model().custom_columns.iteritems():
                     if k != prefs['savemetacol']:
@@ -1405,7 +1422,7 @@ class FanFicFarePlugin(InterfaceAction):
                             value=''
                         book['calibre_columns'][key]={'val':value,'label':label}
                         # logger.debug("%s(%s): %s"%(label,key,value))
-            
+
             # if still 'good', make a temp file to write the output to.
             # For HTML format users, make the filename inside the zip something reasonable.
             # For crazy long titles/authors, limit it to 200chars.
@@ -1472,10 +1489,20 @@ class FanFicFarePlugin(InterfaceAction):
             htmllog = htmllog + '</table></body></html>'
 
             payload = ([], book_list, options)
-            self.gui.proceed_question(self.update_error_column,
+
-                                      payload, htmllog,
+            # log_viewer_unique_name implemented here: https://github.com/kovidgoyal/calibre/compare/v2.56.0...v2.57.0
-                                      _('FanFicFare log'), _('FanFicFare download ended'), msg,
+            if calibre_version >= (2, 57, 0):
-                                      show_copy_button=False)
+                self.gui.proceed_question(self.update_error_column,
+                                          payload, htmllog,
+                                          _('FanFicFare log'), _('FanFicFare download ended'), msg,
+                                          show_copy_button=False,
+                                          log_viewer_unique_name="FanFicFare log viewer")
+            else:
+                self.gui.proceed_question(self.update_error_column,
+                                          payload, htmllog,
+                                          _('FanFicFare log'), _('FanFicFare download ended'), msg,
+                                          show_copy_button=False)
+
             return
 
         cookiejarfile = PersistentTemporaryFile(suffix='.cookiejar',
@@ -1709,12 +1736,21 @@ class FanFicFarePlugin(InterfaceAction):
 
             do_update_func = self.do_download_list_update
 
-        self.gui.proceed_question(do_update_func,
+        # log_viewer_unique_name implemented here: https://github.com/kovidgoyal/calibre/compare/v2.56.0...v2.57.0
-                                  payload, htmllog,
+        if calibre_version >= (2, 57, 0):
-                                  _('FanFicFare log'), _('FanFicFare download complete'), msg,
+            self.gui.proceed_question(do_update_func,
-                                  show_copy_button=False)
+                                      payload, htmllog,
+                                      _('FanFicFare log'), _('FanFicFare download complete'), msg,
+                                      show_copy_button=False,
+                                      log_viewer_unique_name="FanFicFare log viewer")
+        else:
+            self.gui.proceed_question(do_update_func,
+                                      payload, htmllog,
+                                      _('FanFicFare log'), _('FanFicFare download complete'), msg,
+                                      show_copy_button=False)
 
     def do_download_merge_update(self, payload):
+        db = self.gui.current_db
 
         (good_list,bad_list,options) = payload
         total_good = len(good_list)
@@ -1740,19 +1776,62 @@ class FanFicFarePlugin(InterfaceAction):
 
         #print("mergebook:\n%s"%mergebook)
 
-        if mergebook['good']: # there shouldn't be any !'good' books at this point.
+        # make a temp file to write the output to.
-            # if still 'good', make a temp file to write the output to.
+        tmp = PersistentTemporaryFile(suffix='.'+options['fileform'],
-            tmp = PersistentTemporaryFile(suffix='.'+options['fileform'],
+                                      dir=options['tdir'])
-                                          dir=options['tdir'])
+        # logger.debug("title:"+mergebook['title'])
-            logger.debug("title:"+mergebook['title'])
+        logger.debug("outfile:"+tmp.name)
-            logger.debug("outfile:"+tmp.name)
+        mergebook['outfile'] = tmp.name
-            mergebook['outfile'] = tmp.name
 
+        ## Calibre's Polish heuristics for covers can cause problems
+        ## if a merged anthology book has sub-book covers, but not a
+        ## proper main cover.  So, now if there are any covers, we
+        ## will force a main cover.
+
+        ## start with None.  If no subbook covers, don't force one
+        ## here.  User can configure FFF to always create/polish a
+        ## cover if they want.  This is about when we force it.
+        coverpath = None
+        coverimgtype = None
+
+        ## first, look for covers inside the subbooks.  Stop at the
+        ## first one, which will be used if there isn't a pre-existing
+        ## calibre cover.
+        if not coverpath:
+            for book in good_list:
+                coverdata = get_cover_data(book['outfile'])
+                if coverdata: # found a cover.
+                    (coverimgtype,coverimgdata) = coverdata[4:6]
+                    logger.debug('coverimgtype:%s [%s]'%(coverimgtype,imagetypes[coverimgtype]))
+                    tmpcover = PersistentTemporaryFile(suffix='.'+imagetypes[coverimgtype],
+                                                       dir=options['tdir'])
+                    tmpcover.write(coverimgdata)
+                    tmpcover.flush()
+                    tmpcover.close()
+                    coverpath = tmpcover.name
+                    break
+        # logger.debug('coverpath:%s'%coverpath)
+
+        ## if updating an existing book and there is at least one
+        ## subbook cover:
+        if coverpath and mergebook['calibre_id']:
+            # Couldn't find a better way to get the cover path.
+            calcoverpath = os.path.join(db.library_path,
+                                     db.path(mergebook['calibre_id'], index_is_id=True),
+                                     'cover.jpg')
+            ## if there's an existing cover, use it.  Calibre will set
+            ## it for us during lots of different actions anyway.
+            if os.path.exists(calcoverpath):
+                coverpath = calcoverpath
+
+        # logger.debug('coverpath:%s'%coverpath)
         self.get_epubmerge_plugin().do_merge(tmp.name,
                                              [ x['outfile'] for x in good_list ],
+                                             tags=mergebook['tags'],
                                              titleopt=mergebook['title'],
                                              keepmetadatafiles=True,
-                                             source=mergebook['url'])
+                                             source=mergebook['url'],
+                                             coverjpgpath=coverpath)
 
         options['collision']=OVERWRITEALWAYS
         self.update_books_loop(mergebook,self.gui.current_db,options)
@@ -1872,7 +1951,8 @@ class FanFicFarePlugin(InterfaceAction):
             #print("mi.tags:%s"%mi.tags)
 
         if book['all_metadata']['langcode']:
-            mi.languages=[book['all_metadata']['langcode']]
+            # split due to anthologies.  Gives list of one for non-anth.
+            mi.languages=book['all_metadata']['langcode'].split(', ')
         else:
             # Set language english, but only if not already set.
             if not oldmi.languages:
@@ -1939,14 +2019,17 @@ class FanFicFarePlugin(InterfaceAction):
         configuration = None
         if prefs['allow_custcol_from_ini']:
             configuration = get_fff_config(book['url'],options['fileform'])
-            # meta => custcol[,a|n|r]
+            # meta => custcol[,a|n|r|n_anthaver,r_anthaver]
             # cliches=>\#acolumn,r
             for line in configuration.getConfig('custom_columns_settings').splitlines():
                 if "=>" in line:
                     (meta,custcol) = map( lambda x: x.strip(), line.split("=>") )
                     flag='r'
+                    anthaver=False
                     if "," in custcol:
                         (custcol,flag) = map( lambda x: x.strip(), custcol.split(",") )
+                        anthaver = 'anthaver' in flag
+                        flag=flag[0] # first char only.
 
                     if meta not in book['all_metadata']:
                         # if double quoted, use as a literal value.
@@ -1968,8 +2051,15 @@ class FanFicFarePlugin(InterfaceAction):
                     if flag == 'r' or (flag == 'n' and book['added']):
                         if coldef['datatype'] in ('int','float'): # for favs, etc--site specific metadata.
                             if 'anthology_meta_list' in book and meta in book['anthology_meta_list']:
-                                # re-split list, strip commas, convert to floats, sum up.
+                                # re-split list, strip commas, convert to floats
-                                val = sum([ float(x.replace(",","")) for x in val.split(", ") ])
+                                items = [ float(x.replace(",","")) for x in val.split(", ") ]
+                                if anthaver:
+                                    if items:
+                                        val = sum(items) / float(len(items))
+                                    else:
+                                        val = 0
+                                else:
+                                    val = sum(items)
                             else:
                                 val = unicode(val).replace(",","")
                         else:
@@ -2042,7 +2132,7 @@ class FanFicFarePlugin(InterfaceAction):
             prefs['gencalcover'] == SAVE_YES ## yes, always
             or (prefs['gencalcover'] == SAVE_YES_UNLESS_IMG ## yes, unless image.
                 and book['all_metadata']['cover_image'] not in ('specific','first','default')) ):
-        
+
             cover_generated = False # flag for polish below.
             # Yes, should do gencov.  Which?
             if prefs['calibre_gen_cover'] and HAS_CALGC:
@@ -2055,19 +2145,19 @@ class FanFicFarePlugin(InterfaceAction):
                 cover_generated = True
             elif prefs['plugin_gen_cover'] and 'Generate Cover' in self.gui.iactions:
                 # plugin, if available.
-    
+
                 #logger.debug("Do Generate Cover added:%s gcnewonly:%s"%(book['added'],prefs['gcnewonly']))
-    
+
                 # force a refresh if generating cover so complex composite
                 # custom columns are current and correct
                 db.refresh_ids([book_id])
-    
+
                 gc_plugin = self.gui.iactions['Generate Cover']
                 setting_name = None
                 if prefs['allow_gc_from_ini']:
                     if not configuration: # might already have it from allow_custcol_from_ini
                         configuration = get_fff_config(book['url'],options['fileform'])
-    
+
                     # template => regexp to match => GC Setting to use.
                     # generate_cover_settings:
                     # ${category} => Buffy:? the Vampire Slayer => Buffy
@@ -2076,25 +2166,25 @@ class FanFicFarePlugin(InterfaceAction):
                     #         (template,regexp,setting) = map( lambda x: x.strip(), line.split("=>") )
                     for (template,regexp,setting) in configuration.get_generate_cover_settings():
                         value = Template(template).safe_substitute(book['all_metadata']).encode('utf8')
-                        print("%s(%s) => %s => %s"%(template,value,regexp,setting))
+                        # print("%s(%s) => %s => %s"%(template,value,regexp,setting))
                         if re.search(regexp,value):
                             setting_name = setting
                             break
-    
+
                     if setting_name:
                         logger.debug("Generate Cover Setting from generate_cover_settings(%s)"%setting_name)
                         if setting_name not in gc_plugin.get_saved_setting_names():
                             logger.info("GC Name %s not found, discarding! (check personal.ini for typos)"%setting_name)
                             setting_name = None
-    
+
                 if not setting_name and book['all_metadata']['site'] in prefs['gc_site_settings']:
                     setting_name =  prefs['gc_site_settings'][book['all_metadata']['site']]
                     logger.debug("Generate Cover Setting from site(%s)"%setting_name)
-    
+
                 if not setting_name and 'Default' in prefs['gc_site_settings']:
                     setting_name =  prefs['gc_site_settings']['Default']
                     logger.debug("Generate Cover Setting from Default(%s)"%setting_name)
-    
+
                 if setting_name:
                     logger.debug("Running Generate Cover with settings %s."%setting_name)
                     ## fetch updated mi object from
@@ -2103,14 +2193,14 @@ class FanFicFarePlugin(InterfaceAction):
                     realmi = db.get_metadata(book_id, index_is_id=True)
                     gc_plugin.generate_cover_for_book(realmi,saved_setting_name=setting_name)
                     cover_generated = True
-    
+
             if cover_generated and prefs['gc_polish_cover'] and \
                     options['fileform'] == "epub":
                 # set cover inside epub from calibre's polish feature
                 from calibre.ebooks.oeb.polish.main import polish, ALL_OPTS
                 from calibre.utils.logging import Log
                 from collections import namedtuple
-    
+
                 # Couldn't find a better way to get the cover path.
                 cover_path = os.path.join(db.library_path,
                                           db.path(book_id, index_is_id=True),
@@ -2121,7 +2211,7 @@ class FanFicFarePlugin(InterfaceAction):
                 opts.update(data)
                 O = namedtuple('Options', ' '.join(ALL_OPTS.iterkeys()))
                 opts = O(**opts)
-    
+
                 log = Log(level=Log.DEBUG)
                 outfile = db.format_abspath(book_id,
                                             formmapping[options['fileform']],
@@ -2381,7 +2471,9 @@ class FanFicFarePlugin(InterfaceAction):
                 #print("book series:%s"%serieslist[-1])
 
             if b['publisher']:
-                if 'publisher' not in book:
+                if not book['publisher']:
+                    ## not set in all_metadata because it's not one of
+                    ## the permitted metadata--use site instead.
                     book['publisher']=b['publisher']
                 elif book['publisher']!=b['publisher']:
                     book['publisher']=None # if any are different, don't use.
@@ -2439,18 +2531,33 @@ class FanFicFarePlugin(InterfaceAction):
                         book['anthology_meta_list'][k]=True
 
         logger.debug("book['url']:%s"%book['url'])
+
+        book['comments'] = _("Anthology containing:")+"\n\n"
+        if len(book['author']) > 1:
+            mkbooktitle = lambda x : _("%s by %s") % (x['title'],' & '.join(x['author']))
+        else:
+            mkbooktitle = lambda x : x['title']
+
+        if prefs['includecomments']:
+            def mkbookcomments(x):
+                if x['comments']:
+                    return '<b>%s</b>\n\n%s'%(mkbooktitle(x),x['comments'])
+                else:
+                    return '<b>%s</b>\n'%mkbooktitle(x)
+
+            book['comments'] += ('<div class="mergedbook">' +
+                            '<hr></div><div class="mergedbook">'.join([ mkbookcomments(x) for x in book_list]) +
+                            '</div>')
+        else:
+            book['comments'] += '\n'.join( [ mkbooktitle(x) for x in book_list ] )
+
         configuration = get_fff_config(book['url'],fileform)
         if existingbook:
             book['title'] = deftitle = existingbook['title']
-            book['comments'] = existingbook['comments']
+            if prefs['anth_comments_newonly']:
+                book['comments'] = existingbook['comments']
         else:
             book['title'] = deftitle = book_list[0]['title']
-            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
@@ -2487,7 +2594,7 @@ class FanFicFarePlugin(InterfaceAction):
 
     def restore_cursor(self):
         QApplication.restoreOverrideCursor()
-    
+
 def split_text_to_urls(urls):
     # remove dups while preserving order.
     dups=set()

calibre-plugin/jobs.py

@@ -161,7 +161,7 @@ def do_download_for_worker(book,options,merge,notification=lambda x,y:x):
             adapter.set_pagecache(options['pagecache'])
             
             story = adapter.getStoryMetadataOnly()
-            if 'calibre_series' in book:
+            if not story.getMetadata("series") and 'calibre_series' in book:
                 adapter.setSeries(book['calibre_series'][0],book['calibre_series'][1])
                 
             # set PI version instead of default.
@@ -319,8 +319,7 @@ def do_download_for_worker(book,options,merge,notification=lambda x,y:x):
             book['comment']=unicode(e)
             book['icon']='dialog_error.png'
             book['status'] = _('Error')
-            logger.info("Exception: %s:%s"%(book,unicode(e)))
+            logger.info("Exception: %s:%s"%(book,unicode(e)),exc_info=True)
-            traceback.print_exc()
             
         #time.sleep(10)
     return book

calibre-plugin/plugin-defaults.ini

@@ -25,7 +25,7 @@
 ## titlepage_entries: category,genre, status,dateUpdated,rating
 ## [epub]
 ## # overrides defaults & site section
-## titlepage_entries: category,genre, status,datePublished,dateUpdated,dateCreated
+## titlepage_entries: category,genre,status,datePublished,dateUpdated,dateCreated
 ## [www.whofic.com:epub]
 ## # overrides defaults, site section & format section
 ## titlepage_entries: category,genre, status,datePublished
@@ -150,7 +150,7 @@ extratags: FanFiction
 ## Can also be used for other metadata values
 #default_value_category:FanFiction
 
-## number of seconds to sleep between calls to the story site.  May by
+## number of seconds to sleep between calls to the story site.  May be
 ## useful if pulling large numbers of stories or if the site is slow.
 #slow_down_sleep_time:0.5
 
@@ -474,8 +474,8 @@ add_to_include_subject_tags:,tagsfromtitle.SPLIT,forumtags
 ## base_xenforoforum reads Published and Updated datetimes from
 ## Threadmarks if used, or from the posted & updated times of the
 ## 'first' post if no threadmarks.
-datePublished_format:%%Y-%%m-%%d %%H:%%M:%%S
+datePublished_format:%%Y-%%m-%%d %%H:%%M
-dateUpdated_format:%%Y-%%m-%%d %%H:%%M:%%S
+dateUpdated_format:%%Y-%%m-%%d %%H:%%M
 
 ## Only take the first X characters of the 'first' post to use as
 ## the description.
@@ -510,6 +510,20 @@ first_post_title:First Post
 ## if threadmarks are used.  Can result in a duplicated chapter.
 always_include_first_post:false
 
+## In normal operation, when updating an existing epub, old chapters
+## will be reused as-is.  Normally, that works fine, but forum stories
+## sometimes have an index post as the first 'chapter', and the
+## version in the first chapter gets out of sync.
+##
+## If always_reload_first_chapter:true, then the first chapter will
+## always be downloaded again (ie, reloaded).  It will NOT be maked
+## '(new)' (see mark_new_chapters).  Because it is reloaded, manual
+## edits made to the first chapter will be lost.
+##
+## While intended for base_xenforoforum sites, this setting can be
+## applied to other sites.
+always_reload_first_chapter:false
+
 ## In normal operation, forumtags will only be populated when
 ## threadmarks are used for chapters (see minimum_threadmarks above).
 ## When always_use_forumtags:true, always populate forumtags.
@@ -585,6 +599,11 @@ include_logpage: false
 ## end up with Completed stories that have just one logpage entry.
 #include_logpage: smart
 
+## By default, logpage is placed before the story chapters.  This
+## setting, if true, will place the logpage after the chapters
+## instead.
+logpage_at_end: false
+
 ## items to include in the log page Empty metadata entries, or those
 ## that haven't changed since the last update, will *not* appear, even
 ## if in the list.  You can include extra text or HTML that will be
@@ -701,6 +720,18 @@ remove_transparency: true
 ## true--replace_br_with_p also fixes the problem.
 nook_img_fix:true
 
+## Apply adapter's normalize_chapterurl() to all links in chapter
+## texts, if they match chapter URLs.  Currently only implemented by
+## base_xenforoforum adapters.
+#normalize_text_links:false
+
+## Search all links in chapter texts and, if they match any included
+## chapter URLs, replace them with links to the chapter in the
+## download.  Only works with epub and html output formats.
+## base_xenforoforum adapters should also use normalize_text_links
+## with this.
+#internalize_text_links:false
+
 [mobi]
 ## mobi TOC cannot be turned off right now.
 #include_tocpage: true
@@ -748,6 +779,19 @@ extratags: FanFiction,Testing,Text
 [test1.com:html]
 extratags: FanFiction,Testing,HTML
 
+[adult-fanfiction.org]
+extra_valid_entries:eroticatags,disclaimer
+eroticatags_label:Erotica Tags
+disclaimer_label:Disclaimer
+extra_titlepage_entries:eroticatags,disclaimer
+
+## 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
+
 [archive.skyehawke.com]
 
 [archiveofourown.org]
@@ -847,18 +891,6 @@ extracategories:The Sentinel
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
-[bdsm-geschichten.net]
-## Some sites do not require a login, but do require the user to
-## confirm they are adult for adult content.  In commandline version,
-## this should go in your personal.ini, not defaults.ini.
-#is_adult:true
-
-## This site offers no index page so we can either guess the chapter URLs
-## by dec/incrementing numbers ('guess') or walk all the chapters in the metadata
-## parsing state ('parse'). Since guessing can lead to errors for non-standard
-## story URLs, the default is to parse
-#find_chapters:guess 
-
 [bloodshedverse.com]
 ## website encoding(s) In theory, each website reports the character
 ## encoding they use for each page.  In practice, some sites report it
@@ -869,6 +901,12 @@ extracategories:The Sentinel
 ## it has +90% confidence.  'auto' is not reliable.
 website_encodings:Windows-1252,ISO-8859-1,auto
 
+## dateUpdate doesn't usually have time, but it does on
+## bloodshedverse.com.  See
+## http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+## Note that ini format requires % to be escaped as %%.
+dateUpdated_format:%%Y-%%m-%%d %%H:%%M
+
 ## Extra metadata that this adapter knows about.  See [dramione.org]
 ## for examples of how to use them.
 extra_valid_entries:warnings,reviews
@@ -898,15 +936,6 @@ strip_text_links:true
 ## Site dedicated to these categories/characters/ships
 extracategories:Blood Ties
 
-[buffynfaith.net]
-## Site dedicated to these categories/characters/ships
-extracategories:Buffy: The Vampire Slayer
-
-## Some sites also require the user to confirm they are adult for
-## adult content.  In commandline version, this should go in your
-## personal.ini, not defaults.ini.
-#is_adult:true
-
 [fanfic.castletv.net]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -1023,15 +1052,24 @@ cliches_label:Character Cliches
 ## 'mode'.  'r' to Replace any existing values, 'a' to Add to existing
 ## value (use with tag-like columns), and 'n' for setting on New books
 ## only.  (Default is 'r'.)
+
 ## Literal strings can be set into custom columns using double quotes.
 ## Each metadata=>column mapping must be on a separate line and each
 ## needs to have one space at the start of each line.
 
+## 'r_anthaver' and 'n_anthaver' can be used to indicate the same as
+## 'r' and 'n' for normal downloads, but to average the metadata for
+## the differents story in an anthology before setting in integer and
+## float type custom columns.  This can be useful for a averrating
+## column, for example.  Default is to sum the values of all stories,
+## and numChapters and numWords are always summed.
+
 #custom_columns_settings:
 # cliches=>#acolumn
 # themes=>#bcolumn,a
 # timeline=>#ccolumn,n
 # "FanFiction"=>#collection
+# averrating=>#averrating,r_anthaver
 
 [efiction.esteliel.de]
 ## Site dedicated to these categories/characters/ships
@@ -1151,13 +1189,20 @@ romance_label: Romance
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
-[ficwad.com]
+[fictionhunt.com]
-## Some sites require login (or login for some rated stories) The
+## Archive only site for ffnet HP stories.
-## program can prompt you, or you can save it in config.  In
+
-## commandline version, this should go in your personal.ini, not
+## Site dedicated to these categories/characters/ships
-## defaults.ini.
+extracategories:Harry Potter
-#username:YourName
+
-#password:yourpassword
+extra_valid_entries: origin,originUrl,originHTML,reviews
+originHTML_label:Original Story URL
+
+## Assume entryUrl, apply to "<a class='%slink' href='%s'>%s</a>" to
+## make entryHTML.
+make_linkhtml_entries:origin
+
+add_to_extra_titlepage_entries:originHTML
 
 [fictionmania.tv]
 ## website encoding(s) In theory, each website reports the character
@@ -1215,6 +1260,14 @@ views_label:Views
 likes_label:Likes
 dislikes_label:Dislikes
 
+[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
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
 [finestories.com]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -1256,13 +1309,9 @@ universe_as_series: true
 ## cover image.  This lets you exclude them.
 cover_exclusion_regexp:/css/bir.png
 
-[forums.spacebattles.com]
+[forum.questionablequesting.com]
 ## see [base_xenforoforum]
 
-[forums.sufficientvelocity.com]
-## see [base_xenforoforum]
-
-[grangerenchanted.com]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
 ## commandline version, this should go in your personal.ini, not
@@ -1270,18 +1319,24 @@ cover_exclusion_regexp:/css/bir.png
 #username:YourName
 #password:yourpassword
 
-## Some sites also require the user to confirm they are adult for
+[forums.spacebattles.com]
-## adult content.  In commandline version, this should go in your
+## see [base_xenforoforum]
-## personal.ini, not defaults.ini.
+
+[forums.sufficientvelocity.com]
+## see [base_xenforoforum]
+
+[harem.lucifael.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
-## Site dedicated to these categories/characters/ships
+## Some sites require login (or login for some rated stories) The
-extracategories:Harry Potter
+## program can prompt you, or you can save it in config.  In
-extracharacters:Hermione Granger
+## commandline version, this should go in your personal.ini, not
-
+## defaults.ini.
-## Extra metadata that this adapter knows about.  See [dramione.org]
+#username:YourName
-## for examples of how to use them.
+#password:yourpassword
-extra_valid_entries:read,reviews
 
 [hlfiction.net]
 ## Site dedicated to these categories/characters/ships
@@ -1395,6 +1450,19 @@ extra_titlepage_entries: eroticatags
 ## Site dedicated to these categories/characters/ships
 extracategories:Merlin
 
+[mujaji.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
+
 [national-library.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:West Wing
@@ -1496,15 +1564,21 @@ extracategories:My Little Pony: Friendship is Magic
 ## Site dedicated to these categories/characters/ships
 extracategories:The Pretender
 
-[forum.questionablequesting.com]
+[quotev.com]
-## see [base_xenforoforum]
+extra_valid_entries:pages,readers,reads,favorites,searchtags,comments
+pages_label:Pages
+readers_label:Readers
+reads_label:Reads
+favorites_label:Favorites
+searchtags_label:Search Tags
+comments_label:Comments
 
-## Some sites require login (or login for some rated stories) The
+include_in_category:category,searchtags
-## program can prompt you, or you can save it in config.  In
+
-## commandline version, this should go in your personal.ini, not
+[royalroadl.com]
-## defaults.ini.
+extra_valid_entries:stars
-#username:YourName
+
-#password:yourpassword
+#add_to_extra_titlepage_entries:,stars
 
 [samandjack.net]
 ## Some sites require login (or login for some rated stories) The
@@ -1530,22 +1604,6 @@ extracategories:Supernatural
 extracharacters:Sam,Dean
 extraships:Sam/Dean
 
-[scarhead.net]
-## Some sites require login (or login for some rated stories) The
-## program can prompt you, or you can save it in config.  In
-## commandline version, this should go in your personal.ini, not
-## defaults.ini.
-#username:YourName
-#password:yourpassword
-
-## Some sites also require the user to confirm they are adult for
-## adult content.  In commandline version, this should go in your
-## personal.ini, not defaults.ini.
-#is_adult:true
-
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-
 [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
@@ -1687,15 +1745,6 @@ readings_label: Readings
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
-[tokra.fandomnet.com]
-## Some sites do not require a login, but do require the user to
-## confirm they are adult for adult content.  In commandline version,
-## this should go in your personal.ini, not defaults.ini.
-#is_adult:true
-
-## Site dedicated to these categories/characters/ships
-extracategories:Stargate: SG-1
-
 [tolkienfanfiction.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Lord of the Rings
@@ -1763,6 +1812,12 @@ extraships:Draco Malfoy/Ginny Weasley
 ## Site dedicated to these categories/characters/ships
 extracategories:Stargate: SG-1
 
+[www.deepinmysoul.net]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
 [www.destinysgateway.com]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
@@ -1857,6 +1912,10 @@ check_next_chapter:false
 #password:yourpassword
 
 [www.ficbook.net]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
 
 [www.fictionalley.org]
 ## Some sites do not require a login, but do require the user to
@@ -2059,11 +2118,6 @@ cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
 ## Site dedicated to these categories/characters/ships
 extracategories:NCIS
 
-[www.nickngreg.nl]
-## Site dedicated to these categories/characters/ships
-extracategories:CSI
-extraships:Nick Stokes/Greg Sanders
-
 [www.phoenixsong.net]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -2118,6 +2172,8 @@ extracategories:Psych
 extracategories:Queer as Folk
 
 [quotev.com]
+user_agent:
+slow_down_sleep_time:2
 extra_valid_entries:pages,readers,reads,favorites,searchtags,comments
 pages_label:Pages
 readers_label:Readers
@@ -2194,23 +2250,9 @@ extracategories:Lord of the Rings
 #username:YourName
 #password:yourpassword
 
-[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
-## 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
-
-## twcslibrary.net (ab)uses series as personal reading lists.
-collect_series: false
-
 [www.tthfanfic.org]
+user_agent:
+slow_down_sleep_time:2
 ## 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.
@@ -2245,6 +2287,22 @@ pairingcat_to_characters_ships:true
 ## instead be added to characters Buffy, Spike and ships Buffy/Spike
 romancecat_to_characters_ships:true
 
+[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
+## 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
+
+## twcslibrary.net (ab)uses series as personal reading lists.
+collect_series: false
+
 [www.twilightarchives.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Twilight
@@ -2293,8 +2351,9 @@ extracharacters:Wolverine,Rogue
 ## Site dedicated to these categories/characters/ships
 extracategories:Stargate: Atlantis
 
-extra_valid_entries:reviews
+##site stopped showing reviews ~ Oct 2016
-reviews_label:Reviews
+#extra_valid_entries:reviews
+#reviews_label:Reviews
 
 [buffygiles.velocitygrass.com]
 ## Some sites do not require a login, but do require the user to
@@ -2357,20 +2416,6 @@ extracategories:Andromeda
 ## Site dedicated to these categories/characters/ships
 extracategories:Artemis Fowl
 
-[www.therabidreader.com]
-## Some sites do not require a login, but do require the user to
-## confirm they are adult for adult content.  In commandline version,
-## this should go in your personal.ini, not defaults.ini.
-#is_adult:true
-
-## Some sites require login (or login for some rated stories) The
-## program can prompt you, or you can save it in config.  In
-## commandline version, this should go in your personal.ini, not
-## defaults.ini.
-#username:YourName
-#password:yourpassword
-
-
 [www.naiceanilme.net]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
@@ -2384,8 +2429,6 @@ extracategories:Artemis Fowl
 #username:YourName
 #password:yourpassword
 
-
-
 [overrides]
 ## It may sometimes be useful to override all of the specific format,
 ## site and site:format sections in your private configuration.  For

calibre-plugin/prefs.py

@@ -130,6 +130,7 @@ default_prefs['deleteotherforms'] = False
 default_prefs['adddialogstaysontop'] = False
 default_prefs['lookforurlinhtml'] = False
 default_prefs['checkforseriesurlid'] = True
+default_prefs['auto_reject_seriesurlid'] = False
 default_prefs['checkforurlchange'] = True
 default_prefs['injectseries'] = False
 default_prefs['matchtitleauth'] = True
@@ -166,6 +167,8 @@ default_prefs['allow_custcol_from_ini'] = True
 
 default_prefs['std_cols_newonly'] = {}
 default_prefs['set_author_url'] = True
+default_prefs['includecomments'] = False
+default_prefs['anth_comments_newonly'] = True
 
 default_prefs['imapserver'] = ''
 default_prefs['imapuser'] = ''
@@ -174,6 +177,7 @@ default_prefs['imapsessionpass'] = False
 default_prefs['imapfolder'] = 'INBOX'
 default_prefs['imapmarkread'] = True
 default_prefs['auto_reject_from_email'] = False
+default_prefs['update_existing_only_from_email'] = False
 default_prefs['download_from_email_immediately'] = False
 
 def set_library_config(library_config,db):

fanficfare/__init__.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2015 Fanficdownloader team, 2015 FanFicFare team
+# Copyright 2015 Fanficdownloader team, 2016 FanFicFare team
 #
 # Licensed under the Apache License, Version 2.0 (the 'License');
 # you may not use this file except in compliance with the License.
@@ -17,7 +17,7 @@
 
 try:
     # just a way to switch between web service and CLI/PI
-    import google.appengine.api 
+    import google.appengine.api
 except:
     try: # just a way to switch between CLI and PI
         import calibre.constants
@@ -31,4 +31,3 @@ except:
             logger.addHandler(loghandler)
             loghandler.setLevel(logging.DEBUG)
             logger.setLevel(logging.DEBUG)
-

fanficfare/adapters/__init__.py

@@ -85,7 +85,6 @@ import adapter_hpfanficarchivecom
 import adapter_twilightarchivescom
 import adapter_nhamagicalworldsus
 import adapter_hlfictionnet
-import adapter_grangerenchantedcom
 import adapter_dracoandginnycom
 import adapter_scarvesandcoffeenet
 import adapter_thepetulantpoetesscom
@@ -102,13 +101,9 @@ import adapter_efictionestelielde
 import adapter_pommedesangcom
 import adapter_restrictedsectionorg
 import adapter_imagineeficcom
-import adapter_buffynfaithnet
 import adapter_psychficcom
-import adapter_tokrafandomnetcom
 import adapter_asr3slashzoneorg
-import adapter_nickandgregnet
 import adapter_potterheadsanonymouscom
-import adapter_scarheadnet
 import adapter_fictionpadcom
 import adapter_storiesonlinenet
 import adapter_trekiverseorg
@@ -120,7 +115,6 @@ import adapter_nocturnallightnet
 import adapter_fanfichu
 import adapter_fanfictioncsodaidokhu
 import adapter_fictionmaniatv
-import adapter_bdsmgeschichten
 import adapter_tolkienfanfiction
 import adapter_themaplebookshelf
 import adapter_fannation
@@ -139,14 +133,18 @@ import adapter_ninelivesarchivecom
 import adapter_masseffect2in
 import adapter_quotevcom
 import adapter_mcstoriescom
-
 import adapter_lucifaelff
 import adapter_buffygilescom
-#import adapter_rubyquillcom
+import adapter_andromedawebcom
-import adapter_andromedawebcom # Not all lables are captured
 import adapter_artemisfowlcom
-import adapter_rabidreadercom
 import adapter_naiceanilmenet
+import adapter_deepinmysoulnet
+import adapter_haremlucifaelcom
+import adapter_kiarepositorymujajinet
+import adapter_fanfictionlucifaelcom
+import adapter_adultfanfictionorg
+import adapter_fictionhuntcom
+import adapter_royalroadl
 
