Bump versions.

I've added fore more adapters for eFiction sites... one is slightly
dodgy...
The Rabid Reader
Naicea Nilmenet (Lord Of The Rings
Artemis Fowl Fan Fiction
Andromeda Web [doesn't retrieve some labels]

Gcomyn

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:%(filename)s(%(lineno)d):%(message)s"))
+    loghandler.setFormatter(logging.Formatter("FFF: %(levelname)s: %(asctime)s: %(filename)s(%(lineno)d): %(message)s"))
     logger.addHandler(loghandler)
-    loghandler.setLevel(logging.DEBUG)
-    logger.setLevel(logging.DEBUG)
+
+    from calibre.constants import DEBUG
+    if os.environ.get('CALIBRE_WORKER', None) is not None or DEBUG:
+        loghandler.setLevel(logging.DEBUG)
+        logger.setLevel(logging.DEBUG)
+    else:
+        loghandler.setLevel(logging.CRITICAL)
+        logger.setLevel(logging.CRITICAL)
 
 # pulls in translation files for _() strings
 try:
@@ -42,7 +48,7 @@ class FanFicFareBase(InterfaceActionBase):
     description         = _('UI plugin to download FanFiction stories from various sites.')
     supported_platforms = ['windows', 'osx', 'linux']
     author              = 'Jim Miller'
-    version             = (2, 2, 17)
+    version             = (2, 3, 2)
     minimum_calibre_version = (1, 48, 0)
 
     #: This field defines the GUI plugin class that contains all the code

calibre-plugin/config.py

@@ -10,7 +10,7 @@ __docformat__ = 'restructuredtext en'
 import logging
 logger = logging.getLogger(__name__)
 
-import traceback, copy, threading
+import traceback, copy, threading, re
 from collections import OrderedDict
 
 try:
@@ -332,6 +332,7 @@ class ConfigWidget(QWidget):
         # Custom Columns tab
         # error column
         prefs['errorcol'] = unicode(convert_qvariant(self.cust_columns_tab.errorcol.itemData(self.cust_columns_tab.errorcol.currentIndex())))
+        prefs['save_all_errors'] = self.cust_columns_tab.save_all_errors.isChecked()
 
         # metadata column
         prefs['savemetacol'] = unicode(convert_qvariant(self.cust_columns_tab.savemetacol.itemData(self.cust_columns_tab.savemetacol.currentIndex())))
@@ -665,53 +666,94 @@ class PersonalIniTab(QWidget):
         label = QLabel(_('These settings provide more detailed control over what metadata will be displayed inside the ebook as well as let you set %(isa)s and %(u)s/%(p)s for different sites.')%no_trans)
         label.setWordWrap(True)
         self.l.addWidget(label)
-#        self.l.addSpacing(5)
-
-        label = QLabel(_("FanFicFare now includes find, color coding, and error checking for personal.ini editing.  Red generally indicates errors."))
-        label.setWordWrap(True)
-        self.l.addWidget(label)
-        
-        # self.label = QLabel('personal.ini:')
-        # self.l.addWidget(self.label)
-
-        # self.ini = QTextEdit(self)
-        # try:
-        #     self.ini.setFont(QFont("Courier",
-        #                            self.plugin_action.gui.font().pointSize()+1))
-        # except Exception as e:
-        #     logger.error("Couldn't get font: %s"%e)
-        # self.ini.setLineWrapMode(QTextEdit.NoWrap)
-        # self.ini.setText(prefs['personal.ini'])
-        # self.l.addWidget(self.ini)
+        self.l.addSpacing(5)
 
         self.personalini = prefs['personal.ini']
 
+        groupbox = QGroupBox(_("personal.ini"))
+        vert = QVBoxLayout()
+        groupbox.setLayout(vert)
+        self.l.addWidget(groupbox)
+
+        horz = QHBoxLayout()
+        vert.addLayout(horz)        
         self.ini_button = QPushButton(_('Edit personal.ini'), self)
         #self.ini_button.setToolTip(_("Edit personal.ini file."))
         self.ini_button.clicked.connect(self.add_ini_button)
-        self.l.addWidget(self.ini_button)
+        horz.addWidget(self.ini_button)
         
+        label = QLabel(_("FanFicFare now includes find, color coding, and error checking for personal.ini editing.  Red generally indicates errors."))
+        label.setWordWrap(True)
+        horz.addWidget(label)
+        
+        vert.addSpacing(5)
+
+        horz = QHBoxLayout()
+        vert.addLayout(horz)
+        self.ini_button = QPushButton(_('View "Safe" personal.ini'), self)
+        #self.ini_button.setToolTip(_("Edit personal.ini file."))
+        self.ini_button.clicked.connect(self.safe_ini_button)
+        horz.addWidget(self.ini_button)
+        
+        label = QLabel(_("View your personal.ini with usernames and passwords removed.  For safely sharing your personal.ini settings with others."))
+        label.setWordWrap(True)
+        horz.addWidget(label)
+        
+        self.l.addSpacing(5)
+        
+        groupbox = QGroupBox(_("defaults.ini"))
+        horz = QHBoxLayout()
+        groupbox.setLayout(horz)
+        self.l.addWidget(groupbox)
+        
+        view_label = _("View all of the plugin's configurable settings\nand their default settings.")
+        self.defaults = QPushButton(_('View Defaults')+' (plugin-defaults.ini)', self)
+        self.defaults.setToolTip(view_label)
+        self.defaults.clicked.connect(self.show_defaults)
+        horz.addWidget(self.defaults)
+
+        label = QLabel(view_label)
+        label.setWordWrap(True)
+        horz.addWidget(label)
+        
+        self.l.addSpacing(5)
+
+        groupbox = QGroupBox(_("Calibre Columns"))
+        vert = QVBoxLayout()
+        groupbox.setLayout(vert)
+        self.l.addWidget(groupbox)
+
+        horz = QHBoxLayout()
+        vert.addLayout(horz)
+        pass_label = _("If checked, when updating/overwriting an existing book, FanFicFare will have the Calibre Columns available to use in replace_metadata, title_page, etc.<br>Click the button below to see the Calibre Column namess.")%no_trans
+        self.cal_cols_pass_in = QCheckBox(_('Pass Calibre Columns into FanFicFare on Update/Overwrite')%no_trans,self)
+        self.cal_cols_pass_in.setToolTip(pass_label)
+        self.cal_cols_pass_in.setChecked(prefs['cal_cols_pass_in'])
+        horz.addWidget(self.cal_cols_pass_in)
+        
+        label = QLabel(pass_label)
+        label.setWordWrap(True)
+        horz.addWidget(label)
+
+        vert.addSpacing(5)
+        
+        horz = QHBoxLayout()
+        vert.addLayout(horz)
+        col_label = _("FanFicFare can pass the Calibre Columns into the download/update process.<br>This will show you the columns available by name.")
+        self.showcalcols = QPushButton(_('Show Calibre Column Names'), self)
+        self.showcalcols.setToolTip(col_label)
+        self.showcalcols.clicked.connect(self.show_showcalcols)
+        horz.addWidget(self.showcalcols)
+
+        label = QLabel(col_label)
+        label.setWordWrap(True)
+        horz.addWidget(label)
+
         label = QLabel(_("Changes will only be saved if you click 'OK' to leave Customize FanFicFare."))
         label.setWordWrap(True)
         self.l.addWidget(label)
-        
-        self.defaults = QPushButton(_('View Defaults')+' (plugin-defaults.ini)', self)
-        self.defaults.setToolTip(_("View all of the plugin's configurable settings\nand their default settings."))
-        self.defaults.clicked.connect(self.show_defaults)
-        self.l.addWidget(self.defaults)
-
-        self.cal_cols_pass_in = QCheckBox(_('Pass Calibre Columns into FanFicFare on Update/Overwrite')%no_trans,self)
-        self.cal_cols_pass_in.setToolTip(_("If checked, when updating/overwriting an existing book, FanFicFare will have the Calibre Columns available to use in replace_metadata, title_page, etc.<br>Click the button below to see the Calibre Column namess.")%no_trans)
-        self.cal_cols_pass_in.setChecked(prefs['cal_cols_pass_in'])
-        self.l.addWidget(self.cal_cols_pass_in)
-        
-        self.showcalcols = QPushButton(_('Show Calibre Column Names'), self)
-        self.showcalcols.setToolTip(_("FanFicFare can pass the Calibre Columns into the download/update process.<br>This will show you the columns available by name."))
-        self.showcalcols.clicked.connect(self.show_showcalcols)
-        self.l.addWidget(self.showcalcols)
 
         self.l.insertStretch(-1)
-        # let edit box fill the space.
         
     def show_defaults(self):
         IniTextDialog(self,
@@ -723,6 +765,18 @@ class PersonalIniTab(QWidget):
                        read_only=True,
                        save_size_name='fff:defaults.ini').exec_()
         
+    def safe_ini_button(self):
+        personalini = re.sub(r'((username|password) *[=:]).*$',r'\1XXXXXXXX',self.personalini,flags=re.MULTILINE)
+        
+        d = EditTextDialog(self,
+                           personalini,
+                           icon=self.windowIcon(),
+                           title=_("View 'Safe' personal.ini"),
+                           label=_("View your personal.ini with usernames and passwords removed.  For safely sharing your personal.ini settings with others."),
+                           save_size_name='fff:safe personal.ini',
+                           read_only=True)
+        d.exec_()
+        
     def add_ini_button(self):
         d = IniTextDialog(self,
                            self.personalini,
@@ -1287,6 +1341,7 @@ class CustomColumnsTab(QWidget):
         tooltip=_("When an update or overwrite of an existing story fails, record the reason in this column.\n(Text and Long Text columns only.)")
         label.setToolTip(tooltip)
         horz.addWidget(label)
+
         self.errorcol = QComboBox(self)
         self.errorcol.setToolTip(tooltip)
         self.errorcol.addItem('','none')
@@ -1295,6 +1350,15 @@ class CustomColumnsTab(QWidget):
                 self.errorcol.addItem(column['name'],key)
         self.errorcol.setCurrentIndex(self.errorcol.findData(prefs['errorcol']))
         horz.addWidget(self.errorcol)
+        
+        self.save_all_errors = QCheckBox(_('Save All Errors'),self)
+        self.save_all_errors.setToolTip(_('If unchecked, these errors will not be saved:%s')%(
+                '\n'+
+                '\n'.join((_("Not Overwriting, web site is not newer."),
+                           _("Already contains %d chapters.").replace('%d','X')))))
+        self.save_all_errors.setChecked(prefs['save_all_errors'])
+        horz.addWidget(self.save_all_errors)
+        
         self.l.addLayout(horz)
         
         horz = QHBoxLayout()
@@ -1310,6 +1374,10 @@ class CustomColumnsTab(QWidget):
                 self.savemetacol.addItem(column['name'],key)
         self.savemetacol.setCurrentIndex(self.savemetacol.findData(prefs['savemetacol']))
         horz.addWidget(self.savemetacol)
+
+        label = QLabel('')
+        horz.addWidget(label) # empty spacer for alignment with error column line.
+        
         self.l.addLayout(horz)
 
         #print("prefs['custom_cols'] %s"%prefs['custom_cols'])

calibre-plugin/dialogs.py

@@ -158,9 +158,10 @@ class RejectUrlEntry:
         return retval
 
 class NotGoingToDownload(Exception):
-    def __init__(self,error,icon='dialog_error.png'):
+    def __init__(self,error,icon='dialog_error.png',showerror=True):
         self.error=error
         self.icon=icon
+        self.showerror=showerror
 
     def __str__(self):
         return self.error
@@ -580,14 +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")):
@@ -598,7 +619,6 @@ class LoopProgressDialog(QProgressDialog):
         self.setMinimumWidth(500)
         self.book_list = book_list
         self.foreach_function = foreach_function
-        self.finish_function = finish_function
         self.status_prefix = status_prefix
         self.i = 0
         self.start_time = datetime.now()
@@ -638,15 +658,16 @@ 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)
             book['icon'] = d.icon
 
         except Exception as e:
             book['good']=False
             book['comment']=unicode(e)
-            logger.error("Exception: %s:%s"%(book,unicode(e)))
-            traceback.print_exc()
+            logger.error("Exception: %s:%s"%(book,unicode(e)),exc_info=True)
 
         self.updateStatus()
         self.i += 1
@@ -658,8 +679,6 @@ class LoopProgressDialog(QProgressDialog):
 
     def do_when_finished(self):
         self.hide()
-        # Queues a job to process these books in the background.
-        self.finish_function(self.book_list)
 
 def time_duration_format(seconds):
     """

calibre-plugin/fff_plugin.py

@@ -7,6 +7,22 @@ __license__   = 'GPL v3'
 __copyright__ = '2016, Jim Miller'
 __docformat__ = 'restructuredtext en'
 
+
+# import cProfile
+
+# def do_cprofile(func):
+#     def profiled_func(*args, **kwargs):
+#         profile = cProfile.Profile()
+#         try:
+#             profile.enable()
+#             result = func(*args, **kwargs)
+#             profile.disable()
+#             return result
+#         finally:
+#             profile.print_stats()
+#     return profiled_func
+
+
 import logging
 logger = logging.getLogger(__name__)
 
@@ -994,7 +1010,8 @@ class FanFicFarePlugin(InterfaceAction):
                                    show_copy_button=False):
                     rejecturllist.remove(url)
         return False
-            
+
+    # @do_cprofile
     def prep_download_loop(self,book,
                            options={'fileform':'epub',
                                     'collision':ADDNEW,
@@ -1015,6 +1032,7 @@ class FanFicFarePlugin(InterfaceAction):
         ## 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.
+
         if self.reject_url(merge,book):
             return
 
@@ -1300,7 +1318,7 @@ class FanFicFarePlugin(InterfaceAction):
                         urlchaptercount = int(story.getMetadata('numChapters').replace(',',''))
                         if chaptercount == urlchaptercount:
                             if collision == UPDATE:
-                                raise NotGoingToDownload(_("Already contains %d chapters.")%chaptercount,'edit-undo.png')
+                                raise NotGoingToDownload(_("Already contains %d chapters.")%chaptercount,'edit-undo.png',showerror=False)
                         elif chaptercount > urlchaptercount:
                             raise NotGoingToDownload(_("Existing epub contains %d chapters, web site only has %d. Use Overwrite to force update.") % (chaptercount,urlchaptercount),'dialog_error.png')
                         elif chaptercount == 0:
@@ -1311,7 +1329,7 @@ class FanFicFarePlugin(InterfaceAction):
                     logger.debug("OVERWRITE file: "+db.format_abspath(book_id, formmapping[fileform], index_is_id=True))
                     fileupdated=datetime.fromtimestamp(os.stat(db.format_abspath(book_id, formmapping[fileform], index_is_id=True))[8])
                     logger.debug("OVERWRITE file updated: %s"%fileupdated)
-                    book['updated']=fileupdated
+                    book['fileupdated']=fileupdated
                     if not bgmeta:
                         # check make sure incoming is newer.
                         lastupdated=story.getMetadataRaw('dateUpdated')
@@ -1321,7 +1339,7 @@ class FanFicFarePlugin(InterfaceAction):
                         # updated does have time, use full timestamps.
                         if (lastupdated.time() == time.min and fileupdated.date() > lastupdated.date()) or \
                                 (lastupdated.time() != time.min and fileupdated > lastupdated):
-                            raise NotGoingToDownload(_("Not Overwriting, web site is not newer."),'edit-undo.png')
+                            raise NotGoingToDownload(_("Not Overwriting, web site is not newer."),'edit-undo.png',showerror=False)
 
                 # For update, provide a tmp file copy of the existing epub so
                 # it can't change underneath us.  Now also overwrite for logpage preserve.
@@ -1457,7 +1475,8 @@ class FanFicFarePlugin(InterfaceAction):
             self.gui.proceed_question(self.update_error_column,
                                       payload, htmllog,
                                       _('FanFicFare log'), _('FanFicFare download ended'), msg,
-                                      show_copy_button=False)
+                                      show_copy_button=False,
+                                      log_viewer_unique_name="FanFicFare log viewer")
             return
 
         cookiejarfile = PersistentTemporaryFile(suffix='.cookiejar',
@@ -1494,7 +1513,7 @@ class FanFicFarePlugin(InterfaceAction):
         custom_columns = self.gui.library_view.model().custom_columns
         if book['calibre_id'] and prefs['errorcol'] != '' and prefs['errorcol'] in custom_columns:
             label = custom_columns[prefs['errorcol']]['label']
-            if not book['good']:
+            if not book['good'] and (book['showerror'] or prefs['save_all_errors']):
                 logger.debug("record/update error message column %s %s"%(book['title'],book['url']))
                 self.set_custom(db, book['calibre_id'], 'comment', book['comment'], label=label, commit=True) # book['comment']
             else:
@@ -1677,14 +1696,14 @@ class FanFicFarePlugin(InterfaceAction):
                 if 'status' in book:
                     status = book['status']
                 else:
-                    status = 'Good'
+                    status = _('Good')
                 htmllog = htmllog + '<tr><td>' + '</td><td>'.join([escapehtml(status),escapehtml(book['title']),escapehtml(", ".join(book['author'])),escapehtml(book['comment']),book['url']]) + '</td></tr>'
 
             for book in bad_list:
                 if 'status' in book:
                     status = book['status']
                 else:
-                    status = 'Bad'
+                    status = _('Bad')
                 htmllog = htmllog + '<tr><td>' + '</td><td>'.join([escapehtml(status),escapehtml(book['title']),escapehtml(", ".join(book['author'])),escapehtml(book['comment']),book['url']]) + '</td></tr>'
 
             htmllog = htmllog + '</table></body></html>'
@@ -1694,7 +1713,8 @@ class FanFicFarePlugin(InterfaceAction):
         self.gui.proceed_question(do_update_func,
                                   payload, htmllog,
                                   _('FanFicFare log'), _('FanFicFare download complete'), msg,
-                                  show_copy_button=False)
+                                  show_copy_button=False,
+                                  log_viewer_unique_name="FanFicFare log viewer")
 
     def do_download_merge_update(self, payload):
 