 ## This bit of complexity allows adapters to be added by just adding
 ## importing.  It eliminates the long if/else clauses we used to need

fanficfare/adapters/adapter_adultfanfictionorg.py

@@ -0,0 +1,375 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2013 Fanficdownloader team, 2015 FanFicFare team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+################################################################################
+###   Written by GComyn
+################################################################################
+import time
+import logging
+logger = logging.getLogger(__name__)
+import re
+import sys
+
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+################################################################################
+
+def getClass():
+    return AdultFanFictionOrgAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class AdultFanFictionOrgAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+        logger.debug("AdultFanFictionOrgAdapter.__init__ - url='{0}'".format(url))
+
+        self.decode = ["utf8",
+                       "Windows-1252"] # 1252 is a superset of iso-8859-1.
+                            # Most sites that claim to be
+                            # iso-8859-1 (and some that claim to be
+                            # utf8) are really windows-1252.
+
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+
+        # get storyId from url
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+
+        #Setting the 'Zone' for each "Site"
+        self.zone = self.parsedUrl.netloc.split('.')[0]
+
+        # normalized story URL. (checking self.zone against list
+        # removed--it was redundant w/getAcceptDomains and
+        # getSiteURLPattern both)
+        self._setURL('http://' + self.zone + '.' + self.getBaseDomain() + '/story.php?no='+self.story.getMetadata('storyId'))
+
+        # Each adapter needs to have a unique site abbreviation.
+        #self.story.setMetadata('siteabbrev',self.getSiteAbbrev())
+
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev',self.zone+'aff')
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%Y-%m-%d"
+        
+
+    ##This method will be moved to the sub-adapters
+    # @classmethod
+    # def getSiteAbbrev(self):
+    #     return self.zone+'aff'
+
+    ## Added because adult-fanfiction.org does send you to
+    ## www.adult-fanfiction.org when you go to it and it also moves
+    ## the site & examples down the web service front page so the
+    ## first screen isn't dominated by 'adult' links.
+    def getBaseDomain(self):
+        return 'adult-fanfiction.org'
+
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'www.adult-fanfiction.org'
+
+    @classmethod
+    def getAcceptDomains(cls):
+        # mobile.fimifction.com isn't actually a valid domain, but we can still get the story id from URLs anyway
+        return ['anime.adult-fanfiction.org',
+                'anime2.adult-fanfiction.org',
+                'bleach.adult-fanfiction.org',
+                'books.adult-fanfiction.org',
+                'buffy.adult-fanfiction.org',
+                'cartoon.adult-fanfiction.org',
+                'celeb.adult-fanfiction.org',
+                'comics.adult-fanfiction.org',
+                'ff.adult-fanfiction.org',
+                'games.adult-fanfiction.org',
+                'hp.adult-fanfiction.org',
+                'inu.adult-fanfiction.org',
+                'lotr.adult-fanfiction.org',
+                'manga.adult-fanfiction.org',
+                'movies.adult-fanfiction.org',
+                'naruto.adult-fanfiction.org',
+                'ne.adult-fanfiction.org',
+                'original.adult-fanfiction.org',
+                'tv.adult-fanfiction.org',
+                'xmen.adult-fanfiction.org',
+                'ygo.adult-fanfiction.org',
+                'yuyu.adult-fanfiction.org']
+
+
+    @classmethod
+    def getSiteExampleURLs(self):
+        return ("http://anime.adult-fanfiction.org/story.php?no=123456789 "
+              + "http://anime2.adult-fanfiction.org/story.php?no=123456789 "
+              + "http://bleach.adult-fanfiction.org/story.php?no=123456789 "
+              + "http://books.adult-fanfiction.org/story.php?no=123456789 "
+              + "http://buffy.adult-fanfiction.org/story.php?no=123456789 "
+              + "http://cartoon.adult-fanfiction.org/story.php?no=123456789 "
+              + "http://celeb.adult-fanfiction.org/story.php?no=123456789 "
+              + "http://comics.adult-fanfiction.org/story.php?no=123456789 "
+              + "http://ff.adult-fanfiction.org/story.php?no=123456789 "
+              + "http://games.adult-fanfiction.org/story.php?no=123456789 "
+              + "http://hp.adult-fanfiction.org/story.php?no=123456789 "
+              + "http://inu.adult-fanfiction.org/story.php?no=123456789 "
+              + "http://lotr.adult-fanfiction.org/story.php?no=123456789 "
+              + "http://manga.adult-fanfiction.org/story.php?no=123456789 "
+              + "http://movies.adult-fanfiction.org/story.php?no=123456789 "
+              + "http://naruto.adult-fanfiction.org/story.php?no=123456789 "
+              + "http://ne.adult-fanfiction.org/story.php?no=123456789 "
+              + "http://original.adult-fanfiction.org/story.php?no=123456789 "
+              + "http://tv.adult-fanfiction.org/story.php?no=123456789 "
+              + "http://xmen.adult-fanfiction.org/story.php?no=123456789 "
+              + "http://ygo.adult-fanfiction.org/story.php?no=123456789 "
+              + "http://yuyu.adult-fanfiction.org/story.php?no=123456789")
+
+    def getSiteURLPattern(self):
+        return r'http?://(anime|anime2|bleach|books|buffy|cartoon|celeb|comics|ff|games|hp|inu|lotr|manga|movies|naruto|ne|original|tv|xmen|ygo|yuyu)\.adult-fanfiction\.org/story\.php\?no=\d+$'
+
+    ##This is not working right now, so I'm commenting it out, but leaving it for future testing
+    ## Login seems to be reasonably standard across eFiction sites.
+    #def needToLoginCheck(self, data):
+        ##This adapter will always require a login
+    #    return True
+
+#    <form name="login" method="post" action="">
+#      <div class="top">E-mail: <span id="sprytextfield1">
+#        <input name="email" type="text" id="email" size="20" maxlength="255" />
+#        <span class="textfieldRequiredMsg">Email is required.</span><span class="textfieldInvalidFormatMsg">Invalid E-mail.</span></span></div>
+#      <div class="top">Password: <span id="sprytextfield2">
+#        <input name="pass1" type="password" id="pass1" size="20" maxlength="32" />
+#        <span class="textfieldRequiredMsg">password is required.</span><span class="textfieldMinCharsMsg">Minimum 8 characters8.</span><span class="textfieldMaxCharsMsg">Exceeded 32 characters.</span></span></div>
+#      <div class="top"><br /> <input name="loginsubmittop" type="hidden" id="loginsubmit" value="TRUE" />
+#        <input type="submit" value="Login" />
+#      </div>
+#    </form>
+
+
+    ##This is not working right now, so I'm commenting it out, but leaving it for future testing
+    #def performLogin(self, url, soup):
+    #    params = {}
+
+    #    if self.password:
+    #        params['email'] = self.username
+    #        params['pass1'] = self.password
+    #    else:
+    #        params['email'] = self.getConfig("username")
+    #        params['pass1'] = self.getConfig("password")
+    #    params['submit'] = 'Login'
+
+    #    # copy all hidden input tags to pick up appropriate tokens.
+    #    for tag in soup.findAll('input',{'type':'hidden'}):
+    #        params[tag['name']] = tag['value']
+
+    #    logger.debug("Will now login to URL {0} as {1} with password: {2}".format(url, params['email'],params['pass1']))
+
+    #    d = self._postUrl(url, params, usecache=False)
+    #    d = self._fetchUrl(url, params, usecache=False)
+    #    soup = self.make_soup(d)
+        
+        #if not (soup.find('form', {'name' : 'login'}) == None):
+        #    logger.info("Failed to login to URL %s as %s" % (url, params['email']))
+        #    raise exceptions.FailedToLogin(url,params['email'])
+        #    return False
+        #else:
+    #    return True
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def doExtractChapterUrlsAndMetadata(self, get_cover=True):
+
+        ## You need to have your is_adult set to true to get this story
+        if not (self.is_adult or self.getConfig("is_adult")):
+            raise exceptions.AdultCheckRequired(self.url)
+
+        url = self.url
+        logger.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code in 404:
+                raise exceptions.StoryDoesNotExist("Code: 404. %s"%self.url)
+            elif e.code == 410:
+                raise exceptions.StoryDoesNotExist("Code: 410. %s"%self.url)
+            elif e.code == 401:
+                self.needToLogin = True
+                data = ''
+            else:
+                raise e
+
+        if "The dragons running the back end of the site can not seem to find the story you are looking for." in data:
+            raise exceptions.StoryDoesNotExist(self.zone+'.'+self.getBaseDomain() 
+                                               +" says: The dragons running the back end of the site can not seem to find the story you are looking for.")
+
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = self.make_soup(data)
+        
+        ##This is not working right now, so I'm commenting it out, but leaving it for future testing
+        #self.performLogin(url, soup)
+
+        # Now go hunting for all the meta data and the chapter list.
+
+        ## Title
+        ## Some of the titles have a backslash on the story page, but not on the Author's page
+        ## So I am removing it from the title, so it can be found on the Author's page further in the code.
+        ## Also, some titles may have extra spaces '  ', and the search on the Author's page removes them,
+        ## so I have to here as well. I used multiple replaces to make sure, since I did the same below.
+        a = soup.find('a', href=re.compile(r'story.php\?no='+self.story.getMetadata('storyId')+"$"))
+        self.story.setMetadata('title',stripHTML(a).replace('\\','').replace('  ',' ').replace('  ',' ').replace('  ',' ').strip())
+
+        # Find authorid and URL from... author url.
+        a = soup.find('a', href=re.compile(r"profile.php\?no=\d+"))
+        self.story.setMetadata('authorId',a['href'].split('=')[1])
+        self.story.setMetadata('authorUrl',a['href'])
+        self.story.setMetadata('author',stripHTML(a))
+
+        # Find the chapters:
+        chapters = soup.find('div',{'id':'snav'})
+        for i, chapter in enumerate(chapters.findAll('a')):
+            self.chapterUrls.append((stripHTML(chapter),self.url+'&chapter='+str(i+1)))
+        
+        self.story.setMetadata('numChapters', len(self.chapterUrls))
+
+        ##The story page does not give much Metadata, so we go to the Author's page
+        
+        ##Get the first Author page to see if there are multiple pages. 
+        ##AFF doesn't care if the page number is larger than the actual pages, 
+        ##it will continue to show the last page even if the variable is larger than the actual page
+        author_Url = self.story.getMetadata('authorUrl')+'&view=story&zone='+self.zone+'&page=1'
+
+        ##I'm resetting the author page to the zone for this story
+        self.story.setMetadata('authorUrl',author_Url)
+
+        logger.debug('Getting the author page: {0}'.format(author_Url))
+        try:
+            adata = self._fetchUrl(author_Url)
+        except urllib2.HTTPError, e:
+            if e.code in 404:
+                raise exceptions.StoryDoesNotExist("Author Page: Code: 404. %s"%author_Url)
+            elif e.code == 410:
+                raise exceptions.StoryDoesNotExist("Author Page: Code: 410. %s"%author_Url)
+            else:
+                raise e
+
+        if "The member you are looking for does not exist." in adata:
+            raise exceptions.StoryDoesNotExist(self.zone+'.'+self.getBaseDomain() +" says: The member you are looking for does not exist.")
+
+        asoup = self.make_soup(adata)
+
+        ##Getting the number of pages
+        pages=asoup.find('div',{'class' : 'pagination'}).findAll('li')[-1].find('a')
+        if not pages == None:
+            pages = pages['href'].split('=')[-1]
+        else:
+            pages = 0
+        logger.info(pages)
+        ##If there is only 1 page of stories, check it to get the Metadata, 
+        if pages == 0:
+            a = asoup.findAll('li')
+            for lc2 in a:
+                if lc2.find('a', href=re.compile(r'story.php\?no='+self.story.getMetadata('storyId')+"$")):
+                    break
+        ## otherwise go through the pages 
+        else:
+            page=1
+            i=0
+            while i == 0:
+                ##We already have the first page, so if this is the first time through, skip getting the page
+                if page != 1:
+                    author_Url = self.story.getMetadata('authorUrl')+'&view=story&zone='+self.zone+'&page='+str(page)
+                    logger.debug('Getting the author page: {0}'.format(author_Url))
+                    try:
+                        adata = self._fetchUrl(author_Url)
+                    except urllib2.HTTPError, e:
+                        if e.code in 404:
+                            raise exceptions.StoryDoesNotExist("Author Page: Code: 404. %s"%author_Url)
+                        elif e.code == 410:
+                            raise exceptions.StoryDoesNotExist("Author Page: Code: 410. %s"%author_Url)
+                        else:
+                            raise e
+                    ##This will probably never be needed, since AFF doesn't seem to care what number you put as 
+                    ## the page number, it will default to the last page, even if you use 1000, for an author
+                    ## that only hase 5 pages of stories, but I'm keeping it in to appease Saint Justin Case (just in case).
+                    if "The member you are looking for does not exist." in adata:
+                        raise exceptions.StoryDoesNotExist(self.zone+'.'+self.getBaseDomain() +" says: The member you are looking for does not exist.")
+    
+                asoup = self.make_soup(adata)
+    
+                a = asoup.findAll('li')
+                for lc2 in a:
+                    if lc2.find('a', href=re.compile(r'story.php\?no='+self.story.getMetadata('storyId')+"$")):
+                        i=1
+                        break
+                page = page + 1
+                if page > pages:
+                    break
+
+        ##Split the Metadata up into a list
+        ##We have to change the soup type to a string, then remove the newlines, and double spaces, 
+        ##then changes the <br/> to '-:-', which seperates the different elemeents.
+        ##Then we strip the HTML elements from the string.
+        ##There is also a double <br/>, so we have to fix that, then remove the leading and trailing '-:-'.
+        ##They are always in the same order.
+        liMetadata = stripHTML(str(lc2).replace('\n','').replace('\r','').replace('\t',' ').replace('  ',' ').replace('  ',' ').replace('  ',' ').replace(r'<br/>','-:-'))
+        liMetadata = liMetadata.replace(r'-:--:-','-:-').strip('-:-').strip('-:-')
+
+        for i, value in enumerate(liMetadata.split('-:-')):
+            ##The item 6 is the reviews... We are disregarding them.
+            ##The item 7 is the 'Dragon Prints'... not sure what they are, so disregarding them.
+            ##The 0 item is the title
+            if i == 0:
+                if value <> self.story.getMetadata('title'):
+                    raise exceptions.StoryDoesNotExist('Did not find story in author story list: {0}'.format(author_Url))
+            elif i == 1:
+                ##Get the description
+                self.story.setMetadata('description',stripHTML(value.strip()))
+            elif i == 2:
+                ##The Get the Category
+                self.story.setMetadata('category',value.replace(r'&gt;',r'>').replace(r'Located :',r'').strip())
+            elif i == 3:
+                ##Get the Erotic Tags
+                value = stripHTML(value.replace(r'Content Tags :',r'')).strip()
+                for code in re.split(r'\s',value):
+                    self.story.addToList('eroticatags',code)
+            elif i == 4:
+                ##Get the Posted Date
+                value = value.replace(r'Posted :',r'').strip()
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            elif i == 5:
+                ##Get the 'Updated' Edited date
+                ##AFF has the time for the Updated date, and we only want the date,
+                ##so we take the first 10 characters only
+                value = value.replace(r'Edited :',r'').strip()[0:10]
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+        #Since each chapter is on 1 page, we don't need to do anything special, just get the content of the page.
+        logger.debug('Getting chapter text from: %s' % url)
+
+        soup = self.make_soup(self._fetchUrl(url))
+        chaptertag = soup.find('div',{'class' : 'pagination'}).parent.findNext('td')
+
+        if None == chaptertag:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+
+        return self.utf8FromSoup(url,chaptertag)

fanficfare/adapters/adapter_archiveofourownorg.py

@@ -187,7 +187,7 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
         else:
             for a in alist:
                 self.story.addToList('authorId',a['href'].split('/')[-1])
-                self.story.addToList('authorUrl',a['href'])
+                self.story.addToList('authorUrl','http://'+self.host+a['href'])
                 self.story.addToList('author',a.text)
 
         byline = metasoup.find('h3',{'class':'byline'})

fanficfare/adapters/adapter_ashwindersycophanthexcom.py

@@ -77,7 +77,8 @@ class AshwinderSycophantHexComAdapter(BaseSiteAdapter):
     ## Login seems to be reasonably standard across eFiction sites.
     def needToLoginCheck(self, data):
         if 'This story contains adult content and/or themes.' in data \
-                or "That password doesn't match the one in our database" in data:
+                or "That password doesn't match the one in our database" in data \
+                or "Member Login" in data:
             return True
         else:
             return False

fanficfare/adapters/adapter_bdsmgeschichten.py

@@ -1,347 +0,0 @@
-# -*- coding: utf-8 -*-
-
-# Copyright 2014 Fanficdownloader team, 2015 FanFicFare team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-#
-
-import time
-import logging
-logger = logging.getLogger(__name__)
-import re
-import urllib2
-import urlparse
-import time
-
-from bs4.element import Tag, Comment
-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 = self.make_soup(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, 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()
-        # 11. April 2015 - 17:08
-        date = re.sub(r"(\d+\. \D+ \d+ - \d+:\d+).*", r"\1", 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 = self.make_soup(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) != 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 = self.make_soup(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) != 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, unicode(int(curChap) + 1), nextLink)
-                    else:
-                        break
-            try:
-                data = self._fetchUrl(nextLink)
-                soup = self.make_soup(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, 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, unicode(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] = self.make_soup(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, unicode(i), self.url)
-            nextChapterTitle = re.sub("1", unicode(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 = self.make_soup(data1)
-            #strip comments from soup
-            [comment.extract() for comment in soup.findAll(text=lambda text:isinstance(text, Comment))]
-
-        # get story text
-        storyDiv1 = soup.new_tag("div")
-        for para in soup.find("div", "full-node").find('div', 'content').findAll("p"):
-            storyDiv1.append(para)
-        storyDiv1.append(soup.new_tag("br"))
-        storytext = self.utf8FromSoup(url,storyDiv1)
-
-        return storytext
-
-
-def getClass():
-    return BdsmGeschichtenAdapter

fanficfare/adapters/adapter_bloodshedversecom.py

@@ -28,7 +28,7 @@ class BloodshedverseComAdapter(BaseSiteAdapter):
     READ_URL_TEMPLATE = BASE_URL + 'stories.php?go=read&no=%s'
 
     STARTED_DATETIME_FORMAT = '%m/%d/%Y'
-    UPDATED_DATETIME_FORMAT = '%m/%d/%Y %I:%M'
+    UPDATED_DATETIME_FORMAT = '%m/%d/%Y %I:%M %p'
 
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
@@ -168,14 +168,8 @@ class BloodshedverseComAdapter(BaseSiteAdapter):
                     self.story.setMetadata('datePublished', makeDate(value, self.STARTED_DATETIME_FORMAT))
 
                 elif key == 'Updated':
-                    date_string, period = value.rsplit(' ', 1)
+                    date = makeDate(value, self.UPDATED_DATETIME_FORMAT)
-                    date = makeDate(date_string, self.UPDATED_DATETIME_FORMAT)
+                    # ugly %p(am/pm) hack moved into makeDate so other sites can use it.
-
-                    # Rather ugly hack to work around Calibre's changing of
-                    # Python's locale setting, causing am/pm to not be properly
-                    # parsed by strptime() when using a non-english locale
-                    if period == 'pm':
-                        date += timedelta(hours=12)
                     self.story.setMetadata('dateUpdated', date)
 
         if self.story.getMetadata('rating') == 'NC-17' and not (self.is_adult or self.getConfig('is_adult')):

fanficfare/adapters/adapter_buffynfaithnet.py

@@ -1,292 +0,0 @@
-# -*- coding: utf-8 -*-
-
-# Copyright 2013 Fanficdownloader team, 2015 FanFicFare team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-#
-
-import time
-import logging
-logger = logging.getLogger(__name__)
-import re
-import urllib2
-import cookielib as cl
-
-
-from ..htmlcleanup import stripHTML
-from .. import exceptions as exceptions
-
-from base_adapter import BaseSiteAdapter,  makeDate
-
-
-# This function is called by the downloader in all adapter_*.py files
-# in this dir to register the adapter class.  So it needs to be
-# updated to reflect the class below it.  That, plus getSiteDomain()
-# take care of 'Registering'.
-def getClass():
-    return BuffyNFaithNetAdapter
-
-# Class name has to be unique.  Our convention is camel case the
-# sitename with Adapter at the end.  www is skipped.
-class BuffyNFaithNetAdapter(BaseSiteAdapter):
-
-    def __init__(self, config, url):
-        BaseSiteAdapter.__init__(self, config, url)
-
-        self.setHeader()
-
-        self.decode = ["Windows-1252",
-                       "utf8"] # 1252 is a superset of iso-8859-1.
-                               # Most sites that claim to be
-                               # iso-8859-1 (and some that claim to be
-                               # utf8) are really windows-1252.
-        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
-        self.password = ""
-        self.is_adult=False
-
-        # get storyId from url--url validation guarantees query correct
-        m = re.match(self.getSiteURLPattern(),url)
-        if m:
-            self.story.setMetadata('storyId',m.group('id'))
-
-            # normalized story URL. gets rid of chapter if there, left with ch 1 URL on this site
-            nurl = "http://"+self.getSiteDomain()+"/fanfictions/index.php?act=vie&id="+self.story.getMetadata('storyId')
-            self._setURL(nurl)
-        else:
-            raise exceptions.InvalidStoryURL(url,
-                                             self.getSiteDomain(),
-                                             self.getSiteExampleURLs())
-
-
-        # Each adapter needs to have a unique site abbreviation.
-        self.story.setMetadata('siteabbrev','bnfnet')
-
-    @staticmethod # must be @staticmethod, don't remove it.
-    def getSiteDomain():
-        # The site domain.  Does have www here, if it uses it.
-        return 'buffynfaith.net'
-
-    @classmethod
-    def stripURLParameters(cls,url):
-        "Only needs to be overriden if URL contains more than one parameter"
-        ## This adapter needs at least two parameters left on the URL, act and id
-        return re.sub(r"(\?act=(vie|ovr)&id=\d+)&.*$",r"\1",url)
-
-    def setHeader(self):
-        "buffynfaith.net wants a Referer for images.  Used both above and below(after cookieproc added)"
-        self.opener.addheaders.append(('Referer', 'http://'+self.getSiteDomain()+'/'))
-
-    @classmethod
-    def getSiteExampleURLs(cls):
-        return "http://"+cls.getSiteDomain()+"/fanfictions/index.php?act=vie&id=1234 http://"+cls.getSiteDomain()+"/fanfictions/index.php?act=ovr&id=1234 http://"+cls.getSiteDomain()+"/fanfictions/index.php?act=vie&id=1234&ch=2"
-
-    def getSiteURLPattern(self):
-        #http://buffynfaith.net/fanfictions/index.php?act=vie&id=963
-        #http://buffynfaith.net/fanfictions/index.php?act=vie&id=949
-        #http://buffynfaith.net/fanfictions/index.php?act=vie&id=949&ch=2
-        p = re.escape("http://"+self.getSiteDomain()+"/fanfictions/index.php?act=")+\
-            r"(vie|ovr)&id=(?P<id>\d+)(&ch=(?P<ch>\d+))?$"
-        return p
-
-    def use_pagecache(self):
-        '''
-        adapters that will work with the page cache need to implement
-        this and change it to True.
-        '''
-        return True
-
-    def extractChapterUrlsAndMetadata(self):
-
-        dateformat = "%d %B %Y"
-        url = self.url
-        logger.debug("URL: "+url)
-
-        #set a cookie to get past adult check
-        if self.is_adult or self.getConfig("is_adult"):
-            cookie = cl.Cookie(version=0, name='my_age', value='yes',
-                               port=None, port_specified=False,
-                               domain=self.getSiteDomain(), domain_specified=False, domain_initial_dot=False,
-                               path='/', path_specified=True,
-                               secure=False,
-                               expires=time.time()+10000,
-                               discard=False,
-                               comment=None,
-                               comment_url=None,
-                               rest={'HttpOnly': None},
-                               rfc2109=False)
-            self.get_cookiejar().set_cookie(cookie)
-            self.setHeader()
-
-        try:
-            data = self._fetchUrl(url)
-        except urllib2.HTTPError, e:
-            if e.code == 404:
-                raise exceptions.StoryDoesNotExist(self.url)
-            else:
-                raise e
-
-        #print data
-
-        if "ADULT CONTENT WARNING" in data:
-            raise exceptions.AdultCheckRequired(self.url)
-
-        # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = self.make_soup(data)
-
-        # Now go hunting for all the meta data and the chapter list.
-
-        #stuff in <head>: description
-        svalue = soup.head.find('meta',attrs={'name':'description'})['content']
-        #self.story.setMetadata('description',svalue)
-        self.setDescription(url,svalue)
-
-        #useful stuff in rest of doc, all contained in this:
-        doc = soup.body.find('div', id='my_wrapper')
-
-        #first the site category (more of a genre to me, meh) and title, in this element:
-        mt = doc.find('div',attrs={'class':'maintitle'})
-        self.story.addToList('genre',mt.findAll('a')[1].string)
-        self.story.setMetadata('title',stripHTML(mt).split(u'»')[-1].strip())
-        del mt
-
-        #the actual category, for me, is 'Buffy: The Vampire Slayer'
-        #self.story.addToList('category','Buffy: The Vampire Slayer')
-        #No need to do it here, it is better to set it in in plugin-defaults.ini and defaults.ini
-
-        #then a block that sits in a table cell like so:
-        #(contains a lot of metadata)
-        mblock = doc.find('td', align='left', width = '70%').contents
-        while len(mblock) > 0:
-            i = mblock.pop(0)
-            if 'Author:' in i.string:
-                #drop empty space
-                mblock.pop(0)
-                #get author link
-                a = mblock.pop(0)
-                authre = re.escape('./index.php?act=bio&id=')+'(?P<authid>\d+)'
-                m = re.match(authre,a['href'])
-                self.story.setMetadata('author',a.string)
-                self.story.setMetadata('authorId',m.group('authid'))
-                authurl = u'http://%s/fanfictions/index.php?act=bio&id=%s' % ( self.getSiteDomain(),
-                                            self.story.getMetadata('authorId'))
-                self.story.setMetadata('authorUrl',authurl,condremoveentities=False)
-                #drop empty space
-                mblock.pop(0)
-            if 'Rating:' in i.string:
-                self.story.setMetadata('rating',mblock.pop(0).strip())
-            if 'Published:' in i.string:
-                date = mblock.pop(0).strip()
-                #get rid of 'st', 'nd', 'rd', 'th' after day number
-                date = date[0:2]+date[4:]
-                self.story.setMetadata('datePublished',makeDate(date, dateformat))
-            if 'Last Updated:' in i.string:
-                date = mblock.pop(0).strip()
-                #get rid of 'st', 'nd', 'rd', 'th' after day number
-                date = date[0:2]+date[4:]
-                self.story.setMetadata('dateUpdated',makeDate(date, dateformat))
-            if 'Genre:' in i.string:
-                genres = mblock.pop(0).strip()
-                genres = genres.split('/')
-                for genre in genres: self.story.addToList('genre',genre)
-            #end ifs
-        #end while
-
-        # Find the chapter selector
-        select = soup.find('select', { 'name' : 'ch' } )
-
-        if select is None:
-           # no selector found, so it's a one-chapter story.
-           #self.chapterUrls.append((self.story.getMetadata('title'),url))
-           self.chapterUrls.append((self.story.getMetadata('title'),url))
-        else:
-            allOptions = select.findAll('option')
-            for o in allOptions:
-                url = u'http://%s/fanfictions/index.php?act=vie&id=%s&ch=%s' % ( self.getSiteDomain(),
-                                            self.story.getMetadata('storyId'),
-                                            o['value'])
-                title = u"%s" % o
-                title = stripHTML(title)
-                ts = title.split(' ',1)
-                title = ts[0]+'. '+ts[1]
-                self.chapterUrls.append((title,url))
-        self.story.setMetadata('numChapters',len(self.chapterUrls))
-
-        ## Go scrape the rest of the metadata from the author's page.
-        data = self._fetchUrl(self.story.getMetadata('authorUrl'))
-        soup = self.make_soup(data)
-        #find the story link and its parent div
-        storya = soup.find('a',{'href':self.story.getMetadata('storyUrl')})
-        storydiv = storya.parent
-        #warnings come under a <spawn> tag. Never seen that before...
-        #appears to just be a line of freeform text, not necessarily a list
-        #optional
-        spawn = storydiv.find('spawn',{'id':'warnings'})
-        if spawn is not None:
-            warns = spawn.nextSibling.strip()
-            self.story.addToList('warnings',warns)
-        #some meta in spans - this should get all, even the ones jammed in a table
-        spans = storydiv.findAll('span')
-        for s in spans:
-            if s.string == 'Ship:':
-                list = s.nextSibling.strip().split()
-                self.story.extendList('ships',list)
-            if s.string == 'Characters:':
-                list = s.nextSibling.strip().split(',')
-                self.story.extendList('characters',list)
-            if s.string == 'Status:':
-                st = s.nextSibling.strip()
-                self.story.setMetadata('status',st)
-            if s.string == 'Words:':
-                st = s.nextSibling.strip()
-                self.story.setMetadata('numWords',st)
-
-        #reviews - is this worth having?
-        #ffnet adapter gathers it, don't know if anything else does
-        #or if it's ever going to be used!
-        a = storydiv.find('a',{'id':'bold-blue'})
-        if a:
-            revs = a.nextSibling.strip()[1:-1]
-            self.story.setMetadata('reviews',st)
-        else:
-            revs = '0'
-            self.story.setMetadata('reviews',st)
-
-    # grab the text for an individual chapter.
-    def getChapterText(self, url):
-
-        logger.debug('Getting chapter text from: %s' % url)
-
-        soup = self.make_soup(self._fetchUrl(url))
-
-        div = soup.find('div', {'id' : 'fanfiction'})
-        if None == div:
-            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-
-        #remove all the unnecessary bookmark tags
-        [s.extract() for s in div('div',{'class':"tiny_box2"})]
-
-        #is there a review link?
-        r = div.find('a',href=re.compile(re.escape("./index.php?act=irv")+".*$"))
-        if r is not None:
-        #remove the review link and its parent div
-            r.parent.extract()
-
-        #There might also be a link to the sequel on the last chapter
-        #I'm inclined to keep it in, but the URL needs to be changed from relative to absolute
-        #Shame there isn't proper series metadata available
-        #(I couldn't find it anyway)
-        s = div.find('a',href=re.compile(re.escape("./index.php?act=ovr")+".*$"))
-        if s is not None:
-            s['href'] = 'http://'+self.getSiteDomain()+'/fanfictions'+s['href'][1:]
-
-        return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_deepinmysoulnet.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2012 Fanficdownloader team, 2015 FanFicFare team
+# Copyright 2013 Fanficdownloader team, 2015 FanFicFare team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -29,11 +29,11 @@ from .. import exceptions as exceptions
 from base_adapter import BaseSiteAdapter,  makeDate
 
 def getClass():
-    return GrangerEnchantedCom
+    return DeepInMySoulNetAdapter   ## XXX
 
 # Class name has to be unique.  Our convention is camel case the
 # sitename with Adapter at the end.  www is skipped.
-class GrangerEnchantedCom(BaseSiteAdapter):
+class DeepInMySoulNetAdapter(BaseSiteAdapter):  # XXX
 
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
@@ -50,37 +50,29 @@ class GrangerEnchantedCom(BaseSiteAdapter):
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
 
-        self.section=self.parsedUrl.path.split('/',)[1]
 
         # normalized story URL.
-        if "malfoymanor" in self.parsedUrl.netloc:
+        # XXX Most sites don't have the /fiction part.  Replace all to remove it usually.
-            self._setURL('http://malfoymanor.' + self.getSiteDomain() + '/themanor/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        self._setURL('http://' + self.getSiteDomain() + '/fiction/viewstory.php?sid='+self.story.getMetadata('storyId'))
-            self.story.addToList("category","The Manor")
-        else:
-            self._setURL('http://' + self.getSiteDomain() + '/enchant/viewstory.php?sid='+self.story.getMetadata('storyId'))
 
         # Each adapter needs to have a unique site abbreviation.
-        self.story.setMetadata('siteabbrev','gech')
+        self.story.setMetadata('siteabbrev','dimsn')  ## XXX
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = "%d/%b/%Y"
+        self.dateformat = "%B %d, %Y"
 
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
-        return 'grangerenchanted.com'
+        return 'www.deepinmysoul.net'  # XXX
-
-    @classmethod
-    def getAcceptDomains(cls):
-        return ['grangerenchanted.com','malfoymanor.grangerenchanted.com']
 
     @classmethod
     def getSiteExampleURLs(cls):
-        return "http://grangerenchanted.com/enchant/viewstory.php?sid=1234 http://malfoymanor.grangerenchanted.com/themanor/viewstory.php?sid=1234"
+        return "http://"+cls.getSiteDomain()+"/fiction/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
-        return r"http://(malfoymanor.)?grangerenchanted.com/(enchant|themanor)?/viewstory.php\?sid=\d+$"
+        return re.escape("http://"+self.getSiteDomain()+"/fiction/viewstory.php?sid=")+r"\d+$"
 
     ## Login seems to be reasonably standard across eFiction sites.
     def needToLoginCheck(self, data):
@@ -103,10 +95,7 @@ class GrangerEnchantedCom(BaseSiteAdapter):
         params['cookiecheck'] = '1'
         params['submit'] = 'Submit'
 
-        if "enchant" in self.section:
+        loginUrl = 'http://' + self.getSiteDomain() + '/fiction/user.php?action=login'
-            loginUrl = 'http://grangerenchanted.com/enchant/user.php?action=login'
-        else:
-            loginUrl = 'http://malfoymanor.grangerenchanted.com/themanor/user.php?action=login'
         logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
                                                               params['penname']))
 
@@ -128,13 +117,13 @@ class GrangerEnchantedCom(BaseSiteAdapter):
             # If the title search below fails, there's a good chance
             # you need a different number.  print data at that point
             # and see what the 'click here to continue' url says.
-            addurl = "&ageconsent=ok&warning=1"
+            addurl = "&warning=4"
         else:
             addurl=""
 
         # index=1 makes sure we see the story chapter index.  Some
         # sites skip that for one-chapter stories.
-        url = self.url+addurl
+        url = self.url+'&index=1'+addurl
         logger.debug("URL: "+url)
 
         try:
@@ -150,7 +139,16 @@ class GrangerEnchantedCom(BaseSiteAdapter):
             self.performLogin(url)
             data = self._fetchUrl(url)
 
-        m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
+        # Since the warning text can change by warning level, let's
+        # look for the warning pass url.  ksarchive uses
+        # &warning= -- actually, so do other sites.  Must be an
+        # eFiction book.
+
+        # fiction/viewstory.php?sid=1882&warning=4
+        # fiction/viewstory.php?sid=1654&ageconsent=ok&warning=5
+        #print data
+        m = re.search(r"'fiction/viewstory.php\?sid=29(&warning=4)'",data)
+        m = re.search(r"'fiction/viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
         if m != None:
             if self.is_adult or self.getConfig("is_adult"):
                 # We tried the default and still got a warning, so
@@ -173,20 +171,22 @@ class GrangerEnchantedCom(BaseSiteAdapter):
                 raise exceptions.AdultCheckRequired(self.url)
 
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
 
         # use BeautifulSoup HTML parser to make everything easier to find.
         soup = self.make_soup(data)
-        # print data
 
         # Now go hunting for all the meta data and the chapter list.
 
+        pagetitle = soup.find('div',{'id':'pagecontent'})
+
         ## Title
-        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+
         self.story.setMetadata('title',stripHTML(a))
 
         # Find authorid and URL from... author url.
-        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
         self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
         self.story.setMetadata('author',a.string)
@@ -194,9 +194,9 @@ class GrangerEnchantedCom(BaseSiteAdapter):
         # Find the chapters:
         for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
             # just in case there's tags, like <i> in chapter titles.
-            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+self.section+'/'+chapter['href']+addurl))
+            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/fiction/'+chapter['href']+addurl))
 
-        self.story.setMetadata('numChapters',len(self.chapterUrls))
+            self.story.setMetadata('numChapters',len(self.chapterUrls))
 
         # eFiction sites don't help us out a lot with their meta data
         # formating, so it's a little ugly.
@@ -217,10 +217,11 @@ class GrangerEnchantedCom(BaseSiteAdapter):
             if 'Summary' in label:
                 ## Everything until the next span class='label'
                 svalue = ""
-                while value and 'label' not in defaultGetattr(value,'class') and '<span class="label">' not in unicode(value):
+                while 'label' not in defaultGetattr(value,'class'):
                     svalue += unicode(value)
                     value = value.nextSibling
                 self.setDescription(url,svalue)
+                #self.story.setMetadata('description',stripHTML(svalue))
 
             if 'Rated' in label:
                 self.story.setMetadata('rating', value)
@@ -228,9 +229,6 @@ class GrangerEnchantedCom(BaseSiteAdapter):
             if 'Word count' in label:
                 self.story.setMetadata('numWords', value)
 
-            if 'Read' in label:
-                self.story.setMetadata('read', value)
-
             if 'Categories' in label:
                 cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
                 for cat in cats:
@@ -242,12 +240,12 @@ class GrangerEnchantedCom(BaseSiteAdapter):
                     self.story.addToList('characters',char.string)
 
             if 'Genre' in label:
-                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=4'))
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
                 for genre in genres:
                     self.story.addToList('genre',genre.string)
 
             if 'Warnings' in label:
-                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2'))
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=3'))
                 for warning in warnings:
                     self.story.addToList('warnings',warning.string)
 
@@ -261,39 +259,31 @@ class GrangerEnchantedCom(BaseSiteAdapter):
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
 
             if 'Updated' in label:
+                # there's a stray [ at the end.
+                #value = value[0:-1]
                 self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
 
         try:
             # Find Series name from series URL.
-            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            a = soup.find('a', href=re.compile(r"fiction/viewseries.php\?seriesid=\d+"))
             series_name = a.string
-            series_url = 'http://'+self.host+'/'+self.section+'/'+a['href']
+            series_url = 'http://'+self.host+'/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
             seriessoup = self.make_soup(self._fetchUrl(series_url))
-            # can't use ^viewstory...$ in case of higher rated stories with javascript href.
+            storyas = seriessoup.findAll('a', href=re.compile(r'^fiction/viewstory.php\?sid=\d+$'))
-            storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+'))
             i=1
             for a in storyas:
-                # skip 'report this' and 'TOC' links
+                if a['href'] == ('fiction/viewstory.php?sid='+self.story.getMetadata('storyId')):
-                if 'contact.php' not in a['href'] and 'index' not in a['href']:
+                    self.setSeries(series_name, i)
-                    if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                    self.story.setMetadata('seriesUrl',series_url)
-                        self.setSeries(series_name, i)
+                    break
-                        self.story.setMetadata('seriesUrl',series_url)
+                i+=1
-                        break
+
-                    i+=1
         except:
             # I find it hard to care if the series parsing fails
             pass
-
+        
-        try:
-            self.story.setMetadata('reviews',
-                                   stripHTML(soup.find('div',{'id':'sort'}).
-                                             findAll('a', href=re.compile(r'^reviews.php'))[1]))
-        except:
-            # I find it hard to care if the series parsing fails
-            pass
-
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
@@ -301,9 +291,10 @@ class GrangerEnchantedCom(BaseSiteAdapter):
 
         soup = self.make_soup(self._fetchUrl(url))
 
-        div = soup.find('div', {'id' : 'story1'})
+        div = soup.find('div', {'id' : 'story'})
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
 
         return self.utf8FromSoup(url,div)
+

fanficfare/adapters/adapter_fanfictionlucifaelcom.py

@@ -0,0 +1,36 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2015 FanFicFare team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+# Software: eFiction
+from base_efiction_adapter import BaseEfictionAdapter
+
+class FanfictionLucifaelComAdapter(BaseEfictionAdapter):
+
+    @staticmethod
+    def getSiteDomain():
+        return 'fanfiction.lucifael.com'
+
+    @classmethod
+    def getSiteAbbrev(self):
+        return 'luci'
+
+    @classmethod
+    def getDateFormat(self):
+        return "%d/%m/%Y"
+
+def getClass():
+    return FanfictionLucifaelComAdapter

fanficfare/adapters/adapter_fanfictionnet.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
+# Copyright 2011 Fanficdownloader team, 2016 FanFicFare team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -15,14 +15,12 @@
 # limitations under the License.
 #
 
-import time
 from datetime import datetime
 import logging
 logger = logging.getLogger(__name__)
 import re
 import urllib2
 from urllib import unquote_plus
-import time
 
 from .. import exceptions as exceptions
 from ..htmlcleanup import stripHTML
@@ -170,9 +168,11 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         elif 'Crossover' in categories[0]['href']:
             caturl = "https://%s%s"%(self.getSiteDomain(),categories[0]['href'])
             catsoup = self.make_soup(self._fetchUrl(caturl))
+            found = False
             for a in catsoup.findAll('a',href=re.compile(r"^/crossovers/.+?/\d+/")):
                 self.story.addToList('category',stripHTML(a))
-            else:
+                found = True
+            if not found:
                 # Fall back.  I ran across a story with a Crossver
                 # category link to a broken page once.
                 # http://www.fanfiction.net/s/2622060/1/
@@ -181,8 +181,6 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
                 for c in stripHTML(categories[0]).replace(" Crossover","").split(' + '):
                     self.story.addToList('category',c)
 
-
-
         a = soup.find('a', href=re.compile(r'https?://www\.fictionratings\.com/'))
         rating = a.string
         if 'Fiction' in rating: # if rating has 'Fiction ', strip that out for consistency with past.
@@ -206,6 +204,12 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         #     b.extract()
         metatext = stripHTML(grayspan).replace('Hurt/Comfort','Hurt-Comfort')
         #logger.debug("metatext:(%s)"%metatext)
+
+        if 'Status: Complete' in metatext:
+            self.story.setMetadata('status', 'Completed')
+        else:
+            self.story.setMetadata('status', 'In-Progress')
+
         metalist = metatext.split(" - ")
         #logger.debug("metalist:(%s)"%metalist)
 
@@ -240,35 +244,43 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
             self.story.setMetadata('dateUpdated',datetime.fromtimestamp(float(dates[0]['data-xutime'])))
         self.story.setMetadata('datePublished',datetime.fromtimestamp(float(dates[-1]['data-xutime'])))
 
-        donechars = False
+        # Meta key titles and the metadata they go into, if any.
+        metakeys = {
+            # These are already handled separately.
+            'Chapters':False,
+            'Status':False,
+            'id':False,
+            'Updated':False,
+            'Published':False,
+            'Reviews':'reviews',
+            'Favs':'favs',
+            'Follows':'follows',
+            'Words':'numWords',
+            }
+
+        chars_ships_list=[]
         while len(metalist) > 0:
-            if  metalist[0].startswith('Chapters') or metalist[0].startswith('Status') or metalist[0].startswith('id:') or metalist[0].startswith('Updated:') or metalist[0].startswith('Published:'):
+            m = metalist.pop(0)
-                pass
+            if ':' in m:
-            elif  metalist[0].startswith('Reviews'):
+                key = m.split(':')[0].strip()
-                self.story.setMetadata('reviews',metalist[0].split(':')[1].strip())
+                if key in metakeys:
-            elif  metalist[0].startswith('Favs:'):
+                    if metakeys[key]:
-                self.story.setMetadata('favs',metalist[0].split(':')[1].strip())
+                        self.story.setMetadata(metakeys[key],m.split(':')[1].strip())
-            elif  metalist[0].startswith('Follows:'):
+                    continue
-                self.story.setMetadata('follows',metalist[0].split(':')[1].strip())
+            # no ':' or not found in metakeys
-            elif  metalist[0].startswith('Words'):
+            chars_ships_list.append(m)
-                self.story.setMetadata('numWords',metalist[0].split(':')[1].strip())
-            elif not donechars:
-                # with 'pairing' support, pairings are bracketed w/o comma after
-                # [Caspian X, Lucy Pevensie] Edmund Pevensie, Peter Pevensie
-                self.story.extendList('characters',metalist[0].replace('[','').replace(']',',').split(','))
 
-                l = metalist[0]
+        # all because sometimes chars can have ' - ' in them.
-                while '[' in l:
+        chars_ships_text = (' - ').join(chars_ships_list)
-                    self.story.addToList('ships',l[l.index('[')+1:l.index(']')].replace(', ','/'))
+        # print("chars_ships_text:%s"%chars_ships_text)
-                    l = l[l.index(']')+1:]
+        # with 'pairing' support, pairings are bracketed w/o comma after
+        # [Caspian X, Lucy Pevensie] Edmund Pevensie, Peter Pevensie
+        self.story.extendList('characters',chars_ships_text.replace('[','').replace(']',',').split(','))
 
-                donechars = True
+        l = chars_ships_text
-            metalist=metalist[1:]
+        while '[' in l:
-
+            self.story.addToList('ships',l[l.index('[')+1:l.index(']')].replace(', ','/'))
-        if 'Status: Complete' in metatext:
+            l = l[l.index(']')+1:]
-            self.story.setMetadata('status', 'Completed')
-        else:
-            self.story.setMetadata('status', 'In-Progress')
 
         if get_cover:
             # Try the larger image first.
@@ -317,7 +329,7 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
 
         # Find the chapter selector
         select = soup.find('select', { 'name' : 'chapter' } )
-    	
+
         if select is None:
     	   # no selector found, so it's a one-chapter story.
     	   self.chapterUrls.append((self.story.getMetadata('title'),url))
@@ -337,36 +349,17 @@ 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.
         logger.debug('Getting chapter text from: %s' % url)
+        ## 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.
         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)
 
-        # some ancient stories have body tags inside them that cause
-        # soup parsing to discard the content.  For story text we
-        # don't care about anything before "<div role='main'" and
-        # this kills any body tags.
-        # XXX needed with new BS? -- No, doesn't look like it
-        # divstr = "<div role='main'"
-        # if divstr not in data:
-        #     raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-        # else:
-        #     data = data[data.index(divstr):]
-        # data = data.replace("<body","<notbody").replace("<BODY","<NOTBODY")
-
         soup = self.make_soup(data)
 
-        ## Remove the 'share' button.
-        ## No longer appears in the story text.
-        # sharediv = soup.find('div', {'class' : 'a2a_kit a2a_default_style'})
-        # if sharediv:
-        #     sharediv.extract()
-
         div = soup.find('div', {'id' : 'storytextp'})
 
         if None == div:

fanficfare/adapters/adapter_ficbooknet.py

@@ -55,7 +55,7 @@ class FicBookNetAdapter(BaseSiteAdapter):
 
 
         # normalized story URL.
-        self._setURL('http://' + self.getSiteDomain() + '/readfic/'+self.story.getMetadata('storyId'))
+        self._setURL('https://' + self.getSiteDomain() + '/readfic/'+self.story.getMetadata('storyId'))
 
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','fbn')
@@ -71,10 +71,10 @@ class FicBookNetAdapter(BaseSiteAdapter):
 
     @classmethod
     def getSiteExampleURLs(cls):
-        return "http://"+cls.getSiteDomain()+"/readfic/12345 http://"+cls.getSiteDomain()+"/readfic/93626/246417#part_content"
+        return "https://"+cls.getSiteDomain()+"/readfic/12345 https://"+cls.getSiteDomain()+"/readfic/93626/246417#part_content"
 
     def getSiteURLPattern(self):
-        return re.escape("http://"+self.getSiteDomain()+"/readfic/")+r"\d+"
+        return r"https?://"+re.escape(self.getSiteDomain()+"/readfic/")+r"\d+"
 
     ## Getting the chapter list and the meta data, plus 'is adult' checking.
     def extractChapterUrlsAndMetadata(self):
@@ -92,39 +92,51 @@ class FicBookNetAdapter(BaseSiteAdapter):
         # use BeautifulSoup HTML parser to make everything easier to find.
         soup = self.make_soup(data)
 
+        adult_div = soup.find('div',id='adultCoverWarning')
+        if adult_div:
+            if self.is_adult or self.getConfig("is_adult"):
+                adult_div.extract()
+            else:
+                raise exceptions.AdultCheckRequired(self.url)
+        
         # Now go hunting for all the meta data and the chapter list.
 		