@@ -1777,7 +1797,7 @@ class FanFicFarePlugin(InterfaceAction):
                                status_prefix=_("Updated"))
 
     def update_error_column_loop(self,book,db=None,label=None):
-        if book['calibre_id'] and label:
+        if book['calibre_id'] and label and (book['showerror'] or prefs['save_all_errors']):
             logger.debug("add/update bad %s %s %s"%(book['title'],book['url'],book['comment']))
             self.set_custom(db, book['calibre_id'], 'comment', book['comment'], label=label, commit=True)
 
@@ -2058,7 +2078,7 @@ 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
@@ -2194,6 +2214,10 @@ class FanFicFarePlugin(InterfaceAction):
         book['comments'] = '' # note this is the book comments.
 
         book['good'] = True
+        book['showerror'] = True # False when NotGoingToDownload is
+                                 # not-overwrite / not-update / skip
+                                 # -- what some would consider 'not an
+                                 # error'
         book['calibre_id'] = None
         book['begin'] = None
         book['end'] = None
@@ -2213,7 +2237,7 @@ class FanFicFarePlugin(InterfaceAction):
             book = self.convert_url_to_book(url)
             if book['url'] in uniqueurls:
                 book['good'] = False
-                book['comment'] = "Same story already included."
+                book['comment'] = _("Same story already included.")
             uniqueurls.add(book['url'])
             book['listorder']=i # BG d/l jobs don't come back in order.
                                 # Didn't matter until anthologies & 'marked' successes

calibre-plugin/inihighlighter.py

@@ -4,7 +4,7 @@ from __future__ import (unicode_literals, division,
                         print_function)
 
 __license__   = 'GPL v3'
-__copyright__ = '2015, Jim Miller'
+__copyright__ = '2016, Jim Miller'
 __docformat__ = 'restructuredtext en'
 
 import re
@@ -68,6 +68,10 @@ class IniHighlighter(QSyntaxHighlighter):
         self.teststoryRule = HighlightingRule( r"^\[teststory:([0-9]+|defaults)\]", Qt.darkCyan, blocknum=3 )
         self.highlightingRules.append( self.teststoryRule )
 
+        # storyUrl sections
+        self.storyUrlRule = HighlightingRule( r"^\[https?://.*\]", Qt.darkMagenta, blocknum=4 )
+        self.highlightingRules.append( self.storyUrlRule )
+
         # NOT comments -- but can be custom columns, so don't flag.
         #self.highlightingRules.append( HighlightingRule( r"(?<!^)#[^\n]*" , Qt.red ) )
         
@@ -96,6 +100,10 @@ class IniHighlighter(QSyntaxHighlighter):
             if blocknum == 3:
                 self.setFormat( 0, len(text), self.teststoryRule.highlight )
             
+            # storyUrl section rules:
+            if blocknum == 4:
+                self.setFormat( 0, len(text), self.storyUrlRule.highlight )
+            
         self.setCurrentBlockState( blocknum )
 
 class HighlightingRule():

calibre-plugin/jobs.py

@@ -23,6 +23,12 @@ from calibre.library.comments import sanitize_comments_html
 from calibre_plugins.fanficfare_plugin.wordcount import get_word_count
 from calibre_plugins.fanficfare_plugin.prefs import (SAVE_YES, SAVE_YES_UNLESS_SITE)
 
+# pulls in translation files for _() strings
+try:
+    load_translations()
+except NameError:
+    pass # load_translations() added in calibre 1.9
+
 # ------------------------------------------------------------------------------
 #
 #              Functions to perform downloads using worker jobs
@@ -82,7 +88,7 @@ def do_download_worker(book_list,
         book_list.append(job.result)
         book_id = job._book['calibre_id']
         count = count + 1
-        notification(float(count)/total, '%d of %d stories finished downloading'%(count,total))
+        notification(float(count)/total, _('%d of %d stories finished downloading')%(count,total))
         # Add this job's output to the current log
         logger.info('Logfile for book ID %s (%s)'%(book_id, job._book['title']))
         logger.info(job.details)
@@ -189,7 +195,7 @@ def do_download_for_worker(book,options,merge,notification=lambda x,y:x):
             ## No need to download at all.  Shouldn't ever get down here.
             if options['collision'] in (CALIBREONLY, CALIBREONLYSAVECOL):
                 logger.info("Skipping CALIBREONLY 'update' down inside worker--this shouldn't be happening...")
-                book['comment'] = 'Metadata collected.'
+                book['comment'] = _('Metadata collected.')
                 book['all_metadata'] = story.getAllMetadata(removeallentities=True)
                 if options['savemetacol'] != '':
                     book['savemetacol'] = story.dump_html_metadata()
@@ -214,14 +220,14 @@ def do_download_for_worker(book,options,merge,notification=lambda x,y:x):
                     # updated does have time, use full timestamps.
                     if (lastupdated.time() == time.min and fileupdated.date() > lastupdated.date()) or \
                             (lastupdated.time() != time.min and fileupdated > lastupdated):
-                        raise NotGoingToDownload(_("Not Overwriting, web site is not newer."),'edit-undo.png')
+                        raise NotGoingToDownload(_("Not Overwriting, web site is not newer."),'edit-undo.png',showerror=False)
 
                 
                 logger.info("write to %s"%outfile)
                 inject_cal_cols(book,story,configuration)
                 writer.writeStory(outfilename=outfile, forceOverwrite=True)
                 
-                book['comment'] = 'Download %s completed, %s chapters.'%(options['fileform'],story.getMetadata("numChapters"))
+                book['comment'] = _('Download %s completed, %s chapters.')%(options['fileform'],story.getMetadata("numChapters"))
                 book['all_metadata'] = story.getAllMetadata(removeallentities=True)
                 if options['savemetacol'] != '':
                     book['savemetacol'] = story.dump_html_metadata()
@@ -253,7 +259,7 @@ def do_download_for_worker(book,options,merge,notification=lambda x,y:x):
                             book['outfile'] = book['epub_for_update'] # for anthology merge ops.
                             return book
                         else: # not merge,
-                            raise NotGoingToDownload(_("Already contains %d chapters.")%chaptercount,'edit-undo.png')
+                            raise NotGoingToDownload(_("Already contains %d chapters.")%chaptercount,'edit-undo.png',showerror=False)
                     elif chaptercount > urlchaptercount:
                         raise NotGoingToDownload(_("Existing epub contains %d chapters, web site only has %d. Use Overwrite to force update.") % (chaptercount,urlchaptercount),'dialog_error.png')
                     elif chaptercount == 0:
@@ -304,6 +310,7 @@ def do_download_for_worker(book,options,merge,notification=lambda x,y:x):
             
         except NotGoingToDownload as d:
             book['good']=False
+            book['showerror']=d.showerror
             book['comment']=unicode(d)
             book['icon'] = d.icon
     
@@ -311,9 +318,8 @@ def do_download_for_worker(book,options,merge,notification=lambda x,y:x):
             book['good']=False
             book['comment']=unicode(e)
             book['icon']='dialog_error.png'
-            book['status'] = 'Error'
-            logger.info("Exception: %s:%s"%(book,unicode(e)))
-            traceback.print_exc()
+            book['status'] = _('Error')
+            logger.info("Exception: %s:%s"%(book,unicode(e)),exc_info=True)
             
         #time.sleep(10)
     return book

calibre-plugin/plugin-defaults.ini

@@ -1,4 +1,4 @@
-# Copyright 2015 Fanficdownloader team, 2015 FanFicFare team
+# Copyright 2015 Fanficdownloader team, 2016 FanFicFare team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -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
-dateUpdated_format:%%Y-%%m-%%d %%H:%%M:%%S
+datePublished_format:%%Y-%%m-%%d %%H:%%M
+dateUpdated_format:%%Y-%%m-%%d %%H:%%M
 
 ## Only take the first X characters of the 'first' post to use as
 ## the description.
@@ -488,6 +488,33 @@ description_limit:500
 ## in the ebook for that chapter.
 continue_on_chapter_error:false
 
+## When given a thread URL, use threadmarks as chapter links when
+## there are at least this many threadmarks.  A number of older
+## threads have a single threadmark to an 'index' post.  Set to 1 to
+## use threadmarks whenever they exist.
+minimum_threadmarks:2
+
+## When 'first post' (or post URL) is being added as a chapter, give
+## the chapter this title.
+first_post_title:First Post
+
+## In normal operation, if given a post URL or a thread URL with less
+## than minimum_threadmarks, the given post or the first post of the
+## thread will be included as the first chapter (with chapter title
+## from first_post_title) unless that post is explicitly linked to in
+## the collected chapter list.  First post is not included when using
+## thread marks.
+##
+## If always_include_first_post:true, then the given or first post
+## will be included as above even if it is a link in the post or even
+## if threadmarks are used.  Can result in a duplicated chapter.
+always_include_first_post:false
+
+## In normal operation, forumtags will only be populated when
+## threadmarks are used for chapters (see minimum_threadmarks above).
+## When always_use_forumtags:true, always populate forumtags.
+always_use_forumtags:false
+
 ## Each output format has a section that overrides [defaults]
 [html]
 
@@ -842,6 +869,12 @@ 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
@@ -1193,14 +1226,41 @@ dislikes_label:Dislikes
 ## program can prompt you, or you can save it in config.  In
 ## commandline version, this should go in your personal.ini, not
 ## defaults.ini.
-#username:YourName
+## finestories.com has started requiring login by email rather than
+## pen name.
+#username:youremail@yourdomain.dom
 #password:yourpassword
 
-# shows size as "10 KB", not word count
-extra_valid_entries:size
+## Clear FanFiction from defaults, site is original fiction.
+extratags:
 
-# don't show twitter icon.
-cover_exclusion_regexp:/res/css/bir.png
+extra_valid_entries:size,universe,universeUrl,universeHTML,sitetags,notice,codes,score
+#extra_titlepage_entries:size,universeHTML,sitetags,notice,score
+include_in_codes:sitetags
+
+## adds to include_subject_tags instead of replacing it.
+#extra_subject_tags:sitetags
+
+size_label:Size
+universe_label:Universe
+universeUrl_label:Universe URL
+universeHTML_label:Universe
+sitetags_label:Site Tags
+notice_label:Notice
+score_label:Score
+
+## Assume entryUrl, apply to "<a class='%slink' href='%s'>%s</a>" to
+## make entryHTML.
+make_linkhtml_entries:universe
+
+## storiesonline.net stories can be in a series or a universe, but not
+## both.  By default, universe will be populated in 'series' with
+## index=0
+universe_as_series: true
+
+## some sites include images that we don't ever want becoming the
+## cover image.  This lets you exclude them.
+cover_exclusion_regexp:/css/bir.png
 
 [forums.spacebattles.com]
 ## see [base_xenforoforum]
@@ -1280,9 +1340,21 @@ crossoverfandom_label:Crossover Fandom
 extra_titlepage_entries:universe,crossoverfandom
 
 [literotica.com]
-extra_valid_entries:eroticatags
+extra_valid_entries:eroticatags,averrating
 eroticatags_label:Erotica Tags
-extra_titlepage_entries: eroticatags
+averrating_label:Average Rating
+extra_titlepage_entries:eroticatags,averrating
+
+## Extract more erotica_tags from the meta tag of each chapter
+use_meta_keywords: true
+
+## For multiple chapter stories, attempt to clean up the chapter title. This will
+## remove the story title and change "Ch. 01" to "Chapter 1", "Pt. 01" to "Part 1"
+## or just use the text. If this can't be done, the full title is used.
+clean_chapter_titles: false
+
+## Add the chapter description at the start of each chapter.
+description_in_chapter: false
 
 [lotrfanfiction.com]
 extra_valid_entries: readings
@@ -1791,6 +1863,10 @@ 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
@@ -1909,6 +1985,9 @@ extracategories:Harry Potter
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
 
+extra_valid_entries:reads,reviews
+reads_label:Total Read Count
+
 [www.hpfanficarchive.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
@@ -2227,6 +2306,96 @@ extracategories:Stargate: Atlantis
 extra_valid_entries:reviews
 reviews_label:Reviews
 
+[buffygiles.velocitygrass.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Site dedicated to these categories/characters/ships
+extracharacters:Buffy,Giles
+
+[fanfiction.lucifael.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+[www.andromeda-web.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Site dedicated to these categories/characters/ships
+extracategories:Andromeda
+
+[www.artemis-fowl.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Site dedicated to these categories/characters/ships
+extracategories:Artemis Fowl
+
+[www.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,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+
+
 [overrides]
 ## It may sometimes be useful to override all of the specific format,
 ## site and site:format sections in your private configuration.  For

calibre-plugin/prefs.py

@@ -158,6 +158,7 @@ default_prefs['countpagesstats'] = []
 default_prefs['wordcountmissing'] = False
 
 default_prefs['errorcol'] = ''
+default_prefs['save_all_errors'] = True
 default_prefs['savemetacol'] = ''
 default_prefs['custom_cols'] = {}
 default_prefs['custom_cols_newonly'] = {}

fanficfare/__init__.py

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

fanficfare/adapters/__init__.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
+# Copyright 2011 Fanficdownloader team, 2016 FanFicFare team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -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
@@ -139,6 +133,11 @@ import adapter_ninelivesarchivecom
 import adapter_masseffect2in
 import adapter_quotevcom
 import adapter_mcstoriescom
+import adapter_lucifaelff
+import adapter_buffygilescom
+import adapter_andromedawebcom
+import adapter_artemisfowlcom
+import adapter_naiceanilmenet
 
 ## This bit of complexity allows adapters to be added by just adding
 ## importing.  It eliminates the long if/else clauses we used to need
@@ -169,8 +168,9 @@ def getNormalStoryURL(url):
         return None
 
 def getNormalStoryURLSite(url):
+    # print("getNormalStoryURLSite:%s"%url)
     if not getNormalStoryURL.__dummyconfig:
-        getNormalStoryURL.__dummyconfig = Configuration("test1.com","EPUB")
+        getNormalStoryURL.__dummyconfig = Configuration(["test1.com"],"EPUB",lightweight=True)
     # pulling up an adapter is pretty low over-head.  If
     # it fails, it's a bad url.
     try:

fanficfare/adapters/adapter_andromedawebcom.py

@@ -0,0 +1,302 @@
+# -*- 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.
+#
+# ####### Not all lables are captured. they are not formtted correctly on the 
+# #######  webpage.
+
+# 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 AndromedaWebComAdapter # XXX
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class AndromedaWebComAdapter(BaseSiteAdapter):  # XXX
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+
+
+        # normalized story URL.
+        # XXX Most sites don't have the /fiction part.  Replace all to remove it usually.
+        self._setURL('http://' + self.getSiteDomain() + '/fiction/viewstory.php?sid='+self.story.getMetadata('storyId'))
+
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','awc') # XXX
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%d %b %Y" # XXX
+
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'www.andromeda-web.com'  # XXX
+
+    @classmethod
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/fiction/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/fiction/viewstory.php?sid=")+r"\d+$"
+
+    ## Login seems to be reasonably standard across eFiction sites.
+    def needToLoginCheck(self, data):
+        if 'Registered Users Only' in data \
+                or 'There is no such account on our website' in data \
+                or "That password doesn't match the one in our database" in data:
+            return True
+        else:
+            return False
+
+    def performLogin(self, url):
+        params = {}
+
+        if self.password:
+            params['penname'] = self.username
+            params['password'] = self.password
+        else:
+            params['penname'] = self.getConfig("username")
+            params['password'] = self.getConfig("password")
+        params['cookiecheck'] = '1'
+        params['submit'] = 'Submit'
+
+        loginUrl = 'http://' + self.getSiteDomain() + '/user.php?action=login'
+        logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
+                                                              params['penname']))
+
+        d = self._fetchUrl(loginUrl, params)
+
+        if "Member Account" not in d : #Member Account
+            logger.info("Failed to login to URL %s as %s" % (loginUrl,
+                                                              params['penname']))
+            raise exceptions.FailedToLogin(url,params['penname'])
+            return False
+        else:
+            return True
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        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 = "&warning=2"
+        else:
+            addurl=""
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'+addurl
+        logger.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        if self.needToLoginCheck(data):
+            # need to log in for this one.
+            self.performLogin(url)
+            data = self._fetchUrl(url)
+
+        # Since the warning text can change by warning level, let's
+        # look for the warning pass url.  ksarchive uses
+        # &warning= -- actually, so do other sites.  Must be an
+        # eFiction book.
+
+        # fiction/viewstory.php?sid=1882&warning=4
+        # fiction/viewstory.php?sid=1654&ageconsent=ok&warning=2
+        #print data
+        m = re.search(r"'fiction/viewstory.php\?sid=10(&warning=2)'",data)
+        m = re.search(r"'fiction/viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
+        if m != None:
+            if self.is_adult or self.getConfig("is_adult"):
+                # We tried the default and still got a warning, so
+                # let's pull the warning number from the 'continue'
+                # link and reload data.
+                addurl = m.group(1)
+                # correct stupid & error in url.
+                addurl = addurl.replace("&","&")
+                url = self.url+'&index=1'+addurl
+                logger.debug("URL 2nd try: "+url)
+
+                try:
+                    data = self._fetchUrl(url)
+                except urllib2.HTTPError, e:
+                    if e.code == 404:
+                        raise exceptions.StoryDoesNotExist(self.url)
+                    else:
+                        raise e
+            else:
+                raise exceptions.AdultCheckRequired(self.url)
+
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = self.make_soup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+
+        pagetitle = soup.find('div',{'id':'content'})
+
+        ## Title
+        a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+
+        self.story.setMetadata('title',stripHTML(a))
+
+        # Find authorid and URL from... author url.
+        a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        self.story.setMetadata('authorId',a['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('author',a.string)
+
+        # 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+'/fiction/'+chapter['href']+addurl))
+
+            self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+
+        # utility method
+        def defaultGetattr(d,k):
+            try:
+                return d[k]
+            except:
+                return ""
+
+        # <span class="label">Rated:</span> NC-17<br /> etc
+        labels = soup.findAll('span',{'class':'label'})
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.string
+
+            if 'Summary' in label:
+                ## 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"fiction/viewseries.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = self.make_soup(self._fetchUrl(series_url))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^fiction/viewstory.php\?sid=\d+$'))
+            i=1
+            for a in storyas:
+                if a['href'] == ('fiction/viewstory.php?sid='+self.story.getMetadata('storyId')):
+                    self.setSeries(series_name, i)
+                    self.story.setMetadata('seriesUrl',series_url)
+                    break
+                i+=1
+
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+        
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logger.debug('Getting chapter text from: %s' % url)
+
+        soup = self.make_soup(self._fetchUrl(url))
+
+        div = soup.find('div', {'class' : 'story'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+
+        return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_artemisfowlcom.py

@@ -0,0 +1,302 @@
+# -*- 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.
+#
+# ####### Not all lables are captured. they are not formtted correctly on the 
+# #######  webpage.
+
+# 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 ArtemisFowlComAdapter # XXX
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class ArtemisFowlComAdapter(BaseSiteAdapter):  # XXX
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+
+
+        # normalized story URL.
+        # XXX Most sites don't have the /fiction part.  Replace all to remove it usually.
+        self._setURL('http://' + self.getSiteDomain() + '/fanfiction/viewstory.php?sid='+self.story.getMetadata('storyId'))
+
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','afcff') # XXX
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%d/%m/%y" # XXX
+
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'www.artemis-fowl.com'  # XXX
+
+    @classmethod
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/fanfiction/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/fanfiction/viewstory.php?sid=")+r"\d+$"
+
+    ## Login seems to be reasonably standard across eFiction sites.
+    def needToLoginCheck(self, data):
+        if 'Registered Users Only' in data \
+                or 'There is no such account on our website' in data \
+                or "That password doesn't match the one in our database" in data:
+            return True
+        else:
+            return False
+
+    def performLogin(self, url):
+        params = {}
+
+        if self.password:
+            params['penname'] = self.username
+            params['password'] = self.password
+        else:
+            params['penname'] = self.getConfig("username")
+            params['password'] = self.getConfig("password")
+        params['cookiecheck'] = '1'
+        params['submit'] = 'Submit'
+
+        loginUrl = 'http://' + self.getSiteDomain() + '/user.php?action=login'
+        logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
+                                                              params['penname']))
+
+        d = self._fetchUrl(loginUrl, params)
+
+        if "Member Account" not in d : #Member Account
+            logger.info("Failed to login to URL %s as %s" % (loginUrl,
+                                                              params['penname']))
+            raise exceptions.FailedToLogin(url,params['penname'])
+            return False
+        else:
+            return True
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        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 = "&warning=5"
+        else:
+            addurl=""
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'+addurl
+        logger.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        if self.needToLoginCheck(data):
+            # need to log in for this one.
+            self.performLogin(url)
+            data = self._fetchUrl(url)
+
+        # 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.
+
+        # fanfiction/viewstory.php?sid=1882&warning=4
+        # fanfiction/viewstory.php?sid=1654&ageconsent=ok&warning=2
+        #print data
+        m = re.search(r"'fanfiction/viewstory.php\?sid=10(&warning=5)'",data)
+        m = re.search(r"'fanfiction/viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
+        if m != None:
+            if self.is_adult or self.getConfig("is_adult"):
+                # We tried the default and still got a warning, so
+                # let's pull the warning number from the 'continue'
+                # link and reload data.
+                addurl = m.group(1)
+                # correct stupid & error in url.
+                addurl = addurl.replace("&","&")
+                url = self.url+'&index=1'+addurl
+                logger.debug("URL 2nd try: "+url)
+
+                try:
+                    data = self._fetchUrl(url)
+                except urllib2.HTTPError, e:
+                    if e.code == 404:
+                        raise exceptions.StoryDoesNotExist(self.url)
+                    else:
+                        raise e
+            else:
+                raise exceptions.AdultCheckRequired(self.url)
+
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = self.make_soup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+
+        pagetitle = soup.find('div',{'id':'pagetitle'})
+
+        ## Title
+        a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+
+        self.story.setMetadata('title',stripHTML(a))
+
+        # Find authorid and URL from... author url.
+        a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        self.story.setMetadata('authorId',a['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('author',a.string)
+
+        # 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+'/fanfiction/'+chapter['href']+addurl))
+
+            self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+
+        # utility method
+        def defaultGetattr(d,k):
+            try:
+                return d[k]
+            except:
+                return ""
+
+        # <span class="label">Rated:</span> NC-17<br /> etc
+        labels = soup.findAll('span',{'class':'label'})
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.string
+
+            if 'Summary' in label:
+                ## 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"fanfiction/viewseries.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = self.make_soup(self._fetchUrl(series_url))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^fanfiction/viewstory.php\?sid=\d+$'))
+            i=1
+            for a in storyas:
+                if a['href'] == ('fanfiction/viewstory.php?sid='+self.story.getMetadata('storyId')):
+                    self.setSeries(series_name, i)
+                    self.story.setMetadata('seriesUrl',series_url)
+                    break
+                i+=1
+
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+        
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logger.debug('Getting chapter text from: %s' % url)
+
+        soup = self.make_soup(self._fetchUrl(url))
+
+        div = soup.find('div', {'id' : 'story'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+
+        return self.utf8FromSoup(url,div)

fanficfare/adapters/adapter_bdsmgeschichten.py

@@ -1,347 +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(date_string, self.UPDATED_DATETIME_FORMAT)
-
-                    # Rather ugly hack to work around Calibre's changing of
-                    # Python's locale setting, causing am/pm to not be properly
-                    # parsed by strptime() when using a non-english locale
-                    if period == 'pm':
-                        date += timedelta(hours=12)
+                    date = makeDate(value, self.UPDATED_DATETIME_FORMAT)
+                    # ugly %p(am/pm) hack moved into makeDate so other sites can use it.
                     self.story.setMetadata('dateUpdated', date)
 
         if self.story.getMetadata('rating') == 'NC-17' and not (self.is_adult or self.getConfig('is_adult')):

fanficfare/adapters/adapter_buffygilescom.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2013 Fanficdownloader team, 2015 FanFicFare team
+# Copyright 2016 FanFicFare team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -29,11 +29,11 @@ from .. import exceptions as exceptions
 from base_adapter import BaseSiteAdapter,  makeDate
 
 def getClass():
-    return ScarHeadNetAdapter
+    return BuffyGilesComAdapter
 
 # 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 BuffyGilesComAdapter(BaseSiteAdapter):
 
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
@@ -52,10 +52,11 @@ 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 /efiction part.  Replace all to remove it usually.
+        self._setURL('http://' + self.getSiteDomain() + '/efiction/viewstory.php?sid='+self.story.getMetadata('storyId'))
 
         # Each adapter needs to have a unique site abbreviation.
-        self.story.setMetadata('siteabbrev','shn')
+        self.story.setMetadata('siteabbrev','bufg')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
@@ -64,14 +65,14 @@ class ScarHeadNetAdapter(BaseSiteAdapter):
     @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 'buffygiles.velocitygrass.com'
 
     @classmethod
     def getSiteExampleURLs(cls):
-        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
+        return "http://"+cls.getSiteDomain()+"/efiction/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
-        return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
+        return re.escape("http://"+self.getSiteDomain()+"/efiction/viewstory.php?sid=")+r"\d+$"
 
     ## Login seems to be reasonably standard across eFiction sites.
     def needToLoginCheck(self, data):
@@ -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=5"
         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
-        # viewstory.php?sid=1654&ageconsent=ok&warning=5
+        # efiction/viewstory.php?sid=1882&warning=4
+        # efiction/viewstory.php?sid=1654&ageconsent=ok&warning=5
         #print data
-        #m = re.search(r"'viewstory.php\?sid=1882(&warning=4)'",data)
-        m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
+        m = re.search(r"'efiction/viewstory.php\?sid=542(&warning=5)'",data)
+        m = re.search(r"'efiction/viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
         if m != None:
             if self.is_adult or self.getConfig("is_adult"):
                 # We tried the default and still got a warning, so
@@ -170,7 +171,7 @@ 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)
@@ -178,10 +179,11 @@ class ScarHeadNetAdapter(BaseSiteAdapter):
 
         # 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 +195,87 @@ 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+'/efiction/'+chapter['href']+addurl))
 
-        self.story.setMetadata('numChapters',len(self.chapterUrls))
+            self.story.setMetadata('numChapters',len(self.chapterUrls))
 
         # eFiction sites don't help us out a lot with their meta data
         # formating, so it's a little ugly.
 
-        cats = soup.findAll('a',href=re.compile(r'browse.php\?type=categories'))
-        for cat in cats:
-            if '/' == cat.string[0]:
-                self.story.addToList('ships','Harry Potter'+cat.string.split('(')[0])
-            elif 'Harry' in cat.string:
-                self.story.addToList('ships',cat.string.split('(')[0])
-            else:
-                self.story.addToList('category',cat.string)
-            if '(' in cat.string:
-                self.story.addToList('category',cat.string.split('(')[1].split(')')[0])
-
-
-
-
-        chars = soup.findAll('a',href=re.compile(r'browse.php\?type=characters'))
-        for char in chars:
-            self.story.addToList('characters',char.string)
-
-        genres = soup.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2'))
-        for genre in genres:
-            self.story.addToList('genre',genre.string)
-
-        warnings = soup.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
-        for warning in warnings:
-            self.story.addToList('warnings',warning.string)
-
-        textsoup = stripHTML(soup)
-
-        a = textsoup.split('Published: ')[1].split(' ')[0]
-        self.story.setMetadata('datePublished', makeDate(stripHTML(a), self.dateformat))
-        a = textsoup.split('Updated: ')[1].split(' ')[0]
-        self.story.setMetadata('dateUpdated', makeDate(stripHTML(a), self.dateformat))
-        a = textsoup.split('Rating: ')[1].split(' ')[0]
-        self.story.setMetadata('rating', a)
-        a = textsoup.split('Length: ')[1].split('(')[1].split(' ')[0]
-        self.story.setMetadata('numWords', a)
-        a = textsoup.split('Completed: ')[1].split(' ')[0]
-        if 'Yes' in a:
-            self.story.setMetadata('status', 'Completed')
-        else:
-            self.story.setMetadata('status', 'In-Progress')
-        #a = textsoup.split('Summary: ')[1].split('Add Story to Favorites')[0]
-        #self.setDescription(url,a)
-
-
-
-        a=soup.find(text=re.compile("Summary: "))
-        i=0
-        svalue = ""
-        while i == 0:
+        # utility method
+        def defaultGetattr(d,k):
             try:
-                b = unicode(a)
-                svalue += b.split('Summary: ')[1]
+                return d[k]
             except:
-                svalue += unicode(a)
-            if a.nextSibling != None:
-                a = a.nextSibling
-            else:
-                a = a.parent.nextSibling
-            if 'Disclaimer: ' in stripHTML(a):
-                i=1
-        self.setDescription(url,svalue)
+                return ""
+
+        # <span class="label">Rated:</span> NC-17<br /> etc
+        labels = soup.findAll('span',{'class':'label'})
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.string
+
+            if 'Summary' in label:
+                ## Everything until the next span class='label'
+                svalue = ""
+                while 'label' not in defaultGetattr(value,'class'):
+                    svalue += unicode(value)
+                    value = value.nextSibling
+                self.setDescription(url,svalue)
+                #self.story.setMetadata('description',stripHTML(svalue))
+
+            if 'Rated' in label:
+                self.story.setMetadata('rating', value)
+
+            if 'Word count' in label:
+                self.story.setMetadata('numWords', value)
+
+            if 'Categories' in label:
+                cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
+                for cat in cats:
+                    self.story.addToList('category',cat.string)
+
+            if 'Characters' in label:
+                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+                for char in chars:
+                    self.story.addToList('characters',char.string)
+
+            if 'Genre' in label:
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
+                for genre in genres:
+                    self.story.addToList('genre',genre.string)
+
+            if 'Warnings' in label:
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=3'))
+                for warning in warnings:
+                    self.story.addToList('warnings',warning.string)
+
+            if 'Completed' in label:
+                if 'Yes' in value:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+
+            if 'Published' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+
+            if 'Updated' in label:
+                # there's a stray [ at the end.
+                #value = value[0:-1]
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
 
         try:
             # Find Series name from series URL.
-            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            a = soup.find('a', href=re.compile(r"efiction/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+$'))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^efiction/viewstory.php\?sid=\d+$'))
             i=1
             for a in storyas:
-                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                if a['href'] == ('efiction/viewstory.php?sid='+self.story.getMetadata('storyId')):
                     self.setSeries(series_name, i)
                     self.story.setMetadata('seriesUrl',series_url)
                     break
@@ -283,7 +284,7 @@ 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):
 