-        table = soup.find('td',{'width':'50%'})
-
         ## Title
-        a = soup.find('h1')
+        a = soup.find('section',{'class':'chapter-info'}).find('h1')
+        # kill '+' marks if present.
+        sup = a.find('sup')
+        if sup:
+            sup.extract()
         self.story.setMetadata('title',stripHTML(a))
         logger.debug("Title: (%s)"%self.story.getMetadata('title'))
 
         # Find authorid and URL from... author url.
-        a = table.find('a')
+        # assume first avatar-nickname -- there can be a second marked 'beta'.
+        a = soup.find('a',{'class':'avatar-nickname'})
         self.story.setMetadata('authorId',a.text) # Author's name is unique
-        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('authorUrl','https://'+self.host+'/'+a['href'])
         self.story.setMetadata('author',a.text)
         logger.debug("Author: (%s)"%self.story.getMetadata('author'))
 
         # Find the chapters:
-        chapters = soup.find('div', {'class' : 'part_list'})
+        chapters = soup.find('ul', {'class' : 'table-of-contents'})
         if chapters != None:
             chapters=chapters.findAll('a', href=re.compile(r'/readfic/'+self.story.getMetadata('storyId')+"/\d+#part_content$"))
             self.story.setMetadata('numChapters',len(chapters))
             for x in range(0,len(chapters)):
                 chapter=chapters[x]
-                churl='http://'+self.host+chapter['href']
+                churl='https://'+self.host+chapter['href']
                 self.chapterUrls.append((stripHTML(chapter),churl))
                 if x == 0:
-                    pubdate = translit.translit(stripHTML(self.make_soup(self._fetchUrl(churl)).find('div', {'class' : 'part_added'}).find('span')))
+                    pubdate = translit.translit(stripHTML(chapter.parent.find('span')))
+                    # pubdate = translit.translit(stripHTML(self.make_soup(self._fetchUrl(churl)).find('div', {'class' : 'part_added'}).find('span')))
                 if x == len(chapters)-1:
-                    update = translit.translit(stripHTML(self.make_soup(self._fetchUrl(churl)).find('div', {'class' : 'part_added'}).find('span')))
+                    update = translit.translit(stripHTML(chapter.parent.find('span')))
+                    # update = translit.translit(stripHTML(self.make_soup(self._fetchUrl(churl)).find('div', {'class' : 'part_added'}).find('span')))
         else:
             self.chapterUrls.append((self.story.getMetadata('title'),url))
             self.story.setMetadata('numChapters',1)
-            pubdate=translit.translit(stripHTML(soup.find('div', {'class' : 'part_added'}).find('span')))
+            pubdate=translit.translit(stripHTML(soup.find('div',{'class':'title-area'}).find('span')))
             update=pubdate
 
         logger.debug("numChapters: (%s)"%self.story.getMetadata('numChapters'))
@@ -158,54 +170,63 @@ class FicBookNetAdapter(BaseSiteAdapter):
         self.story.setMetadata('dateUpdated', makeDate(update, self.dateformat))
         self.story.setMetadata('datePublished', makeDate(pubdate, self.dateformat))
         self.story.setMetadata('language','Russian')
-		
+
-        pr=soup.find('a', href=re.compile(r'/printfic/\w+'))
+        ## after site change, I don't see word count anywhere.
-        pr='http://'+self.host+pr['href']
+        # pr=soup.find('a', href=re.compile(r'/printfic/\w+'))
-        pr = self.make_soup(self._fetchUrl(pr))
+        # pr='https://'+self.host+pr['href']
-        pr=pr.findAll('div', {'class' : 'part_text'})
+        # pr = self.make_soup(self._fetchUrl(pr))
+        # pr=pr.findAll('div', {'class' : 'part_text'})
+        # i=0
+        # for part in pr:
+        #     i=i+len(stripHTML(part).split(' '))
+        # self.story.setMetadata('numWords', unicode(i))
+
+
+        dlinfo = soup.find('dl',{'class':'info'})
+        
         i=0
-        for part in pr:
+        fandoms = dlinfo.find('dd').findAll('a', href=re.compile(r'/fanfiction/\w+'))
-            i=i+len(stripHTML(part).split(' '))
-        self.story.setMetadata('numWords', unicode(i))
-		
-        i=0
-        fandoms = table.findAll('a', href=re.compile(r'/fanfiction/\w+'))
         for fandom in fandoms:
             self.story.addToList('category',fandom.string)
             i=i+1
         if i > 1:
             self.story.addToList('genre', u'Кроссовер')
-		
-        meta=table.findAll('a', href=re.compile(r'/ratings/'))
-        i=0
-        for m in meta:
-            if i == 0:
-                self.story.setMetadata('rating', stripHTML(m))
-                i=1
-            elif i == 1:
-                if not "," in m.nextSibling:
-                    i=2
-                self.story.addToList('genre', m.find('b').text)
-            elif i == 2:
-                self.story.addToList('warnings', m.find('b').text)
-		
 
-        if table.find('span', {'style' : 'color: green'}):
+        for genre in dlinfo.findAll('a',href=re.compile(r'/genres/')):
+            self.story.addToList('genre',stripHTML(genre))
+
+        ratingdt = dlinfo.find('dt',text='Рейтинг:')
+        self.story.setMetadata('rating', stripHTML(ratingdt.next_sibling))
+            
+        # meta=table.findAll('a', href=re.compile(r'/ratings/'))
+        # i=0
+        # for m in meta:
+        #     if i == 0:
+        #         self.story.setMetadata('rating', stripHTML(m))
+        #         i=1
+        #     elif i == 1:
+        #         if not "," in m.nextSibling:
+        #             i=2
+        #         self.story.addToList('genre', m.find('b').text)
+        #     elif i == 2:
+        #         self.story.addToList('warnings', m.find('b').text)		
+
+        if dlinfo.find('span', {'style' : 'color: green'}):
             self.story.setMetadata('status', 'Completed')
         else:
             self.story.setMetadata('status', 'In-Progress')
 		
 
-        tags = table.findAll('b')
+        tags = dlinfo.findAll('dt')
         for tag in tags:
             label = translit.translit(tag.text)
             if 'Piersonazhi:' in label or u'Персонажи:' in label:
-                chars=tag.nextSibling.string.split(', ')
+                chars=stripHTML(tag.next_sibling).split(', ')
                 for char in chars:
                     self.story.addToList('characters',char)
                 break
 				
-        summary=soup.find('span', {'class' : 'urlize'})
+        summary=soup.find('div', {'class' : 'urlize'})
         self.setDescription(url,summary)
         #self.story.setMetadata('description', summary.text)
 

fanficfare/adapters/adapter_fictionhuntcom.py

@@ -0,0 +1,147 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2016 FanFicFare team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import logging
+logger = logging.getLogger(__name__)
+import re
+import urllib2
+
+from .. import exceptions as exceptions
+from ..htmlcleanup import stripHTML
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+class FictionHuntComSiteAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+        self.story.setMetadata('siteabbrev','fichunt')
+
+        # get storyId from url--url validation guarantees second part is storyId
+        self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2])
+
+        # normalized story URL.
+        self._setURL("http://"+self.getSiteDomain()\
+                         +"/read/"+self.story.getMetadata('storyId')+"/1")
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%d-%m-%Y"
+
+    @staticmethod
+    def getSiteDomain():
+        return 'fictionhunt.com'
+
+    @classmethod
+    def getSiteExampleURLs(cls):
+        return "http://fictionhunt.com/read/1234/1"
+
+    def getSiteURLPattern(self):
+        return r"http://(www.)?fictionhunt.com/read/\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
+
+    def doExtractChapterUrlsAndMetadata(self,get_cover=True):
+
+        # fetch the chapter.  From that we will get almost all the
+        # metadata and chapter list
+
+        url = self.url
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.meta)
+            else:
+                raise e
+
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = self.make_soup(data)
+
+        self.story.setMetadata('title',stripHTML(soup.find('div',{'class':'title'})).strip())
+
+        self.setDescription(url,'<i>(Story descriptions not available on fictionhunt.com)</i>')
+
+        # Find authorid and URL from... author url.
+        # fictionhunt doesn't have author pages, use ffnet original author link.
+        a = soup.find('a', href=re.compile(r"fanfiction.net/u/\d+"))
+        self.story.setMetadata('authorId',a['href'].split('/')[-1])
+        self.story.setMetadata('authorUrl','https://www.fanfiction.net/u/'+self.story.getMetadata('authorId'))
+        self.story.setMetadata('author',a.string)
+
+        # Find original ffnet URL
+        a = soup.find('a', href=re.compile(r"fanfiction.net/s/\d+"))
+        self.story.setMetadata('origin',stripHTML(a))
+        self.story.setMetadata('originUrl',a['href'])
+
+        # Fleur D. & Harry P. & Hermione G. & Susan B. - Words: 42,848 - Rated: M - English - None - Chapters: 9 - Reviews: 248 - Updated: 21-09-2016 - Published: 16-05-2015 - by Elven Sorcerer (FFN)
+        # None - Words: 13,087 - Rated: M - English - Romance & Supernatural - Chapters: 3 - Reviews: 5 - Updated: 21-09-2016 - Published: 20-09-2016
+        # Harry P. & OC - Words: 10,910 - Rated: M - English - None - Chapters: 5 - Reviews: 6 - Updated: 21-09-2016 - Published: 11-09-2016
+        # Dudley D. & Harry P. & Nagini & Vernon D. - Words: 4,328 - Rated: K+ - English - None - Chapters: 2 - Updated: 21-09-2016 - Published: 20-09-2016 -
+        details = soup.find('div',{'class':'details'})
+
+        detail_re = \
+            r'(?P<characters>.+) - Words: (?P<numWords>[0-9,]+) - Rated: (?P<rating>[a-zA-Z\\+]+) - (?P<language>.+) - (?P<genre>.+)'+ \
+            r' - Chapters: (?P<numChapters>[0-9,]+)( - Reviews: (?P<reviews>[0-9,]+))? - Updated: (?P<dateUpdated>[0-9-]+)'+ \
+            r' - Published: (?P<datePublished>[0-9-]+)(?P<completed> - Complete)?'
+
+        details_dict = re.match(detail_re,stripHTML(details)).groupdict()
+
+        # lists
+        for meta in ('characters','genre'):
+            if details_dict[meta] != 'None':
+                self.story.extendList(meta,details_dict[meta].split(' & '))
+
+        # scalars
+        for meta in ('numWords','numChapters','rating','language','reviews'):
+            self.story.setMetadata(meta,details_dict[meta])
+
+        # dates
+        for meta in ('datePublished','dateUpdated'):
+            self.story.setMetadata(meta, makeDate(details_dict[meta], self.dateformat))
+
+        # status
+        if details_dict['completed']:
+            self.story.setMetadata('status', 'Completed')
+        else:
+            self.story.setMetadata('status', 'In-Progress')
+
+        # It's assumed that the number of chapters is correct.
+        # There's no complete list of chapters, so the only
+        # alternative is to get the num of chaps from the last
+        # indiated chapter list instead.
+        for i in range(1,1+int(self.story.getMetadata('numChapters'))):
+            self.chapterUrls.append(("Chapter "+unicode(i),"http://"+self.getSiteDomain()\
+                                         +"/read/"+self.story.getMetadata('storyId')+"/%s"%i))
+
+    def getChapterText(self, url):
+        logger.debug('Getting chapter text from: %s' % url)
+        data = self._fetchUrl(url)
+
+        soup = self.make_soup(data)
+
+        div = soup.find('div', {'class' : 'text'})
+
+        return self.utf8FromSoup(url,div)
+
+def getClass():
+    return FictionHuntComSiteAdapter

fanficfare/adapters/adapter_fictionmaniatv.py

@@ -117,7 +117,7 @@ class FictionManiaTVAdapter(BaseSiteAdapter):
                 self.story.setMetadata('rating', value)
 
             elif key == 'Complete':
-                self.story.setMetadata('status', 'Complete' if value == 'Complete' else 'In-Progress')
+                self.story.setMetadata('status', 'Completed' if value == 'Complete' else 'In-Progress')
 
             elif key == 'Categories':
                 for element in cells[1]('a'):

fanficfare/adapters/adapter_ficwadcom.py

@@ -93,7 +93,7 @@ class FicwadComSiteAdapter(BaseSiteAdapter):
         try:
             data = self._fetchUrl(url)
             # non-existent/removed story urls get thrown to the front page.
-            if "<h2>Welcome to FicWad</h2>" in data:
+            if "<h4>Featured Story</h4>" in data:
                 raise exceptions.StoryDoesNotExist(self.url)
             soup = self.make_soup(data)
         except urllib2.HTTPError, e:

fanficfare/adapters/adapter_forumquestionablequestingcom.py

@@ -14,7 +14,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 #
-import re
 
 from base_xenforoforum_adapter import BaseXenForoForumAdapter
 

fanficfare/adapters/adapter_haremlucifaelcom.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2016 FanFicFare team
+# Copyright 2015 FanFicFare team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -18,19 +18,19 @@
 # Software: eFiction
 from base_efiction_adapter import BaseEfictionAdapter
 
-class RabidReaderComAdapter(BaseEfictionAdapter):
+class HaremLucifaelComAdapter(BaseEfictionAdapter):
 
     @staticmethod
     def getSiteDomain():
-        return 'www.therabidreader.com'
+        return 'harem.lucifael.com'
 
     @classmethod
     def getSiteAbbrev(self):
-        return 'rrcom'
+        return 'seraglio'
 
     @classmethod
     def getDateFormat(self):
-        return "%d %b %Y"
+        return "%d/%m/%Y"
 
 def getClass():
-    return RabidReaderComAdapter
+    return HaremLucifaelComAdapter

fanficfare/adapters/adapter_harrypotterfanfictioncom.py

@@ -188,9 +188,13 @@ class HarryPotterFanFictionComSiteAdapter(BaseSiteAdapter):
 
         data = self._fetchUrl(url)
 
-        # remove everything after here--the site's chapters break the
+        try:
-        # BS4 parser.
+            # remove everything after here--the site's chapters break
-        data = data[:data.index('<script type="text/javascript" src="reviewjs.js">')]
+            # the BS4 parser.
+            data = data[:data.index('<script type="text/javascript" src="reviewjs.js">')]
+        except:
+            # some older stories don't have the code at the end that breaks things.
+            pass
         
         soup = self.make_soup(data)
 

fanficfare/adapters/adapter_kiarepositorymujajinet.py

@@ -29,11 +29,11 @@ from .. import exceptions as exceptions
 from base_adapter import BaseSiteAdapter,  makeDate
 
 def getClass():
-    return ScarHeadNetAdapter
+    return KiaRepositoryMujajiNetAdapter   ## XXX
 
 # Class name has to be unique.  Our convention is camel case the
 # sitename with Adapter at the end.  www is skipped.
-class ScarHeadNetAdapter(BaseSiteAdapter):
+class KiaRepositoryMujajiNetAdapter(BaseSiteAdapter):  # XXX
 
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
@@ -52,26 +52,27 @@ class ScarHeadNetAdapter(BaseSiteAdapter):
 
 
         # normalized story URL.
-        self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        # XXX Most sites don't have the /fiction part.  Replace all to remove it usually.
+        self._setURL('http://' + self.getSiteDomain() + '/repository/viewstory.php?sid='+self.story.getMetadata('storyId'))
 
         # Each adapter needs to have a unique site abbreviation.
-        self.story.setMetadata('siteabbrev','shn')
+        self.story.setMetadata('siteabbrev','kia')  ## XXX
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = "%d/%m/%y"
+        self.dateformat = "%d %b %Y"   ## XXX
 
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
-        return 'scarhead.net'
+        return 'mujaji.net'  # XXX
 
     @classmethod
     def getSiteExampleURLs(cls):
-        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
+        return "http://"+cls.getSiteDomain()+"/repository/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
-        return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
+        return re.escape("http://"+self.getSiteDomain()+"/repository/viewstory.php?sid=")+r"\d+$"
 
     ## Login seems to be reasonably standard across eFiction sites.
     def needToLoginCheck(self, data):
@@ -94,7 +95,7 @@ class ScarHeadNetAdapter(BaseSiteAdapter):
         params['cookiecheck'] = '1'
         params['submit'] = 'Submit'
 
-        loginUrl = 'http://' + self.getSiteDomain() + '/user.php?action=login'
+        loginUrl = 'http://' + self.getSiteDomain() + '/repository/user.php?action=login'
         logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
                                                               params['penname']))
 
@@ -116,7 +117,7 @@ class ScarHeadNetAdapter(BaseSiteAdapter):
             # If the title search below fails, there's a good chance
             # you need a different number.  print data at that point
             # and see what the 'click here to continue' url says.
-            addurl = "&ageconsent=ok&warning=5"
+            addurl = "&warning=4"
         else:
             addurl=""
 
@@ -143,11 +144,11 @@ class ScarHeadNetAdapter(BaseSiteAdapter):
         # &warning= -- actually, so do other sites.  Must be an
         # eFiction book.
 
-        # viewstory.php?sid=1882&warning=4
+        # fiction/viewstory.php?sid=1882&warning=4
-        # viewstory.php?sid=1654&ageconsent=ok&warning=5
+        # fiction/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"'repository/viewstory.php\?sid=29(&warning=4)'",data)
-        m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
+        m = re.search(r"'repository/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
@@ -170,18 +171,18 @@ class ScarHeadNetAdapter(BaseSiteAdapter):
                 raise exceptions.AdultCheckRequired(self.url)
 
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
 
         # use BeautifulSoup HTML parser to make everything easier to find.
         soup = self.make_soup(data)
-        # print data
 
         # Now go hunting for all the meta data and the chapter list.
 
-        pagetitle = soup.find('tr',{'valign':'top'})
+        pagetitle = soup.find('div',{'id':'pagetitle'})
 
         ## Title
         a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+
         self.story.setMetadata('title',stripHTML(a))
 
         # Find authorid and URL from... author url.
@@ -193,88 +194,87 @@ class ScarHeadNetAdapter(BaseSiteAdapter):
         # Find the chapters:
         for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
             # just in case there's tags, like <i> in chapter titles.
-            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']+addurl))
+            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/repository/'+chapter['href']+addurl))
 
-        self.story.setMetadata('numChapters',len(self.chapterUrls))
+            self.story.setMetadata('numChapters',len(self.chapterUrls))
 
         # eFiction sites don't help us out a lot with their meta data
         # formating, so it's a little ugly.
 
-        cats = soup.findAll('a',href=re.compile(r'browse.php\?type=categories'))
+        # utility method
-        for cat in cats:
+        def defaultGetattr(d,k):
-            if '/' == cat.string[0]:
-                self.story.addToList('ships','Harry Potter'+cat.string.split('(')[0])
-            elif 'Harry' in cat.string:
-                self.story.addToList('ships',cat.string.split('(')[0])
-            else:
-                self.story.addToList('category',cat.string)
-            if '(' in cat.string:
-                self.story.addToList('category',cat.string.split('(')[1].split(')')[0])
-
-
-
-
-        chars = soup.findAll('a',href=re.compile(r'browse.php\?type=characters'))
-        for char in chars:
-            self.story.addToList('characters',char.string)
-
-        genres = soup.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2'))
-        for genre in genres:
-            self.story.addToList('genre',genre.string)
-
-        warnings = soup.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
-        for warning in warnings:
-            self.story.addToList('warnings',warning.string)
-
-        textsoup = stripHTML(soup)
-
-        a = textsoup.split('Published: ')[1].split(' ')[0]
-        self.story.setMetadata('datePublished', makeDate(stripHTML(a), self.dateformat))
-        a = textsoup.split('Updated: ')[1].split(' ')[0]
-        self.story.setMetadata('dateUpdated', makeDate(stripHTML(a), self.dateformat))
-        a = textsoup.split('Rating: ')[1].split(' ')[0]
-        self.story.setMetadata('rating', a)
-        a = textsoup.split('Length: ')[1].split('(')[1].split(' ')[0]
-        self.story.setMetadata('numWords', a)
-        a = textsoup.split('Completed: ')[1].split(' ')[0]
-        if 'Yes' in a:
-            self.story.setMetadata('status', 'Completed')
-        else:
-            self.story.setMetadata('status', 'In-Progress')
-        #a = textsoup.split('Summary: ')[1].split('Add Story to Favorites')[0]
-        #self.setDescription(url,a)
-
-
-
-        a=soup.find(text=re.compile("Summary: "))
-        i=0
-        svalue = ""
-        while i == 0:
             try:
-                b = unicode(a)
+                return d[k]
-                svalue += b.split('Summary: ')[1]
             except:
-                svalue += unicode(a)
+                return ""
-            if a.nextSibling != None:
+
-                a = a.nextSibling
+        # <span class="label">Rated:</span> NC-17<br /> etc
-            else:
+        labels = soup.findAll('span',{'class':'label'})
-                a = a.parent.nextSibling
+        for labelspan in labels:
-            if 'Disclaimer: ' in stripHTML(a):
+            value = labelspan.nextSibling
-                i=1
+            label = labelspan.string
-        self.setDescription(url,svalue)
+
+            if 'Summary' in label:
+                ## Everything until the next span class='label'
+                svalue = ""
+                while 'label' not in defaultGetattr(value,'class'):
+                    svalue += unicode(value)
+                    value = value.nextSibling
+                self.setDescription(url,svalue)
+                #self.story.setMetadata('description',stripHTML(svalue))
+
+            if 'Rated' in label:
+                self.story.setMetadata('rating', value)
+
+            if 'Word count' in label:
+                self.story.setMetadata('numWords', value)
+
+            if 'Categories' in label:
+                cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
+                for cat in cats:
+                    self.story.addToList('category',cat.string)
+
+            if 'Characters' in label:
+                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+                for char in chars:
+                    self.story.addToList('characters',char.string)
+
+            if 'Genre' in label:
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
+                for genre in genres:
+                    self.story.addToList('genre',genre.string)
+
+            if 'Warnings' in label:
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=3'))
+                for warning in warnings:
+                    self.story.addToList('warnings',warning.string)
+
+            if 'Completed' in label:
+                if 'Yes' in value:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+
+            if 'Published' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+
+            if 'Updated' in label:
+                # there's a stray [ at the end.
+                #value = value[0:-1]
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
 
         try:
             # Find Series name from series URL.
-            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            a = soup.find('a', href=re.compile(r"repository/viewseries.php\?seriesid=\d+"))
             series_name = a.string
             series_url = 'http://'+self.host+'/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
             seriessoup = self.make_soup(self._fetchUrl(series_url))
-            storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^repository/viewstory.php\?sid=\d+$'))
             i=1
             for a in storyas:
-                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                if a['href'] == ('repository/viewstory.php?sid='+self.story.getMetadata('storyId')):
                     self.setSeries(series_name, i)
                     self.story.setMetadata('seriesUrl',series_url)
                     break
@@ -283,7 +283,7 @@ class ScarHeadNetAdapter(BaseSiteAdapter):
         except:
             # I find it hard to care if the series parsing fails
             pass
-
+        
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
@@ -297,3 +297,4 @@ class ScarHeadNetAdapter(BaseSiteAdapter):
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
 
         return self.utf8FromSoup(url,div)
+

fanficfare/adapters/adapter_literotica.py

@@ -144,6 +144,9 @@ class LiteroticaSiteAdapter(BaseSiteAdapter):
             else:
                 raise e
 
+        if "This submission is awaiting moderator's approval" in data1:
+            raise exceptions.StoryDoesNotExist("This submission is awaiting moderator's approval. %s"%self.url)
+
         # author
         a = soup1.find("span", "b-story-user-y")
         self.story.setMetadata('authorId', urlparse.parse_qs(a.a['href'].split('?')[1])['uid'][0])

fanficfare/adapters/adapter_masseffect2in.py

@@ -459,7 +459,22 @@ class Chapter(object):
                 .strip(u'| \n')
         except AttributeError:
             raise ParsingError(u'Failed to locate date.')
-        date = makeDate(dateText, '%d.%m.%Y')
+
+        # The site uses Europe/Moscow (MSK, UTC+0300) server time.
+        def todayInMoscow():
+            now = datetime.datetime.now() + datetime.timedelta(hours=3)
+            today = datetime.datetime(now.year, now.month, now.day)
+            return today
+
+        def parseDateText(text):
+            if text == u'Вчера':
+                return todayInMoscow() - datetime.timedelta(days=1)
+            elif text == u'Сегодня':
+                return todayInMoscow()
+            else:
+                return makeDate(text, '%d.%m.%Y')
+
+        date = parseDateText(dateText)
         return date
 
     def _getInfoBarElement(self):

fanficfare/adapters/adapter_ncisfictionnet.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2012 Fanficdownloader team, 2015 FanFicFare team
+# Copyright 2012 Fanficdownloader team, 2016 FanFicFare team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -15,195 +15,22 @@
 # limitations under the License.
 #
 
-import time
+# Software: eFiction
-import logging
+from base_efiction_adapter import BaseEfictionAdapter
-logger = logging.getLogger(__name__)
-import re
-import urllib2
 
+class NCISFictionNetAdapter(BaseEfictionAdapter):
 
-from ..htmlcleanup import stripHTML
+    @staticmethod
-from .. import exceptions as exceptions
+    def getSiteDomain():
+        return 'ncisfiction.net'
 
-from base_adapter import BaseSiteAdapter,  makeDate
+    @classmethod
+    def getSiteAbbrev(self):
+        return 'ncisfn'
+
+    @classmethod
+    def getDateFormat(self):
+        return "%m/%d/%Y"
 
 def getClass():
     return NCISFictionNetAdapter
-
-# Class name has to be unique.  Our convention is camel case the
-# sitename with Adapter at the end.  www is skipped.
-class NCISFictionNetAdapter(BaseSiteAdapter):
-
-    def __init__(self, config, url):
-        BaseSiteAdapter.__init__(self, config, url)
-
-        self.decode = ["iso-8859-1",
-                       "Windows-1252"] # 1252 is a superset of iso-8859-1.
-                               # Most sites that claim to be
-                               # iso-8859-1 (and some that claim to be
-                               # utf8) are really windows-1252.
-        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
-        self.password = ""
-        self.is_adult=False
-
-        # get storyId from url--url validation guarantees query is only sid=1234
-        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-
-
-        # normalized story URL.
-        self._setURL("http://"+self.getSiteDomain()\
-                         +"/chapters.php?stid="+self.story.getMetadata('storyId'))
-
-        # Each adapter needs to have a unique site abbreviation.
-        self.story.setMetadata('siteabbrev','ncisfn')
-
-        # The date format will vary from site to site.
-        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = "%d/%m/%Y"
-
-    @staticmethod # must be @staticmethod, don't remove it.
-    def getSiteDomain():
-        # The site domain.  Does have www here, if it uses it.
-        return 'www.ncisfiction.net'
-
-    ## Changed from www.ncisfiction.com to www.ncisfiction.net Oct
-    ## 2012 due to the ncisfiction.com domain expiring.  Still accept
-    ## .com domains for existing updates, etc.
-
-    @classmethod
-    def getAcceptDomains(cls):
-        return ['www.ncisfiction.net','www.ncisfiction.com']
-
-    @classmethod
-    def getSiteExampleURLs(cls):
-        return "http://"+cls.getSiteDomain()+"/story.php?stid=01234 http://"+cls.getSiteDomain()+"/chapters.php?stid=1234"
-
-    def getSiteURLPattern(self):
-        return r'http://www\.ncisfiction\.(net|com)/(chapters|story)?.php\?stid=\d+'
-
-
-    ## Getting the chapter list and the meta data, plus 'is adult' checking.
-    def extractChapterUrlsAndMetadata(self):
-
-        # index=1 makes sure we see the story chapter index.  Some
-        # sites skip that for one-chapter stories.
-        url = self.url
-        logger.debug("URL: "+url)
-
-        try:
-            data = self._fetchUrl(url)
-        except urllib2.HTTPError, e:
-            if e.code == 404:
-                raise exceptions.StoryDoesNotExist(self.url)
-            else:
-                raise e
-
-
-        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-
-        # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = self.make_soup(data)
-        # print data
-
-        # Now go hunting for all the meta data and the chapter list.
-
-        ## Title and author
-        a = soup.find('div', {'class' : 'main_title'})
-
-        aut = a.find('a')
-        self.story.setMetadata('authorId',aut['href'].split('=')[1])
-        self.story.setMetadata('authorUrl','http://'+self.host+'/'+aut['href'])
-        self.story.setMetadata('author',aut.string)
-
-        aut.extract()
-        self.story.setMetadata('title',stripHTML(a)[:len(stripHTML(a))-2])
-
-        # Find the chapters:
-        i=0
-        chapters=soup.findAll('table', {'class' : 'story_table'})
-        for chapter in chapters:
-            ch=chapter.find('a')
-            # just in case there's tags, like <i> in chapter titles.
-            self.chapterUrls.append((stripHTML(ch),'http://'+self.host+'/'+ch['href']))
-            if i == 0:
-                self.story.setMetadata('datePublished', makeDate(stripHTML(chapter.find('td')).split('Added: ')[1], self.dateformat))
-            if i == len(chapters)-1:
-                self.story.setMetadata('dateUpdated', makeDate(stripHTML(chapter.find('td')).split('Added: ')[1], self.dateformat))
-            i=i+1
-
-        self.story.setMetadata('numChapters',len(self.chapterUrls))
-
-        # eFiction sites don't help us out a lot with their meta data
-        # formating, so it's a little ugly.
-
-        info = soup.find('table', {'class' : 'story_info'})
-
-        # no convenient way to calculate word count as it is logged differently for stories with and without series
-
-        labels = info.findAll('tr')
-        for tr in labels:
-            value = tr.find('td')
-            label = tr.find('th').string
-
-            if 'Summary' in label:
-                self.setDescription(url,value)
-
-            if 'Rating' in label:
-                self.story.setMetadata('rating', value.string)
-
-            if 'Category' in label:
-                cats = value.findAll('a')
-                for cat in cats:
-                    self.story.addToList('category',cat.string)
-
-            if 'Characters' in label:
-                chars = value.findAll('a')
-                for char in chars:
-                    self.story.addToList('characters',char.string)
-
-            if 'Pairing' in label:
-                ships = value.findAll('a')
-                for ship in ships:
-                    self.story.addToList('ships',ship.string)
-
-            if 'Genre' in label:
-                genres = value.findAll('a')
-                for genre in genres:
-                    self.story.addToList('genre',genre.string)
-
-            if 'Warnings' in label:
-                warnings = value.findAll('a')
-                for warning in warnings:
-                    self.story.addToList('warnings',warning.string)
-
-            if 'Status' in label:
-                if 'not completed' in value.text:
-                    self.story.setMetadata('status', 'In-Progress')
-                else:
-                    self.story.setMetadata('status', 'Completed')
-
-        try:
-            # Find Series name from series URL.
-            a = soup.find('div',{'class' : 'sub_header'})
-            series_name = a.find('a').string
-            i = a.text.split('#')[1]
-            self.setSeries(series_name, i)
-            self.story.setMetadata('seriesUrl','http://'+self.host+'/'+a.find('a')['href'])
-        except:
-            # I find it hard to care if the series parsing fails
-            pass
-
-    # grab the text for an individual chapter.
-    def getChapterText(self, url):
-
-        logger.debug('Getting chapter text from: %s' % url)
-
-        soup = self.make_soup(self._fetchUrl(url))
-
-        div = soup.find('div', {'class' : 'story_text'})
-
-        if None == div:
-            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-
-        return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_nfacommunitycom.py

@@ -184,7 +184,6 @@ class NfaCommunityComAdapter(BaseSiteAdapter): # XXX
             except:
                 return ""
 
-        # <span class="label">Rated:</span> NC-17<br /> etc
         labels = soup.findAll('span',{'class':'label'})
         for labelspan in labels:
             value = labelspan.nextSibling
@@ -195,7 +194,13 @@ class NfaCommunityComAdapter(BaseSiteAdapter): # XXX
                 svalue = ""
                 while 'label' not in defaultGetattr(value,'class'):
                     svalue += unicode(value)
-                    value = value.nextSibling
+                    # poor HTML(unclosed <p> for one) can cause run on
+                    # over the next label.
+                    if '<span class="label">' in svalue:
+                        svalue = svalue[0:svalue.find('<span class="label">')]
+                        break
+                    else:
+                        value = value.nextSibling
                 self.setDescription(url,svalue)
                 #self.story.setMetadata('description',stripHTML(svalue))
 

fanficfare/adapters/adapter_nickandgregnet.py

@@ -1,179 +0,0 @@
-# -*- coding: utf-8 -*-
-
-# Copyright 2013 Fanficdownloader team, 2015 FanFicFare team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-#
-
-# Software: eFiction
-import time
-import logging
-logger = logging.getLogger(__name__)
-import re
-import urllib2
-
-
-from ..htmlcleanup import stripHTML
-from .. import exceptions as exceptions
-
-from base_adapter import BaseSiteAdapter,  makeDate
-
-def getClass():
-    return NickAndGregNetAdapter
-
-# Class name has to be unique.  Our convention is camel case the
-# sitename with Adapter at the end.  www is skipped.
-class NickAndGregNetAdapter(BaseSiteAdapter):
-
-    def __init__(self, config, url):
-        BaseSiteAdapter.__init__(self, config, url)
-
-        self.decode = ["Windows-1252",
-                       "utf8"] # 1252 is a superset of iso-8859-1.
-                               # Most sites that claim to be
-                               # iso-8859-1 (and some that claim to be
-                               # utf8) are really windows-1252.
-        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
-        self.password = ""
-        self.is_adult=False
-
-        # get storyId from url--url validation guarantees query is only sid=1234
-        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-
-
-        # normalized story URL.
-        # XXX Most sites don't have the /fanfic part.  Replace all to remove it usually.
-        self._setURL('http://' + self.getSiteDomain() + '/desert_archive/viewstory.php?sid='+self.story.getMetadata('storyId'))
-
-        # Each adapter needs to have a unique site abbreviation.
-        self.story.setMetadata('siteabbrev','nag')
-
-        # The date format will vary from site to site.
-        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = "%Y/%m/%d"
-
-    @staticmethod # must be @staticmethod, don't remove it.
-    def getSiteDomain():
-        # The site domain.  Does have www here, if it uses it.
-        return 'www.nickngreg.nl'
-
-    @classmethod
-    def getAcceptDomains(cls):
-        return ['www.nickngreg.nl','www.nickandgreg.net']
-
-    @classmethod
-    def getSiteExampleURLs(cls):
-        return "http://"+cls.getSiteDomain()+"/desert_archive/viewstory.php?sid=1234"
-
-    def getSiteURLPattern(self):
-        return "http://("+self.getSiteDomain()+"|www.nickandgreg.net)"+re.escape("/desert_archive/viewstory.php?sid=")+r"\d+$"
-
-
-    ## Getting the chapter list and the meta data, plus 'is adult' checking.
-    def extractChapterUrlsAndMetadata(self):
-
-        # index=1 makes sure we see the story chapter index.  Some
-        # sites skip that for one-chapter stories.
-        url = self.url+'&i=1'
-        logger.debug("URL: "+url)
-
-        try:
-            data = self._fetchUrl(url)
-        except urllib2.HTTPError, e:
-            if e.code == 404:
-                raise exceptions.StoryDoesNotExist(self.url)
-            else:
-                raise e
-
-        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-
-        # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = self.make_soup(data)
-        # print data
-
-        # Now go hunting for all the meta data and the chapter list.
-
-        ## Title
-        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',stripHTML(a))
-
-        # Find authorid and URL from... author url.
-        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
-        self.story.setMetadata('authorId',a['href'].split('=')[1])
-        self.story.setMetadata('authorUrl','http://'+self.host+'/desert_archive/'+a['href'])
-        self.story.setMetadata('author',a.string)
-
-        # Find the chapters:
-        chapters = soup.find('select')
-        for chapter in chapters.findAll('option'):
-            if chapter.text != 'Story Index' and chapter.text != 'Chapters':
-                self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/desert_archive/'+chapter['value']))
-
-        self.story.setMetadata('numChapters',len(self.chapterUrls))
-
-        asoup = self.make_soup(self._fetchUrl(self.story.getMetadata('authorUrl')))
-
-        for div in asoup.findAll('td', {'class' : 'tblborder6'}):
-            a = div.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-            if a != None:
-                break
-
-        self.setDescription(url,div.find('br').nextSibling)
-
-        a=div.text.split('Rating:')
-        if len(a) == 2: self.story.setMetadata('rating', a[1].split(' -')[0])
-
-        a=div.text.split('Characters:')
-        if len(a) == 2:
-        	for char in a[1].split(' -')[0].split(', '):
-        	    self.story.addToList('characters',char)
-        	
-        a=div.text.split('Genres:')
-        if len(a) == 2:
-        	for genre in a[1].split(' -')[0].split(', '):
-        	    self.story.addToList('genre',genre)
-        	
-        a=div.text.split('Warnings:')
-        if len(a) == 2:
-        	for warn in a[1].split(' -')[0].split(', '):
-        	    if 'none' not in warn:
-        	        self.story.addToList('warnings',warn)
-        	
-        a=div.text.split('Completed:')
-        if len(a) ==2:
-            if 'Yes' in a[1]:
-                self.story.setMetadata('status', 'Completed')
-            else:
-                self.story.setMetadata('status', 'In-Progress')
-
-        a=div.text.split('Published:')
-        if len(a) == 2: self.story.setMetadata('datePublished', makeDate(stripHTML(a[1].split(' -')[0]), self.dateformat))
-
-        a=div.text.split('Updated:')
-        if len(a) == 2: self.story.setMetadata('dateUpdated', makeDate(stripHTML(a[1].split(' -')[0]), self.dateformat))
-
-
-    # grab the text for an individual chapter.
-    def getChapterText(self, url):
-
-        logger.debug('Getting chapter text from: %s' % url)
-
-        soup = self.make_soup(self._fetchUrl(url))
-
-        # wrap a div around it.
-        divsoup = self.make_soup('<div class="story"></div>')
-        div = divsoup.find('div')
-        div.append(soup.find('table', {'class' : 'tblborder6'}))
-
-        return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_quotevcom.py

@@ -63,17 +63,17 @@ class QuotevComAdapter(BaseSiteAdapter):
         title = element.find('h1')
         self.story.setMetadata('title', title.get_text())
         
-        authdiv = title.next_sibling # soup.find('div', {'style':"font-size:0.7em;color:#aaa;margin-top:-10px;text-align:center;margin-left:45px;cursor:pointer"})
+        authdiv = soup.find('div', {'class':"quizAuthorList"})
         if authdiv:
-            #print("div:%s"%authdiv.find_all('a'))
+            print("div:%s"%authdiv)
             for a in authdiv.find_all('a'):
                 self.story.addToList('author', a.get_text())
                 self.story.addToList('authorId', a['href'].split('/')[-1])
                 self.story.addToList('authorUrl', urlparse.urljoin(self.url, a['href']))
-        else:
+        if not self.story.getList('author'):
-            self.story.setMetadata('author','Anonymous')
+            self.story.addToList('author','Anonymous')
-            self.story.setMetadata('authorUrl','http://www.quotev.com')
+            self.story.addToList('authorUrl','http://www.quotev.com')
-            self.story.setMetadata('authorId','0')
+            self.story.addToList('authorId','0')
 
         self.setDescription(self.url, soup.find('div', id='qdesct'))
         imgmeta = soup.find('meta',{'property':"og:image" })

fanficfare/adapters/adapter_royalroadl.py

@@ -0,0 +1,181 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2011 Fanficdownloader team, 2016 FanFicFare team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+logger = logging.getLogger(__name__)
+import re
+import urllib2
+import cookielib as cl
+from datetime import datetime
+
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return RoyalRoadAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class RoyalRoadAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["utf8",
+                       "Windows-1252"
+                       ] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.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 fiction/1234
+        self.story.setMetadata('storyId',re.match('/fiction/(\d+)(:/.+)?$',self.parsedUrl.path).groups()[0])
+
+
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/fiction/'+self.story.getMetadata('storyId'))
+
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','rylrdl')
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = '%d/%m/%Y %H:%M:%S %p'
+
+    def make_date(self, parenttag):
+        # locale dates differ but the timestamp is easily converted
+        ts = parenttag.find('time')['unixtime']
+        return datetime.fromtimestamp(float(ts))
+
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'royalroadl.com'
+
+    @classmethod
+    def getAcceptDomains(cls):
+        return ['royalroadl.com','www.royalroadl.com']
+
+    @classmethod
+    def getSiteExampleURLs(cls):
+        return "https://royalroadl.com/fiction/3056"
+
+    def getSiteURLPattern(self):
+        return "https?"+re.escape("://")+r"(www\.|)royalroadl\.com/fiction/\d+$"
+
+    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):
+
+        url = self.url
+        logger.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = self.make_soup(data)
+        # print data
+
+
+        ## Title
+        title=soup.h2.text
+        self.story.setMetadata('title',title)
+
+        # Find authorid and URL from... author url.
+        author = soup.find('',{'class':'mt-card-social'})
+        author_link = author.findAll('li')[-1]
+        if author_link:
+            authorId = author_link.a['href'].split('=')[-1]
+            self.story.setMetadata('authorId', authorId)
+            self.story.setMetadata('authorUrl','http://'+self.host+'/member.php?action=profile&uid='+authorId)
+        self.story.setMetadata('author',soup.find(attrs=dict(property="books:author"))['content'])
+
+
+        chapters = soup.find('table',{'id':'chapters'}).find('tbody')
+        tds = [tr.findAll('td')[0] for tr in chapters.findAll('tr')]
+        for td in tds:
+            chapterUrl = 'http://' + self.getSiteDomain() + td.a['href']
+            self.chapterUrls.append((stripHTML(td.text), chapterUrl))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # this is forum based so it's a bit ugly
+        description = soup.find('div', {'property': 'description', 'class': 'hidden-content'})
+        self.setDescription(url,description)
+
+        dates = [tr.findAll('td')[1] for tr in chapters.findAll('tr')]
+        self.story.setMetadata('dateUpdated', self.make_date(dates[-1]))
+        self.story.setMetadata('datePublished', self.make_date(dates[0]))
+
+        genre=[tag.text for tag in soup.find('input',{'property':'genre'}).parent.findChildren('span')]
+        if not "Unspecified" in genre:
+            for tag in genre:
+                self.story.addToList('genre',tag)
+
+        # 'rating' in FFF speak means G, PG, Teen, Restricted, etc.
+        # 'stars' is used instead for RR's 1-5 stars rating.
+        stars=soup.find(attrs=dict(property="books:rating:value"))['content']
+        self.story.setMetadata('stars',stars)
+        logger.debug(self.story.getMetadata('stars'))
+
+        warning = soup.find('strong',text='Warning')
+        if warning != None:
+            warnings=[c.text for c in warning.parent.children if getattr(c,'text',None)][1:]
+            for warntag in warnings:
+                self.story.addToList('warnings',warntag)
+
+        # get cover
+        img = soup.find('',{'class':'row fic-header'}).find('img')
+        if img:
+            cover_url = img['src']
+            self.setCoverImage(url,cover_url)
+                    # some content is show as tables, this will preserve them
+
+
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logger.debug('Getting chapter text from: %s' % url)
+
+        soup = self.make_soup(self._fetchUrl(url))
+
+        div = soup.find('div',{'class':"chapter-inner chapter-content"})
+
+        # TODO: these stories often have tables in, but these wont render correctly
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+
+        return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_siyecouk.py

@@ -112,6 +112,11 @@ class SiyeCoUkAdapter(BaseSiteAdapter): # XXX
         # need(or easier) to pull other metadata from the author's list page.
         authsoup = self.make_soup(self._fetchUrl(self.story.getMetadata('authorUrl')))
 
+        # remove author profile incase they've put the story URL in their bio.
+        profile = authsoup.find('div',{'id':'profile'})
+        if profile: # in case it changes.
+            profile.extract()
+
         ## Title
         titlea = authsoup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',stripHTML(titlea))

fanficfare/adapters/adapter_storiesonlinenet.py

@@ -97,7 +97,7 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
         params['page'] = 'http://'+self.getSiteDomain()+'/'
         params['submit'] = 'Login'
 
-        loginUrl = 'https://' + self.getSiteDomain() + '/login.php'
+        loginUrl = 'https://' + self.getSiteDomain() + '/sol-secure/login.php'
         logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
                                                               params['theusername']))
 
@@ -171,7 +171,7 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
             self.story.addToList('author',stripHTML(a).replace("'s Page",""))
 
         # Find the chapters:
-        chapters = soup.findAll('a', href=re.compile(r'^/s/'+self.story.getMetadata('storyId')+":\d+$"))
+        chapters = soup.findAll('a', href=re.compile(r'^/s/'+self.story.getMetadata('storyId')+":\d+(/.*)?$"))
         if len(chapters) != 0:
             for chapter in chapters:
                 # just in case there's tags, like <i> in chapter titles.
@@ -211,7 +211,7 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
 
         try:
             a = lc4.find('a', href=re.compile(r"/series/\d+/.*"))
-            logger.debug("Looking for series - a='{0}'".format(a))
+            # logger.debug("Looking for series - a='{0}'".format(a))
             if a:
                 # if there's a number after the series name, series_contents is a two element list:
                 # [<a href="...">Title</a>, u' (2)']
@@ -220,34 +220,34 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
                 seriesUrl = 'http://'+self.host+a['href']
                 self.story.setMetadata('seriesUrl',seriesUrl)
                 series_name = stripHTML(a)
-                logger.debug("Series name= %s" % series_name)
+                # logger.debug("Series name= %s" % series_name)
                 series_soup = self.make_soup(self._fetchUrl(seriesUrl))
                 if series_soup:
-                    logger.debug("Retrieving Series - looking for name")
+                    # logger.debug("Retrieving Series - looking for name")
                     series_name = stripHTML(series_soup.find('span', {'id' : 'ptitle'}))
                     series_name = re.sub(r' . a series by.*$','',series_name)
-                    logger.debug("Series name: '{0}'".format(series_name))
+                    # logger.debug("Series name: '%s'" % series_name)
                 self.setSeries(series_name, i)
                 desc = lc4.contents[2]
                 # Check if series is in a universe
                 universe_url = self.story.getList('authorUrl')[0]  + "&type=uni"
                 universes_soup = self.make_soup(self._fetchUrl(universe_url) )
-                logger.debug("Universe url='{0}'".format(universe_url))
+                # logger.debug("Universe url='{0}'".format(universe_url))
                 if universes_soup:
                     universes = universes_soup.findAll('div', {'class' : 'ser-box'})
-                    logger.debug("Number of Universes: %d" % len(universes))
+                    # logger.debug("Number of Universes: %d" % len(universes))
                     for universe in universes:
-                        logger.debug("universe.find('a')={0}".format(universe.find('a')))
+                        # logger.debug("universe.find('a')={0}".format(universe.find('a')))
                         # The universe id is in an "a" tag that has an id but nothing else. It is the first tag.
                         # The id is prefixed with the letter "u".
                         universe_id = universe.find('a')['id'][1:]
-                        logger.debug("universe_id='%s'" % universe_id)
+                        # logger.debug("universe_id='%s'" % universe_id)
                         universe_name = stripHTML(universe.find('div', {'class' : 'ser-name'})).partition(' ')[2]
-                        logger.debug("universe_name='%s'" % universe_name)
+                        # logger.debug("universe_name='%s'" % universe_name)
                         # If there is link to the story, we have the right universe
                         story_a = universe.find('a', href=re.compile('/s/'+self.story.getMetadata('storyId')))
                         if story_a:
-                            logger.debug("Story is in a series that is in a universe! The universe is '%s'" % universe_name)
+                            # logger.debug("Story is in a series that is in a universe! The universe is '%s'" % universe_name)
                             self.story.setMetadata("universe", universe_name)
                             self.story.setMetadata('universeUrl','http://'+self.host+ '/library/universe.php?id=' + universe_id)
                             break
@@ -258,24 +258,24 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
             pass
         try:
             a = lc4.find('a', href=re.compile(r"/universe/\d+/.*"))
-            logger.debug("Looking for universe - a='{0}'".format(a))
+            # logger.debug("Looking for universe - a='{0}'".format(a))
             if a:
                 self.story.setMetadata("universe",stripHTML(a))
                 desc = lc4.contents[2]
                 # Assumed only one universe, but it does have a URL--use universeHTML
                 universe_name = stripHTML(a)
                 universeUrl = 'http://'+self.host+a['href']
-                logger.debug("Retrieving Universe - about to get page - universeUrl='{0}".format(universeUrl))
+                # logger.debug("Retrieving Universe - about to get page - universeUrl='{0}".format(universeUrl))
                 universe_soup = self.make_soup(self._fetchUrl(universeUrl))
                 logger.debug("Retrieving Universe - have page")
                 if universe_soup:
                     logger.debug("Retrieving Universe - looking for name")
                     universe_name = stripHTML(universe_soup.find('h1', {'id' : 'ptitle'}))
                     universe_name = re.sub(r' . A Universe from the Mind.*$','',universe_name)
-                    logger.debug("Universes name: '{0}'".format(universe_name))
+                    # logger.debug("Universes name: '{0}'".format(universe_name))
 
                 self.story.setMetadata('universeUrl',universeUrl)
-                logger.debug("Setting universe name: '{0}'".format(universe_name))
+                # logger.debug("Setting universe name: '{0}'".format(universe_name))
                 self.story.setMetadata('universe',universe_name)
                 if self.getConfig("universe_as_series"):
                     self.setSeries(universe_name, 0)
@@ -320,12 +320,12 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
         #     http://storiesonline.net/s/11999
         #     http://storiesonline.net/s/10823
         if get_cover:
-            logger.debug("Looking for the cover image...")
+            # logger.debug("Looking for the cover image...")
             cover_url = ""
             img = soup.find('img')
             if img:
                 cover_url=img['src']
-            logger.debug("cover_url: %s"%cover_url)
+            # logger.debug("cover_url: %s"%cover_url)
             if cover_url:
                 self.setCoverImage(url,cover_url)
 
@@ -363,7 +363,7 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
 
             urls=pager.findAll('a')
             urls=urls[:len(urls)-1]
-            logger.debug("pager urls:%s"%urls)
+            # logger.debug("pager urls:%s"%urls)
             pager.extract()
             chaptertag.contents = chaptertag.contents[2:]
 
@@ -372,7 +372,7 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
 
                 pagetag = soup.find('div', {'id' : 'story'})
                 if not pagetag:
-                    logger.debug("div id=story not found, try article")
+                    # logger.debug("div id=story not found, try article")
                     pagetag = soup.find('article', {'id' : 'story'})
 
                 self.cleanPage(pagetag)

fanficfare/adapters/adapter_tokrafandomnetcom.py

@@ -1,238 +0,0 @@
-# -*- coding: utf-8 -*-
-
-# Copyright 2013 Fanficdownloader team, 2015 FanFicFare team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-#
-
-# Software: eFiction
-import time
-import logging
-logger = logging.getLogger(__name__)
-import re
-import urllib2
-
-
-from ..htmlcleanup import stripHTML
-from .. import exceptions as exceptions
-
-from base_adapter import BaseSiteAdapter,  makeDate
-
-def getClass():
-    return TokraFandomnetComAdapter
-
-# Class name has to be unique.  Our convention is camel case the
-# sitename with Adapter at the end.  www is skipped.
-class TokraFandomnetComAdapter(BaseSiteAdapter):
-
-    def __init__(self, config, url):
-        BaseSiteAdapter.__init__(self, config, url)
-
-        self.decode = ["Windows-1252",
-                       "utf8"] # 1252 is a superset of iso-8859-1.
-                               # Most sites that claim to be
-                               # iso-8859-1 (and some that claim to be
-                               # utf8) are really windows-1252.
-        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
-        self.password = ""
-        self.is_adult=False
-
-        # get storyId from url--url validation guarantees query is only sid=1234
-        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-
-
-        # normalized story URL.
-        self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
-
-        # Each adapter needs to have a unique site abbreviation.
-        self.story.setMetadata('siteabbrev','tokra')
-
-        # The date format will vary from site to site.
-        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = "%m/%d/%Y"
-
-    @staticmethod # must be @staticmethod, don't remove it.
-    def getSiteDomain():
-        # The site domain.  Does have www here, if it uses it.  But it
-        # doesn't matter too much anymore.
-        return 'tokra.fandomnet.com'
-
-    @classmethod
-    def getSiteExampleURLs(cls):
-        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
-
-    def getSiteURLPattern(self):
-        return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
-
-    ## Getting the chapter list and the meta data, plus 'is adult' checking.
-    def extractChapterUrlsAndMetadata(self):
-
-        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=3"
-        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
-
-        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.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-
-        # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = self.make_soup(data)
-        #print data
-
-        # Now go hunting for all the meta data and the chapter list.
-
-        ## Title
-        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',stripHTML(a))
-
-        # Find authorid and URL from... author url.
-        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
-        self.story.setMetadata('authorId',a['href'].split('=')[1])
-        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
-        self.story.setMetadata('author',a.string)
-
-        # Rating
-        rate = stripHTML(soup.find('div',{'id':'pagetitle'}))
-        rate = rate[rate.rindex('[')+1:rate.rindex(']')]
-        self.story.setMetadata('rating', rate)
-
-        # Find the chapters:
-        for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
-            # just in case there's tags, like <i> in chapter titles.
-            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']+addurl))
-
-        self.story.setMetadata('numChapters',len(self.chapterUrls))
-
-        # eFiction sites don't help us out a lot with their meta data
-        # formating, so it's a little ugly.
-
-        metadiv = soup.find('div',{'class':'content'})
-        smalldiv = metadiv.find('div',{'class':'small'})
-
-        # tokra categories -> genre
-        # categories will be filled from ini.
-        genres = smalldiv.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
-        for genre in genres:
-            self.story.addToList('genre',genre.string)
-
-        chars = smalldiv.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
-        for char in chars:
-            self.story.addToList('characters',char.string)
-
-        metatext = stripHTML(smalldiv)
-
-        if 'Completed: Yes' in metatext:
-            self.story.setMetadata('status', 'Completed')
-        else:
-            self.story.setMetadata('status', 'In-Progress')
-
-        wordstart=metatext.rindex('Word count:')+12
-        words = metatext[wordstart:metatext.index(' ',wordstart)]
-        self.story.setMetadata('numWords', words)
-
-        datesdiv = soup.find('div',{'class':'bottom'})
-        dates = stripHTML(datesdiv).split()
-        # Published: 04/26/2011 Updated: 03/06/2013
-        self.story.setMetadata('datePublished', makeDate(dates[1], self.dateformat))
-        self.story.setMetadata('dateUpdated', makeDate(dates[3], self.dateformat))
-
-        try:
-            # Find Series name from series URL.
-            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
-            series_name = a.string
-            series_url = 'http://'+self.host+'/'+a['href']
-
-            # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = self.make_soup(self._fetchUrl(series_url))
-            # can't use ^viewstory...$ in case of higher rated stories with javascript href.
-            storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+'))
-            i=1
-            for a in storyas:
-                # skip 'report this' and 'TOC' links
-                if 'contact.php' not in a['href'] and 'index' not in a['href']:
-                    if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
-                        self.setSeries(series_name, i)
-                        self.story.setMetadata('seriesUrl',series_url)
-                        break
-                    i+=1
-
-        except:
-            # I find it hard to care if the series parsing fails
-            pass
-
-        # remove 'small' leaving only summary.
-        smalldiv.extract()
-        self.setDescription(url,metadiv)
-
-    # grab the text for an individual chapter.
-    def getChapterText(self, url):
-
-        logger.debug('Getting chapter text from: %s' % url)
-
-        soup = self.make_soup(self._fetchUrl(url))
-
-        div = soup.find('div', {'class' : 'content'})
-
-        if None == div:
-            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-
-        # remove some decorations while keeping notes.
-        remove = div.find('div', {'id' : 'pagetitle'})
-        remove.extract()
-
-        for remove in div.findAll('div', {'class' : 'right'}):
-            remove.extract()
-
-        for remove in div.findAll('div', {'class' : 'left'}):
-            remove.extract()
-
-        return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_wraithbaitcom.py

@@ -125,9 +125,10 @@ class WraithBaitComAdapter(BaseSiteAdapter):
         rating=pt.text.split('[')[1].split(']')[0]
         self.story.setMetadata('rating', rating)
 
-        st = soup.find('div', {'class' : 'storytitle'})
+        # site stopped showing reviews ~ Oct 2016
-        a = st.findAll('a', href=re.compile(r'reviews.php\?type=ST&item='+self.story.getMetadata('storyId')+"$"))[1] # second one.
+        # st = soup.find('div', {'class' : 'storytitle'})
-        self.story.setMetadata('reviews',stripHTML(a))
+        # a = st.findAll('a', href=re.compile(r'reviews.php\?type=ST&item='+self.story.getMetadata('storyId')+"$"))[1] # second one.
+        # self.story.setMetadata('reviews',stripHTML(a))
 
         # Find the chapters:
         for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):

fanficfare/adapters/base_adapter.py

@@ -16,7 +16,8 @@
 #
 
 import re
-import datetime
+from datetime import datetime, timedelta
+
 import time
 import logging
 import urllib
@@ -83,7 +84,7 @@ class BaseSiteAdapter(Configurable):
 
     def __init__(self, configuration, url):
         Configurable.__init__(self, configuration)
-        
+
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
@@ -99,7 +100,7 @@ class BaseSiteAdapter(Configurable):
         self.metadataDone = False
         self.story = Story(configuration)
         self.story.setMetadata('site',self.getConfigSection())
-        self.story.setMetadata('dateCreated',datetime.datetime.now())
+        self.story.setMetadata('dateCreated',datetime.now())
         self.chapterUrls = [] # tuples of (chapter title,chapter url)
         self.chapterFirst = None
         self.chapterLast = None
@@ -112,7 +113,7 @@ class BaseSiteAdapter(Configurable):
         self.logfile = None
 
         self.pagecache = self.get_empty_pagecache()
-        
+
         ## order of preference for decoding.
         self.decode = ["utf8",
                        "Windows-1252"] # 1252 is a superset of
@@ -131,20 +132,20 @@ class BaseSiteAdapter(Configurable):
 
     def set_cookiejar(self,cj):
         self.cookiejar = cj
+        saveheaders = self.opener.addheaders
         self.opener = u2.build_opener(u2.HTTPCookieProcessor(self.cookiejar),GZipProcessor())
-        self.opener.addheaders = [('User-Agent', self.getConfig('user_agent')),
+        self.opener.addheaders = saveheaders
-                                  ('X-Clacks-Overhead','GNU Terry Pratchett')]
+
-        
     def load_cookiejar(self,filename):
         '''
         Needs to be called after adapter create, but before any fetchs
         are done.  Takes file *name*.
         '''
         self.get_cookiejar().load(filename, ignore_discard=True, ignore_expires=True)
-        
+
     def get_pagecache(self):
         return self.pagecache
-    
+
     def set_pagecache(self,d):
         self.pagecache=d
 
@@ -158,7 +159,7 @@ class BaseSiteAdapter(Configurable):
 
     def _has_cachekey(self,cachekey):
         return self.use_pagecache() and cachekey in self.get_pagecache()
-    
+
     def _get_from_pagecache(self,cachekey):
         if self.use_pagecache():
             return self.get_pagecache().get(cachekey)
@@ -175,18 +176,18 @@ class BaseSiteAdapter(Configurable):
         this and change it to True.
         '''
         return False
-        
+
     # def story_load(self,filename):
     #     d = pickle.load(self.story.metadata,filename)
     #     self.story.metadata = d['metadata']
     #     self.chapterUrls = d['chapterlist']
     #     self.story.metadataDone = True
-        
+
     def _setURL(self,url):
         self.url = url
         self.parsedUrl = up.urlparse(url)
         self.host = self.parsedUrl.netloc
-        self.path = self.parsedUrl.path        
+        self.path = self.parsedUrl.path
         self.story.setMetadata('storyUrl',self.url,condremoveentities=False)
 
 ## website encoding(s)--in theory, each website reports the character
@@ -200,7 +201,7 @@ class BaseSiteAdapter(Configurable):
             decode = self.getConfigList('website_encodings')
         else:
             decode = self.decode
-        
+
         for code in decode:
             try:
                 #print code
@@ -229,7 +230,7 @@ class BaseSiteAdapter(Configurable):
                  usecache=True):
         '''
         When should cache be cleared or not used? logins...
-        
+
         extrasleep is primarily for ffnet adapter which has extra
         sleeps.  Passed into fetchs so it can be bypassed when
         cache hits.
@@ -239,7 +240,7 @@ class BaseSiteAdapter(Configurable):
             logger.debug("#####################################\npagecache HIT: %s"%safe_url(cachekey))
             data,redirecturl = self._get_from_pagecache(cachekey)
             return data
-        
+
         logger.debug("#####################################\npagecache MISS: %s"%safe_url(cachekey))
         self.do_sleep(extrasleep)
 
@@ -260,19 +261,19 @@ class BaseSiteAdapter(Configurable):
                      parameters=None,
                      extrasleep=None,
                      usecache=True):
-        
+
         return self._fetchUrlRawOpened(url,
                                        parameters,
                                        extrasleep,
                                        usecache)[0]
-        
+
     def _fetchUrlRawOpened(self, url,
                            parameters=None,
                            extrasleep=None,
                            usecache=True):
         '''
         When should cache be cleared or not used? logins...
-        
+
         extrasleep is primarily for ffnet adapter which has extra
         sleeps.  Passed into fetchs so it can be bypassed when
         cache hits.
@@ -288,7 +289,7 @@ class BaseSiteAdapter(Configurable):
                 def geturl(self): return self.url
                 def read(self): return self.data
             return (data,FakeOpened(data,redirecturl))
-        
+
         logger.debug("#####################################\npagecache MISS: %s"%safe_url(cachekey))
         self.do_sleep(extrasleep)
         if parameters != None:
@@ -297,13 +298,13 @@ class BaseSiteAdapter(Configurable):
             opened = self.opener.open(url.replace(' ','%20'),None,float(self.getConfig('connect_timeout',30.0)))
         data = opened.read()
         self._set_to_pagecache(cachekey,data,opened.url)
-        
+
         return (data,opened)
 
     def set_sleep(self,val):
         logger.debug("\n===========\n set sleep time %s\n==========="%val)
         self.override_sleep = val
-    
+
     def do_sleep(self,extrasleep=None):
         if extrasleep:
             time.sleep(float(extrasleep))
@@ -311,7 +312,7 @@ class BaseSiteAdapter(Configurable):
             time.sleep(float(self.override_sleep))
         elif self.getConfig('slow_down_sleep_time'):
             time.sleep(float(self.getConfig('slow_down_sleep_time')))
-        
+
     def _fetchUrl(self, url,
                   parameters=None,
                   usecache=True,
@@ -329,7 +330,7 @@ class BaseSiteAdapter(Configurable):
 
         excpt=None
         for sleeptime in [0, 0.5, 4, 9]:
-            time.sleep(sleeptime)	
+            time.sleep(sleeptime)
             try:
                 (data,opened)=self._fetchUrlRawOpened(url,
                                                       parameters=parameters,
@@ -344,7 +345,7 @@ class BaseSiteAdapter(Configurable):
             except Exception, e:
                 excpt=e
                 logger.warn("Caught an exception reading URL: %s sleeptime(%s) Exception %s."%(unicode(safe_url(url)),sleeptime,unicode(e)))
-                
+
         logger.error("Giving up on %s" %safe_url(url))
         logger.debug(excpt, exc_info=True)
         raise(excpt)
@@ -356,12 +357,16 @@ class BaseSiteAdapter(Configurable):
         if last:
             self.chapterLast=int(last)-1
         self.story.set_chapters_range(first,last)
-    
+
     # Does the download the first time it's called.
     def getStory(self):
         if not self.storyDone:
             self.getStoryMetadataOnly(get_cover=True)
 
+            ## one-off step to normalize old chapter URLs if present.
+            if self.oldchaptersmap:
+                self.oldchaptersmap = dict((self.normalize_chapterurl(key), value) for (key, value) in self.oldchaptersmap.items())
+
             for index, (title,url) in enumerate(self.chapterUrls):
                 newchap = False
                 if (self.chapterFirst!=None and index < self.chapterFirst) or \
@@ -387,18 +392,25 @@ class BaseSiteAdapter(Configurable):
                                url in self.oldchaptersdata and (
                             self.oldchaptersdata[url]['chapterorigtitle'] !=
                             self.oldchaptersdata[url]['chaptertitle']) )
-                    
+
                     if not data:
                         data = self.getChapterText(url)
                         # if had to fetch and has existing chapters
                         newchap = bool(self.oldchapters or self.oldchaptersmap)
-                        
+
+                    if index == 0 and self.getConfig('always_reload_first_chapter'):
+                        data = self.getChapterText(url)
+                        # first chapter is rarely marked new
+                        # anyway--only if it's replaced during an
+                        # update.
+                        newchap = False
+
                     self.story.addChapter(url,
                                           removeEntities(title),
                                           removeEntities(data),
                                           newchap)
             self.storyDone = True
-            
+
             # include image, but no cover from story, add default_cover_image cover.
             if self.getConfig('include_images') and \
                     not self.story.cover and \
@@ -415,26 +427,30 @@ class BaseSiteAdapter(Configurable):
             if not self.story.cover and self.oldcover:
                 self.story.oldcover = self.oldcover
                 self.story.setMetadata('cover_image','old')
-                
+
             # cheesy way to carry calibre bookmark file forward across update.
             if self.calibrebookmark:
                 self.story.calibrebookmark = self.calibrebookmark
             if self.logfile:
                 self.story.logfile = self.logfile
-                
+
         return self.story
 
     def getStoryMetadataOnly(self,get_cover=True):
         if not self.metadataDone:
             self.doExtractChapterUrlsAndMetadata(get_cover=get_cover)
-            
+
             if not self.story.getMetadataRaw('dateUpdated'):
                 if self.story.getMetadataRaw('datePublished'):
                     self.story.setMetadata('dateUpdated',self.story.getMetadataRaw('datePublished'))
                 else:
-                    self.story.setMetadata('dateUpdated',self.story.getMetadataRaw('dateCreated'))                
+                    self.story.setMetadata('dateUpdated',self.story.getMetadataRaw('dateCreated'))
 
             self.metadataDone = True
+            # normalize chapter urls.
+            for index, (title,url) in enumerate(self.chapterUrls):
+                self.chapterUrls[index] = (title,self.normalize_chapterurl(url))
+
         return self.story
 
     def setStoryMetadata(self,metahtml):
@@ -445,36 +461,36 @@ class BaseSiteAdapter(Configurable):
                 if self.story.getMetadataRaw('datePublished'):
                     self.story.setMetadata('dateUpdated',self.story.getMetadataRaw('datePublished'))
                 else:
-                    self.story.setMetadata('dateUpdated',self.story.getMetadataRaw('dateCreated'))                
+                    self.story.setMetadata('dateUpdated',self.story.getMetadataRaw('dateCreated'))
-    
+
     def hookForUpdates(self,chaptercount):
         "Usually not needed."
         return chaptercount
 
     ###############################
-    
+
     @staticmethod
     def getSiteDomain():
         "Needs to be overriden in each adapter class."
         return 'no such domain'
-    
+
     @classmethod
     def getConfigSection(cls):
         "Only needs to be overriden if != site domain."
         return cls.getSiteDomain()
-    
+
     @classmethod
     def getConfigSections(cls):
         "Only needs to be overriden if has additional ini sections."
         return [cls.getConfigSection()]
-    
+
     @classmethod
     def stripURLParameters(cls,url):
         "Only needs to be overriden if URL contains more than one parameter"
         ## remove any trailing '&' parameters--?sid=999 will be left.
         ## that's all that any of the current adapters need or want.
         return re.sub(r"&.*$","",url)
-    
+
     ## URL pattern validation is done *after* picking an adaptor based
     ## on domain instead of *as* the adaptor selector so we can offer
     ## the user example(s) for that particular site.
@@ -482,7 +498,7 @@ class BaseSiteAdapter(Configurable):
     def getSiteURLPattern(self):
         "Used to validate URL.  Should be override in each adapter class."
         return '^http://'+re.escape(self.getSiteDomain())
-    
+
     @classmethod
     def getSiteExampleURLs(cls):
         """
@@ -492,7 +508,7 @@ class BaseSiteAdapter(Configurable):
         validateURL method.
         """
         return 'no such example'
-    
+
     def doExtractChapterUrlsAndMetadata(self,get_cover=True):
         '''
         There are a handful of adapters that fetch a cover image while
@@ -501,7 +517,7 @@ class BaseSiteAdapter(Configurable):
         this instead of extractChapterUrlsAndMetadata()
         '''
         return self.extractChapterUrlsAndMetadata()
-    
+
     def extractChapterUrlsAndMetadata(self):
         "Needs to be overriden in each adapter class.  Populates self.story metadata and self.chapterUrls"
         pass
@@ -553,7 +569,7 @@ class BaseSiteAdapter(Configurable):
             # bs4
             return soup.attrs.keys()
         return []
-        
+
     # This gives us a unicode object, not just a string containing bytes.
     # (I gave soup a unicode string, you'd think it could give it back...)
     # Now also does a bunch of other common processing for us.
@@ -562,12 +578,12 @@ class BaseSiteAdapter(Configurable):
             fetch=self._fetchUrlRaw
 
         acceptable_attributes = self.getConfigList('keep_html_attrs',['href','name','class','id'])
-        
+
         if self.getConfig("keep_style_attr"):
             acceptable_attributes.append('style')
         if self.getConfig("keep_title_attr"):
             acceptable_attributes.append('title')
-            
+
         #print("include_images:"+self.getConfig('include_images'))
         if self.getConfig('include_images'):
             acceptable_attributes.extend(('src','alt','longdesc'))
@@ -584,6 +600,19 @@ class BaseSiteAdapter(Configurable):
             if attr not in acceptable_attributes:
                 del soup[attr] ## strip all tag attributes except href and name
 