fanficfare/adapters/adapter_buffynfaithnet.py

@@ -1,295 +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)
-            #argh, this mangles the ampersands I need on metadata['storyUrl']
-            #will set it this way
-            self.story.setMetadata('storyUrl',nurl,condremoveentities=False)
-        else:
-            raise exceptions.InvalidStoryURL(url,
-                                             self.getSiteDomain(),
-                                             self.getSiteExampleURLs())
-
-
-        # Each adapter needs to have a unique site abbreviation.
-        self.story.setMetadata('siteabbrev','bnfnet')
-
-    @staticmethod # must be @staticmethod, don't remove it.
-    def getSiteDomain():
-        # The site domain.  Does have www here, if it uses it.
-        return 'buffynfaith.net'
-
-    @classmethod
-    def stripURLParameters(cls,url):
-        "Only needs to be overriden if URL contains more than one parameter"
-        ## This adapter needs at least two parameters left on the URL, act and id
-        return re.sub(r"(\?act=(vie|ovr)&id=\d+)&.*$",r"\1",url)
-
-    def setHeader(self):
-        "buffynfaith.net wants a Referer for images.  Used both above and below(after cookieproc added)"
-        self.opener.addheaders.append(('Referer', 'http://'+self.getSiteDomain()+'/'))
-
-    @classmethod
-    def getSiteExampleURLs(cls):
-        return "http://"+cls.getSiteDomain()+"/fanfictions/index.php?act=vie&id=1234 http://"+cls.getSiteDomain()+"/fanfictions/index.php?act=ovr&id=1234 http://"+cls.getSiteDomain()+"/fanfictions/index.php?act=vie&id=1234&ch=2"
-
-    def getSiteURLPattern(self):
-        #http://buffynfaith.net/fanfictions/index.php?act=vie&id=963
-        #http://buffynfaith.net/fanfictions/index.php?act=vie&id=949
-        #http://buffynfaith.net/fanfictions/index.php?act=vie&id=949&ch=2
-        p = re.escape("http://"+self.getSiteDomain()+"/fanfictions/index.php?act=")+\
-            r"(vie|ovr)&id=(?P<id>\d+)(&ch=(?P<ch>\d+))?$"
-        return p
-
-    def use_pagecache(self):
-        '''
-        adapters that will work with the page cache need to implement
-        this and change it to True.
-        '''
-        return True
-
-    def extractChapterUrlsAndMetadata(self):
-
-        dateformat = "%d %B %Y"
-        url = self.url
-        logger.debug("URL: "+url)
-
-        #set a cookie to get past adult check
-        if self.is_adult or self.getConfig("is_adult"):
-            cookie = cl.Cookie(version=0, name='my_age', value='yes',
-                               port=None, port_specified=False,
-                               domain=self.getSiteDomain(), domain_specified=False, domain_initial_dot=False,
-                               path='/', path_specified=True,
-                               secure=False,
-                               expires=time.time()+10000,
-                               discard=False,
-                               comment=None,
-                               comment_url=None,
-                               rest={'HttpOnly': None},
-                               rfc2109=False)
-            self.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',mt.findAll('a')[1].nextSibling[len('&nbsp;&raquo;&nbsp;'):])
-        del mt
-
-        #the actual category, for me, is 'Buffy: The Vampire Slayer'
-        #self.story.addToList('category','Buffy: The Vampire Slayer')
-        #No need to do it here, it is better to set it in in plugin-defaults.ini and defaults.ini
-
-        #then a block that sits in a table cell like so:
-        #(contains a lot of metadata)
-        mblock = doc.find('td', align='left', width = '70%').contents
-        while len(mblock) > 0:
-            i = mblock.pop(0)
-            if 'Author:' in i.string:
-                #drop empty space
-                mblock.pop(0)
-                #get author link
-                a = mblock.pop(0)
-                authre = re.escape('./index.php?act=bio&id=')+'(?P<authid>\d+)'
-                m = re.match(authre,a['href'])
-                self.story.setMetadata('author',a.string)
-                self.story.setMetadata('authorId',m.group('authid'))
-                authurl = u'http://%s/fanfictions/index.php?act=bio&id=%s' % ( self.getSiteDomain(),
-                                            self.story.getMetadata('authorId'))
-                self.story.setMetadata('authorUrl',authurl,condremoveentities=False)
-                #drop empty space
-                mblock.pop(0)
-            if 'Rating:' in i.string:
-                self.story.setMetadata('rating',mblock.pop(0).strip())
-            if 'Published:' in i.string:
-                date = mblock.pop(0).strip()
-                #get rid of 'st', 'nd', 'rd', 'th' after day number
-                date = date[0:2]+date[4:]
-                self.story.setMetadata('datePublished',makeDate(date, dateformat))
-            if 'Last Updated:' in i.string:
-                date = mblock.pop(0).strip()
-                #get rid of 'st', 'nd', 'rd', 'th' after day number
-                date = date[0:2]+date[4:]
-                self.story.setMetadata('dateUpdated',makeDate(date, dateformat))
-            if 'Genre:' in i.string:
-                genres = mblock.pop(0).strip()
-                genres = genres.split('/')
-                for genre in genres: self.story.addToList('genre',genre)
-            #end ifs
-        #end while
-
-        # Find the chapter selector
-        select = soup.find('select', { 'name' : 'ch' } )
-
-        if select is None:
-           # no selector found, so it's a one-chapter story.
-           #self.chapterUrls.append((self.story.getMetadata('title'),url))
-           self.chapterUrls.append((self.story.getMetadata('title'),url))
-        else:
-            allOptions = select.findAll('option')
-            for o in allOptions:
-                url = u'http://%s/fanfictions/index.php?act=vie&id=%s&ch=%s' % ( self.getSiteDomain(),
-                                            self.story.getMetadata('storyId'),
-                                            o['value'])
-                title = u"%s" % o
-                title = stripHTML(title)
-                ts = title.split(' ',1)
-                title = ts[0]+'. '+ts[1]
-                self.chapterUrls.append((title,url))
-        self.story.setMetadata('numChapters',len(self.chapterUrls))
-
-        ## Go scrape the rest of the metadata from the author's page.
-        data = self._fetchUrl(self.story.getMetadata('authorUrl'))
-        soup = 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_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+'))
-        pr='http://'+self.host+pr['href']
-        pr = self.make_soup(self._fetchUrl(pr))
-        pr=pr.findAll('div', {'class' : 'part_text'})
+
+        ## after site change, I don't see word count anywhere.
+        # pr=soup.find('a', href=re.compile(r'/printfic/\w+'))
+        # pr='https://'+self.host+pr['href']
+        # pr = self.make_soup(self._fetchUrl(pr))
+        # pr=pr.findAll('div', {'class' : 'part_text'})
+        # i=0
+        # for part in pr:
+        #     i=i+len(stripHTML(part).split(' '))
+        # self.story.setMetadata('numWords', unicode(i))
+
+
+        dlinfo = soup.find('dl',{'class':'info'})
+        
         i=0
-        for part in pr:
-            i=i+len(stripHTML(part).split(' '))
-        self.story.setMetadata('numWords', unicode(i))
-		
-        i=0
-        fandoms = table.findAll('a', href=re.compile(r'/fanfiction/\w+'))
+        fandoms = dlinfo.find('dd').findAll('a', href=re.compile(r'/fanfiction/\w+'))
         for fandom in fandoms:
             self.story.addToList('category',fandom.string)
             i=i+1
         if i > 1:
             self.story.addToList('genre', 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_fimfictionnet.py

@@ -272,7 +272,7 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
 
         #groups
         if soup.find('button', {'id':'button-view-all-groups'}):
-            groupResponse = self._fetchUrl("http://www.fimfiction.net/ajax/groups/story_groups_list.php?story=%s" % (self.story.getMetadata("storyId")))
+            groupResponse = self._fetchUrl("https://www.fimfiction.net/ajax/stories/%s/groups" % (self.story.getMetadata("storyId")))
             groupData = json.loads(groupResponse)
             groupList = self.make_soup(groupData["content"])
         else:

fanficfare/adapters/adapter_finestoriescom.py

@@ -15,279 +15,32 @@
 # limitations under the License.
 #
 
-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
+from adapter_storiesonlinenet import StoriesOnlineNetAdapter
 
 def getClass():
     return FineStoriesComAdapter
 
 # Class name has to be unique.  Our convention is camel case the
 # sitename with Adapter at the end.  www is skipped.
-class FineStoriesComAdapter(BaseSiteAdapter):
+class FineStoriesComAdapter(StoriesOnlineNetAdapter):
 
-    def __init__(self, config, url):
-        BaseSiteAdapter.__init__(self, config, url)
-
-        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
-        self.password = ""
-        self.is_adult=False
-
-        # get storyId from url
-        self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2].split(':')[0])
-        if 'storyInfo' in self.story.getMetadata('storyId'):
-            self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-
-        # normalized story URL.
-        self._setURL('http://' + self.getSiteDomain() + '/s/storyInfo.php?id='+self.story.getMetadata('storyId'))
-
-        # Each adapter needs to have a unique site abbreviation.
-        self.story.setMetadata('siteabbrev','fnst')
-
-        # The date format will vary from site to site.
-        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = "%Y-%m-%d"
+    @classmethod
+    def getSiteAbbrev(self):
+        return 'fnst'
 
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
         return 'finestories.com'
 
-    @classmethod
-    def getSiteExampleURLs(cls):
-        return "http://"+cls.getSiteDomain()+"/s/1234 http://"+cls.getSiteDomain()+"/s/1234:4010 http://"+cls.getSiteDomain()+"/library/storyInfo.php?id=1234"
-
-    def getSiteURLPattern(self):
-        return re.escape("http://"+self.getSiteDomain())+r"/(s|library)?/(storyInfo.php\?id=)?\d+(:\d+)?(;\d+)?$"
-
     ## Login seems to be reasonably standard across eFiction sites.
     def needToLoginCheck(self, data):
         if 'Free Registration' in data \
+                or "Log In" in data \
                 or "Invalid Password!" in data \
                 or "Invalid User Name!" in data:
             return True
         else:
             return False
-
-    def performLogin(self, url):
-        params = {}
-
-        if self.password:
-            params['theusername'] = self.username
-            params['thepassword'] = self.password
-        else:
-            params['theusername'] = self.getConfig("username")
-            params['thepassword'] = self.getConfig("password")
-        params['rememberMe'] = '1'
-        params['page'] = 'http://'+self.getSiteDomain()+'/'
-        params['submit'] = 'Login'
-
-        loginUrl = 'http://' + self.getSiteDomain() + '/login.php'
-        logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
-                                                              params['theusername']))
-
-        d = self._fetchUrl(loginUrl, params)
-
-        if "My Account" not in d : #Member Account
-            logger.info("Failed to login to URL %s as %s" % (loginUrl,
-                                                              params['theusername']))
-            raise exceptions.FailedToLogin(url,params['theusername'])
-            return False
-        else:
-            return True
-
-    ## Getting the chapter list and the meta data, plus 'is adult' checking.
-    def extractChapterUrlsAndMetadata(self):
-
-        # index=1 makes sure we see the story chapter index.  Some
-        # sites skip that for one-chapter stories.
-        url = self.url
-        logger.debug("URL: "+url)
-
-        try:
-            data = self._fetchUrl(url)
-        except urllib2.HTTPError, e:
-            if e.code == 404:
-                raise exceptions.StoryDoesNotExist(self.url)
-            else:
-                raise e
-
-        if self.needToLoginCheck(data):
-            # need to log in for this one.
-            self.performLogin(url)
-            data = self._fetchUrl(url)
-
-        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.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'/s/'+self.story.getMetadata('storyId')))
-        self.story.setMetadata('title',stripHTML(a))
-
-        # Find authorid and URL from... author url.
-        a = soup.find('a', href=re.compile(r"/a/\w+"))
-        self.story.setMetadata('authorId',a['href'].split('/')[2])
-        self.story.setMetadata('authorUrl','http://'+self.host+a['href'])
-        self.story.setMetadata('author',a.text)
-
-        # Find the chapters:
-        chapters = soup.findAll('a', href=re.compile(r'/s/'+self.story.getMetadata('storyId')+":\d+$"))
-        if len(chapters) != 0:
-            for chapter in chapters:
-                # just in case there's tags, like <i> in chapter titles.
-                self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+chapter['href']))
-        else:
-            self.chapterUrls.append((self.story.getMetadata('title'),'http://'+self.host+'/s/'+self.story.getMetadata('storyId')))
-
-        self.story.setMetadata('numChapters',len(self.chapterUrls))
-
-        # surprisingly, the detailed page does not give enough details, so go to author's page
-
-        skip=0
-        i=0
-        while i == 0:
-            asoup = self.make_soup(self._fetchUrl(self.story.getMetadata('authorUrl')+"&skip="+unicode(skip)))
-
-            tds = asoup.findAll('td', {'class' : 'lc2'})
-            for lc2 in tds:
-                if lc2.find('a', href=re.compile(r'/s/'+self.story.getMetadata('storyId'))):
-                    i=1
-                    break
-                if tds[len(tds)-1] == lc2:
-                    skip=skip+10
-
-        for cat in lc2.findAll('div', {'class' : 'typediv'}):
-            self.story.addToList('category',cat.text)
-
-        self.story.setMetadata('size', lc2.findNext('td', {'class' : 'num'}).text)
-
-        lc4 = lc2.findNext('td', {'class' : 'lc4'})
-
-        try:
-            a = lc4.find('a', href=re.compile(r"/library/show_series.php\?id=\d+"))
-            i = a.parent.text.split('(')[1].split(')')[0]
-            self.setSeries(a.text, i)
-            self.story.setMetadata('seriesUrl','http://'+self.host+a['href'])
-        except:
-            pass
-        try:
-            a = lc4.find('a', href=re.compile(r"/library/universe.php\?id=\d+"))
-            self.story.addToList("category",a.text)
-        except:
-            pass
-
-        for a in lc4.findAll('span', {'class' : 'help'}) + lc4.findAll('script'):
-            a.extract()
-
-        self.setDescription('http://'+self.host+'/s/'+self.story.getMetadata('storyId'),lc4.text.split('[More Info')[0])
-
-        for b in lc4.findAll('b'):
-            label = b.text
-            value = b.nextSibling
-
-            if 'For Age' in label:
-                self.story.setMetadata('rating', value)
-
-            if 'Tags' in label:
-                for genre in value.split(', '):
-                    self.story.addToList('genre',genre)
-
-            ## Site uses a <script> to inject timestamp in locale plus <noscript> general version.
-            if 'Posted' in label:
-                value = b.find_next_sibling('noscript')
-                if '(' in value:
-                    date = makeDate(stripHTML(value.split(' (')[0]), self.dateformat)
-                else:
-                    date = makeDate(stripHTML(value), self.dateformat)
-                self.story.setMetadata('datePublished', date)
-                self.story.setMetadata('dateUpdated', date)
-
-            if 'Concluded' in label or 'Updated' in label:
-                value = b.find_next_sibling('noscript')
-                if '(' in value:
-                    date = makeDate(stripHTML(value.split(' (')[0]), self.dateformat)
-                else:
-                    date = makeDate(stripHTML(value), self.dateformat)
-                self.story.setMetadata('dateUpdated', date)
-
-        status = lc4.find('span', {'class' : 'ab'})
-        if  status != None:
-            self.story.setMetadata('status', 'In-Progress')
-            if "Last Activity" in status.text:
-                self.story.setMetadata('dateUpdated', makeDate(status.text.split('Activity: ')[1].split(')')[0], self.dateformat))
-        else:
-            self.story.setMetadata('status', 'Completed')
-
-
-    # grab the text for an individual chapter.
-    def getChapterText(self, url):
-
-        logger.debug('Getting chapter text from: %s' % url)
-
-        soup = self.make_soup(self._fetchUrl(url))
-
-        div = soup.find('article')
-
-        if None == div:
-            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-
-        # some big chapters are split over several pages
-        pager = div.find('span', {'class' : 'pager'})
-        if pager != None:
-            urls=pager.findAll('a')
-            urls=urls[:len(urls)-1]
-
-            for ur in urls:
-                soup = self.make_soup(self._fetchUrl("http://"+self.getSiteDomain()+ur['href']))
-
-                div1 = soup.find('article')
-
-                #print("div.contents:%s"%(div.contents,))
-                # appending next section
-                last=div.findAll('p')
-                next=div1.find('span', {'class' : 'conTag'}).nextSibling
-                last[len(last)-1]=last[len(last)-1].append(next)
-
-                self.clean_chapter(div1)
-                #print("div.contents:%s"%(div.contents,))
-                for t in div1.contents:
-                    div.append(t)
-
-        self.clean_chapter(div)
-
-        return self.utf8FromSoup(url,div)
-    def clean_chapter(self,art):
-        # discard included chapter heading.
-        # discard included date
-        # discard share block
-        # continued/continues
-        # discard next link
-        for tag in art.find_all('h2') + \
-                art.find_all('div', class_="date") + \
-                art.find_all('div', class_="vform") + \
-                art.find_all('span', class_="conTag") + \
-                art.find_all('h3', class_="end"):
-            tag.extract()
-
-        # remove pager blocks.
-        for pager in art.find_all('span', class_="pager"):
-            # remove br tags before and after pager.
-            #print("br list prev: %s"%len(pager.find_previous_siblings('br')))
-            #print("br list next: %s"%len(pager.find_next_siblings('br')))
-            for tag in pager.find_next_siblings('br')[:2] + pager.find_previous_siblings('br')[:2]:
-                tag.extract()
-            pager.extract()

fanficfare/adapters/adapter_hpfandomnet.py

@@ -136,10 +136,11 @@ class HPFandomNetAdapterAdapter(BaseSiteAdapter): # XXX
 
         authsoup = self.make_soup(authdata)
 
-        reviewsa = authsoup.find('a', href=re.compile(r"reviews\.php\?sid="+self.story.getMetadata('storyId')+r".*"))
+        reviewsa = authsoup.find_all('a', href=re.compile(r"reviews\.php\?sid="+self.story.getMetadata('storyId')+r".*"))
         # <table><tr><td><p><b><a ...>
-        metablock = reviewsa.findParent("table")
+        metablock = reviewsa[0].findParent("table")
         #print("metablock:%s"%metablock)
+        self.story.setMetadata('reviews',stripHTML(reviewsa[-1]))
 
         ## Title
         titlea = metablock.find('a', href=re.compile("viewstory.php"))
@@ -148,6 +149,7 @@ class HPFandomNetAdapterAdapter(BaseSiteAdapter): # XXX
             raise exceptions.FailedToDownload("Story URL (%s) not found on author's page, can't use chapter URLs"%url)
         self.story.setMetadata('title',stripHTML(titlea))
 
+        total_reads = 0
         # Find the chapters: !!! hpfandom.net differs from every other
         # eFiction site--the sid on viewstory for chapters is
         # *different* for each chapter
@@ -156,10 +158,16 @@ class HPFandomNetAdapterAdapter(BaseSiteAdapter): # XXX
             # just in case there's tags, like <i> in chapter titles.
             #print("====chapter===%s"%m.group(1))
             self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/eff/'+m.group(1)))
-
+            try:
+                total_reads += int(stripHTML((chapter.find_parent('tr').find_all('td')[-1])))
+            except:
+                pass # don't care
         if len(self.chapterUrls) == 0:
             self.chapterUrls.append((stripHTML(self.story.getMetadata('title')),url))
 
+        if total_reads > 0:
+            self.story.setMetadata('reads',total_reads)
+
         self.story.setMetadata('numChapters',len(self.chapterUrls))
 
         # eFiction sites don't help us out a lot with their meta data

fanficfare/adapters/adapter_literotica.py

@@ -21,7 +21,6 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 import urlparse
-import time
 
 from bs4.element import Comment
 from ..htmlcleanup import stripHTML
@@ -33,13 +32,15 @@ class LiteroticaSiteAdapter(BaseSiteAdapter):
 
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
+        logger.debug("LiteroticaComAdapter:__init__ - url='%s'" % url)
 
         self.decode = ["utf8",
                        "Windows-1252"] # 1252 is a superset of iso-8859-1.
-                               # Most sites that claim to be
-                               # iso-8859-1 (and some that claim to be
-                               # utf8) are really windows-1252.
+                            # Most sites that claim to be
+                            # iso-8859-1 (and some that claim to be
+                            # utf8) are really windows-1252.
 