+        ## apply adapter's normalize_chapterurls to all links in
+        ## chapter texts, if they match chapter URLs.  While this will
+        ## be occasionally helpful by itself, it's really for the next
+        ## feature: internal text links.
+        if self.getConfig('normalize_text_links'):
+            for alink in soup.find_all('a'):
+                # try:
+                if alink.has_attr('href'):
+                    # logger.debug("normalize_text_links %s -> %s"%(alink['href'],self.normalize_chapterurl(alink['href'])))
+                    alink['href'] = self.normalize_chapterurl(alink['href'])
+                # except AttributeError as ae:
+                #     logger.info("Parsing for normalize_text_links failed...")
+
         try:
             # as a generator, each tag will be returned even if there's a
             # mismatch at the end.
@@ -591,8 +620,8 @@ class BaseSiteAdapter(Configurable):
                 for attr in self.get_attr_keys(t):
                     if attr not in acceptable_attributes:
                         del t[attr] ## strip all tag attributes except acceptable_attributes
-    
+
-                # these are not acceptable strict XHTML.  But we do already have 
+                # these are not acceptable strict XHTML.  But we do already have
                 # CSS classes of the same names defined
                 if t and hasattr(t,'name') and t.name is not None:
                     if t.name in self.getConfigList('replace_tags_with_spans',['u']):
@@ -608,11 +637,11 @@ class BaseSiteAdapter(Configurable):
                     # remove script tags cross the board.
                     if t.name=='script':
                         t.extract()
-                        
+
         except AttributeError, ae:
             if "%s"%ae != "'NoneType' object has no attribute 'next_element'":
                 logger.error("Error parsing HTML, probably poor input HTML. %s"%ae)
-        
+
         retval = unicode(soup)
 
         if self.getConfig('nook_img_fix') and not self.getConfig('replace_br_with_p'):
@@ -621,16 +650,16 @@ class BaseSiteAdapter(Configurable):
             # that under the text for the rest of the chapter.
             retval = re.sub(r"(?!<(div|p)>)\s*(?P<imgtag><img[^>]+>)\s*(?!</(div|p)>)",
                             "<div>\g<imgtag></div>",retval)
-            
+
         # Don't want html, head or body tags in chapter html--writers add them.
         # This is primarily for epub updates.
         retval = re.sub(r"</?(html|head|body)[^>]*>\r?\n?","",retval)
-        
+
         if self.getConfig("replace_br_with_p") and allow_replace_br_with_p:
             # Apply heuristic processing to replace <br> paragraph
             # breaks with <p> tags.
             retval = replace_br_with_p(retval)
-            
+
         if self.getConfig('replace_hr'):
             # replacing a self-closing tag with a container tag in the
             # soup is more difficult than it first appears.  So cheat.
@@ -640,31 +669,35 @@ class BaseSiteAdapter(Configurable):
 
     def make_soup(self,data):
         '''
-        Convenience method for getting a bs4 soup.  Older and
+        Convenience method for getting a bs4 soup.  bs3 has been removed.
-        non-updated adapters call the included bs3 library themselves.
         '''
-        
+
         ## html5lib handles <noscript> oddly.  See:
         ## https://bugs.launchpad.net/beautifulsoup/+bug/1277464
         ## This should 'hide' and restore <noscript> tags.
         data = data.replace("noscript>","fff_hide_noscript>")
-        
+
         ## soup and re-soup because BS4/html5lib is more forgiving of
         ## incorrectly nested tags that way.
         soup = bs4.BeautifulSoup(data,'html5lib')
         soup = bs4.BeautifulSoup(unicode(soup),'html5lib')
-        
+
         for ns in soup.find_all('fff_hide_noscript'):
             ns.name = 'noscript'
-            
+
         return soup
-    
+
+    ## For adapters, especially base_xenforoforum to override.  Make
+    ## sure to return unchanged URL if it's NOT a chapter URL...
+    def normalize_chapterurl(self,url):
+        return url
+
 def cachedfetch(realfetch,cache,url):
     if url in cache:
         return cache[url]
     else:
         return realfetch(url)
-    
+
 fullmon = {u"January":u"01", u"February":u"02", u"March":u"03", u"April":u"04", u"May":u"05",
            u"June":u"06","July":u"07", u"August":u"08", u"September":u"09", u"October":u"10",
            u"November":u"11", u"December":u"12" }
@@ -679,7 +712,7 @@ def makeDate(string,dateform):
     # lie.  It has to do something even more complicated to get
     # Russian month names correct everywhere.
     do_abbrev = "%b" in dateform
-        
+
     if u"%B" in dateform or do_abbrev:
         dateform = dateform.replace(u"%B",u"%m").replace(u"%b",u"%m")
         for (name,num) in fullmon.items():
@@ -688,8 +721,23 @@ def makeDate(string,dateform):
             if name in string:
                 string = string.replace(name,num)
                 break
-            
+
-    return datetime.datetime.strptime(string.encode('utf-8'),dateform.encode('utf-8'))
+    # Many locales don't define %p for AM/PM.  So if %p, remove from
+    # dateform, look for 'pm' in string, remove am/pm from string and
+    # add 12 hours if pm found.
+    add_hours = False
+    if u"%p" in dateform:
+        dateform = dateform.replace(u"%p",u"")
+        if 'pm' in string or 'PM' in string:
+            add_hours = True
+        string = string.replace(u"AM",u"").replace(u"PM",u"").replace(u"am",u"").replace(u"pm",u"")
+
+    date = datetime.strptime(string.encode('utf-8'),dateform.encode('utf-8'))
+
+    if add_hours:
+        date += timedelta(hours=12)
+
+    return date
 
 # .? for AO3's ']' in param names.
 safe_url_re = re.compile(r'(?P<attr>(password|name|login).?=)[^&]*(?P<amp>&|$)',flags=re.MULTILINE)

fanficfare/adapters/base_efiction_adapter.py

@@ -85,7 +85,7 @@ class BaseEfictionAdapter(BaseSiteAdapter):
 
     @classmethod
     def getSiteURLPattern(self):
-        return r"http://(www\.)?%s%s/%s\?sid=(?P<storyId>\d+)" % (self.getSiteDomain(), self.getPathToArchive(), self.getViewStoryPhpName())
+        return r"https?://(www\.)?%s%s/%s\?sid=(?P<storyId>\d+)" % (self.getSiteDomain(), self.getPathToArchive(), self.getViewStoryPhpName())
 
     @classmethod
     def getEncoding(cls):

fanficfare/adapters/base_xenforoforum_adapter.py

@@ -1,6 +1,6 @@
 #  -*- coding: utf-8 -*-
 
-# Copyright 2015 FanFicFare team
+# Copyright 2016 FanFicFare team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -85,6 +85,62 @@ class BaseXenForoForumAdapter(BaseSiteAdapter):
     def getSiteURLPattern(self):
         return r"https?://"+re.escape(self.getSiteDomain())+r"/(?P<tp>threads|posts)/(.+\.)?(?P<id>\d+)/?[^#]*?(#post-(?P<anchorpost>\d+))?$"
 
+    ## For adapters, especially base_xenforoforum to override.  Make
+    ## sure to return unchanged URL if it's NOT a chapter URL.  This
+    ## is most helpful for xenforoforum because threadmarks use
+    ## thread-name URLs--which can change if the thread name changes.
+    def normalize_chapterurl(self,url):
+        (is_chapter_url,normalized_url) = self._is_normalize_chapterurl(url)
+        if is_chapter_url:
+            return normalized_url
+        else:
+            return url
+
+    ## returns (is_chapter_url,normalized_url)
+    def _is_normalize_chapterurl(self,url):
+        is_chapter_url = False
+
+        ## moved from extract metadata to share with normalize_chapterurl.
+        if not url.startswith('http'):
+            url = self.getURLPrefix()+'/'+url
+
+        if ( url.startswith(self.getURLPrefix()) or
+             url.startswith('http://'+self.getSiteDomain()) or
+             url.startswith('https://'+self.getSiteDomain()) ) and \
+             ( '/posts/' in url or '/threads/' in url or 'showpost.php' in url or 'goto/post' in url):
+            # brute force way to deal with SB's http->https change when hardcoded http urls.
+            url = url.replace('http://'+self.getSiteDomain(),self.getURLPrefix())
+
+            # http://forums.spacebattles.com/showpost.php?p=4755532&postcount=9
+            url = re.sub(r'showpost\.php\?p=([0-9]+)(&postcount=[0-9]+)?',r'/posts/\1/',url)
+
+            # http://forums.spacebattles.com/goto/post?id=15222406#post-15222406
+            url = re.sub(r'/goto/post\?id=([0-9]+)(#post-[0-9]+)?',r'/posts/\1/',url)
+
+            url = re.sub(r'(^[\'"]+|[\'"]+$)','',url) # strip leading or trailing '" from incorrect quoting.
+            url = re.sub(r'like$','',url) # strip 'like' if incorrect 'like' link instead of proper post URL.
+
+            #### moved from getChapterText()
+            ## there's some history of stories with links to the wrong
+            ## page.  This changes page#post URLs to perma-link URLs.
+            ## Which will be redirected back to page#posts, but the
+            ## *correct* ones.
+            # http://forums.sufficientvelocity.com/threads/harry-potter-and-the-not-fatal-at-all-cultural-exchange-program.330/page-4#post-39915
+            # https://forums.sufficientvelocity.com/posts/39915/
+            if '#post-' in url:
+                url = self.getURLPrefix()+'/posts/'+url.split('#post-')[1]+'/'
+
+            ## Same as above except for for case where author mistakenly
+            ## used the reply link instead of normal link to post.
+            # "http://forums.spacebattles.com/threads/manager-worm-story-thread-iv.301602/reply?quote=15962513"
+            # https://forums.spacebattles.com/posts/
+            if 'reply?quote=' in url:
+                url = self.getURLPrefix()+'/posts/'+url.split('reply?quote=')[1]+'/'
+
+            is_chapter_url = True
+        return (is_chapter_url,url)
+
+
     def use_pagecache(self):
         '''
         adapters that will work with the page cache need to implement
@@ -119,7 +175,7 @@ class BaseXenForoForumAdapter(BaseSiteAdapter):
         # params[soup.find('input', {'id':'password'})['name']] = params['password']
 
         d = self._fetchUrl(loginUrl, params)
-    
+
         if "Log Out" not in d :
             logger.info("Failed to login to URL %s as %s" % (loginUrl,
                                                              params['login']))
@@ -183,7 +239,7 @@ class BaseXenForoForumAdapter(BaseSiteAdapter):
                     threadmark_chaps = True
                     if self.getConfig('always_include_first_post'):
                         self.chapterUrls.append((first_post_title,useurl))
-                    
+
                     for (atag,url,name) in [ (x,x['href'],stripHTML(x)) for x in markas ]:
                         date = self.make_date(atag.find_next_sibling('div',{'class':'extra'}))
                         if not self.story.getMetadataRaw('datePublished') or date < self.story.getMetadataRaw('datePublished'):
@@ -196,13 +252,13 @@ class BaseXenForoForumAdapter(BaseSiteAdapter):
             soup = soup.find('li',{'class':'message'}) # limit first post for date stuff below. ('#' posts above)
 
         if threadmark_chaps or self.getConfig('always_use_forumtags'):
-            ## only  use  tags if  threadmarks  for  chapters or
+            ## only use tags if threadmarks for chapters or always_use_forumtags is on.
-            for tag in topsoup.findAll('a',{'class':'tag'}):
+            for tag in topsoup.findAll('a',{'class':'tag'}) + topsoup.findAll('span',{'class':'prefix'}):
                 tstr = stripHTML(tag)
                 if self.getConfig('capitalize_forumtags'):
                     tstr = tstr.title()
                 self.story.addToList('forumtags',tstr)
-            
+
         # Now go hunting for the 'chapter list'.
         bq = soup.find('blockquote') # assume first posting contains TOC urls.
 
@@ -222,21 +278,9 @@ class BaseXenForoForumAdapter(BaseSiteAdapter):
         if not self.chapterUrls:
             self.chapterUrls.append((first_post_title,useurl))
             for (url,name) in [ (x['href'],stripHTML(x)) for x in bq.find_all('a') ]:
-                #logger.debug("found chapurl:%s"%url)
-                if not url.startswith('http'):
-                    url = self.getURLPrefix()+'/'+url
 
-                if ( url.startswith(self.getURLPrefix()) or
+                (is_chapter_url,url) = self._is_normalize_chapterurl(url)
-                     url.startswith('http://'+self.getSiteDomain()) or
+                if is_chapter_url:
-                     url.startswith('https://'+self.getSiteDomain()) ) and ('/posts/' in url or '/threads/' in url):
-
-                    # brute force way to deal with SB's http->https change when hardcoded http urls.
-                    url = url.replace('http://'+self.getSiteDomain(),self.getURLPrefix())
-
-                    url = re.sub(r'(^[\'"]+|[\'"]+$)','',url) # strip leading or trailing '" from incorrect quoting.
-                    url = re.sub(r'like$','',url) # strip 'like' if incorrect 'like' link instead of proper post URL.
-
-                    logger.debug("(ch:%s)used chapurl:%s"%(len(self.chapterUrls)+1,url))
                     self.chapterUrls.append((name,url))
                     if url == useurl and first_post_title == self.chapterUrls[0][0] \
                             and not self.getConfig('always_include_first_post',False):
@@ -272,29 +316,13 @@ class BaseXenForoForumAdapter(BaseSiteAdapter):
             datestr = re.sub(r' (\d[^\d])',r' 0\1',datestr) # add leading 0 for single digit day & hours.
             return makeDate(datestr, self.dateformat)
         except:
-            logger.debug('No date found in %s'%parenttag)
+            logger.debug('No date found in %s'%parenttag,exc_info=True)
             return None
 
     # grab the text for an individual chapter.
     def getChapterText(self, url):
         logger.debug('Getting chapter text from: %s' % url)
 
-        ## there's some history of stories with links to the wrong
-        ## page.  This changes page#post URLs to perma-link URLs.
-        ## Which will be redirected back to page#posts, but the
-        ## *correct* ones.
-        # http://forums.sufficientvelocity.com/threads/harry-potter-and-the-not-fatal-at-all-cultural-exchange-program.330/page-4#post-39915
-        # https://forums.sufficientvelocity.com/posts/39915/
-        if '#post-' in url:
-            url = self.getURLPrefix()+'/posts/'+url.split('#post-')[1]+'/'
-
-        ## Same as above except for for case where author mistakenly
-        ## used the reply link instead of normal link to post.
-        # "http://forums.spacebattles.com/threads/manager-worm-story-thread-iv.301602/reply?quote=15962513"
-        # https://forums.spacebattles.com/posts/
-        if 'reply?quote=' in url:
-            url = self.getURLPrefix()+'/posts/'+url.split('reply?quote=')[1]+'/'
-
         try:
             origurl = url
             (data,opened) = self._fetchUrlOpened(url)
@@ -302,20 +330,20 @@ class BaseXenForoForumAdapter(BaseSiteAdapter):
             if '#' in origurl and '#' not in url:
                 url = url + origurl[origurl.index('#'):]
             logger.debug("chapter URL redirected to: %s"%url)
-            
+
             soup = self.make_soup(data)
-    
+
             if '#' in url:
                 anchorid = url.split('#')[1]
                 soup = soup.find('li',id=anchorid)
-    
+
             bq = soup.find('blockquote')
-    
+
             bq.name='div'
-    
+
             for iframe in bq.find_all('iframe'):
                 iframe.extract() # calibre book reader & editor don't like iframes to youtube.
-    
+
             for qdiv in bq.find_all('div',{'class':'quoteExpand'}):
                 qdiv.extract() # Remove <div class="quoteExpand">click to expand</div>
 
@@ -323,7 +351,7 @@ class BaseXenForoForumAdapter(BaseSiteAdapter):
             ## include lazy load images.
             for img in bq.find_all('img',{'class':'lazyload'}):
                 img['src'] = img['data-src']
-    
+
         except Exception as e:
             if self.getConfig('continue_on_chapter_error'):
                 bq = self.make_soup("""<div>

fanficfare/cli.py

@@ -26,6 +26,8 @@ import pprint
 import string
 import sys
 
+version="2.5.1"
+
 if sys.version_info < (2, 5):
     print 'This program requires Python 2.5 or newer.'
     sys.exit(1)
@@ -43,13 +45,13 @@ try:
     from calibre_plugins.fanficfare_plugin.fanficfare.configurable import Configuration
     from calibre_plugins.fanficfare_plugin.fanficfare.epubutils import (
         get_dcsource_chaptercount, get_update_data, reset_orig_chapters_epub)
-    from calibre_plugins.fanficfare_plugin.fanficfare.geturls import get_urls_from_page
+    from calibre_plugins.fanficfare_plugin.fanficfare.geturls import get_urls_from_page, get_urls_from_imap
 except ImportError:
     from fanficfare import adapters, writers, exceptions
     from fanficfare.configurable import Configuration
     from fanficfare.epubutils import (
         get_dcsource_chaptercount, get_update_data, reset_orig_chapters_epub)
-    from fanficfare.geturls import get_urls_from_page
+    from fanficfare.geturls import get_urls_from_page, get_urls_from_imap
 
 
 def write_story(config, adapter, writeformat, metaonly=False, outstream=None):
@@ -59,13 +61,15 @@ def write_story(config, adapter, writeformat, metaonly=False, outstream=None):
     del writer
     return output_filename
 
-
+def main(argv=None,
-def main(argv=None, parser=None, passed_defaultsini=None, passed_personalini=None):
+         parser=None,
+         passed_defaultsini=None,
+         passed_personalini=None):
     if argv is None:
         argv = sys.argv[1:]
     # read in args, anything starting with -- will be treated as --<varible>=<value>
     if not parser:
-        parser = OptionParser('usage: %prog [options] storyurl')
+        parser = OptionParser('usage: %prog [options] [STORYURL]...')
     parser.add_option('-f', '--format', dest='format', default='epub',
                       help='write story as FORMAT, epub(default), mobi, text or html', metavar='FORMAT')
 
@@ -88,41 +92,68 @@ def main(argv=None, parser=None, passed_defaultsini=None, passed_personalini=Non
                       help='Retrieve metadata and stop.  Or, if --update-epub, update metadata title page only.', )
     parser.add_option('-u', '--update-epub',
                       action='store_true', dest='update',
-                      help='Update an existing epub with new chapters, give epub filename instead of storyurl.', )
+                      help='Update an existing epub(if present) with new chapters.  Give either epub filename or story URL.', )
-    parser.add_option('--unnew',
-                      action='store_true', dest='unnew',
-                      help='Remove (new) chapter marks left by mark_new_chapters setting.', )
     parser.add_option('--update-cover',
                       action='store_true', dest='updatecover',
                       help='Update cover in an existing epub, otherwise existing cover (if any) is used on update.  Only valid with --update-epub.', )
+    parser.add_option('--unnew',
+                      action='store_true', dest='unnew',
+                      help='Remove (new) chapter marks left by mark_new_chapters setting.', )
     parser.add_option('--force',
                       action='store_true', dest='force',
                       help='Force overwrite of an existing epub, download and overwrite all chapters.', )
     parser.add_option('-i', '--infile',
-                      help='Give a filename to read for URLs (and/or existing EPUB files with -u for updates).',
+                      help='Give a filename to read for URLs (and/or existing EPUB files with --update-epub).',
                       dest='infile', default=None,
                       metavar='INFILE')
+
     parser.add_option('-l', '--list',
-                      action='store_true', dest='list',
+                      dest='list', default=None, metavar='URL',
                       help='Get list of valid story URLs from page given.', )
     parser.add_option('-n', '--normalize-list',
-                      action='store_true', dest='normalize', default=False,
+                      dest='normalize', default=None, metavar='URL',
                       help='Get list of valid story URLs from page given, but normalized to standard forms.', )
+    parser.add_option('--download-list',
+                      dest='downloadlist', default=None, metavar='URL',
+                      help='Download story URLs retrieved from page given.  Update existing EPUBs if used with --update-epub.', )
+
+    parser.add_option('--imap',
+                      action='store_true', dest='imaplist',
+                      help='Get list of valid story URLs from unread email from IMAP account configured in ini.', )
+
+    parser.add_option('--download-imap',
+                      action='store_true', dest='downloadimap',
+                      help='Download valid story URLs from unread email from IMAP account configured in ini.  Update existing EPUBs if used with --update-epub.', )
+
     parser.add_option('-s', '--sites-list',
                       action='store_true', dest='siteslist', default=False,
                       help='Get list of valid story URLs examples.', )
     parser.add_option('-d', '--debug',
                       action='store_true', dest='debug',
-                      help='Show debug output while downloading.', )
+                      help='Show debug and notice output.', )
+    parser.add_option('-v', '--version',
+                      action='store_true', dest='version',
+                      help='Display version and quit.', )
 
     options, args = parser.parse_args(argv)
 
+    if options.version:
+        print("Version: %s" % version)
+        return
+
     if not options.debug:
         logger = logging.getLogger('fanficfare')
-        logger.setLevel(logging.INFO)
+        logger.setLevel(logging.WARNING)
 
-    if not (options.siteslist or options.infile) and len(args) != 1:
+    list_only = any((options.imaplist,
-        parser.error('incorrect number of arguments')
+                     options.siteslist,
+                     options.list,
+                     options.normalize,
+                     ))
+
+    if list_only and (args or any((options.downloadimap,
+                                   options.downloadlist))):
+        parser.error('Incorrect arguments: Cannot download and list URLs at the same time.')
 
     if options.siteslist:
         for site, examples in adapters.getSiteExamples():
@@ -137,43 +168,85 @@ def main(argv=None, parser=None, passed_defaultsini=None, passed_personalini=Non
     if options.unnew and options.format != 'epub':
         parser.error('--unnew only works with epub')
 
+    urls=args
+
+    if not list_only and not (args or any((options.infile,
+                                           options.downloadimap,
+                                           options.downloadlist))):
+        parser.print_help();
+        return
+    
+    if options.list:
+        configuration = get_configuration(options.list,
+                                          passed_defaultsini,
+                                          passed_personalini,options)
+        retlist = get_urls_from_page(options.list, configuration)
+        print '\n'.join(retlist)
+
+    if options.normalize:
+        configuration = get_configuration(options.normalize,
+                                          passed_defaultsini,
+                                          passed_personalini,options)
+        retlist = get_urls_from_page(options.normalize, configuration,normalize=True)
+        print '\n'.join(retlist)
+
+    if options.downloadlist:
+        configuration = get_configuration(options.downloadlist,
+                                          passed_defaultsini,
+                                          passed_personalini,options)
+        retlist = get_urls_from_page(options.downloadlist, configuration)
+        urls.extend(retlist)
+
+    if options.imaplist or options.downloadimap:
+        # list doesn't have a supported site.
+        configuration = get_configuration('test1.com',passed_defaultsini,passed_personalini,options)
+        markread = configuration.getConfig('imap_mark_read') == 'true' or \
+            (configuration.getConfig('imap_mark_read') == 'downloadonly' and options.downloadimap)
+        retlist = get_urls_from_imap(configuration.getConfig('imap_server'),
+                                     configuration.getConfig('imap_username'),
+                                     configuration.getConfig('imap_password'),
+                                     configuration.getConfig('imap_folder'),
+                                     markread)
+
+        if options.downloadimap:
+            urls.extend(retlist)
+        else:
+            print '\n'.join(retlist)
+
     # for passing in a file list
     if options.infile:
-        urls=[]
         with open(options.infile,"r") as infile:
             #print "File exists and is readable"
-          
-            #fileurls = [line.strip() for line in infile]
             for url in infile:
-                url = url[:url.find('#')].strip()
+                if '#' in url:
+                    url = url[:url.find('#')].strip()
+                url = url.strip()
                 if len(url) > 0:
                     #print "URL: (%s)"%url
                     urls.append(url)
-    else:
-        urls = args
 
-    if len(urls) > 1:
+    if not list_only:
-        for url in urls:
+        if len(urls) < 1:
-            try:
+            print "No valid story URLs found"
-                do_download(url,
+        else:
-                            options,
+            for url in urls:
-                            passed_defaultsini,
+                try:
-                            passed_personalini)
+                    do_download(url,
+                                options,
+                                passed_defaultsini,
+                                passed_personalini)
                 #print("pagecache:%s"%options.pagecache.keys())
-            except Exception, e:
+                except Exception, e:
-                print "URL(%s) Failed: Exception (%s). Run URL individually for more detail."%(url,e)
+                    if len(urls) == 1:
-    else:
+                        raise
-        do_download(urls[0],
+                    print "URL(%s) Failed: Exception (%s). Run URL individually for more detail."%(url,e)
-                    options,
-                    passed_defaultsini,
-                    passed_personalini)
 
 # make rest a function and loop on it.
 def do_download(arg,
                 options,
                 passed_defaultsini,
                 passed_personalini):
-                
+
     # Attempt to update an existing epub.
     chaptercount = None
     output_filename = None
@@ -182,7 +255,7 @@ def do_download(arg,
         # remove mark_new_chapters marks
         reset_orig_chapters_epub(arg,arg)
         return
-    
+
     if options.update:
         try:
             url, chaptercount = get_dcsource_chaptercount(arg)
@@ -197,71 +270,13 @@ def do_download(arg,
             url = arg
     else:
         url = arg
-        
-    try:
-        configuration = Configuration(adapters.getConfigSectionsFor(url), options.format)
-    except exceptions.UnknownSite, e:
-        if options.list or options.normalize:
-            # list for page doesn't have to be a supported site.
-            configuration = Configuration('test1.com', options.format)
-        else:
-            raise e
 
-    conflist = []
+    configuration = get_configuration(url,
-    homepath = join(expanduser('~'), '.fanficdownloader')
+                                      passed_defaultsini,
-    ## also look for .fanficfare now, give higher priority than old dir.
+                                      passed_personalini,
-    homepath2 = join(expanduser('~'), '.fanficfare')
+                                      options,
-
+                                      chaptercount,
-    if passed_defaultsini:
+                                      output_filename)
-        configuration.readfp(passed_defaultsini)
-
-    # don't need to check existance for our selves.
-    conflist.append(join(dirname(__file__), 'defaults.ini'))
-    conflist.append(join(homepath, 'defaults.ini'))
-    conflist.append(join(homepath2, 'defaults.ini'))
-    conflist.append('defaults.ini')
-
-    if passed_personalini:
-        configuration.readfp(passed_personalini)
-
-    conflist.append(join(homepath, 'personal.ini'))
-    conflist.append(join(homepath2, 'personal.ini'))
-    conflist.append('personal.ini')
-
-    if options.configfile:
-        conflist.extend(options.configfile)
-
-    logging.debug('reading %s config file(s), if present' % conflist)
-    configuration.read(conflist)
-
-    try:
-        configuration.add_section('overrides')
-    except ConfigParser.DuplicateSectionError:
-        pass
-
-    if options.force:
-        configuration.set('overrides', 'always_overwrite', 'true')
-
-    if options.update and chaptercount:
-        configuration.set('overrides', 'output_filename', output_filename)
-
-    if options.update and not options.updatecover:
-        configuration.set('overrides', 'never_make_cover', 'true')
-
-    # images only for epub, even if the user mistakenly turned it
-    # on else where.
-    if options.format not in ('epub', 'html'):
-        configuration.set('overrides', 'include_images', 'false')
-
-    if options.options:
-        for opt in options.options:
-            (var, val) = opt.split('=')
-            configuration.set('overrides', var, val)
-
-    if options.list or options.normalize:
-        retlist = get_urls_from_page(arg, configuration, normalize=options.normalize)
-        print '\n'.join(retlist)
-        return
 
     try:
         adapter = adapters.getAdapter(configuration, url)
@@ -269,10 +284,10 @@ def do_download(arg,
         if not hasattr(options,'pagecache'):
             options.pagecache = adapter.get_empty_pagecache()
             options.cookiejar = adapter.get_empty_cookiejar()
-        
+
         adapter.set_pagecache(options.pagecache)
         adapter.set_cookiejar(options.cookiejar)
-        
+
         adapter.setChaptersRange(options.begin, options.end)
 
         # check for updating from URL (vs from file)
@@ -290,17 +305,20 @@ def do_download(arg,
         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')
             except ImportError:
                 try:
-                    import Image
+                    ## Pillow is a more current fork of PIL library
-
+                    from PIL import Image
-                    logging.debug('Using PIL')
+                    logging.debug('Using Pillow')
                 except ImportError:
-                    print "You have include_images enabled, but Python Image Library(PIL) isn't found.\nImages will be included full size in original format.\nContinue? (y/n)?"
+                    try:
-                    if not sys.stdin.readline().strip().lower().startswith('y'):
+                        import Image
-                        return
+                        logging.debug('Using PIL')
+                    except ImportError:
+                        print "You have include_images enabled, but Python Image Library(PIL) isn't found.\nImages will be included full size in original format.\nContinue? (y/n)?"
+                        if not sys.stdin.readline().strip().lower().startswith('y'):
+                            return
 
         # three tries, that's enough if both user/pass & is_adult needed,
         # or a couple tries of one or the other
@@ -360,7 +378,10 @@ def do_download(arg,
             output_filename = write_story(configuration, adapter, options.format, options.metaonly)
 
         if not options.metaonly and adapter.getConfig('post_process_cmd'):
-            metadata = adapter.story.metadata
+            if adapter.getConfig('post_process_apply_filename_safepattern'):
+                metadata = adapter.story.get_filename_safe_metadata()
+            else:
+                metadata = adapter.story.getAllMetadata()
             metadata['output_filename'] = output_filename
             call(string.Template(adapter.getConfig('post_process_cmd')).substitute(metadata), shell=True)
 
@@ -375,6 +396,73 @@ def do_download(arg,
     except exceptions.AccessDenied as ad:
         print ad
 
+def get_configuration(url,
+                      passed_defaultsini,
+                      passed_personalini,
+                      options,
+                      chaptercount=None,
+                      output_filename=None):
+    try:
+        configuration = Configuration(adapters.getConfigSectionsFor(url), options.format)
+    except exceptions.UnknownSite, e:
+        if options.list or options.normalize or options.downloadlist:
+            # list for page doesn't have to be a supported site.
+            configuration = Configuration('test1.com', options.format)
+        else:
+            raise e
+
+    conflist = []
+    homepath = join(expanduser('~'), '.fanficdownloader')
+    ## also look for .fanficfare now, give higher priority than old dir.
+    homepath2 = join(expanduser('~'), '.fanficfare')
+
+    if passed_defaultsini:
+        configuration.readfp(passed_defaultsini)
+
+    # don't need to check existance for our selves.
+    conflist.append(join(dirname(__file__), 'defaults.ini'))
+    conflist.append(join(homepath, 'defaults.ini'))
+    conflist.append(join(homepath2, 'defaults.ini'))
+    conflist.append('defaults.ini')
+
+    if passed_personalini:
+        configuration.readfp(passed_personalini)
+
+    conflist.append(join(homepath, 'personal.ini'))
+    conflist.append(join(homepath2, 'personal.ini'))
+    conflist.append('personal.ini')
+
+    if options.configfile:
+        conflist.extend(options.configfile)
+
+    logging.debug('reading %s config file(s), if present' % conflist)
+    configuration.read(conflist)
+
+    try:
+        configuration.add_section('overrides')
+    except ConfigParser.DuplicateSectionError:
+        pass
+
+    if options.force:
+        configuration.set('overrides', 'always_overwrite', 'true')
+
+    if options.update and chaptercount and output_filename:
+        configuration.set('overrides', 'output_filename', output_filename)
+
+    if options.update and not options.updatecover:
+        configuration.set('overrides', 'never_make_cover', 'true')
+
+    # images only for epub, even if the user mistakenly turned it
+    # on else where.
+    if options.format not in ('epub', 'html'):
+        configuration.set('overrides', 'include_images', 'false')
+
+    if options.options:
+        for opt in options.options:
+            (var, val) = opt.split('=')
+            configuration.set('overrides', var, val)
+
+    return configuration
 
 if __name__ == '__main__':
     main()

fanficfare/configurable.py

@@ -40,7 +40,7 @@ import adapters
 def re_compile(regex,line):
     try:
         return re.compile(regex)
-    except Exception, e: 
+    except Exception, e:
         raise exceptions.RegularExpresssionFailed(e,regex,line)
 
 # fall back labels.
@@ -59,6 +59,7 @@ titleLabels = {
     'warnings':'Warnings',
     'numChapters':'Chapters',
     'numWords':'Words',
+    'words_added':'Words Added', # logpage only
     'site':'Site',
     'storyId':'Story ID',
     'authorId':'Author ID',
@@ -78,7 +79,7 @@ formatsections = ['html','txt','epub','mobi']
 othersections = ['defaults','overrides']
 
 def get_valid_sections():
-    sites = adapters.getConfigSections() 
+    sites = adapters.getConfigSections()
     sitesections = list(othersections)
     for section in sites:
         sitesections.append(section)
@@ -90,7 +91,7 @@ def get_valid_sections():
         else:
             # add w/ www if doesn't www
             sitesections.append('www.%s'%section)
-            
+
     allowedsections = []
     allowedsections.extend(formatsections)
 
@@ -99,7 +100,7 @@ def get_valid_sections():
         for f in formatsections:
             allowedsections.append('%s:%s'%(section,f))
     return allowedsections
-    
+
 def get_valid_list_entries():
     return list(['category',
                  'genre',
@@ -127,6 +128,12 @@ def get_valid_set_options():
     This is to further restrict keywords to certain sections and/or
     values.  get_valid_keywords() below is the list of allowed
     keywords.  Any keyword listed here must also be listed there.
+
+    This is what's used by the code when you save personal.ini in
+    plugin that stops and points out possible errors in keyword
+    *values*.  It doesn't flag 'bad' keywords.  Note that it's
+    separate from color highlighting and most keywords need to be
+    added to both.
     '''
 
     valdict = {'collect_series':(None,None,boollist),
@@ -144,15 +151,15 @@ def get_valid_set_options():
                'strip_chapter_numbers':(None,None,boollist),
                'mark_new_chapters':(None,None,boollist),
                'titlepage_use_table':(None,None,boollist),
-               
+
                'use_ssl_unverified_context':(None,None,boollist),
-                              
+
                'add_chapter_numbers':(None,None,boollist+['toconly']),
-               
+
                'check_next_chapter':(['fanfiction.net'],None,boollist),
                'tweak_fg_sleep':(['fanfiction.net'],None,boollist),
                'skip_author_cover':(['fanfiction.net'],None,boollist),
-               
+
                'fix_fimf_blockquotes':(['fimfiction.net'],None,boollist),
                'fail_on_password':(['fimfiction.net'],None,boollist),
                'do_update_hook':(['fimfiction.net',
@@ -174,20 +181,24 @@ def get_valid_set_options():
                # kept forgetting to add them, so now it's automatic.
                'bulk_load':(adapters.get_bulk_load_sites(),
                             None,boollist),
-               
+
                'include_logpage':(None,['epub'],boollist+['smart']),
-               
+               'logpage_at_end':(None,['epub'],boollist),
+
                'windows_eol':(None,['txt'],boollist),
-               
+
                'include_images':(None,['epub','html'],boollist),
                'grayscale_images':(None,['epub','html'],boollist),
                'no_image_processing':(None,['epub','html'],boollist),
+               'normalize_text_links':(None,['epub','html'],boollist),
+               'internalize_text_links':(None,['epub','html'],boollist),
 
                'capitalize_forumtags':(base_xenforo_list,None,boollist),
                'continue_on_chapter_error':(base_xenforo_list,None,boollist),
                'minimum_threadmarks':(base_xenforo_list,None,None),
                'first_post_title':(base_xenforo_list,None,None),
                'always_include_first_post':(base_xenforo_list,None,boollist),
+               'always_reload_first_chapter':(base_xenforo_list,None,boollist),
                }
 
     return dict(valdict)
@@ -203,6 +214,7 @@ def get_valid_scalar_entries():
                  'rating',
                  'numChapters',
                  'numWords',
+                 'words_added', # logpage only.
                  'site',
                  'storyId',
                  'title',
@@ -225,6 +237,11 @@ def get_valid_entries():
 
 # *known* keywords -- or rather regexps for them.
 def get_valid_keywords():
+    '''
+    Among other things, this list is used by the color highlighting in
+    personal.ini editing in plugin.  Note that it's separate from
+    value checking and most keywords need to be added to both.
+    '''
     return list(['(in|ex)clude_metadata_(pre|post)',
                  'add_chapter_numbers',
                  'add_genre_when_multi_category',
@@ -282,6 +299,7 @@ def get_valid_keywords():
                  'image_max_size',
                  'include_images',
                  'include_logpage',
+                 'logpage_at_end',
                  'include_subject_tags',
                  'include_titlepage',
                  'include_tocpage',
@@ -356,7 +374,9 @@ def get_valid_keywords():
                  'minimum_threadmarks',
                  'first_post_title',
                  'always_include_first_post',
-                 '',
+                 'always_reload_first_chapter',
+                 'normalize_text_links',
+                 'internalize_text_links',
                  ])
 
 # *known* entry keywords -- or rather regexps for them.
@@ -373,9 +393,9 @@ def make_generate_cover_settings(param):
                 (template,regexp,setting) = map( lambda x: x.strip(), line.split("=>") )
                 re_compile(regexp,line)
                 vlist.append((template,regexp,setting))
-            except Exception, e: 
+            except Exception, e:
                 raise exceptions.PersonalIniFailed(e,line,param)
-                
+
     return vlist
 
 
@@ -386,9 +406,9 @@ class Configuration(ConfigParser.SafeConfigParser):
         ConfigParser.SafeConfigParser.__init__(self)
 
         self.lightweight = lightweight
-        
+
         self.linenos=dict() # key by section or section,key -> lineno
-        
+
         ## [injected] section has even less priority than [defaults]
         self.sectionslist = ['defaults','injected']
 
@@ -396,17 +416,17 @@ class Configuration(ConfigParser.SafeConfigParser):
         ## but before site-specific.
         for section in sections[:-1]:
             self.addConfigSection(section)
-        
+
         if site.startswith("www."):
             sitewith = site
             sitewithout = site.replace("www.","")
         else:
             sitewith = "www."+site
             sitewithout = site
-        
+
         self.addConfigSection(sitewith)
         self.addConfigSection(sitewithout)
-        
+
         if fileform:
             self.addConfigSection(fileform)
             ## add other sections:fileform (not including site DN)
@@ -416,9 +436,9 @@ class Configuration(ConfigParser.SafeConfigParser):
             self.addConfigSection(sitewith+":"+fileform)
             self.addConfigSection(sitewithout+":"+fileform)
         self.addConfigSection("overrides")
-        
+
         self.listTypeEntries = get_valid_list_entries()
-        
+
         self.validEntries = get_valid_entries()
 
         self.url_config_set = False
@@ -443,7 +463,7 @@ class Configuration(ConfigParser.SafeConfigParser):
 
     def isListType(self,key):
         return key in self.listTypeEntries or self.hasConfig("include_in_"+key)
-        
+
     def isValidMetaEntry(self, key):
         return key in self.getValidMetaList()
 
@@ -473,7 +493,7 @@ class Configuration(ConfigParser.SafeConfigParser):
     # used by adapters & writers, non-convention naming style
     def getConfig(self, key, default=""):
         return self.get_config(self.sectionslist,key,default)
-    
+
     def get_config(self, sections, key, default=""):
         val = default
         for section in sections:
@@ -493,7 +513,7 @@ class Configuration(ConfigParser.SafeConfigParser):
                 #print "getConfig(add_to_%s)=[%s]%s" % (key,section,val)
             except (ConfigParser.NoOptionError, ConfigParser.NoSectionError), e:
                 pass
-            
+
         return val
 
     # split and strip each.
@@ -505,7 +525,7 @@ class Configuration(ConfigParser.SafeConfigParser):
             return default
         else:
             return vlist
-    
+
     # used by adapters & writers, non-convention naming style
     def getConfigList(self, key, default=[]):
         return self.get_config_list(self.sectionslist, key, default)
@@ -519,7 +539,7 @@ class Configuration(ConfigParser.SafeConfigParser):
             return self.linenos.get(section+','+key,None)
         else:
             return self.linenos.get(section,None)
-    
+
     ## Copied from Python 2.7 library so as to make read utf8.
     def read(self, filenames):
         """Read and parse a filename or a list of filenames.
@@ -543,7 +563,7 @@ class Configuration(ConfigParser.SafeConfigParser):
             fp.close()
             read_ok.append(filename)
         return read_ok
-    
+
     ## Copied from Python 2.7 library so as to make it save linenos too.
     #
     # Regular expressions for parsing section headers and options.
@@ -623,7 +643,7 @@ class Configuration(ConfigParser.SafeConfigParser):
                             optval = ''
                         optname = self.optionxform(optname.rstrip())
                         cursect[optname] = optval
-                        self.linenos[cursect['__name__']+','+optname]=lineno                        
+                        self.linenos[cursect['__name__']+','+optname]=lineno
                     else:
                         # a non-fatal parsing error occurred.  set up the
                         # exception but keep going. the exception will be
@@ -651,11 +671,11 @@ class Configuration(ConfigParser.SafeConfigParser):
         from story import set_in_ex_clude, make_replacements
 
         custom_columns_settings_re = re.compile(r'(add_to_)?custom_columns_settings')
-        
+
         generate_cover_settings_re = re.compile(r'(add_to_)?generate_cover_settings')
-        
+
         valdict = get_valid_set_options()
-        
+
         for section in self.sections():
             allow_all_section = allow_all_sections_re.match(section)
             if section not in allowedsections and not allow_all_section:
@@ -671,17 +691,17 @@ class Configuration(ConfigParser.SafeConfigParser):
                 elif sitename in othersections:
                     formatname = None
                     sitename = None
-                    
+
                 ## check each keyword in section.  Due to precedence
                 ## order of sections, it's possible for bad lines to
                 ## never be used.
                 for keyword,value in self.items(section):
                     try:
-                        
+
                         ## check regex bearing keywords first.  Each
                         ## will raise exceptions if flawed.
                         if clude_metadata_re.match(keyword):
-                            set_in_ex_clude(value)    
+                            set_in_ex_clude(value)
 
                         if replace_metadata_re.match(keyword):
                             make_replacements(value)
@@ -713,7 +733,7 @@ class Configuration(ConfigParser.SafeConfigParser):
                         ## used with CLI/web yet.
 
                     except Exception as e:
-                        errors.append((self.get_lineno(section,keyword),"Error:%s in (%s:%s)"%(e,keyword,value)))                
+                        errors.append((self.get_lineno(section,keyword),"Error:%s in (%s:%s)"%(e,keyword,value)))
 
         return errors
 
@@ -728,7 +748,7 @@ class Configurable(object):
 
     def addUrlConfigSection(self,url):
         self.configuration.addUrlConfigSection(url)
-        
+
     def isListType(self,key):
         return self.configuration.isListType(key)
 
@@ -737,10 +757,10 @@ class Configurable(object):
 
     def getValidMetaList(self):
         return self.configuration.getValidMetaList()
-    
+
     def hasConfig(self, key):
-        return self.configuration.hasConfig(key)        
+        return self.configuration.hasConfig(key)
-        
+
     def has_config(self, sections, key):
         return self.configuration.has_config(sections, key)
 

fanficfare/defaults.ini

@@ -25,7 +25,7 @@
 ## titlepage_entries: category,genre, status,dateUpdated,rating
 ## [epub]
 ## # overrides defaults & site section
-## titlepage_entries: category,genre, status,datePublished,dateUpdated,dateCreated
+## titlepage_entries: category,genre,status,datePublished,dateUpdated,dateCreated
 ## [www.whofic.com:epub]
 ## # overrides defaults, site section & format section
 ## titlepage_entries: category,genre, status,datePublished
@@ -180,7 +180,7 @@ extratags: FanFiction
 ## Can also be used for other metadata values
 #default_value_category:FanFiction
 
-## number of seconds to sleep between calls to the story site.  May by
+## number of seconds to sleep between calls to the story site.  May be
 ## useful if pulling large numbers of stories or if the site is slow.
 #slow_down_sleep_time:0.5
 
@@ -189,11 +189,17 @@ extratags: FanFiction
 ## prevent excessive wait when your network or the site is down.
 connect_timeout:60.0
 
-## For use only with stand-alone CLI version--run a command on the
+## For use only with CLI version--run a command on the generated file
-## generated file after it's produced.  All of the titlepage_entries
+## after it's produced.  All of the titlepage_entries values are
-## values are available, plus output_filename.
+## available, plus output_filename.
 #post_process_cmd: addbook -f "${output_filename}" -t "${title}"
 
+## Some operating systems and command shells have problems with some
+## characters.  When true, the output_filename_safepattern will be
+## applied to each metadata item passed to post_process_cmd before
+## it's called.
+#post_process_apply_filename_safepattern:false
+
 ## Use regular expressions to find and replace (or remove) metadata.
 ## For example, you could change Sci-Fi=>SF, remove *-Centered tags,
 ## etc.  See http://docs.python.org/library/re.html (look for re.sub)
@@ -404,6 +410,40 @@ user_agent:FFF/2.X
 ## non-intuitive.
 #description_limit:1000
 
+## The FFF CLI can fetch story URLs from unread emails when configured
+## to read from your IMAP mail server.  The example shows GMail, but
+## other services that support IMAP can be used.  GMail requires you
+## to turn on an option to enable IMAP access. Only the CLI uses these
+## options--the Calibre Plugin stores these separately.
+##
+## It's safest if you create a separate email account that you use
+## only for your story update notices.  FanFicFare cannot guarantee
+## that malicious code cannot get your email password once you've
+## saved it. Use this feature at your own risk.
+##
+#imap_server:imap.gmail.com
+#imap_username:youraddress@gmail.com
+#imap_password:XXXXXXXX
+#imap_folder:INBOX
+
+## Mark mails with story URLs read:
+## imap_mark_read can be 'true', 'false'(default) or 'downloadonly'.
+##
+## If 'true', unread emails will be marked as read when
+## either CLI option --imap to list the story URLs or --download-imap
+## to download story URLs from email are used.
+##
+## If 'downloadonly', unread emails will be marked as read
+## only when CLI --download-imap to download story URLs from email are
+## used.
+##
+## If 'false', unread emails will not be marked as read.
+##
+## Only unread emails will be searched for story URLs, and only emails
+## containing valid story URLs will ever be marked read.
+##
+#imap_mark_read:true
+
 [base_efiction]
 ## At the time of writing, eFiction Base adapters allow downloading
 ## the whole story in bulk using the 'Print' feature. If 'bulk_load'
@@ -473,8 +513,8 @@ add_to_include_subject_tags:,tagsfromtitle.SPLIT,forumtags
 ## base_xenforoforum reads Published and Updated datetimes from
 ## Threadmarks if used, or from the posted & updated times of the
 ## 'first' post if no threadmarks.
-datePublished_format:%%Y-%%m-%%d %%H:%%M:%%S
+datePublished_format:%%Y-%%m-%%d %%H:%%M
-dateUpdated_format:%%Y-%%m-%%d %%H:%%M:%%S
+dateUpdated_format:%%Y-%%m-%%d %%H:%%M
 
 ## Only take the first X characters of the 'first' post to use as
 ## the description.
@@ -509,6 +549,20 @@ first_post_title:First Post
 ## if threadmarks are used.  Can result in a duplicated chapter.
 always_include_first_post:false
 
+## In normal operation, when updating an existing epub, old chapters
+## will be reused as-is.  Normally, that works fine, but forum stories
+## sometimes have an index post as the first 'chapter', and the
+## version in the first chapter gets out of sync.
+##
+## If always_reload_first_chapter:true, then the first chapter will
+## always be downloaded again (ie, reloaded).  It will NOT be maked
+## '(new)' (see mark_new_chapters).  Because it is reloaded, manual
+## edits made to the first chapter will be lost.
+##
+## While intended for base_xenforoforum sites, this setting can be
+## applied to other sites.
+always_reload_first_chapter:false
+
 ## In normal operation, forumtags will only be populated when
 ## threadmarks are used for chapters (see minimum_threadmarks above).
 ## When always_use_forumtags:true, always populate forumtags.
@@ -590,6 +644,11 @@ include_logpage: false
 ## end up with Completed stories that have just one logpage entry.
 #include_logpage: smart
 
+## By default, logpage is placed before the story chapters.  This
+## setting, if true, will place the logpage after the chapters
+## instead.
+logpage_at_end: false
+
 ## items to include in the log page Empty metadata entries, or those
 ## that haven't changed since the last update, will *not* appear, even
 ## if in the list.  You can include extra text or HTML that will be
@@ -707,6 +766,18 @@ remove_transparency: true
 ## true--replace_br_with_p also fixes the problem.
 nook_img_fix:true
 
+## Apply adapter's normalize_chapterurl() to all links in chapter
+## texts, if they match chapter URLs.  Currently only implemented by
+## base_xenforoforum adapters.
+#normalize_text_links:false
+
+## Search all links in chapter texts and, if they match any included
+## chapter URLs, replace them with links to the chapter in the
+## download.  Only works with epub and html output formats.
+## base_xenforoforum adapters should also use normalize_text_links
+## with this.
+#internalize_text_links:false
+
 [mobi]
 ## mobi TOC cannot be turned off right now.
 #include_tocpage: true
@@ -754,6 +825,19 @@ extratags: FanFiction,Testing,Text
 [test1.com:html]
 extratags: FanFiction,Testing,HTML
 
+[adult-fanfiction.org]
+extra_valid_entries:eroticatags,disclaimer
+eroticatags_label:Erotica Tags
+disclaimer_label:Disclaimer
+extra_titlepage_entries:eroticatags,disclaimer
+
+## 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
+
 [archive.skyehawke.com]
 
 [archiveofourown.org]
@@ -853,18 +937,6 @@ extracategories:The Sentinel
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
-[bdsm-geschichten.net]
-## Some sites do not require a login, but do require the user to
-## confirm they are adult for adult content.  In commandline version,
-## this should go in your personal.ini, not defaults.ini.
-#is_adult:true
-
-## This site offers no index page so we can either guess the chapter URLs
-## by dec/incrementing numbers ('guess') or walk all the chapters in the metadata
-## parsing state ('parse'). Since guessing can lead to errors for non-standard
-## story URLs, the default is to parse
-#find_chapters:guess 
-
 [bloodshedverse.com]
 ## website encoding(s) In theory, each website reports the character
 ## encoding they use for each page.  In practice, some sites report it
@@ -875,6 +947,12 @@ extracategories:The Sentinel
 ## it has +90% confidence.  'auto' is not reliable.
 website_encodings:Windows-1252,ISO-8859-1,auto
 
+## dateUpdate doesn't usually have time, but it does on
+## bloodshedverse.com.  See
+## http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+## Note that ini format requires % to be escaped as %%.
+dateUpdated_format:%%Y-%%m-%%d %%H:%%M
+
 ## Extra metadata that this adapter knows about.  See [dramione.org]
 ## for examples of how to use them.
 extra_valid_entries:warnings,reviews
@@ -904,15 +982,6 @@ strip_text_links:true
 ## Site dedicated to these categories/characters/ships
 extracategories:Blood Ties
 
-[buffynfaith.net]
-## Site dedicated to these categories/characters/ships
-extracategories:Buffy: The Vampire Slayer
-
-## Some sites also require the user to confirm they are adult for
-## adult content.  In commandline version, this should go in your
-## personal.ini, not defaults.ini.
-#is_adult:true
-
 [fanfic.castletv.net]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -1139,13 +1208,20 @@ romance_label: Romance
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
-[ficwad.com]
+[fictionhunt.com]
-## Some sites require login (or login for some rated stories) The
+## Archive only site for ffnet HP stories.
-## program can prompt you, or you can save it in config.  In
+
-## commandline version, this should go in your personal.ini, not
+## Site dedicated to these categories/characters/ships
-## defaults.ini.
+extracategories:Harry Potter
-#username:YourName
+
-#password:yourpassword
+extra_valid_entries: origin,originUrl,originHTML,reviews
+originHTML_label:Original Story URL
+
+## Assume entryUrl, apply to "<a class='%slink' href='%s'>%s</a>" to
+## make entryHTML.
+make_linkhtml_entries:origin
+
+add_to_extra_titlepage_entries:originHTML
 
 [fictionmania.tv]
 ## website encoding(s) In theory, each website reports the character
@@ -1203,6 +1279,14 @@ views_label:Views
 likes_label:Likes
 dislikes_label:Dislikes
 
+[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
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
 [finestories.com]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -1244,13 +1328,9 @@ universe_as_series: true
 ## cover image.  This lets you exclude them.
 cover_exclusion_regexp:/css/bir.png
 
-[forums.spacebattles.com]
+[forum.questionablequesting.com]
 ## see [base_xenforoforum]
 
-[forums.sufficientvelocity.com]
-## see [base_xenforoforum]
-
-[grangerenchanted.com]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
 ## commandline version, this should go in your personal.ini, not
@@ -1258,18 +1338,24 @@ cover_exclusion_regexp:/css/bir.png
 #username:YourName
 #password:yourpassword
 
-## Some sites also require the user to confirm they are adult for
+[forums.spacebattles.com]
-## adult content.  In commandline version, this should go in your
+## see [base_xenforoforum]
-## personal.ini, not defaults.ini.
+
+[forums.sufficientvelocity.com]
+## see [base_xenforoforum]
+
+[harem.lucifael.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
-## Site dedicated to these categories/characters/ships
+## Some sites require login (or login for some rated stories) The
-extracategories:Harry Potter
+## program can prompt you, or you can save it in config.  In
-extracharacters:Hermione Granger
+## commandline version, this should go in your personal.ini, not
-
+## defaults.ini.
-## Extra metadata that this adapter knows about.  See [dramione.org]
+#username:YourName
-## for examples of how to use them.
+#password:yourpassword
-extra_valid_entries:read,reviews
 
 [hlfiction.net]
 ## Site dedicated to these categories/characters/ships
@@ -1383,6 +1469,19 @@ extra_titlepage_entries: eroticatags
 ## Site dedicated to these categories/characters/ships
 extracategories:Merlin
 
+[mujaji.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
+
 [national-library.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:West Wing
@@ -1484,15 +1583,21 @@ extracategories:My Little Pony: Friendship is Magic
 ## Site dedicated to these categories/characters/ships
 extracategories:The Pretender
 
-[forum.questionablequesting.com]
+[quotev.com]
-## see [base_xenforoforum]
+extra_valid_entries:pages,readers,reads,favorites,searchtags,comments
+pages_label:Pages
+readers_label:Readers
+reads_label:Reads
+favorites_label:Favorites
+searchtags_label:Search Tags
+comments_label:Comments
 
-## Some sites require login (or login for some rated stories) The
+include_in_category:category,searchtags
-## program can prompt you, or you can save it in config.  In
+
-## commandline version, this should go in your personal.ini, not
+[royalroadl.com]
-## defaults.ini.
+extra_valid_entries:stars
-#username:YourName
+
-#password:yourpassword
+#add_to_extra_titlepage_entries:,stars
 
 [samandjack.net]
 ## Some sites require login (or login for some rated stories) The
@@ -1518,22 +1623,6 @@ extracategories:Supernatural
 extracharacters:Sam,Dean
 extraships:Sam/Dean
 
-[scarhead.net]
-## Some sites require login (or login for some rated stories) The
-## program can prompt you, or you can save it in config.  In
-## commandline version, this should go in your personal.ini, not
-## defaults.ini.
-#username:YourName
-#password:yourpassword
-
-## Some sites also require the user to confirm they are adult for
-## adult content.  In commandline version, this should go in your
-## personal.ini, not defaults.ini.
-#is_adult:true
-
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-
 [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
@@ -1675,15 +1764,6 @@ readings_label: Readings
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
-[tokra.fandomnet.com]
-## Some sites do not require a login, but do require the user to
-## confirm they are adult for adult content.  In commandline version,
-## this should go in your personal.ini, not defaults.ini.
-#is_adult:true
-
-## Site dedicated to these categories/characters/ships
-extracategories:Stargate: SG-1
-
 [tolkienfanfiction.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Lord of the Rings
@@ -1751,6 +1831,12 @@ extraships:Draco Malfoy/Ginny Weasley
 ## Site dedicated to these categories/characters/ships
 extracategories:Stargate: SG-1
 
+[www.deepinmysoul.net]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
 [www.destinysgateway.com]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
@@ -1836,6 +1922,10 @@ check_next_chapter:false
 #password:yourpassword
 
 [www.ficbook.net]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
 
 [www.fictionalley.org]
 ## Some sites do not require a login, but do require the user to
@@ -2041,11 +2131,6 @@ cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
 ## Site dedicated to these categories/characters/ships
 extracategories:NCIS
 
-[www.nickngreg.nl]
-## Site dedicated to these categories/characters/ships
-extracategories:CSI
-extraships:Nick Stokes/Greg Sanders
-
 [www.phoenixsong.net]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -2100,6 +2185,8 @@ extracategories:Psych
 extracategories:Queer as Folk
 
 [quotev.com]
+user_agent:
+slow_down_sleep_time:2
 extra_valid_entries:pages,readers,reads,favorites,searchtags,comments
 pages_label:Pages
 readers_label:Readers
@@ -2176,23 +2263,9 @@ extracategories:Lord of the Rings
 #username:YourName
 #password:yourpassword
 
-[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
-## 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
-
-## twcslibrary.net (ab)uses series as personal reading lists.
-collect_series: false
-
 [www.tthfanfic.org]
+user_agent:
+slow_down_sleep_time:2
 ## 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.
@@ -2227,6 +2300,22 @@ pairingcat_to_characters_ships:true
 ## instead be added to characters Buffy, Spike and ships Buffy/Spike
 romancecat_to_characters_ships:true
 
+[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
+## 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
+
+## twcslibrary.net (ab)uses series as personal reading lists.
+collect_series: false
+
 [www.twilightarchives.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Twilight
@@ -2275,8 +2364,9 @@ extracharacters:Wolverine,Rogue
 ## Site dedicated to these categories/characters/ships
 extracategories:Stargate: Atlantis
 
-extra_valid_entries:reviews
+##site stopped showing reviews ~ Oct 2016
-reviews_label:Reviews
+#extra_valid_entries:reviews
+#reviews_label:Reviews
 
 [buffygiles.velocitygrass.com]
 ## Some sites do not require a login, but do require the user to
@@ -2339,20 +2429,6 @@ extracategories:Andromeda
 ## Site dedicated to these categories/characters/ships
 extracategories:Artemis Fowl
 
-[www.therabidreader.com]
-## Some sites do not require a login, but do require the user to
-## confirm they are adult for adult content.  In commandline version,
-## this should go in your personal.ini, not defaults.ini.
-#is_adult:true
-
-## Some sites require login (or login for some rated stories) The
-## program can prompt you, or you can save it in config.  In
-## commandline version, this should go in your personal.ini, not
-## defaults.ini.
-#username:YourName
-#password:yourpassword
-
-
 [www.naiceanilme.net]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
@@ -2366,8 +2442,6 @@ extracategories:Artemis Fowl
 #username:YourName
 #password:yourpassword
 
-
-
 [overrides]
 ## It may sometimes be useful to override all of the specific format,
 ## site and site:format sections in your private configuration.  For

fanficfare/epubutils.py

@@ -21,6 +21,10 @@ def get_dcsource(inputio):
 def get_dcsource_chaptercount(inputio):
     return get_update_data(inputio,getfilecount=True,getsoups=False)[:2] # (source,filecount)
 
+def get_cover_data(inputio):
+    # (oldcoverhtmlhref,oldcoverhtmltype,oldcoverhtmldata,oldcoverimghref,oldcoverimgtype,oldcoverimgdata)
+    return get_update_data(inputio,getfilecount=True,getsoups=False)[4]
+
 def get_update_data(inputio,
                     getfilecount=True,
                     getsoups=True):
@@ -50,26 +54,32 @@ def get_update_data(inputio,
         if item.getAttribute("type") == "cover":
             # there is a cover (x)html file, save the soup for it.
             href=relpath+item.getAttribute("href")
-            oldcoverhtmlhref = href
-            oldcoverhtmldata = epub.read(href)
-            oldcoverhtmltype = "application/xhtml+xml"
-            for item in contentdom.getElementsByTagName("item"):
-                if( relpath+item.getAttribute("href") == oldcoverhtmlhref ):
-                    oldcoverhtmltype = item.getAttribute("media-type")
-                    break
-            soup = bs.BeautifulSoup(oldcoverhtmldata.decode("utf-8"),"html5lib")
             src = None
-            # first img or image tag.
+            try:
-            imgs = soup.findAll('img')
+                oldcoverhtmlhref = href
-            if imgs:
+                oldcoverhtmldata = epub.read(href)
-                src = get_path_part(href)+imgs[0]['src']
+                oldcoverhtmltype = "application/xhtml+xml"
-            else:
+                for item in contentdom.getElementsByTagName("item"):
-                imgs = soup.findAll('image')
+                    if( relpath+item.getAttribute("href") == oldcoverhtmlhref ):
+                        oldcoverhtmltype = item.getAttribute("media-type")
+                        break
+                soup = bs.BeautifulSoup(oldcoverhtmldata.decode("utf-8"),"html5lib")
+                # first img or image tag.
+                imgs = soup.findAll('img')
                 if imgs:
-                    src=get_path_part(href)+imgs[0]['xlink:href']
+                    src = get_path_part(href)+imgs[0]['src']
+                else:
+                    imgs = soup.findAll('image')
+                    if imgs:
+                        src=get_path_part(href)+imgs[0]['xlink:href']
+
+                if not src:
+                    continue
+            except Exception as e:
+                ## Calibre's Polish Book corrupts sub-book covers.
+                logger.warn("Cover (x)html file %s not found"%href)
+                logger.warn("Exception: %s"%(unicode(e)))
 
-            if not src:
-                continue
             try:
                 # remove all .. and the path part above it, if present.
                 # Mostly for epubs edited by Sigil.
@@ -85,7 +95,6 @@ def get_update_data(inputio,
             except Exception as e:
                 logger.warn("Cover Image %s not found"%src)
                 logger.warn("Exception: %s"%(unicode(e)))
-                traceback.print_exc()
 
     filecount = 0
     soups = [] # list of xhmtl blocks
@@ -101,12 +110,14 @@ def get_update_data(inputio,
             if( item.getAttribute("media-type") == "application/xhtml+xml" ):
                 href=relpath+item.getAttribute("href")
                 #print("---- item href:%s path part: %s"%(href,get_path_part(href)))
-                if re.match(r'.*/log_page\.x?html',href):
+                if re.match(r'.*/log_page(_u\d+)?\.x?html',href):
                     try:
                         logfile = epub.read(href).decode("utf-8")
                     except:
                         pass # corner case I bumped into while testing.
-                if re.match(r'.*/(file|chapter)\d+\.x?html',href):
+                if re.match(r'.*/(file|chapter)\d+(_u\d+)?\.x?html',href):
+                    # (_u\d+)? is from calibre convert naming files
+                    # 3/OEBPS/file0005_u3.xhtml etc.
                     if getsoups:
                         soup = bs.BeautifulSoup(epub.read(href).decode("utf-8"),"html5lib")
                         for img in soup.findAll('img'):
@@ -127,8 +138,7 @@ def get_update_data(inputio,
                                 # originally.
                                 if newsrc != u'OEBPS/failedtoload':
                                     logger.warn("Image %s not found!\n(originally:%s)"%(newsrc,longdesc))
-                                    logger.warn("Exception: %s"%(unicode(e)))
+                                    logger.warn("Exception: %s"%(unicode(e)),exc_info=True)
-                                    traceback.print_exc()
                         bodysoup = soup.find('body')
                         # ffdl epubs have chapter title h3
                         h3 = bodysoup.find('h3')

fanficfare/geturls.py

@@ -125,7 +125,10 @@ def get_urls_from_html(data,url=None,configuration=None,normalize=False,restrict
 
 def get_urls_from_text(data,configuration=None,normalize=False):
     urls = collections.OrderedDict()
-    data=unicode(data)
+    try:
+        data = unicode(data)
+    except UnicodeDecodeError:
+        data=data.decode('utf8') ## for when called outside calibre.
 
     if not configuration:
         configuration = Configuration(["test1.com"],"EPUB",lightweight=True)
@@ -229,7 +232,7 @@ def get_urls_from_imap(srv,user,passwd,folder,markread=True):
                 if part.get_content_type() == 'text/html':
                     urllist.extend(get_urls_from_html(part.get_payload(decode=True)))
             except Exception as e:
-                logger.error("Failed to read email content: %s"%e)
+                logger.error("Failed to read email content: %s"%e,exc_info=True)
         #logger.debug "urls:%s"%get_urls_from_text(get_first_text_block(email_message))
 
         if urllist and markread:

fanficfare/html2text.py

@@ -1,453 +0,0 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-
-"""html2text: Turn HTML into equivalent Markdown-structured text."""
-__version__ = "2.37"
-__author__ = "Aaron Swartz (me@aaronsw.com)"
-__copyright__ = "(C) 2004-2008 Aaron Swartz. GNU GPL 3."
-__contributors__ = ["Martin 'Joey' Schulze", "Ricardo Reyes", "Kevin Jay North"]
-
-# TODO:
-#   Support decoded entities with unifiable.
-
-if not hasattr(__builtins__, 'True'): True, False = 1, 0
-import re, sys, urllib, htmlentitydefs, codecs, StringIO, types
-import sgmllib
-import urlparse
-sgmllib.charref = re.compile('&#([xX]?[0-9a-fA-F]+)[^0-9a-fA-F]')
-
-try: from textwrap import wrap
-except: pass
-
-# Use Unicode characters instead of their ascii psuedo-replacements
-UNICODE_SNOB = 0
-
-# Put the links after each paragraph instead of at the end.
-LINKS_EACH_PARAGRAPH = 0
-
-# Wrap long lines at position. 0 for no wrapping. (Requires Python 2.3.)
-BODY_WIDTH = 78
-
-# Don't show internal links (href="#local-anchor") -- corresponding link targets
-# won't be visible in the plain text file anyway.
-SKIP_INTERNAL_LINKS = False
-
-### Entity Nonsense ###
-
-def name2cp(k):
-    if k == 'apos': return ord("'")
-    if hasattr(htmlentitydefs, "name2codepoint"): # requires Python 2.3
-        return htmlentitydefs.name2codepoint[k]
-    else:
-        k = htmlentitydefs.entitydefs[k]
-        if k.startswith("&#") and k.endswith(";"): return int(k[2:-1]) # not in latin-1
-        return ord(codecs.latin_1_decode(k)[0])
-
-unifiable = {'rsquo':"'", 'lsquo':"'", 'rdquo':'"', 'ldquo':'"', 
-'copy':'(C)', 'mdash':'--', 'nbsp':' ', 'rarr':'->', 'larr':'<-', 'middot':'*',
-'ndash':'-', 'oelig':'oe', 'aelig':'ae',
-'agrave':'a', 'aacute':'a', 'acirc':'a', 'atilde':'a', 'auml':'a', 'aring':'a', 
-'egrave':'e', 'eacute':'e', 'ecirc':'e', 'euml':'e', 
-'igrave':'i', 'iacute':'i', 'icirc':'i', 'iuml':'i',
-'ograve':'o', 'oacute':'o', 'ocirc':'o', 'otilde':'o', 'ouml':'o', 
-'ugrave':'u', 'uacute':'u', 'ucirc':'u', 'uuml':'u'}
-
-unifiable_n = {}
-
-for k in unifiable.keys():
-    unifiable_n[name2cp(k)] = unifiable[k]
-
-def charref(name):
-    if name[0] in ['x','X']:
-        c = int(name[1:], 16)
-    else:
-        c = int(name)
-    
-    if not UNICODE_SNOB and c in unifiable_n.keys():
-        return unifiable_n[c]
-    else:
-        return unichr(c)
-
-def entityref(c):
-    if not UNICODE_SNOB and c in unifiable.keys():
-        return unifiable[c]
-    else:
-        try: name2cp(c)
-        except KeyError: return "&" + c
-        else: return unichr(name2cp(c))
-
-def replaceEntities(s):
-    s = s.group(1)
-    if s[0] == "#": 
-        return charref(s[1:])
-    else: return entityref(s)
-
-r_unescape = re.compile(r"&(#?[xX]?(?:[0-9a-fA-F]+|\w{1,8}));")
-def unescape(s):
-    return r_unescape.sub(replaceEntities, s)
-    
-def fixattrs(attrs):
-    # Fix bug in sgmllib.py
-    if not attrs: return attrs
-    newattrs = []
-    for attr in attrs:
-        newattrs.append((attr[0], unescape(attr[1])))
-    return newattrs
-
-### End Entity Nonsense ###
-
-def onlywhite(line):
-    """Return true if the line does only consist of whitespace characters."""
-    for c in line:
-        if c is not ' ' and c is not '  ':
-            return c is ' '
-    return line
-
-def optwrap(text,wrap_width=BODY_WIDTH):
-    """Wrap all paragraphs in the provided text."""
-    
-    if not wrap_width:
-        return text
-    
-    assert wrap, "Requires Python 2.3."
-    result = ''
-    newlines = 0
-    for para in text.split("\n"):
-        if len(para) > 0:
-            if para[0] is not ' ' and para[0] is not '-' and para[0] is not '*':
-                for line in wrap(para, wrap_width):
-                    result += line + "\n"
-                result += "\n"
-                newlines = 2
-            else:
-                if not onlywhite(para):
-                    result += para + "\n"
-                    newlines = 1
-        else:
-            if newlines < 2:
-                result += "\n"
-                newlines += 1
-    return result
-
-def hn(tag):
-    if tag[0] == 'h' and len(tag) == 2:
-        try:
-            n = int(tag[1])
-            if n in range(1, 10): return n
-        except ValueError: return 0
-
-class _html2text(sgmllib.SGMLParser):
-    def __init__(self, out=None, baseurl=''):
-        sgmllib.SGMLParser.__init__(self)
-        
-        if out is None: self.out = self.outtextf
-        else: self.out = out
-        self.outtext = u''
-        self.quiet = 0
-        self.p_p = 0
-        self.outcount = 0
-        self.start = 1
-        self.space = 0
-        self.a = []
-        self.astack = []
-        self.acount = 0
-        self.list = []
-        self.blockquote = 0
-        self.pre = 0
-        self.startpre = 0
-        self.lastWasNL = 0
-        self.abbr_title = None # current abbreviation definition
-        self.abbr_data = None # last inner HTML (for abbr being defined)
-        self.abbr_list = {} # stack of abbreviations to write later
-        self.baseurl = baseurl
-    
-    def outtextf(self, s): 
-        self.outtext += s
-    
-    def close(self):
-        sgmllib.SGMLParser.close(self)
-        
-        self.pbr()
-        self.o('', 0, 'end')
-        
-        return self.outtext
-        
-    def handle_charref(self, c):
-        self.o(charref(c))
-
-    def handle_entityref(self, c):
-        self.o(entityref(c))
-            
-    def unknown_starttag(self, tag, attrs):
-        self.handle_tag(tag, attrs, 1)
-    
-    def unknown_endtag(self, tag):
-        self.handle_tag(tag, None, 0)
-        
-    def previousIndex(self, attrs):
-        """ returns the index of certain set of attributes (of a link) in the
-            self.a list
- 
-            If the set of attributes is not found, returns None
-        """
-        if not attrs.has_attr('href'): return None
-        
-        i = -1
-        for a in self.a:
-            i += 1
-            match = 0
-            
-            if a.has_attr('href') and a['href'] == attrs['href']:
-                if a.has_attr('title') or attrs.has_attr('title'):
-                        if (a.has_attr('title') and attrs.has_attr('title') and
-                            a['title'] == attrs['title']):
-                            match = True
-                else:
-                    match = True
-
-            if match: return i
-
-    def handle_tag(self, tag, attrs, start):
-        attrs = fixattrs(attrs)
-    
-        if hn(tag):
-            self.p()
-            if start: self.o(hn(tag)*"#" + ' ')
-
-        if tag in ['p', 'div']: self.p()
-        
-        if tag == "br" and start: self.o("  \n")
-
-        if tag == "hr" and start:
-            self.p()
-            self.o("* * *")
-            self.p()
-
-        if tag in ["head", "style", 'script']: 
-            if start: self.quiet += 1
-            else: self.quiet -= 1
-
-        if tag in ["body"]:
-            self.quiet = 0 # sites like 9rules.com never close <head>
-        
-        if tag == "blockquote":
-            if start: 
-                self.p(); self.o('> ', 0, 1); self.start = 1
-                self.blockquote += 1
-            else:
-                self.blockquote -= 1
-                self.p()
-        
-        if tag in ['em', 'i', 'u']: self.o("_")
-        if tag in ['strong', 'b']: self.o("**")
-        if tag == "code" and not self.pre: self.o('`') #TODO: `` `this` ``
-        if tag == "abbr":
-            if start:
-                attrsD = {}
-                for (x, y) in attrs: attrsD[x] = y
-                attrs = attrsD
-                
-                self.abbr_title = None
-                self.abbr_data = ''
-                if attrs.has_attr('title'):
-                    self.abbr_title = attrs['title']
-            else:
-                if self.abbr_title != None:
-                    self.abbr_list[self.abbr_data] = self.abbr_title
-                    self.abbr_title = None
-                self.abbr_data = ''
-        
-        if tag == "a":
-            if start:
-                attrsD = {}
-                for (x, y) in attrs: attrsD[x] = y
-                attrs = attrsD
-                if attrs.has_attr('href') and not (SKIP_INTERNAL_LINKS and attrs['href'].startswith('#')): 
-                    self.astack.append(attrs)
-                    self.o("[")
-                else:
-                    self.astack.append(None)
-            else:
-                if self.astack:
-                    a = self.astack.pop()
-                    if a:
-                        i = self.previousIndex(a)
-                        if i is not None:
-                            a = self.a[i]
-                        else:
-                            self.acount += 1
-                            a['count'] = self.acount
-                            a['outcount'] = self.outcount
-                            self.a.append(a)
-                        self.o("][" + `a['count']` + "]")
-        
-        if tag == "img" and start:
-            attrsD = {}
-            for (x, y) in attrs: attrsD[x] = y
-            attrs = attrsD
-            if attrs.has_attr('src'):
-                attrs['href'] = attrs['src']
-                alt = attrs.get('alt', '')
-                i = self.previousIndex(attrs)
-                if i is not None:
-                    attrs = self.a[i]
-                else:
-                    self.acount += 1
-                    attrs['count'] = self.acount
-                    attrs['outcount'] = self.outcount
-                    self.a.append(attrs)
-                self.o("![")
-                self.o(alt)
-                self.o("]["+`attrs['count']`+"]")
-        
-        if tag == 'dl' and start: self.p()
-        if tag == 'dt' and not start: self.pbr()
-        if tag == 'dd' and start: self.o('    ')
-        if tag == 'dd' and not start: self.pbr()
-        
-        if tag in ["ol", "ul"]:
-            if start:
-                self.list.append({'name':tag, 'num':0})
-            else:
-                if self.list: self.list.pop()
-            
-            self.p()
-        
-        if tag == 'li':
-            if start:
-                self.pbr()
-                if self.list: li = self.list[-1]
-                else: li = {'name':'ul', 'num':0}
-                self.o("  "*len(self.list)) #TODO: line up <ol><li>s > 9 correctly.
-                if li['name'] == "ul": self.o("* ")
-                elif li['name'] == "ol":
-                    li['num'] += 1
-                    self.o(`li['num']`+". ")
-                self.start = 1
-            else:
-                self.pbr()
-        
-        if tag in ["table", "tr"] and start: self.p()
-        if tag == 'td': self.pbr()
-        
-        if tag == "pre":
-            if start:
-                self.startpre = 1
-                self.pre = 1
-            else:
-                self.pre = 0
-            self.p()
-            
-    def pbr(self):
-        if self.p_p == 0: self.p_p = 1
-
-    def p(self): self.p_p = 2
-    
-    def o(self, data, puredata=0, force=0):
-        if self.abbr_data is not None: self.abbr_data += data
-        
-        if not self.quiet: 
-            if puredata and not self.pre:
-                data = re.sub('\s+', ' ', data)
-                if data and data[0] == ' ':
-                    self.space = 1
-                    data = data[1:]
-            if not data and not force: return
-            
-            if self.startpre:
-                #self.out(" :") #TODO: not output when already one there
-                self.startpre = 0
-            
-            bq = (">" * self.blockquote)
-            if not (force and data and data[0] == ">") and self.blockquote: bq += " "
-            
-            if self.pre:
-                bq += "    "
-                data = data.replace("\n", "\n"+bq)
-            
-            if self.start:
-                self.space = 0
-                self.p_p = 0
-                self.start = 0
-
-            if force == 'end':
-                # It's the end.
-                self.p_p = 0
-                self.out("\n")
-                self.space = 0
-
-
-            if self.p_p:
-                self.out(('\n'+bq)*self.p_p)
-                self.space = 0
-                
-            if self.space:
-                if not self.lastWasNL: self.out(' ')
-                self.space = 0
-
-            if self.a and ((self.p_p == 2 and LINKS_EACH_PARAGRAPH) or force == "end"):
-                if force == "end": self.out("\n")
-
-                newa = []
-                for link in self.a:
-                    if self.outcount > link['outcount']:
-                        self.out("   ["+`link['count']`+"]: " + urlparse.urljoin(self.baseurl, link['href'])) 
-                        if link.has_attr('title'): self.out(" ("+link['title']+")")
-                        self.out("\n")
-                    else:
-                        newa.append(link)
-
-                if self.a != newa: self.out("\n") # Don't need an extra line when nothing was done.
-
-                self.a = newa
-            
-            if self.abbr_list and force == "end":
-                for abbr, definition in self.abbr_list.items():
-                    self.out("  *[" + abbr + "]: " + definition + "\n")
-
-            self.p_p = 0
-            self.out(data)
-            self.lastWasNL = data and data[-1] == '\n'
-            self.outcount += 1
-
-    def handle_data(self, data):
-        if r'\/script>' in data: self.quiet -= 1
-        self.o(data, 1)
-    
-    def unknown_decl(self, data): pass
-
-def wrapwrite(text): sys.stdout.write(text.encode('utf8'))
-
-def html2text_file(html, out=wrapwrite, baseurl=''):
-    h = _html2text(out, baseurl)
-    h.feed(html)
-    h.feed("")
-    return h.close()
-
-def html2text(html, baseurl='', wrap_width=BODY_WIDTH):
-    return optwrap(html2text_file(html, None, baseurl),wrap_width)
-
-if __name__ == "__main__":
-    baseurl = ''
-    if sys.argv[1:]:
-        arg = sys.argv[1]
-        if arg.startswith('http://'):
-            baseurl = arg
-            j = urllib.urlopen(baseurl)
-            try:
-                from feedparser import _getCharacterEncoding as enc
-            except ImportError:
-                   enc = lambda x, y: ('utf-8', 1)
-            text = j.read()
-            encoding = enc(j.headers, text)[0]
-            if encoding == 'us-ascii': encoding = 'utf-8'
-            data = text.decode(encoding)
-
-        else:
-            encoding = 'utf8'
-            if len(sys.argv) > 2:
-                encoding = sys.argv[2]
-            data = open(arg, 'r').read().decode(encoding)
-    else:
-        data = sys.stdin.read().decode('utf8')
-    wrapwrite(html2text(data, baseurl))

fanficfare/story.py

@@ -997,20 +997,28 @@ class Story(Configurable):
 
         return retval
 
+    def get_filename_safe_metadata(self):
+        origvalues = self.getAllMetadata()
+        values={}
+        pattern = re_compile(self.getConfig("output_filename_safepattern",
+                                            r"(^\.|/\.|[^a-zA-Z0-9_\. \[\]\(\)&'-]+)"),
+                             "output_filename_safepattern")
+        for k in origvalues.keys():
+            if k == 'formatext': # don't do file extension--we set it anyway.
+                values[k]=self.getMetadata(k)
+            else:
+                values[k]=re.sub(pattern,'_', removeAllEntities(self.getMetadata(k)))
+        return values
+    
     def formatFileName(self,template,allowunsafefilename=True):
-        values = origvalues = self.getAllMetadata()
         # fall back default:
         if not template:
             template="${title}-${siteabbrev}_${storyId}${formatext}"
 