+        # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','litero')
 
         # normalize to first chapter.  Not sure if they ever have more than 2 digits.
@@ -62,7 +63,7 @@ class LiteroticaSiteAdapter(BaseSiteAdapter):
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = '%m/%d/%y'
+        self.dateformat = "%m/%d/%y"
 
     @staticmethod
     def getSiteDomain():
@@ -96,6 +97,18 @@ class LiteroticaSiteAdapter(BaseSiteAdapter):
     def getSiteURLPattern(self):
         return r"https?://(www|german|spanish|french|dutch|italian|romanian|portuguese|other)(\.i)?\.literotica\.com/s/([a-zA-Z0-9_-]+)"
 
+    def getCategories(self, soup):
+        if self.getConfig("use_meta_keywords"):
+            categories = soup.find("meta", {"name":"keywords"})['content'].split(', ')
+            categories = [c for c in categories if not self.story.getMetadata('title') in c]
+            if self.story.getMetadata('author') in categories:
+                categories.remove(self.story.getMetadata('author'))
+            logger.debug("Meta = %s" % categories)
+            for category in categories:
+    #            logger.debug("\tCategory=%s" % category)
+#                 self.story.addToList('category', category.title())
+                self.story.addToList('eroticatags', category.title())
+
     def extractChapterUrlsAndMetadata(self):
         """
         NOTE: Some stories can have versions,
@@ -119,6 +132,7 @@ class LiteroticaSiteAdapter(BaseSiteAdapter):
             raise exceptions.AdultCheckRequired(self.url)
 
         logger.debug("Chapter/Story URL: <%s> " % self.url)
+
         try:
             data1 = self._fetchUrl(self.url)
             soup1 = self.make_soup(data1)
@@ -145,6 +159,7 @@ class LiteroticaSiteAdapter(BaseSiteAdapter):
             soupAuth = self.make_soup(dataAuth)
             #strip comments from soup
             [comment.extract() for comment in soupAuth.findAll(text=lambda text:isinstance(text, Comment))]
+#            logger.debug(soupAuth)
         except urllib2.HTTPError, e:
             if e.code == 404:
                 raise exceptions.StoryDoesNotExist(authorurl)
@@ -155,6 +170,15 @@ class LiteroticaSiteAdapter(BaseSiteAdapter):
         ## site has started using //domain.name/asdf urls remove https?: from front
         ## site has started putting https back on again.
         storyLink = soupAuth.find('a', href=re.compile(r'(https?:)?'+re.escape(self.url[self.url.index(':')+1:])))
+#         storyLink = soupAuth.find('a', href=self.url)#[self.url.index(':')+1:])
+
+        if storyLink is not None:
+            # pull the published date from the author page
+            # default values from single link.  Updated below if multiple chapter.
+            logger.debug("Found story on the author page.")
+            date = storyLink.parent.parent.findAll('td')[-1].text
+            self.story.setMetadata('datePublished', makeDate(date, self.dateformat))
+            self.story.setMetadata('dateUpdated',makeDate(date, self.dateformat))
 
         if storyLink is not None:
             urlTr = storyLink.parent.parent
@@ -166,101 +190,184 @@ class LiteroticaSiteAdapter(BaseSiteAdapter):
             raise exceptions.FailedToDownload("Couldn't find story <%s> on author's page <%s>" % (self.url, authorurl))
 
         if isSingleStory:
-            self.story.setMetadata('title', storyLink.text)
+#             self.chapterUrls = [(soup1.h1.string, self.url)]
+#             self.story.setMetadata('title', soup1.h1.string)
+
+            self.story.setMetadata('title', storyLink.text.strip('/'))
+            logger.debug('Title: "%s"' % storyLink.text.strip('/'))
             self.story.setMetadata('description', urlTr.findAll("td")[1].text)
-            self.story.addToList('eroticatags', urlTr.findAll("td")[2].text)
+            self.story.addToList('category', urlTr.findAll("td")[2].text)
+#             self.story.addToList('eroticatags', urlTr.findAll("td")[2].text)
             date = urlTr.findAll('td')[-1].text
             self.story.setMetadata('datePublished', makeDate(date, self.dateformat))
             self.story.setMetadata('dateUpdated',makeDate(date, self.dateformat))
             self.chapterUrls = [(storyLink.text, self.url)]
+            averrating = stripHTML(storyLink.parent)
+            ## title (0.00)
+            averrating = averrating[averrating.rfind('(')+1:averrating.rfind(')')]
+            try:
+                self.story.setMetadata('averrating', float(averrating))
+            except:
+                pass
+#             self.story.setMetadata('averrating',averrating)
+        # parse out the list of chapters
         else:
             seriesTr = urlTr.previousSibling
             while 'ser-ttl' not in seriesTr['class']:
                 seriesTr = seriesTr.previousSibling
             m = re.match("^(?P<title>.*?):\s(?P<numChapters>\d+)\sPart\sSeries$", seriesTr.find("strong").text)
             self.story.setMetadata('title', m.group('title'))
+            seriesTitle = m.group('title')
 
             ## Walk the chapters
             chapterTr = seriesTr.nextSibling
             self.chapterUrls = []
             dates = []
             descriptions = []
+            ratings = []
+            chapters = []
             while chapterTr is not None and 'sl' in chapterTr['class']:
-                descriptions.append(chapterTr.findAll("td")[1].text)
+                description = "%d. %s" % (len(descriptions)+1,stripHTML(chapterTr.findAll("td")[1]))
+                description = stripHTML(chapterTr.findAll("td")[1])
                 chapterLink = chapterTr.find("td", "fc").find("a")
-                if not chapterLink["href"].startswith('http'):
-                    chapterLink["href"] = "http:" + chapterLink["href"]
-                self.chapterUrls.append((chapterLink.text, chapterLink["href"]))
                 self.story.addToList('eroticatags', chapterTr.findAll("td")[2].text)
-                dates.append(makeDate(chapterTr.findAll('td')[-1].text, self.dateformat))
+                pub_date = makeDate(chapterTr.findAll('td')[-1].text, self.dateformat)
+                dates.append(pub_date)
                 chapterTr = chapterTr.nextSibling
+                
+                chapter_title = chapterLink.text
+                if self.getConfig("clean_chapter_titles"):
+                    logger.debug('\tChapter Name: "%s"' % chapterLink.string)
+                    logger.debug('\tChapter Name: "%s"' % chapterLink.text)
+                    if chapterLink.text.lower().startswith(seriesTitle.lower()):
+                        chapter = chapterLink.text[len(seriesTitle):].strip()
+                        logger.debug('\tChapter: "%s"' % chapter)
+                        if chapter == '':
+                            chapter_title = 'Chapter %d' % (len(self.chapterUrls) + 1)
+                        else:
+                            separater_char = chapter[0]
+                            logger.debug('\tseparater_char: "%s"' % separater_char)
+                            chapter = chapter[1:].strip() if separater_char in [":", "-"] else chapter
+                            logger.debug('\tChapter: "%s"' % chapter)
+                            if chapter.lower().startswith('ch.'):
+                                chapter = chapter[len('ch.'):]
+                                try:
+                                    chapter_title = 'Chapter %d' % int(chapter)
+                                except:
+                                    chapter_title = 'Chapter %s' % chapter
+                            elif chapter.lower().startswith('pt.'):
+                                chapter = chapter[len('pt.'):]
+                                try:
+                                    chapter_title = 'Part %d' % int(chapter)
+                                except:
+                                    chapter_title = 'Part %s' % chapter
+                            elif separater_char in [":", "-"]:
+                                chapter_title = chapter
+    
+    #                 if chapter_title == '':
+    #                     chapter_title = chapterLink.string
 
-            ## Set description to joint chapter descriptions
-            self.story.setMetadata('description', " / ".join(descriptions))
+                # pages include full URLs.
+                chapurl = chapterLink['href']
+                if chapurl.startswith('//'):
+                    chapurl = self.parsedUrl.scheme + ':' + chapurl
+                logger.debug("Chapter URL: " + chapurl)
+                logger.debug("Chapter Title: " + chapter_title)
+                logger.debug("Chapter description: " + description)
+                chapters.append((chapter_title, chapurl, description, pub_date))
+#                 self.chapterUrls.append((chapter_title, chapurl))
+                numrating = stripHTML(chapterLink.parent)
+                ## title (0.00)
+                numrating = numrating[numrating.rfind('(')+1:numrating.rfind(')')]
+                try:
+                    ratings.append(float(numrating))
+                except:
+                    pass
 
+            chapters = sorted(chapters, key=lambda chapter: chapter[3])
+            for i, chapter in enumerate(chapters):
+                self.chapterUrls.append((chapter[0], chapter[1]))
+                descriptions.append("%d. %s" % (i + 1, chapter[2]))
             ## Set the oldest date as publication date, the newest as update date
             dates.sort()
             self.story.setMetadata('datePublished', dates[0])
             self.story.setMetadata('dateUpdated', dates[-1])
+            self.story.setMetadata('datePublished', chapters[0][3])
+            self.story.setMetadata('dateUpdated', chapters[-1][3])
+            ## Set description to joint chapter descriptions
+            self.setDescription(authorurl,"<p>"+"</p>\n<p>".join(descriptions)+"</p>")
 
-            # normalize on first chapter URL.
-            self._setURL(self.chapterUrls[0][1])
+            if len(ratings) > 0:
+                self.story.setMetadata('averrating','%4.2f' % (sum(ratings) / float(len(ratings))))
+
+        # normalize on first chapter URL.
+        self._setURL(self.chapterUrls[0][1])
+
+        # reset storyId to first chapter.
+        self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2])
 
         self.story.setMetadata('numChapters', len(self.chapterUrls))
 
-        # set storyId to 'title-author' to avoid duplicates
-        # self.story.setMetadata('storyId',
-        #     re.sub("[^a-z0-9]", "", self.story.getMetadata('title').lower())
-        #     + "-"
-        #     + re.sub("[^a-z0-9]", "", self.story.getMetadata('author').lower()))
+        self.story.setMetadata('category', soup1.find('div', 'b-breadcrumbs').findAll('a')[1].string)
+        self.getCategories(soup1)
+#         self.story.setMetadata('description', soup1.find('meta', {'name': 'description'})['content'])
 
         return
 
+
+    def getPageText(self, raw_page, url):
+        logger.debug('Getting page text')
+#         logger.debug(soup)
+        raw_page = raw_page.replace('<div class="b-story-body-x x-r15"><div><p>','<div class="b-story-body-x x-r15"><div>')
+#         logger.debug("\tChapter text: %s" % raw_page)
+        page_soup = self.make_soup(raw_page)
+        [comment.extract() for comment in page_soup.findAll(text=lambda text:isinstance(text, Comment))]
+        story2 = page_soup.find('div', 'b-story-body-x').div
+#         logger.debug("getPageText- name div div...")
+#         logger.debug(soup)
+#         story2.append(page_soup.new_tag('br'))
+        div = self.utf8FromSoup(url, story2)
+#        logger.debug(div)
+
+        fullhtml = unicode(div)
+#         logger.debug(fullhtml)
+        fullhtml = re.sub(r'<br />\s*<br />', r'</p><p>', fullhtml)
+        fullhtml = re.sub(r'^<div>', r'', fullhtml)
+        fullhtml = re.sub(r'</div>$', r'', fullhtml)
+        fullhtml = re.sub(r'(<p><br/></p>\s+)+$', r'', fullhtml)
+#         logger.debug(fullhtml)
+        return fullhtml
+
     def getChapterText(self, url):
-        logger.debug('Getting chapter text from <%s>' % url)
-        data1 = self._fetchUrl(url)
-        # brute force approach to replace the wrapping <p> tag.  If
-        # done by changing tag name, it causes problems with nested
-        # <p> tags.
-        data1 = data1.replace('<div class="b-story-body-x x-r15"><div><p>','<div class="b-story-body-x x-r15"><div>')
-        soup1 = self.make_soup(data1)
 
-        #strip comments from soup
-        [comment.extract() for comment in soup1.findAll(text=lambda text:isinstance(text, Comment))]
+        logger.debug('Getting chapter text from: %s' % url)
 
-        # get story text
-        story1 = soup1.find('div', 'b-story-body-x').div
-        #print("story1:%s"%story1)
-        # story1.name='div'
-        story1.append(soup1.new_tag('br'))
-        storytext = self.utf8FromSoup(url,story1)
+        raw_page = self._fetchUrl(url)
+        page_soup = self.make_soup(raw_page)
+        pages = page_soup.find('select', {'name' : 'page'})
+        page_nums = [page.text for page in pages.findAll('option')] if pages else 0
 
-        # find num pages
-        pgs = int(soup1.find("span", "b-pager-caption-t r-d45").string.split(' ')[0])
-        logger.debug("pages: "+unicode(pgs))
+        fullhtml = "" 
+        self.getCategories(page_soup)
+        if self.getConfig("description_in_chapter"):
+            chapter_description = page_soup.find("meta", {"name" : "description"})['content']
+            logger.debug("\tChapter description: %s" % chapter_description)
+            fullhtml += '<p><b>Description:</b> %s</p><hr />' % chapter_description
+        fullhtml += self.getPageText(raw_page, url)
+        if pages:
+            for page_no in xrange(2, len(page_nums) + 1):
+                page_url = url +  "?page=%s" % page_no
+                logger.debug("page_url= %s" % page_url)
+                raw_page = self._fetchUrl(page_url)
+                fullhtml += self.getPageText(raw_page, url)
+        
+#        fullhtml = self.utf8FromSoup(url, bs.BeautifulSoup(fullhtml))
+#        fullhtml = re.sub(r'^<div>', r'', fullhtml)
+#        fullhtml = re.sub(r'</div>$', r'', fullhtml)
+#        if None == div:
+#            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
 
-        # get all the pages
-        for i in xrange(2, pgs+1):
-            try:
-                logger.debug("fetching page "+unicode(i))
-                time.sleep(0.5)
-                data2 = self._fetchUrl(url, {'page': i})
-                # brute force approach to replace the wrapping <p> tag.  If
-                # done by changing tag name, it causes problems with nested
-                # <p> tags.
-                data2 = data2.replace('<div class="b-story-body-x x-r15"><div><p>','<div class="b-story-body-x x-r15"><div>')
-                soup2 = self.make_soup(data2)
-                [comment.extract() for comment in soup2.findAll(text=lambda text:isinstance(text, Comment))]
-                story2 = soup2.find('div', 'b-story-body-x').div
-                # story2.name='div'
-                story2.append(soup2.new_tag('br'))
-                storytext += self.utf8FromSoup(url,story2)
-            except urllib2.HTTPError, e:
-                if e.code == 404:
-                    raise exceptions.StoryDoesNotExist(url)
-                else:
-                    raise e
-        return storytext
+        return fullhtml
 
 
 def getClass():

fanficfare/adapters/adapter_lucifaelff.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2012 Fanficdownloader team, 2015 FanFicFare team
+# Copyright 2016 FanFicFare team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -22,18 +22,18 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-
+from bs4.element import Comment
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
 from base_adapter import BaseSiteAdapter,  makeDate
 
 def getClass():
-    return GrangerEnchantedCom
+    return Lucifaelff
 
 # Class name has to be unique.  Our convention is camel case the
 # sitename with Adapter at the end.  www is skipped.
-class GrangerEnchantedCom(BaseSiteAdapter):
+class Lucifaelff(BaseSiteAdapter):
 
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
@@ -50,37 +50,28 @@ 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:
-            self._setURL('http://malfoymanor.' + self.getSiteDomain() + '/themanor/viewstory.php?sid='+self.story.getMetadata('storyId'))
-            self.story.addToList("category","The Manor")
-        else:
-            self._setURL('http://' + self.getSiteDomain() + '/enchant/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
 
         # Each adapter needs to have a unique site abbreviation.
-        self.story.setMetadata('siteabbrev','gech')
+        self.story.setMetadata('siteabbrev','luci')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = "%d/%b/%Y"
+        self.dateformat = "%d/%m/%Y"
 
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
-        return 'grangerenchanted.com'
-
-    @classmethod
-    def getAcceptDomains(cls):
-        return ['grangerenchanted.com','malfoymanor.grangerenchanted.com']
+        return 'fanfiction.lucifael.com'
 
     @classmethod
     def getSiteExampleURLs(cls):
-        return "http://grangerenchanted.com/enchant/viewstory.php?sid=1234 http://malfoymanor.grangerenchanted.com/themanor/viewstory.php?sid=1234"
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
-        return r"http://(malfoymanor.)?grangerenchanted.com/(enchant|themanor)?/viewstory.php\?sid=\d+$"
+        return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
 
     ## Login seems to be reasonably standard across eFiction sites.
     def needToLoginCheck(self, data):
@@ -103,10 +94,7 @@ class GrangerEnchantedCom(BaseSiteAdapter):
         params['cookiecheck'] = '1'
         params['submit'] = 'Submit'
 
-        if "enchant" in self.section:
-            loginUrl = 'http://grangerenchanted.com/enchant/user.php?action=login'
-        else:
-            loginUrl = 'http://malfoymanor.grangerenchanted.com/themanor/user.php?action=login'
+        loginUrl = 'http://' + self.getSiteDomain() + '/user.php?action=login'
         logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
                                                               params['penname']))
 
@@ -128,13 +116,13 @@ class GrangerEnchantedCom(BaseSiteAdapter):
             # If the title search below fails, there's a good chance
             # you need a different number.  print data at that point
             # and see what the 'click here to continue' url says.
-            addurl = "&ageconsent=ok&warning=1"
+            addurl = "&ageconsent=ok&warning=4"
         else:
             addurl=""
 
         # index=1 makes sure we see the story chapter index.  Some
         # sites skip that for one-chapter stories.
-        url = self.url+addurl
+        url = self.url
         logger.debug("URL: "+url)
 
         try:
@@ -145,11 +133,21 @@ class GrangerEnchantedCom(BaseSiteAdapter):
             else:
                 raise e
 
-        if self.needToLoginCheck(data):
+
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
             # need to log in for this one.
             self.performLogin(url)
             data = self._fetchUrl(url)
 
+        # Since the warning text can change by warning level, let's
+        # look for the warning pass url.  ksarchive uses
+        # &warning= -- actually, so do other sites.  Must be an
+        # eFiction book.
+
+        # viewstory.php?sid=1882&warning=4
+        # viewstory.php?sid=1654&ageconsent=ok&warning=5
+        #print data
+        #m = re.search(r"'viewstory.php\?sid=1882(&warning=4)'",data)
         m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
         if m != None:
             if self.is_adult or self.getConfig("is_adult"):
@@ -173,7 +171,7 @@ 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)
@@ -181,12 +179,14 @@ class GrangerEnchantedCom(BaseSiteAdapter):
 
         # Now go hunting for all the meta data and the chapter list.
 
+        pagetitle = soup.find('div',{'id':'pagetitle'})
+
         ## Title
-        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',stripHTML(a))
 
         # Find authorid and URL from... author url.
-        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
         self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
         self.story.setMetadata('author',a.string)
@@ -194,7 +194,7 @@ class GrangerEnchantedCom(BaseSiteAdapter):
         # Find the chapters:
         for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
             # just in case there's tags, like <i> in chapter titles.
-            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+self.section+'/'+chapter['href']+addurl))
+            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']+addurl))
 
         self.story.setMetadata('numChapters',len(self.chapterUrls))
 
@@ -217,10 +217,11 @@ class GrangerEnchantedCom(BaseSiteAdapter):
             if 'Summary' in label:
                 ## Everything until the next span class='label'
                 svalue = ""
-                while value and '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)
 
@@ -261,35 +259,27 @@ 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+"))
             series_name = a.string
-            series_url = 'http://'+self.host+'/'+self.section+'/'+a['href']
+            series_url = 'http://'+self.host+'/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
             seriessoup = self.make_soup(self._fetchUrl(series_url))
-            # can't use ^viewstory...$ in case of higher rated stories with javascript href.
-            storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+'))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
             i=1
             for a in storyas:
-                # skip 'report this' and 'TOC' links
-                if 'contact.php' not in a['href'] and 'index' not in a['href']:
-                    if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
-                        self.setSeries(series_name, i)
-                        self.story.setMetadata('seriesUrl',series_url)
-                        break
-                    i+=1
-        except:
-            # I find it hard to care if the series parsing fails
-            pass
+                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                    self.setSeries(series_name, i)
+                    self.story.setMetadata('seriesUrl',series_url)
+                    break
+                i+=1
 
-        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
@@ -301,7 +291,7 @@ 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)

fanficfare/adapters/adapter_mcstoriescom.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2013 Fanficdownloader team, 2015 FanFicFare team
+# Copyright 2013 Fanficdownloader team, 2016 FanFicFare team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -91,7 +91,7 @@ class MCStoriesComSiteAdapter(BaseSiteAdapter):
             data1 = self._fetchUrl(self.url)
             soup1 = self.make_soup(data1)
             #strip comments from soup
-            [comment.extract() for comment in soup1.findAll(text=lambda text:isinstance(text, Comment))]
+            [comment.extract() for comment in soup1.find_all(text=lambda text:isinstance(text, Comment))]
         except urllib2.HTTPError, e:
             if e.code == 404:
                 raise exceptions.StoryDoesNotExist(self.url)
@@ -112,18 +112,18 @@ class MCStoriesComSiteAdapter(BaseSiteAdapter):
 
         # Description
         synopsis = soup1.find('section', class_='synopsis')
-        description = "\n\n".join([p.text for p in synopsis.findAll('p')])
+        description = "\n\n".join([p.text for p in synopsis.find_all('p')])
         self.story.setMetadata('description', description)
 
         # Tags
         codesDiv = soup1.find('div', class_="storyCodes")
-        for a in codesDiv.findAll('a'):
+        for a in codesDiv.find_all('a'):
             self.story.addToList('eroticatags', a.text)
 
         # Publish and update dates
         publishdate = None
         updatedate = None
-        datelines = soup1.findAll('h3', class_='dateline')
+        datelines = soup1.find_all('h3', class_='dateline')
         for dateline in datelines:
             if dateline.text.startswith('Added '):
                 publishdate = makeDate(dateline.text, "Added " + self.dateformat)
@@ -139,7 +139,7 @@ class MCStoriesComSiteAdapter(BaseSiteAdapter):
 
         if chapterTable is not None:
             # Multi-chapter story
-            chapterRows = chapterTable.findAll('tr')
+            chapterRows = chapterTable.find_all('tr')
 
             for row in chapterRows:
                 chapterCell = row.td
@@ -172,13 +172,13 @@ class MCStoriesComSiteAdapter(BaseSiteAdapter):
         soup1 = self.make_soup(data1)
 
         #strip comments from soup
-        [comment.extract() for comment in soup1.findAll(text=lambda text:isinstance(text, Comment))]
+        [comment.extract() for comment in soup1.find_all(text=lambda text:isinstance(text, Comment))]
 
         # get story text
         story1 = soup1.find('article', id='mcstories')
 
         # Remove duplicate name and author headers
-        [h3.extract() for h3 in story1.findAll('h3')]
+        [h3.extract() for h3 in story1.find_all('h3',class_=re.compile(r'(title|chapter|byline)'))]
 
         storytext = self.utf8FromSoup(url, story1)
 

fanficfare/adapters/adapter_mugglenetcom.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
+# Copyright 2011 Fanficdownloader team, 2016 FanFicFare team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -16,58 +16,12 @@
 #
 
 # Software: eFiction
-import time
-import logging
-logger = logging.getLogger(__name__)
-import re
-import urllib2
+from base_efiction_adapter import BaseEfictionAdapter
 
-
-from ..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 MuggleNetComAdapter # XXX
-
-# Class name has to be unique.  Our convention is camel case the
-# sitename with Adapter at the end.  www is skipped.
-class MuggleNetComAdapter(BaseSiteAdapter): # XXX
-
-    def __init__(self, config, url):
-        BaseSiteAdapter.__init__(self, config, url)
-
-        self.decode = ["Windows-1252",
-                       "utf8"] # 1252 is a superset of iso-8859-1.
-                               # Most sites that claim to be
-                               # iso-8859-1 (and some that claim to be
-                               # utf8) are really windows-1252.
-        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
-        self.password = ""
-        self.is_adult=False
-
-        # get storyId from url--url validation guarantees query is only sid=1234
-        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-
-
-        # normalized story URL.
-        self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
-
-        # Each adapter needs to have a unique site abbreviation.
-        self.story.setMetadata('siteabbrev','mgln') # XXX
-
-        # The date format will vary from site to site.
-        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = "%m/%d/%y" # XXX
+class MuggleNetComAdapter(BaseEfictionAdapter):
 
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
-        # The site domain.
         return 'fanfiction.mugglenet.com'
 
     @classmethod
@@ -75,251 +29,12 @@ class MuggleNetComAdapter(BaseSiteAdapter): # XXX
         return ['fanfiction.mugglenet.com','fanfic.mugglenet.com']
 
     @classmethod
-    def getSiteExampleURLs(cls):
-        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
+    def getSiteAbbrev(self):
+        return 'mgln'
 
-    def getSiteURLPattern(self):
-        return re.escape("http://")+r"fanfic(tion)?\.mugglenet\.com"+re.escape("/viewstory.php?sid=")+r"\d+$"
+    @classmethod
+    def getDateFormat(self):
+        return "%m/%d/%y"
 
-    ## Login seems to be reasonably standard across eFiction sites.
-    def needToLoginCheck(self, data):
-        if "class='errortext'>Registered Users Only" in data \
-                or 'There is no such account on our website' in data \
-                or "That password doesn't match the one in our database" in data:
-            return True
-        else:
-            return False
-
-    def performLogin(self, url):
-        params = {}
-
-        if self.password:
-            params['penname'] = self.username
-            params['password'] = self.password
-        else:
-            params['penname'] = self.getConfig("username")
-            params['password'] = self.getConfig("password")
-        params['cookiecheck'] = '1'
-        params['submit'] = 'Submit'
-
-        loginUrl = 'http://' + self.getSiteDomain() + '/user.php?action=login&sid='+self.story.getMetadata('storyId')
-        logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
-                                                              params['penname']))
-
-        d = self._fetchUrl(loginUrl, params)
-
-        if "Member Account" not in d : #Member Account
-            logger.info("Failed to login to URL %s as %s" % (loginUrl,
-                                                              params['penname']))
-            raise exceptions.FailedToLogin(url,params['penname'])
-            return False
-        else:
-            return True
-
-    ## Getting the chapter list and the meta data, plus 'is adult' checking.
-    def extractChapterUrlsAndMetadata(self):
-
-        if self.is_adult or self.getConfig("is_adult"):
-            # Weirdly, different sites use different warning numbers.
-            # If the title search below fails, there's a good chance
-            # you need a different number.  print data at that point
-            # and see what the 'click here to continue' url says.
-            # http://fanfiction.mugglenet.com/viewstory.php?sid=91079&ageconsent=ok&warning=3
-            addurl = "&ageconsent=ok&warning=3" # XXX  &warning=5
-        else:
-            addurl=""
-
-        # index=1 makes sure we see the story chapter index.  Some
-        # sites skip that for one-chapter stories.
-        url = self.url+'&index=1'+addurl
-        logger.debug("URL: "+url)
-
-        try:
-            data = self._fetchUrl(url)
-        except urllib2.HTTPError, e:
-            if e.code == 404:
-                raise exceptions.StoryDoesNotExist(self.url)
-            else:
-                raise e
-
-        if self.needToLoginCheck(data):
-            # need to log in for this one.
-            self.performLogin(url)
-            data = self._fetchUrl(url)
-            #print("\nurl:%s\ndata:\n%s\n"%(url,data))
-
-        # The actual text that is used to announce you need to be an
-        # adult varies from site to site.  Again, print data before
-        # the title search to troubleshoot.
-
-        # Since the warning text can change by warning level, let's
-        # look for the warning pass url.  nfacommunity uses
-        # &warning= -- actually, so do other sites.  Must be an
-        # eFiction book.
-
-        # viewstory.php?sid=1882&warning=4
-        # viewstory.php?sid=1654&ageconsent=ok&warning=5
-        #print data
-        #m = re.search(r"'viewstory.php\?sid=1882(&warning=4)'",data)
-        m = re.search(r"'viewstory.php\?sid=%s((?:&ageconsent=ok)?&warning=\d+)'"%self.story.getMetadata('storyId'),data)
-        if m != None:
-            if self.is_adult or self.getConfig("is_adult"):
-                # We tried the default and still got a warning, so
-                # let's pull the warning number from the 'continue'
-                # link and reload data.
-                addurl = m.group(1)
-                # correct stupid & error in url.
-                addurl = addurl.replace("&","&")
-                url = self.url+'&index=1'+addurl
-                logger.debug("URL 2nd try: "+url)
-
-                try:
-                    data = self._fetchUrl(url)
-                except urllib2.HTTPError, e:
-                    if e.code == 404:
-                        raise exceptions.StoryDoesNotExist(self.url)
-                    else:
-                        raise e
-            else:
-                raise exceptions.AdultCheckRequired(self.url)
-
-        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.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')+"$"))
-        self.story.setMetadata('title',stripHTML(a))
-
-        # Find authorid and URL from... author url.
-        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
-        self.story.setMetadata('authorId',a['href'].split('=')[1])
-        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
-        self.story.setMetadata('author',a.string)
-
-        # Find the chapters:
-        for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
-            # just in case there's tags, like <i> in chapter titles.
-            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']+addurl))
-
-        self.story.setMetadata('numChapters',len(self.chapterUrls))
-
-
-        # Not good enough-- content can contain a ('), which ends the content prematurely.
-        # metadesc = soup.find('meta',{'name':'description'})
-        # print("removeAllEntities(metadesc['content']):\n%s\n"%removeAllEntities(metadesc['content']))
-        start='<span class="label">Summary: </span>'
-        end='<span class="label">Rated:</span>'
-        summarydata = data[data.index(start)+len(start):data.index(end)]
-        #print("summarydata:\n%s\n"%summarydata)
-        self.setDescription(url,self.make_soup(summarydata))
-
-        # eFiction sites don't help us out a lot with their meta data
-        # formating, so it's a little ugly.
-
-        # utility method
-        def defaultGetattr(d,k):
-            try:
-                return d[k]
-            except:
-                return ""
-
-        # <span class="label">Rated:</span> NC-17<br /> etc
-        labels = soup.findAll('span',{'class':'label'})
-        for labelspan in labels:
-            value = labelspan.nextSibling
-            label = labelspan.string
-
-            if 'Rated' in label:
-                self.story.setMetadata('rating', value)
-
-            if 'Word count' in label:
-                self.story.setMetadata('numWords', value)
-
-            if 'Categories' in label:
-                cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
-                catstext = [cat.string for cat in cats]
-                for cat in catstext:
-                    self.story.addToList('category',cat.string)
-
-            if 'Characters' in label:
-                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
-                charstext = [char.string for char in chars]
-                for char in charstext:
-                    self.story.addToList('characters',char.string)
-
-            ## Not all sites use Genre, but there's no harm to
-            ## leaving it in.  Check to make sure the type_id number
-            ## is correct, though--it's site specific.
-            if 'Genre' in label:
-                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')) # XXX
-                genrestext = [genre.string for genre in genres]
-                self.genre = ', '.join(genrestext)
-                for genre in genrestext:
-                    self.story.addToList('genre',genre.string)
-
-            ## Not all sites use Warnings, but there's no harm to
-            ## leaving it in.  Check to make sure the type_id number
-            ## is correct, though--it's site specific.
-            if 'Warnings' in label:
-                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')) # XXX
-                warningstext = [warning.string for warning in warnings]
-                self.warning = ', '.join(warningstext)
-                for warning in warningstext:
-                    self.story.addToList('warnings',warning.string)
-
-            if 'Completed' in label:
-                if 'Yes' in value:
-                    self.story.setMetadata('status', 'Completed')
-                else:
-                    self.story.setMetadata('status', 'In-Progress')
-
-            if 'Published' in label:
-                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-
-            if 'Updated' in label:
-                # there's a stray [ at the end.
-                #value = value[0:-1]
-                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
-
-        try:
-            # Find Series name from series URL.
-            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
-            series_name = a.string
-            series_url = 'http://'+self.host+'/'+a['href']
-
-            # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = self.make_soup(self._fetchUrl(series_url))
-            storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+'))
-            i=1
-            for a in storyas:
-                # skip 'report this' and 'TOC' links
-                if 'contact.php' not in a['href'] and 'index' not in a['href']:
-                    if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
-                        self.setSeries(series_name, i)
-                        self.story.setMetadata('seriesUrl',series_url)
-                        break
-                    i+=1
-
-        except:
-            # I find it hard to care if the series parsing fails
-            pass
-
-    # grab the text for an individual chapter.
-    def getChapterText(self, url):
-
-        logger.debug('Getting chapter text from: %s' % url)
-
-        soup = self.make_soup(self._fetchUrl(url))
-
-        div = soup.find('div', {'id' : 'story'})
-
-        if None == div:
-            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-
-        return self.utf8FromSoup(url,div)
+def getClass():
+    return MuggleNetComAdapter

fanficfare/adapters/adapter_naiceanilmenet.py

@@ -0,0 +1,36 @@
+# -*- 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.
+#
+
+# Software: eFiction
+from base_efiction_adapter import BaseEfictionAdapter
+
+class NaiceaNilmeNetAdapter(BaseEfictionAdapter):
+
+    @staticmethod
+    def getSiteDomain():
+        return 'www.naiceanilme.net'
+
+    @classmethod
+    def getSiteAbbrev(self):
+        return 'nnnet'
+
+    @classmethod
+    def getDateFormat(self):
+        return "%m/%d/%y"
+
+def getClass():
+    return NaiceaNilmeNetAdapter

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
-import logging
-logger = logging.getLogger(__name__)
-import re
-import urllib2
+# Software: eFiction
+from base_efiction_adapter import BaseEfictionAdapter
 
+class NCISFictionNetAdapter(BaseEfictionAdapter):
 