-        if not allowunsafefilename:
+        if allowunsafefilename:
-            values={}
+            values = self.getAllMetadata()
-            pattern = re_compile(self.getConfig("output_filename_safepattern",r"(^\.|/\.|[^a-zA-Z0-9_\. \[\]\(\)&'-]+)"),"output_filename_safepattern")
+        else:
-            for k in origvalues.keys():
+            values = self.get_filename_safe_metadata()
-                if k == 'formatext': # don't do file extension--we set it anyway.
-                    values[k]=self.getMetadata(k)
-                else:
-                    values[k]=re.sub(pattern,'_', removeAllEntities(self.getMetadata(k)))
 
         return string.Template(template).substitute(values).encode('utf8')
 
@@ -1069,6 +1077,9 @@ class Story(Configurable):
         if imgurl not in self.imgurls:
 
             try:
+                if imgurl == 'failedtoload':
+                    raise Exception("Previously failed to load")
+
                 parsedUrl = urlparse.urlparse(imgurl)
                 if self.getConfig('no_image_processing'):
                     (data,ext,mime) = no_convert_image(imgurl,

fanficfare/writers/writer_epub.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
+# Copyright 2011 Fanficdownloader team, 2016 FanFicFare team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -27,8 +27,11 @@ import re
 ## use DOM to generate the XML files.
 from xml.dom.minidom import parse, parseString, getDOMImplementation
 
+import bs4
+
 from base_writer import *
 from ..htmlcleanup import stripHTML,removeEntities
+from ..story import commaGroups
 
 logger = logging.getLogger(__name__)
 
@@ -46,7 +49,7 @@ class EpubWriter(BaseStoryWriter):
         BaseStoryWriter.__init__(self, config, story)
 
         self.EPUB_CSS = string.Template('''${output_css}''')
-        
+
         self.EPUB_TITLE_PAGE_START = string.Template('''<?xml version="1.0" encoding="UTF-8"?>
 <html xmlns="http://www.w3.org/1999/xhtml">
 <head>
@@ -117,7 +120,7 @@ ${value}<br />
         self.EPUB_TOC_ENTRY = string.Template('''
 <a href="file${index}.xhtml">${chapter}</a><br />
 ''')
-                          
+
         self.EPUB_TOC_PAGE_END = string.Template('''
 </div>
 </body>
@@ -156,15 +159,15 @@ ${value}<br />
         self.EPUB_LOG_UPDATE_START = string.Template('''
 <p class='log_entry'>
 ''')
-                          
+
         self.EPUB_LOG_ENTRY = string.Template('''
 <b>${label}:</b> <span id="${id}">${value}</span>
 ''')
-                          
+
         self.EPUB_LOG_UPDATE_END = string.Template('''
 </p><hr />
 ''')
-                          
+
         self.EPUB_LOG_PAGE_END = string.Template('''
 </body>
 </html>
@@ -184,7 +187,7 @@ div { margin: 0pt; padding: 0pt; }
 <img src="${coverimg}" alt="cover"/>
 </div></body></html>
 ''')
-        
+
     def writeLogPage(self, out):
         """
         Write the log page, but only include entries that there's
@@ -201,12 +204,12 @@ div { margin: 0pt; padding: 0pt; }
             END = string.Template(self.getConfig("logpage_end"))
         else:
             END = self.EPUB_LOG_PAGE_END
-        
+
         # if there's a self.story.logfile, there's an existing log
         # to add to.
         if self.story.logfile:
             logger.debug("existing logfile found, appending")
-            logger.debug("existing data:%s"%self._getLastLogData(self.story.logfile))
+            # logger.debug("existing data:%s"%self._getLastLogData(self.story.logfile))
             replace_string = "</body>" # "</h3>"
             self._write(out,self.story.logfile.replace(replace_string,self._makeLogEntry(self._getLastLogData(self.story.logfile))+replace_string))
         else:
@@ -234,7 +237,7 @@ div { margin: 0pt; padding: 0pt; }
                 pass
 
         return values
-        
+
     def _makeLogEntry(self, oldvalues={}):
         if self.hasConfig("logpage_update_start"):
             START = string.Template(self.getConfig("logpage_update_start"))
@@ -253,6 +256,14 @@ div { margin: 0pt; padding: 0pt; }
 
         retval = START.substitute(self.story.getAllMetadata())
 
+        ## words_added is only used in logpage because it's the only
+        ## place we know the previous version's word count.
+        if 'words_added' in (self.getConfigList("logpage_entries") + self.getConfigList("extra_logpage_entries")):
+            new_words = self.story.getMetadata('numWords')
+            old_words = oldvalues.get('numWords',None)
+            if new_words and old_words:
+                self.story.setMetadata('words_added',commaGroups(unicode(int(new_words.replace(',',''))-int(old_words.replace(',','')))))
+
         for entry in self.getConfigList("logpage_entries") + self.getConfigList("extra_logpage_entries"):
             if self.isValidMetaEntry(entry):
                 val = self.story.getMetadata(entry)
@@ -275,16 +286,16 @@ div { margin: 0pt; padding: 0pt; }
                 # mostly it makes it easy to tell when you get the
                 # keyword wrong.
                 retval = retval + entry
-                
+
         retval = retval + END.substitute(self.story.getAllMetadata())
-        
+
         if self.getConfig('replace_hr'):
             # replacing a self-closing tag with a container tag in the
             # soup is more difficult than it first appears.  So cheat.
             retval = re.sub("<hr[^>]*>","<div class='center'>* * *</div>",retval)
-            
+
         return retval
-                
+
     def writeStoryImpl(self, out):
 
         ## Python 2.5 ZipFile is rather more primative than later
@@ -305,7 +316,7 @@ div { margin: 0pt; padding: 0pt; }
         ## Re-open file for content.
         outputepub = ZipFile(zipio, 'a', compression=ZIP_DEFLATED)
         outputepub.debug=3
-        
+
         ## Create META-INF/container.xml file.  The only thing it does is
         ## point to content.opf
         containerdom = getDOMImplementation().createDocument(None, "container", None)
@@ -332,7 +343,7 @@ div { margin: 0pt; padding: 0pt; }
             self.getMetadata('site'),
             self.story.getList('authorId')[0],
             self.getMetadata('storyId'))
-        
+
         contentdom = getDOMImplementation().createDocument(None, "package", None)
         package = contentdom.documentElement
         package.setAttribute("version","2.0")
@@ -374,12 +385,12 @@ div { margin: 0pt; padding: 0pt; }
             metadata.appendChild(newTag(contentdom,"dc:date",
                                         attrs={"opf:event":"publication"},
                                         text=self.story.getMetadataRaw('datePublished').strftime("%Y-%m-%d")))
-        
+
         if self.story.getMetadataRaw('dateCreated'):
             metadata.appendChild(newTag(contentdom,"dc:date",
                                         attrs={"opf:event":"creation"},
                                         text=self.story.getMetadataRaw('dateCreated').strftime("%Y-%m-%d")))
-        
+
         if self.story.getMetadataRaw('dateUpdated'):
             metadata.appendChild(newTag(contentdom,"dc:date",
                                         attrs={"opf:event":"modification"},
@@ -387,7 +398,7 @@ div { margin: 0pt; padding: 0pt; }
             metadata.appendChild(newTag(contentdom,"meta",
                                         attrs={"name":"calibre:timestamp",
                                                "content":self.story.getMetadataRaw('dateUpdated').strftime("%Y-%m-%dT%H:%M:%S")}))
-        
+
         if self.getMetadata('description'):
             metadata.appendChild(newTag(contentdom,"dc:description",text=
                                         self.getMetadata('description')))
@@ -395,11 +406,11 @@ div { margin: 0pt; padding: 0pt; }
         for subject in self.story.getSubjectTags():
             metadata.appendChild(newTag(contentdom,"dc:subject",text=subject))
 
-                    
+
         if self.getMetadata('site'):
             metadata.appendChild(newTag(contentdom,"dc:publisher",
                                         text=self.getMetadata('site')))
-        
+
         if self.getMetadata('storyUrl'):
             metadata.appendChild(newTag(contentdom,"dc:identifier",
                                         attrs={"opf:scheme":"URL"},
@@ -415,7 +426,7 @@ div { margin: 0pt; padding: 0pt; }
 
         guide = None
         coverIO = None
-                
+
         coverimgid = "image0000"
         if not self.story.cover and self.story.oldcover:
             logger.debug("writer_epub: no new cover, has old cover, write image.")
@@ -427,7 +438,7 @@ div { margin: 0pt; padding: 0pt; }
              oldcoverimgdata) = self.story.oldcover
             outputepub.writestr(oldcoverhtmlhref,oldcoverhtmldata)
             outputepub.writestr(oldcoverimghref,oldcoverimgdata)
-            
+
             coverimgid = "image0"
             items.append((coverimgid,
                           oldcoverimghref,
@@ -441,8 +452,8 @@ div { margin: 0pt; padding: 0pt; }
             guide.appendChild(newTag(contentdom,"reference",attrs={"type":"cover",
                                                                    "title":"Cover",
                                                                    "href":oldcoverhtmlhref}))
-            
+
-            
+
 
         if self.getConfig('include_images'):
             imgcount=0
@@ -459,7 +470,7 @@ div { margin: 0pt; padding: 0pt; }
                     # just the first image.
                     coverimgid = items[-1][0]
 
-        
+
         items.append(("style","OEBPS/stylesheet.css","text/css",None))
 
         if self.story.cover:
@@ -467,7 +478,7 @@ div { margin: 0pt; padding: 0pt; }
             # for it to work on Nook.
             items.append(("cover","OEBPS/cover.xhtml","application/xhtml+xml",None))
             itemrefs.append("cover")
-            # 
+            #
             # <meta name="cover" content="cover.jpg"/>
             metadata.appendChild(newTag(contentdom,"meta",{"content":coverimgid,
                                                            "name":"cover"}))
@@ -480,14 +491,14 @@ div { margin: 0pt; padding: 0pt; }
             guide.appendChild(newTag(contentdom,"reference",attrs={"type":"cover",
                                                        "title":"Cover",
                                                        "href":"OEBPS/cover.xhtml"}))
-            
+
             if self.hasConfig("cover_content"):
                 COVER = string.Template(self.getConfig("cover_content"))
             else:
                 COVER = self.EPUB_COVER
             coverIO = StringIO.StringIO()
             coverIO.write(COVER.substitute(dict(self.story.getAllMetadata().items()+{'coverimg':self.story.cover}.items())))
-            
+
         if self.getConfig("include_titlepage"):
             items.append(("title_page","OEBPS/title_page.xhtml","application/xhtml+xml","Title Page"))
             itemrefs.append("title_page")
@@ -495,14 +506,15 @@ div { margin: 0pt; padding: 0pt; }
             items.append(("toc_page","OEBPS/toc_page.xhtml","application/xhtml+xml","Table of Contents"))
             itemrefs.append("toc_page")
 
+        ## save where to insert logpage.
+        logpage_indices = (len(items),len(itemrefs))
+
         dologpage = ( self.getConfig("include_logpage") == "smart" and \
                           (self.story.logfile or self.story.getMetadataRaw("status") == "In-Progress") )  \
                      or self.getConfig("include_logpage") == "true"
 
-        if dologpage:
+        ## collect chapter urls and file names for internalize_text_links option.
-            items.append(("log_page","OEBPS/log_page.xhtml","application/xhtml+xml","Update Log"))
+        chapurlmap = {}
-            itemrefs.append("log_page")
-            
         for index, chap in enumerate(self.story.getChapters(fortoc=True)):
             if chap.html:
                 i=index+1
@@ -511,6 +523,14 @@ div { margin: 0pt; padding: 0pt; }
                               "application/xhtml+xml",
                               chap.title))
                 itemrefs.append("file%04d"%i)
+                chapurlmap[chap.url]="file%04d.xhtml"%i # url -> relative epub file name.
+
+        if dologpage:
+            if self.getConfig("logpage_at_end") == "true":
+                ## insert logpage after chapters.
+                logpage_indices = (len(items),len(itemrefs))
+            items.insert(logpage_indices[0],("log_page","OEBPS/log_page.xhtml","application/xhtml+xml","Update Log"))
+            itemrefs.insert(logpage_indices[1],"log_page")
 
         manifest = contentdom.createElement("manifest")
         package.appendChild(manifest)
@@ -520,7 +540,7 @@ div { margin: 0pt; padding: 0pt; }
                                         attrs={'id':id,
                                                'href':href,
                                                'media-type':type}))
-        
+
         spine = newTag(contentdom,"spine",attrs={"toc":"ncx"})
         package.appendChild(spine)
         for itemref in itemrefs:
@@ -530,10 +550,10 @@ div { margin: 0pt; padding: 0pt; }
         # guide only exists if there's a cover.
         if guide:
             package.appendChild(guide)
-            
+
         # write content.opf to zip.
         contentxml = contentdom.toxml(encoding='utf-8')
-        
+
         # tweak for brain damaged Nook STR.  Nook insists on name before content.
         contentxml = contentxml.replace('<meta content="%s" name="cover"/>'%coverimgid,
                                         '<meta name="cover" content="%s"/>'%coverimgid)
@@ -557,11 +577,11 @@ div { margin: 0pt; padding: 0pt; }
                                 attrs={"name":"dtb:totalPageCount", "content":"0"}))
         head.appendChild(newTag(tocncxdom,"meta",
                                 attrs={"name":"dtb:maxPageNumber", "content":"0"}))
-        
+
         docTitle = tocncxdom.createElement("docTitle")
         docTitle.appendChild(newTag(tocncxdom,"text",text=self.getMetadata('title')))
         ncx.appendChild(docTitle)
-    
+
         tocnavMap = tocncxdom.createElement("navMap")
         ncx.appendChild(tocnavMap)
 
@@ -586,14 +606,14 @@ div { margin: 0pt; padding: 0pt; }
                 navLabel.appendChild(newTag(tocncxdom,"text",text=stripHTML(title)))
                 navPoint.appendChild(newTag(tocncxdom,"content",attrs={"src":href}))
                 index=index+1
-        
+
         # write toc.ncx to zip file
         outputepub.writestr("toc.ncx",tocncxdom.toxml(encoding='utf-8'))
         tocncxdom.unlink()
         del tocncxdom
 
         # write stylesheet.css file.
-        outputepub.writestr("OEBPS/stylesheet.css",self.EPUB_CSS.substitute(self.story.getAllMetadata())) 
+        outputepub.writestr("OEBPS/stylesheet.css",self.EPUB_CSS.substitute(self.story.getAllMetadata()))
 
         # write title page.
         if self.getConfig("titlepage_use_table"):
@@ -612,7 +632,7 @@ div { margin: 0pt; padding: 0pt; }
         if coverIO:
             outputepub.writestr("OEBPS/cover.xhtml",coverIO.getvalue())
             coverIO.close()
-            
+
         titlepageIO = StringIO.StringIO()
         self.writeTitlePage(out=titlepageIO,
                             START=TITLE_PAGE_START,
@@ -624,7 +644,7 @@ div { margin: 0pt; padding: 0pt; }
             outputepub.writestr("OEBPS/title_page.xhtml",titlepageIO.getvalue())
         titlepageIO.close()
 
-        # write toc page.  
+        # write toc page.
         tocpageIO = StringIO.StringIO()
         self.writeTOCPage(tocpageIO,
                           self.EPUB_TOC_PAGE_START,
@@ -645,14 +665,28 @@ div { margin: 0pt; padding: 0pt; }
             CHAPTER_START = string.Template(self.getConfig("chapter_start"))
         else:
             CHAPTER_START = self.EPUB_CHAPTER_START
-        
+
         if self.hasConfig('chapter_end'):
             CHAPTER_END = string.Template(self.getConfig("chapter_end"))
         else:
             CHAPTER_END = self.EPUB_CHAPTER_END
-        
+
         for index, chap in enumerate(self.story.getChapters()): # (url,title,html)
             if chap.html:
+                chap_data = chap.html
+                if self.getConfig('internalize_text_links'):
+                    soup = bs4.BeautifulSoup(chap.html,'html5lib')
+                    changed=False
+                    for alink in soup.find_all('a'):
+                        if alink.has_attr('href') and alink['href'] in chapurlmap:
+                            alink['href']=chapurlmap[alink['href']]
+                            changed=True
+                    if changed:
+                        chap_data = unicode(soup)
+                        # Don't want html, head or body tags in
+                        # chapter html--bs4 insists on adding them.
+                        chap_data = re.sub(r"</?(html|head|body)[^>]*>\r?\n?","",chap_data)
+
                 #logger.debug('Writing chapter text for: %s' % chap.title)
                 vals={'url':removeEntities(chap.url),
                       'chapter':removeEntities(chap.title),
@@ -664,7 +698,9 @@ div { margin: 0pt; padding: 0pt; }
                 for k,v in vals.items():
                     if isinstance(v,basestring): vals[k]=v.replace('"','&quot;')
                 fullhtml = CHAPTER_START.substitute(vals) + \
-                    chap.html + CHAPTER_END.substitute(vals)
+                    chap_data.strip() + \
+                    CHAPTER_END.substitute(vals)
+                # strip to avoid ever growning numbers of newlines.
                 # ffnet(& maybe others) gives the whole chapter text
                 # as one line.  This causes problems for nook(at
                 # least) when the chapter size starts getting big

fanficfare/writers/writer_html.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
+# Copyright 2011 Fanficdownloader team, 2016 FanFicFare team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -18,6 +18,8 @@
 import logging
 import string
 
+import bs4
+
 from base_writer import *
 
 class HTMLWriter(BaseStoryWriter):
@@ -32,7 +34,7 @@ class HTMLWriter(BaseStoryWriter):
 
     def __init__(self, config, story):
         BaseStoryWriter.__init__(self, config, story)
-        
+
         self.HTML_FILE_START = string.Template('''<!DOCTYPE html>
 <html>
 <head>
@@ -48,7 +50,7 @@ ${output_css}
         self.HTML_COVER = string.Template('''
 <img src="${coverimg}" alt="cover" />
 ''')
-        
+
         self.HTML_TITLE_PAGE_START = string.Template('''
 <table class="full">
 ''')
@@ -62,14 +64,14 @@ ${output_css}
 ''')
 
         self.HTML_TOC_PAGE_START = string.Template('''
-<a name="TOCTOP"><h2>Table of Contents</h2>
+<a name="TOCTOP"><h2>Table of Contents</h2></a>
 <p>
 ''')
 
         self.HTML_TOC_ENTRY = string.Template('''
 <a href="#section${index}">${chapter}</a><br />
 ''')
-                          
+
         self.HTML_TOC_PAGE_END = string.Template('''
 </p>
 ''')
@@ -100,12 +102,12 @@ ${output_css}
             FILE_END = string.Template(self.getConfig("file_end"))
         else:
             FILE_END = self.HTML_FILE_END
-        
+
         self._write(out,FILE_START.substitute(self.story.getAllMetadata()))
 
         if self.getConfig('include_images') and self.story.cover:
             self._write(out,COVER.substitute(dict(self.story.getAllMetadata().items()+{'coverimg':self.story.cover}.items())))
-            
+
         self.writeTitlePage(out,
                             self.HTML_TITLE_PAGE_START,
                             self.HTML_TITLE_ENTRY,
@@ -120,18 +122,43 @@ ${output_css}
             CHAPTER_START = string.Template(self.getConfig("chapter_start"))
         else:
             CHAPTER_START = self.HTML_CHAPTER_START
-        
+
         if self.hasConfig('chapter_end'):
             CHAPTER_END = string.Template(self.getConfig("chapter_end"))
         else:
             CHAPTER_END = self.HTML_CHAPTER_END
-        
+
+        ## collect chapter urls and file names for internalize_text_links option.
+        chapurlmap = {}
         for index, chap in enumerate(self.story.getChapters()):
             if chap.html:
+                ## HTML_CHAPTER_START needs to have matching <a>
+                ## anchor to work.  Which it does by default.  This
+                ## could also be made configurable if some user
+                ## changed it.
+                chapurlmap[chap.url]="#section%04d"%(index+1) # url -> index
+
+        for index, chap in enumerate(self.story.getChapters()):
+            if chap.html:
+                chap_data = chap.html
+                if self.getConfig('internalize_text_links'):
+                    soup = bs4.BeautifulSoup(chap.html,'html5lib')
+                    changed=False
+                    for alink in soup.find_all('a'):
+                        if alink.has_attr('href') and alink['href'] in chapurlmap:
+                            alink['href']=chapurlmap[alink['href']]
+                            changed=True
+                    if changed:
+                        chap_data = unicode(soup)
+                        # Don't want html, head or body tags in
+                        # chapter html--bs4 insists on adding them.
+                        chap_data = re.sub(r"</?(html|head|body)[^>]*>\r?\n?","",chap_data)
+
+
                 logging.debug('Writing chapter text for: %s' % chap.title)
                 vals={'url':chap.url, 'chapter':chap.title, 'index':"%04d"%(index+1), 'number':index+1}
                 self._write(out,CHAPTER_START.substitute(vals))
-                self._write(out,chap.html)
+                self._write(out,chap_data)
                 self._write(out,CHAPTER_END.substitute(vals))
 
         self._write(out,FILE_END.substitute(self.story.getAllMetadata()))
@@ -139,4 +166,4 @@ ${output_css}
         if self.getConfig('include_images'):
             for imgmap in self.story.getImgUrls():
                 self.writeFile(imgmap['newsrc'],imgmap['data'])
-        
+

fanficfare/writers/writer_txt.py

@@ -21,7 +21,7 @@ from textwrap import wrap
 
 from base_writer import *
 
-from ..html2text import html2text
+from html2text import html2text
 
 ## In BaseStoryWriter, we define _write to encode <unicode> objects
 ## back into <string> for true output.  But txt needs to write the
@@ -109,7 +109,7 @@ End file.
 
         self.wrap_width = self.getConfig('wrap_width')
         if self.wrap_width == '' or self.wrap_width == '0':
-            self.wrap_width = None
+            self.wrap_width = 0
         else:
             self.wrap_width = int(self.wrap_width)
         
@@ -159,7 +159,7 @@ End file.
                 logging.debug('Writing chapter text for: %s' % chap.title)
                 vals={'url':chap.url, 'chapter':chap.title, 'index':"%04d"%(index+1), 'number':index+1}
                 self._write(out,self.lineends(self.wraplines(removeAllEntities(CHAPTER_START.substitute(vals)))))
-                self._write(out,self.lineends(html2text(chap.html,wrap_width=self.wrap_width)))
+                self._write(out,self.lineends(html2text(chap.html,bodywidth=self.wrap_width)))
                 self._write(out,self.lineends(self.wraplines(removeAllEntities(CHAPTER_END.substitute(vals)))))
 
         self._write(out,self.lineends(self.wraplines(FILE_END.substitute(self.story.getAllMetadata()))))

included_dependencies/html2text/__init__.py

@@ -0,0 +1,857 @@
+#!/usr/bin/env python
+# coding: utf-8
+"""html2text: Turn HTML into equivalent Markdown-structured text."""
+from __future__ import division
+import re
+import sys
+import cgi
+
+try:
+    from textwrap import wrap
+except ImportError:  # pragma: no cover
+    pass
+
+from html2text.compat import urlparse, HTMLParser
+from html2text import config
+
+from html2text.utils import (
+    name2cp,
+    unifiable_n,
+    google_text_emphasis,
+    google_fixed_width_font,
+    element_style,
+    hn,
+    google_has_height,
+    escape_md,
+    google_list_style,
+    list_numbering_start,
+    dumb_css_parser,
+    escape_md_section,
+    skipwrap
+)
+
+__version__ = (2016, 4, 2)
+
+
+# TODO:
+# Support decoded entities with UNIFIABLE.
+
+
+class HTML2Text(HTMLParser.HTMLParser):
+    def __init__(self, out=None, baseurl='', bodywidth=config.BODY_WIDTH):
+        """
+        Input parameters:
+            out: possible custom replacement for self.outtextf (which
+                 appends lines of text).
+            baseurl: base URL of the document we process
+        """
+        kwargs = {}
+        if sys.version_info >= (3, 4):
+            kwargs['convert_charrefs'] = False
+        HTMLParser.HTMLParser.__init__(self, **kwargs)
+
+        # Config options
+        self.split_next_td = False
+        self.td_count = 0
+        self.table_start = False
+        self.unicode_snob = config.UNICODE_SNOB  # covered in cli
+        self.escape_snob = config.ESCAPE_SNOB  # covered in cli
+        self.links_each_paragraph = config.LINKS_EACH_PARAGRAPH
+        self.body_width = bodywidth  # covered in cli
+        self.skip_internal_links = config.SKIP_INTERNAL_LINKS  # covered in cli
+        self.inline_links = config.INLINE_LINKS  # covered in cli
+        self.protect_links = config.PROTECT_LINKS  # covered in cli
+        self.google_list_indent = config.GOOGLE_LIST_INDENT  # covered in cli
+        self.ignore_links = config.IGNORE_ANCHORS  # covered in cli
+        self.ignore_images = config.IGNORE_IMAGES  # covered in cli
+        self.images_to_alt = config.IMAGES_TO_ALT  # covered in cli
+        self.images_with_size = config.IMAGES_WITH_SIZE  # covered in cli
+        self.ignore_emphasis = config.IGNORE_EMPHASIS  # covered in cli
+        self.bypass_tables = config.BYPASS_TABLES  # covered in cli
+        self.google_doc = False  # covered in cli
+        self.ul_item_mark = '*'  # covered in cli
+        self.emphasis_mark = '_'  # covered in cli
+        self.strong_mark = '**'
+        self.single_line_break = config.SINGLE_LINE_BREAK  # covered in cli
+        self.use_automatic_links = config.USE_AUTOMATIC_LINKS  # covered in cli
+        self.hide_strikethrough = False  # covered in cli
+        self.mark_code = config.MARK_CODE
+        self.wrap_links = config.WRAP_LINKS  # covered in cli
+        self.tag_callback = None
+
+        if out is None:  # pragma: no cover
+            self.out = self.outtextf
+        else:  # pragma: no cover
+            self.out = out
+
+        # empty list to store output characters before they are "joined"
+        self.outtextlist = []
+
+        self.quiet = 0
+        self.p_p = 0  # number of newline character to print before next output
+        self.outcount = 0
+        self.start = 1
+        self.space = 0
+        self.a = []
+        self.astack = []
+        self.maybe_automatic_link = None
+        self.empty_link = False
+        self.absolute_url_matcher = re.compile(r'^[a-zA-Z+]+://')
+        self.acount = 0
+        self.list = []
+        self.blockquote = 0
+        self.pre = 0
+        self.startpre = 0
+        self.code = False
+        self.br_toggle = ''
+        self.lastWasNL = 0
+        self.lastWasList = False
+        self.style = 0
+        self.style_def = {}
+        self.tag_stack = []
+        self.emphasis = 0
+        self.drop_white_space = 0
+        self.inheader = False
+        self.abbr_title = None  # current abbreviation definition
+        self.abbr_data = None  # last inner HTML (for abbr being defined)
+        self.abbr_list = {}  # stack of abbreviations to write later
+        self.baseurl = baseurl
+
+        try:
+            del unifiable_n[name2cp('nbsp')]
+        except KeyError:
+            pass
+        config.UNIFIABLE['nbsp'] = '&nbsp_place_holder;'
+
+    def feed(self, data):
+        data = data.replace("</' + 'script>", "</ignore>")
+        HTMLParser.HTMLParser.feed(self, data)
+
+    def handle(self, data):
+        self.feed(data)
+        self.feed("")
+        return self.optwrap(self.close())
+
+    def outtextf(self, s):
+        self.outtextlist.append(s)
+        if s:
+            self.lastWasNL = s[-1] == '\n'
+
+    def close(self):
+        HTMLParser.HTMLParser.close(self)
+
+        try:
+            nochr = unicode('')
+        except NameError:
+            nochr = str('')
+
+        self.pbr()
+        self.o('', 0, 'end')
+
+        outtext = nochr.join(self.outtextlist)
+        if self.unicode_snob:
+            try:
+                nbsp = unichr(name2cp('nbsp'))
+            except NameError:
+                nbsp = chr(name2cp('nbsp'))
+        else:
+            try:
+                nbsp = unichr(32)
+            except NameError:
+                nbsp = chr(32)
+        try:
+            outtext = outtext.replace(unicode('&nbsp_place_holder;'), nbsp)
+        except NameError:
+            outtext = outtext.replace('&nbsp_place_holder;', nbsp)
+
+        # Clear self.outtextlist to avoid memory leak of its content to
+        # the next handling.
+        self.outtextlist = []
+
+        return outtext
+
+    def handle_charref(self, c):
+        charref = self.charref(c)
+        if not self.code and not self.pre:
+            charref = cgi.escape(charref)
+        self.handle_data(charref, True)
+
+    def handle_entityref(self, c):
+        entityref = self.entityref(c)
+        if (not self.code and not self.pre
+                and entityref != '&nbsp_place_holder;'):
+            entityref = cgi.escape(entityref)
+        self.handle_data(entityref, True)
+
+    def handle_starttag(self, tag, attrs):
+        self.handle_tag(tag, attrs, 1)
+
+    def handle_endtag(self, tag):
+        self.handle_tag(tag, None, 0)
+
+    def previousIndex(self, attrs):
+        """
+        :type attrs: dict
+
+        :returns: The index of certain set of attributes (of a link) in the
+        self.a list. If the set of attributes is not found, returns None
+        :rtype: int
+        """
+        if 'href' not in attrs:  # pragma: no cover
+            return None
+        i = -1
+        for a in self.a:
+            i += 1
+            match = 0
+
+            if ('href' in a) and a['href'] == attrs['href']:
+                if ('title' in a) or ('title' in attrs):
+                    if (('title' in a) and ('title' in attrs) and
+                                a['title'] == attrs['title']):
+                        match = True
+                else:
+                    match = True
+
+            if match:
+                return i
+
+    def handle_emphasis(self, start, tag_style, parent_style):
+        """
+        Handles various text emphases
+        """
+        tag_emphasis = google_text_emphasis(tag_style)
+        parent_emphasis = google_text_emphasis(parent_style)
+
+        # handle Google's text emphasis
+        strikethrough = 'line-through' in \
+                        tag_emphasis and self.hide_strikethrough
+        bold = 'bold' in tag_emphasis and not 'bold' in parent_emphasis
+        italic = 'italic' in tag_emphasis and not 'italic' in parent_emphasis
+        fixed = google_fixed_width_font(tag_style) and not \
+            google_fixed_width_font(parent_style) and not self.pre
+
+        if start:
+            # crossed-out text must be handled before other attributes
+            # in order not to output qualifiers unnecessarily
+            if bold or italic or fixed:
+                self.emphasis += 1
+            if strikethrough:
+                self.quiet += 1
+            if italic:
+                self.o(self.emphasis_mark)
+                self.drop_white_space += 1
+            if bold:
+                self.o(self.strong_mark)
+                self.drop_white_space += 1
+            if fixed:
+                self.o('`')
+                self.drop_white_space += 1
+                self.code = True
+        else:
+            if bold or italic or fixed:
+                # there must not be whitespace before closing emphasis mark
+                self.emphasis -= 1
+                self.space = 0
+            if fixed:
+                if self.drop_white_space:
+                    # empty emphasis, drop it
+                    self.drop_white_space -= 1
+                else:
+                    self.o('`')
+                self.code = False
+            if bold:
+                if self.drop_white_space:
+                    # empty emphasis, drop it
+                    self.drop_white_space -= 1
+                else:
+                    self.o(self.strong_mark)
+            if italic:
+                if self.drop_white_space:
+                    # empty emphasis, drop it
+                    self.drop_white_space -= 1
+                else:
+                    self.o(self.emphasis_mark)
+            # space is only allowed after *all* emphasis marks
+            if (bold or italic) and not self.emphasis:
+                self.o(" ")
+            if strikethrough:
+                self.quiet -= 1
+
+    def handle_tag(self, tag, attrs, start):
+        # attrs is None for endtags
+        if attrs is None:
+            attrs = {}
+        else:
+            attrs = dict(attrs)
+
+        if self.tag_callback is not None:
+            if self.tag_callback(self, tag, attrs, start) is True:
+                return
+
+        # first thing inside the anchor tag is another tag that produces some output
+        if (start and not self.maybe_automatic_link is None
+                and tag not in ['p', 'div', 'style', 'dl', 'dt']
+                and (tag != "img" or self.ignore_images)):
+            self.o("[")
+            self.maybe_automatic_link = None
+            self.empty_link = False
+
+        if self.google_doc:
+            # the attrs parameter is empty for a closing tag. in addition, we
+            # need the attributes of the parent nodes in order to get a
+            # complete style description for the current element. we assume
+            # that google docs export well formed html.
+            parent_style = {}
+            if start:
+                if self.tag_stack:
+                    parent_style = self.tag_stack[-1][2]
+                tag_style = element_style(attrs, self.style_def, parent_style)
+                self.tag_stack.append((tag, attrs, tag_style))
+            else:
+                dummy, attrs, tag_style = self.tag_stack.pop() if self.tag_stack else (None, {}, {})
+                if self.tag_stack:
+                    parent_style = self.tag_stack[-1][2]
+
+        if hn(tag):
+            self.p()
+            if start:
+                self.inheader = True
+                self.o(hn(tag) * "#" + ' ')
+            else:
+                self.inheader = False
+                return  # prevent redundant emphasis marks on headers
+
+        if tag in ['p', 'div']:
+            if self.google_doc:
+                if start and google_has_height(tag_style):
+                    self.p()
+                else:
+                    self.soft_br()
+            else:
+                self.p()
+
+        if tag == "br" and start:
+            self.o("  \n")
+
+        if tag == "hr" and start:
+            self.p()
+            self.o("* * *")
+            self.p()
+
+        if tag in ["head", "style", 'script']:
+            if start:
+                self.quiet += 1
+            else:
+                self.quiet -= 1
+
+        if tag == "style":
+            if start:
+                self.style += 1
+            else:
+                self.style -= 1
+
+        if tag in ["body"]:
+            self.quiet = 0  # sites like 9rules.com never close <head>
+
+        if tag == "blockquote":
+            if start:
+                self.p()
+                self.o('> ', 0, 1)
+                self.start = 1
+                self.blockquote += 1
+            else:
+                self.blockquote -= 1
+                self.p()
+
+        if tag in ['em', 'i', 'u'] and not self.ignore_emphasis:
+            self.o(self.emphasis_mark)
+        if tag in ['strong', 'b'] and not self.ignore_emphasis:
+            self.o(self.strong_mark)
+        if tag in ['del', 'strike', 's']:
+            if start:
+                self.o('~~')
+            else:
+                self.o('~~')
+
+        if self.google_doc:
+            if not self.inheader:
+                # handle some font attributes, but leave headers clean
+                self.handle_emphasis(start, tag_style, parent_style)
+
+        if tag in ["code", "tt"] and not self.pre:
+            self.o('`')  # TODO: `` `this` ``
+            self.code = not self.code
+        if tag == "abbr":
+            if start:
+                self.abbr_title = None
+                self.abbr_data = ''
+                if ('title' in attrs):
+                    self.abbr_title = attrs['title']
+            else:
+                if self.abbr_title is not None:
+                    self.abbr_list[self.abbr_data] = self.abbr_title
+                    self.abbr_title = None
+                self.abbr_data = ''
+
+        if tag == "a" and not self.ignore_links:
+            if start:
+                if ('href' in attrs) and \
+                        (attrs['href'] is not None) and \
+                        not (self.skip_internal_links and
+                                 attrs['href'].startswith('#')):
+                    self.astack.append(attrs)
+                    self.maybe_automatic_link = attrs['href']
+                    self.empty_link = True
+                    if self.protect_links:
+                        attrs['href'] = '<'+attrs['href']+'>'
+                else:
+                    self.astack.append(None)
+            else:
+                if self.astack:
+                    a = self.astack.pop()
+                    if self.maybe_automatic_link and not self.empty_link:
+                        self.maybe_automatic_link = None
+                    elif a:
+                        if self.empty_link:
+                            self.o("[")
+                            self.empty_link = False
+                            self.maybe_automatic_link = None
+                        if self.inline_links:
+                            try:
+                                title = escape_md(a['title'])
+                            except KeyError:
+                                self.o("](" + escape_md(urlparse.urljoin(self.baseurl, a['href'])) + ")")
+                            else:
+                                self.o("](" + escape_md(urlparse.urljoin(self.baseurl, a['href']))
+                                       + ' "' + title + '" )')
+                        else:
+                            i = self.previousIndex(a)
+                            if i is not None:
+                                a = self.a[i]
+                            else:
+                                self.acount += 1
+                                a['count'] = self.acount
+                                a['outcount'] = self.outcount
+                                self.a.append(a)
+                            self.o("][" + str(a['count']) + "]")
+
+        if tag == "img" and start and not self.ignore_images:
+            if 'src' in attrs:
+                if not self.images_to_alt:
+                    attrs['href'] = attrs['src']
+                alt = attrs.get('alt') or ''
+
+                # If we have images_with_size, write raw html including width,
+                # height, and alt attributes
+                if self.images_with_size and \
+                        ("width" in attrs or "height" in attrs):
+                    self.o("<img src='" + attrs["src"] + "' ")
+                    if "width" in attrs:
+                        self.o("width='" + attrs["width"] + "' ")
+                    if "height" in attrs:
+                        self.o("height='" + attrs["height"] + "' ")
+                    if alt:
+                        self.o("alt='" + alt + "' ")
+                    self.o("/>")
+                    return
+
+                # If we have a link to create, output the start
+                if not self.maybe_automatic_link is None:
+                    href = self.maybe_automatic_link
+                    if self.images_to_alt and escape_md(alt) == href and \
+                            self.absolute_url_matcher.match(href):
+                        self.o("<" + escape_md(alt) + ">")
+                        self.empty_link = False
+                        return
+                    else:
+                        self.o("[")
+                        self.maybe_automatic_link = None
+                        self.empty_link = False
+
+                # If we have images_to_alt, we discard the image itself,
+                # considering only the alt text.
+                if self.images_to_alt:
+                    self.o(escape_md(alt))
+                else:
+                    self.o("![" + escape_md(alt) + "]")
+                    if self.inline_links:
+                        href = attrs.get('href') or ''
+                        self.o("(" + escape_md(urlparse.urljoin(self.baseurl, href)) + ")")
+                    else:
+                        i = self.previousIndex(attrs)
+                        if i is not None:
+                            attrs = self.a[i]
+                        else:
+                            self.acount += 1
+                            attrs['count'] = self.acount
+                            attrs['outcount'] = self.outcount
+                            self.a.append(attrs)
+                        self.o("[" + str(attrs['count']) + "]")
+
+        if tag == 'dl' and start:
+            self.p()
+        if tag == 'dt' and not start:
+            self.pbr()
+        if tag == 'dd' and start:
+            self.o('    ')
+        if tag == 'dd' and not start:
+            self.pbr()
+
+        if tag in ["ol", "ul"]:
+            # Google Docs create sub lists as top level lists
+            if (not self.list) and (not self.lastWasList):
+                self.p()
+            if start:
+                if self.google_doc:
+                    list_style = google_list_style(tag_style)
+                else:
+                    list_style = tag
+                numbering_start = list_numbering_start(attrs)
+                self.list.append({
+                    'name': list_style,
+                    'num': numbering_start
+                })
+            else:
+                if self.list:
+                    self.list.pop()
+                    if (not self.google_doc) and (not self.list):
+                        self.o('\n')
+            self.lastWasList = True
+        else:
+            self.lastWasList = False
+
+        if tag == 'li':
+            self.pbr()
+            if start:
+                if self.list:
+                    li = self.list[-1]
+                else:
+                    li = {'name': 'ul', 'num': 0}
+                if self.google_doc:
+                    nest_count = self.google_nest_count(tag_style)
+                else:
+                    nest_count = len(self.list)
+                # TODO: line up <ol><li>s > 9 correctly.
+                self.o("  " * nest_count)
+                if li['name'] == "ul":
+                    self.o(self.ul_item_mark + " ")
+                elif li['name'] == "ol":
+                    li['num'] += 1
+                    self.o(str(li['num']) + ". ")
+                self.start = 1
+
+        if tag in ["table", "tr", "td", "th"]:
+            if self.bypass_tables:
+                if start:
+                    self.soft_br()
+                if tag in ["td", "th"]:
+                    if start:
+                        self.o('<{0}>\n\n'.format(tag))
+                    else:
+                        self.o('\n</{0}>'.format(tag))
+                else:
+                    if start:
+                        self.o('<{0}>'.format(tag))
+                    else:
+                        self.o('</{0}>'.format(tag))
+
+            else:
+                if tag == "table" and start:
+                    self.table_start = True
+                if tag in ["td", "th"] and start:
+                    if self.split_next_td:
+                        self.o("| ")
+                    self.split_next_td = True
+
+                if tag == "tr" and start:
+                    self.td_count = 0
+                if tag == "tr" and not start:
+                    self.split_next_td = False
+                    self.soft_br()
+                if tag == "tr" and not start and self.table_start:
+                    # Underline table header
+                    self.o("|".join(["---"] * self.td_count))
+                    self.soft_br()
+                    self.table_start = False
+                if tag in ["td", "th"] and start:
+                    self.td_count += 1
+
+        if tag == "pre":
+            if start:
+                self.startpre = 1
+                self.pre = 1
+            else:
+                self.pre = 0
+                if self.mark_code:
+                    self.out("\n[/code]")
+            self.p()
+
+    # TODO: Add docstring for these one letter functions
+    def pbr(self):
+        "Pretty print has a line break"
+        if self.p_p == 0:
+            self.p_p = 1
+
+    def p(self):
+        "Set pretty print to 1 or 2 lines"
+        self.p_p = 1 if self.single_line_break else 2
+
+    def soft_br(self):
+        "Soft breaks"
+        self.pbr()
+        self.br_toggle = '  '
+
+    def o(self, data, puredata=0, force=0):
+        """
+        Deal with indentation and whitespace
+        """
+        if self.abbr_data is not None:
+            self.abbr_data += data
+
+        if not self.quiet:
+            if self.google_doc:
+                # prevent white space immediately after 'begin emphasis'
+                # marks ('**' and '_')
+                lstripped_data = data.lstrip()
+                if self.drop_white_space and not (self.pre or self.code):
+                    data = lstripped_data
+                if lstripped_data != '':
+                    self.drop_white_space = 0
+
+            if puredata and not self.pre:
+                # This is a very dangerous call ... it could mess up
+                # all handling of &nbsp; when not handled properly
+                # (see entityref)
+                data = re.sub(r'\s+', r' ', data)
+                if data and data[0] == ' ':
+                    self.space = 1
+                    data = data[1:]
+            if not data and not force:
+                return
+
+            if self.startpre:
+                #self.out(" :") #TODO: not output when already one there
+                if not data.startswith("\n"):  # <pre>stuff...
+                    data = "\n" + data
+                if self.mark_code:
+                    self.out("\n[code]")
+                    self.p_p = 0
+
+            bq = (">" * self.blockquote)
+            if not (force and data and data[0] == ">") and self.blockquote:
+                bq += " "
+
+            if self.pre:
+                if not self.list:
+                    bq += "    "
+                #else: list content is already partially indented
+                for i in range(len(self.list)):
+                    bq += "    "
+                data = data.replace("\n", "\n" + bq)
+
+            if self.startpre:
+                self.startpre = 0
+                if self.list:
+                    # use existing initial indentation
+                    data = data.lstrip("\n")
+
+            if self.start:
+                self.space = 0
+                self.p_p = 0
+                self.start = 0
+
+            if force == 'end':
+                # It's the end.
+                self.p_p = 0
+                self.out("\n")
+                self.space = 0
+
+            if self.p_p:
+                self.out((self.br_toggle + '\n' + bq) * self.p_p)
+                self.space = 0
+                self.br_toggle = ''
+
+            if self.space:
+                if not self.lastWasNL:
+                    self.out(' ')
+                self.space = 0
+
+            if self.a and ((self.p_p == 2 and self.links_each_paragraph)
+                           or force == "end"):
+                if force == "end":
+                    self.out("\n")
+
+                newa = []
+                for link in self.a:
+                    if self.outcount > link['outcount']:
+                        self.out("   [" + str(link['count']) + "]: " +
+                                 urlparse.urljoin(self.baseurl, link['href']))
+                        if 'title' in link:
+                            self.out(" (" + link['title'] + ")")
+                        self.out("\n")
+                    else:
+                        newa.append(link)
+
+                # Don't need an extra line when nothing was done.
+                if self.a != newa:
+                    self.out("\n")
+
+                self.a = newa
+
+            if self.abbr_list and force == "end":
+                for abbr, definition in self.abbr_list.items():
+                    self.out("  *[" + abbr + "]: " + definition + "\n")
+
+            self.p_p = 0
+            self.out(data)
+            self.outcount += 1
+
+    def handle_data(self, data, entity_char=False):
+        if r'\/script>' in data:
+            self.quiet -= 1
+
+        if self.style:
+            self.style_def.update(dumb_css_parser(data))
+
+        if not self.maybe_automatic_link is None:
+            href = self.maybe_automatic_link
+            if (href == data and self.absolute_url_matcher.match(href)
+                    and self.use_automatic_links):
+                self.o("<" + data + ">")
+                self.empty_link = False
+                return
+            else:
+                self.o("[")
+                self.maybe_automatic_link = None
+                self.empty_link = False
+
+        if not self.code and not self.pre and not entity_char:
+            data = escape_md_section(data, snob=self.escape_snob)
+        self.o(data, 1)
+
+    def unknown_decl(self, data):  # pragma: no cover
+        # TODO: what is this doing here?
+        pass
+
+    def charref(self, name):
+        if name[0] in ['x', 'X']:
+            c = int(name[1:], 16)
+        else:
+            c = int(name)
+
+        if not self.unicode_snob and c in unifiable_n.keys():
+            return unifiable_n[c]
+        else:
+            try:
+                try:
+                    return unichr(c)
+                except NameError:  # Python3
+                    return chr(c)
+            except ValueError:  # invalid unicode
+                return ''
+
+    def entityref(self, c):
+        if not self.unicode_snob and c in config.UNIFIABLE.keys():
+            return config.UNIFIABLE[c]
+        else:
+            try:
+                name2cp(c)
+            except KeyError:
+                return "&" + c + ';'
+            else:
+                if c == 'nbsp':
+                    return config.UNIFIABLE[c]
+                else:
+                    try:
+                        return unichr(name2cp(c))
+                    except NameError:  # Python3
+                        return chr(name2cp(c))
+
+    def replaceEntities(self, s):
+        s = s.group(1)
+        if s[0] == "#":
+            return self.charref(s[1:])
+        else:
+            return self.entityref(s)
+
+    def unescape(self, s):
+        return config.RE_UNESCAPE.sub(self.replaceEntities, s)
+
+    def google_nest_count(self, style):
+        """
+        Calculate the nesting count of google doc lists
+
+        :type style: dict
+
+        :rtype: int
+        """
+        nest_count = 0
+        if 'margin-left' in style:
+            nest_count = int(style['margin-left'][:-2]) \
+                         // self.google_list_indent
+
+        return nest_count
+
+    def optwrap(self, text):
+        """
+        Wrap all paragraphs in the provided text.
+
+        :type text: str
+
+        :rtype: str
+        """
+        if not self.body_width:
+            return text
+
+        assert wrap, "Requires Python 2.3."
+        result = ''
+        newlines = 0
+        # I cannot think of a better solution for now.
+        # To avoid the non-wrap behaviour for entire paras
+        # because of the presence of a link in it
+        if not self.wrap_links:
+            self.inline_links = False
+        for para in text.split("\n"):
+            if len(para) > 0:
+                if not skipwrap(para, self.wrap_links):
+                    result += "\n".join(wrap(para, self.body_width))
+                    if para.endswith('  '):
+                        result += "  \n"
+                        newlines = 1
+                    else:
+                        result += "\n\n"
+                        newlines = 2
+                else:
+                    # Warning for the tempted!!!
+                    # Be aware that obvious replacement of this with
+                    # line.isspace()
+                    # DOES NOT work! Explanations are welcome.
+                    if not config.RE_SPACE.match(para):
+                        result += para + "\n"
+                        newlines = 1
+            else:
+                if newlines < 2:
+                    result += "\n"
+                    newlines += 1
+        return result
+
+
+def html2text(html, baseurl='', bodywidth=None):
+    if bodywidth is None:
+        bodywidth = config.BODY_WIDTH
+    h = HTML2Text(baseurl=baseurl, bodywidth=bodywidth)
+
+    return h.handle(html)
+
+
+def unescape(s, unicode_snob=False):
+    h = HTML2Text()
+    h.unicode_snob = unicode_snob
+
+    return h.unescape(s)
+
+
+if __name__ == "__main__":
+    from html2text.cli import main
+
+    main()