-from ..htmlcleanup import stripHTML
-from .. import exceptions as exceptions
+    @staticmethod
+    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_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_portkeyorg.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
+# Copyright 2011 Fanficdownloader team, 2016 FanFicFare team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -270,7 +270,10 @@ class PortkeyOrgAdapter(BaseSiteAdapter): # XXX
         tag = soup.find('td', {'class' : 'story'})
         if tag == None and "<center><b>Chapter does not exist!</b></center>" in data:
             logger.error("Chapter is missing at: %s"%url)
-            return  self.utf8FromSoup(url,self.make_soup("<div><p><center><b>Chapter does not exist!</b></center></p><p>Chapter is missing at: <a href='%s'>%s</a></p></div>"%(url,url)))
+            return  self.utf8FromSoup(url,self.make_soup("<div><p><center><b>Site says: Chapter does not exist!</b></center></p><p>Chapter is missing at: <a href='%s'>%s</a></p></div>"%(url,url)))
+        elif tag == None and "<center><b>This chapter has corrupted or a blank chapter was uploaded. Please contact the author and request that they re-upload the chapter</b></center>" in data:
+            logger.error("Chapter is missing at: %s"%url)
+            return  self.utf8FromSoup(url,self.make_soup("<div><p><center><b>Site says: This chapter has corrupted or a blank chapter was uploaded.</b></center></p><p>Chapter is missing at: <a href='%s'>%s</a></p></div>"%(url,url)))
         tag.name='div' # force to be a div to avoid problems with nook.
 
         centers = tag.findAll('center')

fanficfare/adapters/adapter_quotevcom.py

@@ -1,3 +1,5 @@
+#  -*- coding: utf-8 -*-
+
 import re
 import urlparse
 import urllib2
@@ -58,25 +60,25 @@ class QuotevComAdapter(BaseSiteAdapter):
         if not element:
             raise exceptions.StoryDoesNotExist(self.url)
 
-        self.story.setMetadata('title', element.find('h1').get_text())
-
-        # quotev html is all about formatting without any content tagging
-        authdiv = soup.find('div', {'style':"text-align:left;"})
+        title = element.find('h1')
+        self.story.setMetadata('title', title.get_text())
+        
+        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:
-            self.story.setMetadata('author','Anonymous')
-            self.story.setMetadata('authorUrl','http://www.quotev.com')
-            self.story.setMetadata('authorId','0')
+        if not self.story.getList('author'):
+            self.story.addToList('author','Anonymous')
+            self.story.addToList('authorUrl','http://www.quotev.com')
+            self.story.addToList('authorId','0')
 
         self.setDescription(self.url, soup.find('div', id='qdesct'))
         imgmeta = soup.find('meta',{'property':"og:image" })
         if imgmeta:
-            self.setCoverImage(self.url, urlparse.urljoin(self.url, imgmeta['content']))
+            self.coverurl = self.setCoverImage(self.url, urlparse.urljoin(self.url, imgmeta['content']))[1]
 
         for a in soup.find_all('a', {'href': re.compile(SITE_DOMAIN+'/stories/c/')}):
             self.story.addToList('category', a.get_text())
@@ -89,9 +91,9 @@ class QuotevComAdapter(BaseSiteAdapter):
         if len(elements) > 1:
             self.story.setMetadata('dateUpdated', datetime.datetime.fromtimestamp(float(elements[1]['ts'])))
 
-        metadiv = elements[0].parent
-        
-        if 'completed' in stripHTML(metadiv):
+        metadiv = elements[0].parent.parent
+        # print stripHTML(metadiv)
+        if u'· completed ·' in stripHTML(metadiv):
             self.story.setMetadata('status', 'Completed')
         else:
             self.story.setMetadata('status', 'In-Progress')        
@@ -102,16 +104,13 @@ class QuotevComAdapter(BaseSiteAdapter):
             parts = datum.split()
             if len(parts) < 2 or parts[1] not in self.getConfig('extra_valid_entries'):
                 continue
-            # Not a valid metadatum
-            # if not len(parts) == 2:
-            #     continue
 
             key, value = parts[1], parts[0]
             self.story.setMetadata(key, value.replace(',', '').replace('.', ''))
 
         favspans = soup.find('a',{'id':'fav_btn'}).find_all('span')
         if len(favspans) > 1:
-            self.story.setMetadata('favorites', stripHTML(favspans[1]).replace(',', ''))
+            self.story.setMetadata('favorites', stripHTML(favspans[-1]).replace(',', ''))
             
         commentspans = soup.find('a',{'id':'comment_btn'}).find_all('span')
         #print("commentspans:%s"%commentspans)
@@ -119,7 +118,8 @@ class QuotevComAdapter(BaseSiteAdapter):
             self.story.setMetadata('comments', stripHTML(commentspans[0]).replace(',', ''))
 
         for a in soup.find('div', id='rselect')('a'):
-            self.chapterUrls.append((a.get_text(), urlparse.urljoin(self.url, a['href'])))
+            if 'javascript' not in a['href']:
+                self.chapterUrls.append((a.get_text(), urlparse.urljoin(self.url, a['href'])))
 
         self.story.setMetadata('numChapters', len(self.chapterUrls))
         
@@ -127,8 +127,15 @@ class QuotevComAdapter(BaseSiteAdapter):
         data = self._fetchUrl(url)
         soup = self.make_soup(data)
 
-        element = soup.find('div', id='rescontent')
-        for a in element('a'):
+        rescontent = soup.find('div', id='rescontent')
+        
+        # attempt to find and include chapter specific images.
+        img = soup.find('div',{'id':'quizHeader'}).find('img')
+        #print("img['src'](%s) != self.coverurl(%s)"%(img['src'],self.coverurl))
+        if img['src'] != self.coverurl:
+            rescontent.insert(0,img)
+        
+        for a in rescontent('a'):
             a.unwrap()
 
-        return self.utf8FromSoup(url, element)
+        return self.utf8FromSoup(url, rescontent)

fanficfare/adapters/adapter_storiesonlinenet.py

@@ -36,6 +36,7 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
 
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
+        logger.debug("StoriesOnlineNetAdapter.__init__ - url='%s'" % url)
 
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
@@ -50,12 +51,16 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
         self._setURL('http://' + self.getSiteDomain() + '/s/'+self.story.getMetadata('storyId'))
 
         # Each adapter needs to have a unique site abbreviation.
-        self.story.setMetadata('siteabbrev','strol')
+        self.story.setMetadata('siteabbrev',self.getSiteAbbrev())
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%Y-%m-%d"
 
+    @classmethod
+    def getSiteAbbrev(self):
+        return 'strol'
+
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
@@ -66,7 +71,7 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
         return "http://"+cls.getSiteDomain()+"/s/1234 http://"+cls.getSiteDomain()+"/s/1234:4010"
 
     def getSiteURLPattern(self):
-        return re.escape("http://"+self.getSiteDomain())+r"/s/\d+((:\d+)?(;\d+)?$|(:i)?$)?"
+        return re.escape("http://"+self.getSiteDomain())+r"/(s|library)/(storyInfo.php\?id=)?(?P<id>\d+)((:\d+)?(;\d+)?$|(:i)?$)?"
 
     ## Login seems to be reasonably standard across eFiction sites.
     def needToLoginCheck(self, data):
@@ -142,6 +147,8 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
             raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
         elif "Error! The story you're trying to access is being filtered by your choice of contents filtering." in data:
             raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Error! The story you're trying to access is being filtered by your choice of contents filtering.")
+        elif "Error! Daily Limit Reached" in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Error! Daily Limit Reached")
 
         # use BeautifulSoup HTML parser to make everything easier to find.
         soup = self.make_soup(data)
@@ -178,7 +185,8 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
         page=0
         i=0
         while i == 0:
-            asoup = self.make_soup(self._fetchUrl(self.story.getList('authorUrl')[0]+"/"+unicode(page)))
+            data = self._fetchUrl(self.story.getList('authorUrl')[0]+"/"+unicode(page))
+            asoup = self.make_soup(data)
 
             a = asoup.findAll('td', {'class' : 'lc2'})
             for lc2 in a:
@@ -203,6 +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))
             if a:
                 # if there's a number after the series name, series_contents is a two element list:
                 # [<a href="...">Title</a>, u' (2)']
@@ -211,59 +220,62 @@ 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")
-                    series_name = series_soup.find('span', {'id' : 'ptitle'}).text.partition(' — ')[0]
-                    logger.debug("Series name: '{0}'".format(series_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: '%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)
-                        universe_name = universe.find('div', {'class' : 'ser-name'}).text.partition(' ')[2]
-                        logger.debug("universe_name='%s'" % universe_name)
+                        # 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)
                         # 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
                 else:
                     logger.debug("No universe page")
         except:
+            raise
             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 = universe_soup.find('h1', {'id' : 'ptitle'}).text.partition('—')[0]
-                    logger.debug("Universes name: '{0}'".format(universe_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))
 
                 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)
@@ -271,6 +283,7 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
             else:
                 logger.debug("Do not have a universe")
         except:
+            raise
             pass
 
         self.setDescription('http://'+self.host+'/s/'+self.story.getMetadata('storyId'),desc)
@@ -290,7 +303,7 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
 
             if 'Tags' in label or 'Codes' in label:
                 for code in re.split(r'\s*,\s*', value.strip()):
-                     self.story.addToList('sitetags',code)
+                    self.story.addToList('sitetags',code)
 
             if 'Posted' in label:
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
@@ -307,12 +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)
 
@@ -350,7 +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:]
 
@@ -359,7 +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_test1.py

@@ -34,6 +34,8 @@ class TestSiteAdapter(BaseSiteAdapter):
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
         self.username=''
         self.is_adult=False
+        # happens inside BaseSiteAdapter.__init__
+        # self._setURL(url)
 
     @staticmethod
     def getSiteDomain():
@@ -117,7 +119,6 @@ class TestSiteAdapter(BaseSiteAdapter):
         else:
             self.story.setMetadata(u'title',"Test Story Title "+idstr)
             self.story.setMetadata('author','Test Author aa')
-        self.story.setMetadata('storyUrl',self.url)
         self.setDescription(self.url,u'Description '+self.crazystring+u''' Done
 <p>
 Some more longer description.  "I suck at summaries!"  "Better than it sounds!"  "My first fic"

fanficfare/adapters/adapter_thehexfilesnet.py

@@ -193,14 +193,10 @@ class TheHexFilesNetAdapter(BaseSiteAdapter):
         if None == soup:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
 
-        # Ugh.  chapter html doesn't haven't anything useful around it to demarcate.
-        for a in soup.findAll('table'):
+        content = soup.find('table',{'class':'table'}).find('td') # td inside <table class='table'>
+        content.name='div'
+        
+        for a in content.findAll('table'):
             a.extract()
 
-        for a in soup.findAll('head'):
-            a.extract()
-
-        html = soup.find('html')
-        html.name='div'
-
-        return self.utf8FromSoup(url,soup)
+        return self.utf8FromSoup(url,content)

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_tthfanficorg.py

@@ -131,7 +131,7 @@ class TwistingTheHellmouthSiteAdapter(BaseSiteAdapter):
             #print("data:%s"%data)
             soup = self.make_soup(data)
         except urllib2.HTTPError, e:
-            if e.code == 404:
+            if e.code in (404,410):
                 raise exceptions.StoryDoesNotExist(url)
             else:
                 raise e
@@ -257,10 +257,11 @@ class TwistingTheHellmouthSiteAdapter(BaseSiteAdapter):
         for cat in verticaltable.findAll('a', href=re.compile(r"^/Category-")):
             # assumes only one -Centered and one Pairing: cat can ever
             # be applied to one story.
-            if self.getConfig('centeredcat_to_characters') and cat.string.endswith('-Centered'):
+            # Seen at least once: incorrect (empty) cat link, thus "and cat.string"
+            if self.getConfig('centeredcat_to_characters') and cat.string and cat.string.endswith('-Centered'):
                 char = cat.string[:-len('-Centered')]
                 self.story.addToList('characters',char)
-            elif self.getConfig('pairingcat_to_characters_ships') and cat.string.startswith('Pairing: '):
+            elif self.getConfig('pairingcat_to_characters_ships') and cat.string and cat.string.startswith('Pairing: '):
                 pair = cat.string[len('Pairing: '):]
                 self.story.addToList('characters',pair)
                 if char:

fanficfare/adapters/base_adapter.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
+# Copyright 2011 Fanficdownloader team, 2016 FanFicFare team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -16,7 +16,8 @@
 #
 
 import re
-import datetime
+from datetime import datetime, timedelta
+
 import time
 import logging
 import urllib
@@ -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
@@ -187,7 +188,7 @@ class BaseSiteAdapter(Configurable):
         self.parsedUrl = up.urlparse(url)
         self.host = self.parsedUrl.netloc
         self.path = self.parsedUrl.path        
-        self.story.setMetadata('storyUrl',self.url)
+        self.story.setMetadata('storyUrl',self.url,condremoveentities=False)
 
 ## website encoding(s)--in theory, each website reports the character
 ## encoding they use for each page.  In practice, some sites report it
@@ -236,11 +237,11 @@ class BaseSiteAdapter(Configurable):
         '''
         cachekey=self._get_cachekey(url, parameters, headers)
         if usecache and self._has_cachekey(cachekey):
-            logger.debug("#####################################\npagecache HIT: %s"%cachekey)
+            logger.debug("#####################################\npagecache HIT: %s"%safe_url(cachekey))
             data,redirecturl = self._get_from_pagecache(cachekey)
             return data
         
-        logger.debug("#####################################\npagecache MISS: %s"%cachekey)
+        logger.debug("#####################################\npagecache MISS: %s"%safe_url(cachekey))
         self.do_sleep(extrasleep)
 
         ## u2.Request assumes POST when data!=None.  Also assumes data
@@ -279,7 +280,7 @@ class BaseSiteAdapter(Configurable):
         '''
         cachekey=self._get_cachekey(url, parameters)
         if usecache and self._has_cachekey(cachekey):
-            logger.debug("#####################################\npagecache HIT: %s"%cachekey)
+            logger.debug("#####################################\npagecache HIT: %s"%safe_url(cachekey))
             data,redirecturl = self._get_from_pagecache(cachekey)
             class FakeOpened:
                 def __init__(self,data,url):
@@ -289,7 +290,7 @@ class BaseSiteAdapter(Configurable):
                 def read(self): return self.data
             return (data,FakeOpened(data,redirecturl))
         
-        logger.debug("#####################################\npagecache MISS: %s"%cachekey)
+        logger.debug("#####################################\npagecache MISS: %s"%safe_url(cachekey))
         self.do_sleep(extrasleep)
         if parameters != None:
             opened = self.opener.open(url.replace(' ','%20'),urllib.urlencode(parameters),float(self.getConfig('connect_timeout',30.0)))
@@ -338,15 +339,15 @@ class BaseSiteAdapter(Configurable):
                 return (self._decode(data),opened)
             except u2.HTTPError, he:
                 excpt=he
-                if he.code in (403,404):
-                    logger.warn("Caught an exception reading URL: %s  Exception %s."%(unicode(url),unicode(he)))
+                if he.code in (403,404,410):
+                    logger.warn("Caught an exception reading URL: %s  Exception %s."%(unicode(safe_url(url)),unicode(he)))
                     break # break out on 404
             except Exception, e:
                 excpt=e
-                logger.warn("Caught an exception reading URL: %s sleeptime(%s) Exception %s."%(unicode(url),sleeptime,unicode(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" %url)
-        logger.exception(excpt)
+        logger.error("Giving up on %s" %safe_url(url))
+        logger.debug(excpt, exc_info=True)
         raise(excpt)
 
     # Limit chapters to download.  Input starts at 1, list starts at 0
@@ -571,11 +572,14 @@ class BaseSiteAdapter(Configurable):
         #print("include_images:"+self.getConfig('include_images'))
         if self.getConfig('include_images'):
             acceptable_attributes.extend(('src','alt','longdesc'))
-            for img in soup.findAll('img'):
-                # some pre-existing epubs have img tags that had src stripped off.
-                if img.has_attr('src'):
-                    (img['src'],img['longdesc'])=self.story.addImgUrl(url,img['src'],fetch,
-                                                                      coverexclusion=self.getConfig('cover_exclusion_regexp'))
+            try:
+                for img in soup.find_all('img'):
+                    # some pre-existing epubs have img tags that had src stripped off.
+                    if img.has_attr('src'):
+                        (img['src'],img['longdesc'])=self.story.addImgUrl(url,img['src'],fetch,
+                                                                          coverexclusion=self.getConfig('cover_exclusion_regexp'))
+            except AttributeError as ae:
+                logger.info("Parsing for img tags failed--probably poor input HTML.  Skipping images.")
 
         for attr in self.get_attr_keys(soup):
             if attr not in acceptable_attributes:
@@ -685,6 +689,26 @@ 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)
+def safe_url(url):
+    # return url with password attr (if present) obscured.
+    return re.sub(safe_url_re,r'\g<attr>XXXXXXXX\g<amp>',url)

fanficfare/adapters/base_efiction_adapter.py

@@ -51,7 +51,7 @@ _WRONGPASSWORD = "That password doesn't match the one in our database"
 _USERACCOUNT = 'Member Account'
 