included_dependencies/html2text/compat.py

@@ -0,0 +1,13 @@
+import sys
+
+
+if sys.version_info[0] == 2:
+    import htmlentitydefs
+    import urlparse
+    import HTMLParser
+    import urllib
+else:
+    import urllib.parse as urlparse
+    import html.entities as htmlentitydefs
+    import html.parser as HTMLParser
+    import urllib.request as urllib

included_dependencies/html2text/config.py

@@ -0,0 +1,123 @@
+import re
+
+# Use Unicode characters instead of their ascii psuedo-replacements
+UNICODE_SNOB = 0
+
+# Escape all special characters.  Output is less readable, but avoids
+# corner case formatting issues.
+ESCAPE_SNOB = 0
+
+# Put the links after each paragraph instead of at the end.
+LINKS_EACH_PARAGRAPH = 0
+
+# Wrap long lines at position. 0 for no wrapping. (Requires Python 2.3.)
+BODY_WIDTH = 78
+
+# Don't show internal links (href="#local-anchor") -- corresponding link
+# targets won't be visible in the plain text file anyway.
+SKIP_INTERNAL_LINKS = True
+
+# Use inline, rather than reference, formatting for images and links
+INLINE_LINKS = True
+
+# Protect links from line breaks surrounding them with angle brackets (in
+# addition to their square brackets)
+PROTECT_LINKS = False
+# WRAP_LINKS = True
+WRAP_LINKS = True
+
+# Number of pixels Google indents nested lists
+GOOGLE_LIST_INDENT = 36
+
+IGNORE_ANCHORS = False
+IGNORE_IMAGES = False
+IMAGES_TO_ALT = False
+IMAGES_WITH_SIZE = False
+IGNORE_EMPHASIS = False
+MARK_CODE = False
+DECODE_ERRORS = 'strict'
+
+# Convert links with same href and text to <href> format if they are absolute links
+USE_AUTOMATIC_LINKS = True
+
+# For checking space-only lines on line 771
+RE_SPACE = re.compile(r'\s\+')
+
+RE_UNESCAPE = re.compile(r"&(#?[xX]?(?:[0-9a-fA-F]+|\w{1,8}));")
+RE_ORDERED_LIST_MATCHER = re.compile(r'\d+\.\s')
+RE_UNORDERED_LIST_MATCHER = re.compile(r'[-\*\+]\s')
+RE_MD_CHARS_MATCHER = re.compile(r"([\\\[\]\(\)])")
+RE_MD_CHARS_MATCHER_ALL = re.compile(r"([`\*_{}\[\]\(\)#!])")
+RE_LINK = re.compile(r"(\[.*?\] ?\(.*?\))|(\[.*?\]:.*?)")  # to find links in the text
+RE_MD_DOT_MATCHER = re.compile(r"""
+    ^             # start of line
+    (\s*\d+)      # optional whitespace and a number
+    (\.)          # dot
+    (?=\s)        # lookahead assert whitespace
+    """, re.MULTILINE | re.VERBOSE)
+RE_MD_PLUS_MATCHER = re.compile(r"""
+    ^
+    (\s*)
+    (\+)
+    (?=\s)
+    """, flags=re.MULTILINE | re.VERBOSE)
+RE_MD_DASH_MATCHER = re.compile(r"""
+    ^
+    (\s*)
+    (-)
+    (?=\s|\-)     # followed by whitespace (bullet list, or spaced out hr)
+                  # or another dash (header or hr)
+    """, flags=re.MULTILINE | re.VERBOSE)
+RE_SLASH_CHARS = r'\`*_{}[]()#+-.!'
+RE_MD_BACKSLASH_MATCHER = re.compile(r'''
+    (\\)          # match one slash
+    (?=[%s])      # followed by a char that requires escaping
+    ''' % re.escape(RE_SLASH_CHARS),
+    flags=re.VERBOSE)
+
+UNIFIABLE = {
+    'rsquo': "'",
+    'lsquo': "'",
+    'rdquo': '"',
+    'ldquo': '"',
+    'copy': '(C)',
+    'mdash': '--',
+    'nbsp': ' ',
+    'rarr': '->',
+    'larr': '<-',
+    'middot': '*',
+    'ndash': '-',
+    'oelig': 'oe',
+    'aelig': 'ae',
+    'agrave': 'a',
+    'aacute': 'a',
+    'acirc': 'a',
+    'atilde': 'a',
+    'auml': 'a',
+    'aring': 'a',
+    'egrave': 'e',
+    'eacute': 'e',
+    'ecirc': 'e',
+    'euml': 'e',
+    'igrave': 'i',
+    'iacute': 'i',
+    'icirc': 'i',
+    'iuml': 'i',
+    'ograve': 'o',
+    'oacute': 'o',
+    'ocirc': 'o',
+    'otilde': 'o',
+    'ouml': 'o',
+    'ugrave': 'u',
+    'uacute': 'u',
+    'ucirc': 'u',
+    'uuml': 'u',
+    'lrm': '',
+    'rlm': ''
+}
+
+BYPASS_TABLES = False
+
+# Use a single line break after a block element rather an two line breaks.
+# NOTE: Requires body width setting to be 0.
+SINGLE_LINE_BREAK = False

included_dependencies/html2text/utils.py

@@ -0,0 +1,246 @@
+import sys
+
+from html2text import config
+from html2text.compat import htmlentitydefs
+
+
+def name2cp(k):
+    """Return sname to codepoint"""
+    if k == 'apos':
+        return ord("'")
+    return htmlentitydefs.name2codepoint[k]
+
+
+unifiable_n = {}
+
+for k in config.UNIFIABLE.keys():
+    unifiable_n[name2cp(k)] = config.UNIFIABLE[k]
+
+
+def hn(tag):
+    if tag[0] == 'h' and len(tag) == 2:
+        try:
+            n = int(tag[1])
+            if n in range(1, 10):  # pragma: no branch
+                return n
+        except ValueError:
+            return 0
+
+
+def dumb_property_dict(style):
+    """
+    :returns: A hash of css attributes
+    """
+    out = dict([(x.strip(), y.strip()) for x, y in
+                [z.split(':', 1) for z in
+                 style.split(';') if ':' in z
+                 ]
+                ]
+               )
+
+    return out
+
+
+def dumb_css_parser(data):
+    """
+    :type data: str
+
+    :returns: A hash of css selectors, each of which contains a hash of
+    css attributes.
+    :rtype: dict
+    """
+    # remove @import sentences
+    data += ';'
+    importIndex = data.find('@import')
+    while importIndex != -1:
+        data = data[0:importIndex] + data[data.find(';', importIndex) + 1:]
+        importIndex = data.find('@import')
+
+    # parse the css. reverted from dictionary comprehension in order to
+    # support older pythons
+    elements = [x.split('{') for x in data.split('}') if '{' in x.strip()]
+    try:
+        elements = dict([(a.strip(), dumb_property_dict(b))
+                         for a, b in elements])
+    except ValueError:  # pragma: no cover
+        elements = {}  # not that important
+
+    return elements
+
+
+def element_style(attrs, style_def, parent_style):
+    """
+    :type attrs: dict
+    :type style_def: dict
+    :type style_def: dict
+
+    :returns: A hash of the 'final' style attributes of the element
+    :rtype: dict
+    """
+    style = parent_style.copy()
+    if 'class' in attrs:
+        for css_class in attrs['class'].split():
+            css_style = style_def.get('.' + css_class, {})
+            style.update(css_style)
+    if 'style' in attrs:
+        immediate_style = dumb_property_dict(attrs['style'])
+        style.update(immediate_style)
+
+    return style
+
+
+def google_list_style(style):
+    """
+    Finds out whether this is an ordered or unordered list
+
+    :type style: dict
+
+    :rtype: str
+    """
+    if 'list-style-type' in style:
+        list_style = style['list-style-type']
+        if list_style in ['disc', 'circle', 'square', 'none']:
+            return 'ul'
+
+    return 'ol'
+
+
+def google_has_height(style):
+    """
+    Check if the style of the element has the 'height' attribute
+    explicitly defined
+
+    :type style: dict
+
+    :rtype: bool
+    """
+    if 'height' in style:
+        return True
+
+    return False
+
+
+def google_text_emphasis(style):
+    """
+    :type style: dict
+
+    :returns: A list of all emphasis modifiers of the element
+    :rtype: list
+    """
+    emphasis = []
+    if 'text-decoration' in style:
+        emphasis.append(style['text-decoration'])
+    if 'font-style' in style:
+        emphasis.append(style['font-style'])
+    if 'font-weight' in style:
+        emphasis.append(style['font-weight'])
+
+    return emphasis
+
+
+def google_fixed_width_font(style):
+    """
+    Check if the css of the current element defines a fixed width font
+
+    :type style: dict
+
+    :rtype: bool
+    """
+    font_family = ''
+    if 'font-family' in style:
+        font_family = style['font-family']
+    if 'Courier New' == font_family or 'Consolas' == font_family:
+        return True
+
+    return False
+
+
+def list_numbering_start(attrs):
+    """
+    Extract numbering from list element attributes
+
+    :type attrs: dict
+
+    :rtype: int or None
+    """
+    if 'start' in attrs:
+        try:
+            return int(attrs['start']) - 1
+        except ValueError:
+            pass
+
+    return 0
+
+
+def skipwrap(para, wrap_links):
+    # If it appears to contain a link
+    # don't wrap
+    if (len(config.RE_LINK.findall(para)) > 0) and not wrap_links:
+        return True
+    # If the text begins with four spaces or one tab, it's a code block;
+    # don't wrap
+    if para[0:4] == '    ' or para[0] == '\t':
+        return True
+
+    # If the text begins with only two "--", possibly preceded by
+    # whitespace, that's an emdash; so wrap.
+    stripped = para.lstrip()
+    if stripped[0:2] == "--" and len(stripped) > 2 and stripped[2] != "-":
+        return False
+
+    # I'm not sure what this is for; I thought it was to detect lists,
+    # but there's a <br>-inside-<span> case in one of the tests that
+    # also depends upon it.
+    if stripped[0:1] == '-' or stripped[0:1] == '*':
+        return True
+
+    # If the text begins with a single -, *, or +, followed by a space,
+    # or an integer, followed by a ., followed by a space (in either
+    # case optionally proceeded by whitespace), it's a list; don't wrap.
+    if config.RE_ORDERED_LIST_MATCHER.match(stripped) or \
+            config.RE_UNORDERED_LIST_MATCHER.match(stripped):
+        return True
+
+    return False
+
+
+def wrapwrite(text):
+    text = text.encode('utf-8')
+    try:  # Python3
+        sys.stdout.buffer.write(text)
+    except AttributeError:
+        sys.stdout.write(text)
+
+
+def wrap_read():  # pragma: no cover
+    """
+    :rtype: str
+    """
+    try:
+        return sys.stdin.read()
+    except AttributeError:
+        return sys.stdin.buffer.read()
+
+
+def escape_md(text):
+    """
+    Escapes markdown-sensitive characters within other markdown
+    constructs.
+    """
+    return config.RE_MD_CHARS_MATCHER.sub(r"\\\1", text)
+
+
+def escape_md_section(text, snob=False):
+    """
+    Escapes markdown-sensitive characters across whole document sections.
+    """
+    text = config.RE_MD_BACKSLASH_MATCHER.sub(r"\\\1", text)
+
+    if snob:
+        text = config.RE_MD_CHARS_MATCHER_ALL.sub(r"\\\1", text)
+
+    text = config.RE_MD_DOT_MATCHER.sub(r"\1\\\2", text)
+    text = config.RE_MD_PLUS_MATCHER.sub(r"\1\\\2", text)
+    text = config.RE_MD_DASH_MATCHER.sub(r"\1\\\2", text)
+
+    return text

makeplugin.py

@@ -36,7 +36,7 @@ if __name__=="__main__":
 
     os.chdir('../included_dependencies')
     # 'a' for append
-    files=['gif.py','six.py','bs4','html5lib','chardet']
+    files=['gif.py','six.py','bs4','html5lib','chardet','html2text']
     createZipFile("../"+filename,"a",
                   files,
                   exclude=exclude)

setup.py

@@ -16,14 +16,12 @@ from os import path
 # Get the long description from the relevant file
 with codecs.open('DESCRIPTION.rst', encoding='utf-8') as f:
     long_description = f.read()
-
+    
 setup(
     name="FanFicFare",
 
-    # Versions should comply with PEP440.  For a discussion on single-sourcing
+    # Versions should comply with PEP440.
-    # the version across setup.py and the project code, see
+    version="2.5.1",
-    # https://packaging.python.org/en/latest/single_source_version.html
-    version="2.3.1",
 
     description='A tool for downloading fanfiction to eBook formats',
     long_description=long_description,
@@ -81,7 +79,7 @@ setup(
     # your project is installed. For an analysis of "install_requires" vs pip's
     # requirements files see:
     # https://packaging.python.org/en/latest/requirements.html
-    install_requires=['beautifulsoup4','chardet','html5lib'], # html5lib requires 'six'.
+    install_requires=['beautifulsoup4','chardet','html5lib','html2text'], # html5lib requires 'six'.
 
     # List additional groups of dependencies here (e.g. development
     # dependencies). You can install these using the following syntax,

version_update.py

@@ -0,0 +1,79 @@
+# -*- coding: utf-8 -*-
+
+import codecs, sys, re
+
+from tempfile import mkstemp
+from os import rename, close, unlink
+
+#print sys.argv[1:]
+
+## Files that contain version numbers that will need to be updated.
+version_files = [
+    # 'version_test.sml',
+    # 'version_test.txt',
+    'setup.py',
+    'calibre-plugin/__init__.py',
+    'webservice/app.yaml',
+    'fanficfare/cli.py',
+    ]
+
+## save version from this file for index.html link.
+# save_file='version_test.txt'
+save_file='webservice/app.yaml'
+saved_version = None
+
+
+def main(args):
+   ## major.minor.micro
+    '''
+    version             = (2, 3, 6)
+    version="2.3.6",
+version: 2-3-06a
+version="2.3.6"
+'''
+    version_re = \
+        r'^(?P<prefix>[ ]*)version(?P<infix>[ =:"\\(]+)' \
+        r'(?P<major>[0-9]+)(?P<dot1>[, \\.-]+)' \
+        r'(?P<minor>[0-9]+)(?P<dot2>[, \\.-]+)' \
+        r'(?P<micro>[0-9]+[a-z]?)(?P<suffix>[",\\)]*\r?\n)$'
+
+    version_subs = '\g<prefix>version\g<infix>%s\g<dot1>%s\g<dot2>%s\g<suffix>' % tuple(args)
+    
+    do_loop(version_files, version_re, version_subs)
+
+    if saved_version:
+        # index_files = ['index.html']
+        index_files = ['webservice/index.html']
+        index_re = 'http://([0-9-]+[a-z]?)\\.fanficfare\\.appspot\\.com'
+        index_subs = 'http://%s-%s-%s.fanficfare.appspot.com'%saved_version
+        do_loop(index_files, index_re, index_subs)
+
+def do_loop(files, pattern, substring):
+    global saved_version
+    for source_file_path in files:
+        print "src:"+source_file_path
+        fh, target_file_path = mkstemp()
+        with codecs.open(target_file_path, 'w', 'utf-8') as target_file:
+            with codecs.open(source_file_path, 'r', 'utf-8') as source_file:
+                for line in source_file:
+                    repline = re.sub(pattern, substring, line)
+                    if line != repline and source_file_path == save_file:
+                        m = re.match(pattern,line)
+                        saved_version = (m.group('major'),m.group('minor'),m.group('micro'))
+                        print("<-%s->%s"%(line,repline))
+                    target_file.write(repline)
+        close(fh)
+        unlink(source_file_path)
+        rename(target_file_path,source_file_path)
+
+if __name__ == '__main__':
+    args = sys.argv[1:]
+    try:
+        if len(args) != 3:
+            raise Exception()
+        [int(x) for x in args]
+    except:
+        print "Requires exactly 3 numeric args: major minor micro"
+        exit()
+    main(args)
+#    print saved_version

webservice/app.yaml

@@ -1,6 +1,6 @@
 # ffd-retief-hrd fanficfare
 application: fanficfare
-version: 2-3-01
+version: 2-5-0
 runtime: python27
 api_version: 1
 threadsafe: true
@@ -34,13 +34,3 @@ handlers:
 
 - url: /.*
   script: main.app
-
-#builtins:
-#- datastore_admin: on
-
-libraries:
-- name: django
-  version: "1.2"
-
-- name: PIL
-  version: "1.1.7"

webservice/editconfig.html

@@ -39,8 +39,8 @@
 	<img src="http://code.google.com/appengine/images/appengine-silver-120x30.gif"
 	     alt="Powered by Google App Engine" />
 	<br/><br/>
-	This is a web front-end to <A href="http://code.google.com/p/fanficdownloader/">FanFicFare</a><br/>
+	This is a web front-end to <a href="https://github.com/JimmXinu/FanFicFare/">FanFicFare</a><br/>
-	Copyright &copy; Fanficdownloader team
+	Copyright &copy; FanFicFare team
       </div>
 
     </div>

webservice/index.html

@@ -24,7 +24,7 @@
 	<div id='urlbox'>
 	  <div id='greeting'>
 	    <p>Hi, {{ nickname }}! This is FanFicFare, which makes reading stories from various websites
-	      much easier. </p>
+	      much easier by helping you download them to EBook files. </p>
 	  </div>
 
 	  <p>
@@ -35,7 +35,7 @@
 	    If you have any problems with this application, please
 	    report them in
 	    the <a href="http://groups.google.com/group/fanfic-downloader">FanFicFare Google Group</a>.  The
-	    <a href="http://2-3-00.fanficfare.appspot.com">previous version
+	    <a href="http://2-4-0.fanficfare.appspot.com">previous version
 	    </a> is also available for you to use if necessary.
 	  </p>
 	  <div id='error'>
@@ -75,7 +75,7 @@
       <div id='urlbox'>
 	<div id='greeting'>
 	  <p>
-	    This is a FanFicFare, which makes reading stories from various websites much easier. Before you
+	    This is a FanFicFare, which makes reading stories from various websites much easier by helping you download them to EBook files. Before you
 	    can start downloading fanfics, you need to login, so FanFicFare can remember your fanfics and store them.
 	  </p>
 	  <p><a href="{{ login_url }}">Login using Google account</a></p>
@@ -85,17 +85,17 @@
       
       <div id='typebox'>
 	  <p>
-	    <b>FanFicFare calibre Plugin</b>
+	    <b>FanFicFare Calibre Plugin</b>
 	    <br /><br />
 	    
 	    There's also a version of this downloader that runs inside
-	    the popular <a href="http://calibre-ebook.com/">calibre</a>
+	    the popular <a href="http://calibre-ebook.com/">Calibre</a>
 	    ebook management package as a plugin.
 	    
 	    <br /><br />
 	    
-	    Once you have calibre installed and running, inside
+	    Once you have Calibre installed and running, inside
-	    calibre, you can go to 'Get plugins to enhance calibre' or
+	    Calibre, you can go to 'Get plugins to enhance calibre' or
 	    'Get new plugins' and
 	    install <a href="http://www.mobileread.com/forums/showthread.php?t=259221">FanFicFare</a>.
 	    

webservice/login.html

@@ -68,7 +68,7 @@
 	<img src="http://code.google.com/appengine/images/appengine-silver-120x30.gif"
 	     alt="Powered by Google App Engine" />
 	<br/><br/>
-	This is a web front-end to <A href="http://code.google.com/p/fanficdownloader/">FanFicFare</a><br/>
+	This is a web front-end to <a href="https://github.com/JimmXinu/FanFicFare/">FanFicFare</a><br/>
 	Copyright &copy; FanFicFare team
       </div>
 

webservice/main.py

@@ -30,20 +30,6 @@ import datetime
 import traceback
 from StringIO import StringIO
 
-## Just to shut up the appengine warning about "You are using the
-## default Django version (0.96). The default Django version will
-## change in an App Engine release in the near future. Please call
-## use_library() to explicitly select a Django version. For more
-## information see
-## http://code.google.com/appengine/docs/python/tools/libraries.html#Django"
-## Note that if you are using the SDK App Engine Launcher and hit an SDK
-## Console page first, you will get a django version mismatch error when you
-## to go hit one of the application pages.  Just change a file again, and
-## make sure to hit an app page before the SDK page to clear it.
-#os.environ['DJANGO_SETTINGS_MODULE'] = 'settings'
-#from google.appengine.dist import use_library
-#use_library('django', '1.2')
-
 from google.appengine.ext import db
 from google.appengine.api import taskqueue
 from google.appengine.api import users
@@ -59,11 +45,11 @@ from fanficfare import adapters, writers, exceptions
 from fanficfare.configurable import Configuration
 
 class UserConfigServer(webapp2.RequestHandler):
-    
+
     def getUserConfig(self,user,url,fileformat):
 
         configuration = Configuration(adapters.getConfigSectionsFor(url),fileformat)
-        
+
         logging.debug('reading defaults.ini config file')
         configuration.read('fanficfare/defaults.ini')
 
@@ -110,7 +96,7 @@ class MainHandler(webapp2.RequestHandler):
             template_values = {'login_url' : url, 'authorized': False}
             path = os.path.join(os.path.dirname(__file__), 'index.html')
 
-        
+
         template_values['supported_sites'] = '<dl>\n'
         for (site,examples) in adapters.getSiteExamples():
             template_values['supported_sites'] += "<dt>%s</dt>\n<dd>Example Story URLs:<br>"%site
@@ -153,7 +139,7 @@ class EditConfigServer(UserConfigServer):
                 self.redirect("/?error=configsaved")
             except Exception, e:
                 logging.info("Saved Config Failed:%s"%e)
-                self.redirect("/?error=custom&errtext=%s"%urlEscape(unicode(e)))
+                self.redirect("/?error=custom&errtext=%s"%urllib.quote(unicode(e),''))
         else: # not update, assume display for edit
             if uconfig is not None and uconfig.config:
                 config = uconfig.config
@@ -254,7 +240,7 @@ class FileStatusServer(webapp2.RequestHandler):
             if download:
                 logging.info("Status url: %s" % download.url)
                 if download.completed and download.format=='epub':
-                    escaped_url = urlEscape(self.request.host_url+"/file/"+download.name+"."+download.format+"?id="+fileId+"&fake=file."+download.format)
+                    escaped_url = urllib.quote(self.request.host_url+"/file/"+download.name+"."+download.format+"?id="+fileId+"&fake=file."+download.format,'')
             else:
                 download = DownloadMeta()
                 download.failure = "Download not found"
@@ -309,7 +295,7 @@ class RecentFilesServer(webapp2.RequestHandler):
 
         for fic in fics:
             if fic.completed and fic.format == 'epub':
-                fic.escaped_url = urlEscape(self.request.host_url+"/file/"+fic.name+"."+fic.format+"?id="+unicode(fic.key())+"&fake=file."+fic.format)
+                fic.escaped_url = urllib.quote(self.request.host_url+"/file/"+fic.name+"."+fic.format+"?id="+unicode(fic.key())+"&fake=file."+fic.format,'')
 
         template_values = dict(fics = fics, nickname = user.nickname())
         path = os.path.join(os.path.dirname(__file__), 'recent.html')
@@ -327,7 +313,7 @@ class AllRecentFilesServer(webapp2.RequestHandler):
             q.order('-date')
         else:
             q.order('-count')
-            
+
         fics = q.fetch(200)
         logging.info("Recent fetched %d downloads for user %s."%(len(fics),user.nickname()))
 
@@ -336,7 +322,7 @@ class AllRecentFilesServer(webapp2.RequestHandler):
         for fic in fics:
             ficslug = FicSlug(fic)
             sendslugs.append(ficslug)
-                
+
         template_values = dict(fics = sendslugs, nickname = user.nickname())
         path = os.path.join(os.path.dirname(__file__), 'allrecent.html')
         self.response.out.write(template.render(path, template_values))
@@ -347,7 +333,7 @@ class FicSlug():
         self.count = savedmeta.count
         for k, v in savedmeta.meta.iteritems():
             setattr(self,k,v)
-        
+
 class FanfictionDownloader(UserConfigServer):
     def get(self):
         self.post()
@@ -375,7 +361,7 @@ class FanfictionDownloader(UserConfigServer):
         ch_end = mc.group('end')
         if ch_begin and not mc.group('comma'):
             ch_end = ch_begin
-        
+
         logging.info("Queuing Download: %s" % url)
         login = self.request.get('login')
         password = self.request.get('password')
@@ -390,8 +376,11 @@ class FanfictionDownloader(UserConfigServer):
         try:
             try:
                 configuration = self.getUserConfig(user,url,format)
+            except exceptions.UnknownSite:
+                self.redirect("/?error=custom&errtext=%s"%urllib.quote("Unsupported site in URL (%s).  See 'Support sites' list below."%url,''))
+                return
             except Exception, e:
-                self.redirect("/?error=custom&errtext=%s"%urlEscape("There's an error in your User Configuration: "+unicode(e)))
+                self.redirect("/?error=custom&errtext=%s"%urllib.quote("There's an error in your User Configuration: "+unicode(e),'')[:2048]) # limited due to Locatton header length limit.
                 return
 
             adapter = adapters.getAdapter(configuration,url)
@@ -551,7 +540,7 @@ class FanfictionDownloaderTask(UserConfigServer):
             # delete existing chunks first
             for chunk in download.data_chunks:
                 chunk.delete()
-                
+
             index=0
             while( len(data) > 0 ):
                 # logging.info("len(data): %s" % len(data))
@@ -577,7 +566,7 @@ class FanfictionDownloaderTask(UserConfigServer):
             smeta.meta = allmeta
             smeta.date = datetime.datetime.now()
             smeta.put()
-            
+
             logging.info("Download finished OK")
             del data
 
@@ -630,16 +619,6 @@ def getDownloadMeta(id=None,url=None,user=None,format=None,new=False):
 
     return download
 
-def toPercentDecimal(match):
-    "Return the %decimal number for the character for url escaping"
-    s = match.group(1)
-    return "%%%02x" % ord(s)
-
-def urlEscape(data):
-    "Escape text, including unicode, for use in URLs"
-    p = re.compile(r'([^\w])')
-    return p.sub(toPercentDecimal, data.encode("utf-8"))
-
 logging.getLogger().setLevel(logging.DEBUG)
 app = webapp2.WSGIApplication([('/', MainHandler),
                                ('/fdowntask', FanfictionDownloaderTask),

webservice/status.html

@@ -45,7 +45,7 @@
 	<img src="http://code.google.com/appengine/images/appengine-silver-120x30.gif"
 	     alt="Powered by Google App Engine" />
 	<br/><br/>
-	This is a web front-end to <A href="http://code.google.com/p/fanficdownloader/">FanFicFare</a><br/>
+	This is a web front-end to <a href="https://github.com/JimmXinu/FanFicFare/">FanFicFare</a><br/>
 	Copyright &copy; FanFicFare team
       </div>