 # Regular expressions
-_REGEX_WARING_PARAM = re.compile("warning=(?P<warningId>\d+)")
+_REGEX_WARNING_PARAM = re.compile("warning=(?P<warningId>\d+)")
 _REGEX_CHAPTER_B = re.compile("^(?P<chapterId>\d+)\.")
 _REGEX_CHAPTER_PARAM = re.compile("chapter=(?P<chapterId>\d+)$")
 _REGEX_CHAPTER_FRAGMENT = re.compile("^#(?P<chapterId>\d+)$")
@@ -345,6 +345,8 @@ class BaseEfictionAdapter(BaseSiteAdapter):
                     self.triedLoggingIn = True
                 else:
                     raise exceptions.FailedToLogin(self.url, unicode(errorDiv))
+            elif "This story has not been validated" in stripHTML(errorDiv):
+                raise exceptions.AccessDenied(self.getSiteDomain() +" says: "+stripHTML(errorDiv))
             else:
                 warningLink = errorDiv.find("a")
                 if warningLink is not None and ( \
@@ -354,15 +356,15 @@ class BaseEfictionAdapter(BaseSiteAdapter):
                         if not (self.is_adult or self.getConfig("is_adult")):
                             raise exceptions.AdultCheckRequired(self.url)
                         # XXX Using this method, we're independent of # getHighestWarningLevel
-                        printUrl += "&ageconsent=ok&warning=%s" % (_REGEX_WARING_PARAM.search(warningLink['href']).group(1))
+                        printUrl += "&ageconsent=ok&warning=%s" % (_REGEX_WARNING_PARAM.search(warningLink['href']).group(1))
                         # printUrl += "&ageconsent=ok&warning=%s" % self.getHighestWarningLevel()
                         soup = self._fetch_to_soup(printUrl)
                         errorDiv = soup.find("div", "errortext")
                         self.triedAcceptWarnings = True
                     else:
-                        raise exception.FailedToDownload(self.url, unicode(errorDiv))
+                        raise exceptions.FailedToDownload("Error with URL: %s (%s)" % (self.url,stripHTML(errorDiv)))
                 else:
-                    raise exception.FailedToDownload(self.url, unicode(errorDiv))
+                    raise exceptions.FailedToDownload("Error with URL: %s (%s)" % (self.url,stripHTML(errorDiv)))
 
         # title and author
         pagetitleDiv = soup.find("div", {"id": "pagetitle"})
@@ -382,7 +384,7 @@ class BaseEfictionAdapter(BaseSiteAdapter):
             while nextEl is not None and not (\
                         type(nextEl) is bs.Tag \
                         and nextEl.name == "span" \
-                        and 'label' in nextEl['class'] \
+                        and 'label' in nextEl.get('class',[]) \
                         ):
                 ## must string copy nextEl or nextEl will change trees
                 if (type(nextEl) is bs.Tag):

fanficfare/adapters/base_xenforoforum_adapter.py

@@ -49,9 +49,9 @@ class BaseXenForoForumAdapter(BaseSiteAdapter):
         m = re.match(self.getSiteURLPattern(),url)
         if m:
             #logger.debug("groupdict:%s"%m.groupdict())
-            if m.group('post'):
-                self.story.setMetadata('storyId',m.group('post'))
-                self._setURL(self.getURLPrefix() + '/posts/'+m.group('post')+'/')
+            if m.group('anchorpost'):
+                self.story.setMetadata('storyId',m.group('anchorpost'))
+                self._setURL(self.getURLPrefix() + '/posts/'+m.group('anchorpost')+'/')
             else:
                 self.story.setMetadata('storyId',m.group('id'))
                 # normalized story URL.
@@ -83,7 +83,7 @@ class BaseXenForoForumAdapter(BaseSiteAdapter):
         return cls.getURLPrefix()+"/threads/some-story-name.123456/ "+cls.getURLPrefix()+"/posts/123456/"
 
     def getSiteURLPattern(self):
-        return r"https?://"+re.escape(self.getSiteDomain())+r"/(?P<tp>threads|posts)/(.+\.)?(?P<id>\d+)/?[^#]*?(#post-(?P<post>\d+))?$"
+        return r"https?://"+re.escape(self.getSiteDomain())+r"/(?P<tp>threads|posts)/(.+\.)?(?P<id>\d+)/?[^#]*?(#post-(?P<anchorpost>\d+))?$"
 
     def use_pagecache(self):
         '''
@@ -150,7 +150,7 @@ class BaseXenForoForumAdapter(BaseSiteAdapter):
                 raise
 
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = self.make_soup(data)
+        topsoup = soup = self.make_soup(data)
 
         a = soup.find('h3',{'class':'userText'}).find('a')
         self.story.addToList('authorId',a['href'].split('/')[1])
@@ -160,6 +160,9 @@ class BaseXenForoForumAdapter(BaseSiteAdapter):
         h1 = soup.find('div',{'class':'titleBar'}).h1
         self.story.setMetadata('title',stripHTML(h1))
 
+        first_post_title = self.getConfig('first_post_title','First Post')
+
+        threadmark_chaps = False
         if '#' in useurl:
             anchorid = useurl.split('#')[1]
             soup = soup.find('li',id=anchorid)
@@ -176,7 +179,11 @@ class BaseXenForoForumAdapter(BaseSiteAdapter):
                     ## SV changed their threadmarks.  Not isolated to
                     ## SV only incase SB or QQ make the same change.
                     markas = soupmarks.find('div',{'class':'threadmarks'}).find_all('a',{'class':'PreviewTooltip'})
-                if len(markas) > 1:
+                if len(markas) >= int(self.getConfig('minimum_threadmarks',2)):
+                    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'):
@@ -186,16 +193,16 @@ class BaseXenForoForumAdapter(BaseSiteAdapter):
 
                         self.chapterUrls.append((name,self.getURLPrefix()+'/'+url))
 
-                    ## only use tags if threadmarks for chapters.
-                    ##  a bit arbitrary, but likely.
-                    for tag in soup.findAll('a',{'class':'tag'}):
-                        tstr = stripHTML(tag)
-                        if self.getConfig('capitalize_forumtags'):
-                            tstr = tstr.title()
-                        self.story.addToList('forumtags',tstr)
-
             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
+            for tag in topsoup.findAll('a',{'class':'tag'}):
+                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.
 
@@ -211,8 +218,9 @@ class BaseXenForoForumAdapter(BaseSiteAdapter):
 
         # otherwise, use first post links--include first post since
         # that's often also the first chapter.
+
         if not self.chapterUrls:
-            self.chapterUrls.append(("First Post",useurl))
+            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'):
@@ -230,9 +238,9 @@ class BaseXenForoForumAdapter(BaseSiteAdapter):
 
                     logger.debug("(ch:%s)used chapurl:%s"%(len(self.chapterUrls)+1,url))
                     self.chapterUrls.append((name,url))
-                    if url == useurl and 'First Post' == self.chapterUrls[0][0]:
+                    if url == useurl and first_post_title == self.chapterUrls[0][0] \
+                            and not self.getConfig('always_include_first_post',False):
                         # remove "First Post" if included in list.
-                        logger.debug("delete dup 'First Post' chapter: %s %s"%self.chapterUrls[0])
                         del self.chapterUrls[0]
 
             # Didn't use threadmarks, so take created/updated dates
@@ -264,7 +272,7 @@ 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.

fanficfare/cli.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.
@@ -31,7 +31,7 @@ if sys.version_info < (2, 5):
     sys.exit(1)
 
 if sys.version_info >= (2, 7):
-    # suppresses default logger.  Logging is setup in fanficdownload/__init__.py so it works in calibre, too.
+    # suppresses default logger.  Logging is setup in fanficfare/__init__.py so it works in calibre, too.
     rootlogger = logging.getLogger()
     loghandler = logging.NullHandler()
     loghandler.setFormatter(logging.Formatter('(=====)(levelname)s:%(message)s'))
@@ -39,11 +39,11 @@ if sys.version_info >= (2, 7):
 
 try:
     # running under calibre
-    from calibre_plugins.fanfictiondownloader_plugin.fanficfare import adapters, writers, exceptions
-    from calibre_plugins.fanfictiondownloader_plugin.fanficfare.configurable import Configuration
-    from calibre_plugins.fanfictiondownloader_plugin.fanficfare.epubutils import (
+    from calibre_plugins.fanficfare_plugin.fanficfare import adapters, writers, exceptions
+    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.fanfictiondownloader_plugin.fanficfare.geturls import get_urls_from_page
+    from calibre_plugins.fanficfare_plugin.fanficfare.geturls import get_urls_from_page
 except ImportError:
     from fanficfare import adapters, writers, exceptions
     from fanficfare.configurable import Configuration
@@ -355,6 +355,7 @@ def do_download(arg,
             # regular download
             if options.metaonly:
                 pprint.pprint(adapter.getStoryMetadataOnly().getAllMetadata())
+                pprint.pprint(adapter.chapterUrls)
 
             output_filename = write_story(configuration, adapter, options.format, options.metaonly)
 

fanficfare/configurable.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.
@@ -111,8 +111,6 @@ def get_valid_list_entries():
                  'authorId',
                  'authorUrl',
                  'lastupdate',
-                 'keep_html_attrs',
-                 'replace_tags_with_spans',
                  ])
 
 boollist=['true','false']
@@ -125,6 +123,10 @@ def get_valid_set_options():
     '''
     dict() of names of boolean options, but as a tuple with
     valid sites, valid formats and valid values (None==all)
+
+    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.
     '''
 
     valdict = {'collect_series':(None,None,boollist),
@@ -158,12 +160,16 @@ def get_valid_set_options():
 
                'force_login':(['phoenixsong.net'],None,boollist),
                'non_breaking_spaces':(['fictionmania.tv'],None,boollist),
-               'universe_as_series':(['storiesonline.net'],None,boollist),
+               'universe_as_series':(['storiesonline.net','finestories.com'],None,boollist),
                'strip_text_links':(['bloodshedverse.com'],None,boollist),
                'centeredcat_to_characters':(['tthfanfic.org'],None,boollist),
                'pairingcat_to_characters_ships':(['tthfanfic.org'],None,boollist),
                'romancecat_to_characters_ships':(['tthfanfic.org'],None,boollist),
 
+               'use_meta_keywords':(['literotica.com'],None,boollist),
+               'clean_chapter_titles':(['literotica.com'],None,boollist),
+               'description_in_chapter':(['literotica.com'],None,boollist),
+
                # eFiction Base adapters allow bulk_load
                # kept forgetting to add them, so now it's automatic.
                'bulk_load':(adapters.get_bulk_load_sites(),
@@ -177,8 +183,11 @@ def get_valid_set_options():
                'grayscale_images':(None,['epub','html'],boollist),
                'no_image_processing':(None,['epub','html'],boollist),
 
+               'capitalize_forumtags':(base_xenforo_list,None,boollist),
                'continue_on_chapter_error':(base_xenforo_list,None,boollist),
-               '':(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),
                }
 
     return dict(valdict)
@@ -318,6 +327,9 @@ def get_valid_keywords():
                  'centeredcat_to_characters',
                  'pairingcat_to_characters_ships',
                  'romancecat_to_characters_ships',
+                 'use_meta_keywords',
+                 'clean_chapter_titles',
+                 'description_in_chapter',
                  'titlepage_end',
                  'titlepage_entries',
                  'titlepage_entry',
@@ -339,8 +351,12 @@ def get_valid_keywords():
                  'wrap_width',
                  'zip_filename',
                  'zip_output',
-                 'continue_on_chapter_error',
                  'capitalize_forumtags',
+                 'continue_on_chapter_error',
+                 'minimum_threadmarks',
+                 'first_post_title',
+                 'always_include_first_post',
+                 '',
                  ])
 
 # *known* entry keywords -- or rather regexps for them.
@@ -365,10 +381,12 @@ def make_generate_cover_settings(param):
 
 class Configuration(ConfigParser.SafeConfigParser):
 
-    def __init__(self, sections, fileform):
+    def __init__(self, sections, fileform, lightweight=False):
         site = sections[-1] # first section is site DN.
         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]
@@ -403,8 +421,25 @@ class Configuration(ConfigParser.SafeConfigParser):
         
         self.validEntries = get_valid_entries()
 
-    def addConfigSection(self,section):
-        self.sectionslist.insert(0,section)
+        self.url_config_set = False
+
+    def addUrlConfigSection(self,url):
+        if not self.lightweight: # don't need when just checking for normalized URL.
+            # replace if already set once.
+            if self.url_config_set:
+                self.sectionslist[self.sectionslist.index('overrides')+1]=url
+            else:
+                self.addConfigSection(url,'overrides')
+                self.url_config_set=True
+
+    def addConfigSection(self,section,before=None):
+        if section not in self.sectionslist: # don't add if already present.
+            if before is None:
+                self.sectionslist.insert(0,section)
+            else:
+                ## because sectionslist is hi-pri first, lo-pri last,
+                ## 'before' means after in the list.
+                self.sectionslist.insert(self.sectionslist.index(before)+1,section)
 
     def isListType(self,key):
         return key in self.listTypeEntries or self.hasConfig("include_in_"+key)
@@ -604,7 +639,10 @@ class Configuration(ConfigParser.SafeConfigParser):
     def test_config(self):
         errors=[]
 
-        teststory_re = re.compile(r'^teststory:(defaults|[0-9]+)$')
+        ## too complicated right now to enforce
+        ## get_valid_set_options() warnings on teststory and
+        ## [storyUrl] sections.
+        allow_all_sections_re = re.compile(r'^(teststory:(defaults|[0-9]+)|https?://.*)$')
         allowedsections = get_valid_sections()
 
         clude_metadata_re = re.compile(r'(add_to_)?(in|ex)clude_metadata_(pre|post)')
@@ -614,12 +652,13 @@ class Configuration(ConfigParser.SafeConfigParser):
 
         custom_columns_settings_re = re.compile(r'(add_to_)?custom_columns_settings')
         
-        generate_cover_settings_re = re.compile(r'(add_to_)?generate_cover_settings')        
-
+        generate_cover_settings_re = re.compile(r'(add_to_)?generate_cover_settings')
+        
         valdict = get_valid_set_options()
         
         for section in self.sections():
-            if section not in allowedsections and not teststory_re.match(section):
+            allow_all_section = allow_all_sections_re.match(section)
+            if section not in allowedsections and not allow_all_section:
                 errors.append((self.get_lineno(section),"Bad Section Name: [%s]"%section))
             else:
                 sitename = section.replace('www.','')
@@ -657,26 +696,25 @@ class Configuration(ConfigParser.SafeConfigParser):
                         # timeline=>#ccolumn,n
                         # "FanFiction"=>#collection
 
-                        def make_sections(x):
-                            return '['+'], ['.join(x)+']'
-                        if keyword in valdict:
-                            (valsites,valformats,vals)=valdict[keyword]
-                            if valsites != None and sitename != None and sitename not in valsites:
-                                errors.append((self.get_lineno(section,keyword),"%s not valid in section [%s] -- only valid in %s sections."%(keyword,section,make_sections(valsites))))
-                            if valformats != None and formatname != None and formatname not in valformats:
-                                errors.append((self.get_lineno(section,keyword),"%s not valid in section [%s] -- only valid in %s sections."%(keyword,section,make_sections(valformats))))
-                            if value not in vals:
-                                errors.append((self.get_lineno(section,keyword),"%s not a valid value for %s"%(value,keyword)))
+                        if not allow_all_section:
+                            def make_sections(x):
+                                return '['+'], ['.join(x)+']'
+                            if keyword in valdict:
+                                (valsites,valformats,vals)=valdict[keyword]
+                                if valsites != None and sitename != None and sitename not in valsites:
+                                    errors.append((self.get_lineno(section,keyword),"%s not valid in section [%s] -- only valid in %s sections."%(keyword,section,make_sections(valsites))))
+                                if valformats != None and formatname != None and formatname not in valformats:
+                                    errors.append((self.get_lineno(section,keyword),"%s not valid in section [%s] -- only valid in %s sections."%(keyword,section,make_sections(valformats))))
+                                if vals != None and value not in vals:
+                                    errors.append((self.get_lineno(section,keyword),"%s not a valid value for %s"%(value,keyword)))
 
-                            
                         ## skipping output_filename_safepattern
                         ## regex--not used with plugin and this isn't
                         ## 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
 
 # extended by adapter, writer and story for ease of calling configuration.
@@ -685,6 +723,12 @@ class Configurable(object):
     def __init__(self, configuration):
         self.configuration = configuration
 
+    def is_lightweight(self):
+        return self.configuration.lightweight
+
+    def addUrlConfigSection(self,url):
+        self.configuration.addUrlConfigSection(url)
+        
     def isListType(self,key):
         return self.configuration.isListType(key)
 

fanficfare/defaults.ini

@@ -1,4 +1,4 @@
-# Copyright 2015 Fanficdownloader team, 2015 FanFicFare team
+# Copyright 2015 Fanficdownloader team, 2016 FanFicFare team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -473,8 +473,8 @@ 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
-dateUpdated_format:%%Y-%%m-%%d %%H:%%M:%%S
+datePublished_format:%%Y-%%m-%%d %%H:%%M
+dateUpdated_format:%%Y-%%m-%%d %%H:%%M
 
 ## Only take the first X characters of the 'first' post to use as
 ## the description.
@@ -487,6 +487,33 @@ description_limit:500
 ## in the ebook for that chapter.
 continue_on_chapter_error:false
 
+## When given a thread URL, use threadmarks as chapter links when
+## there are at least this many threadmarks.  A number of older
+## threads have a single threadmark to an 'index' post.  Set to 1 to
+## use threadmarks whenever they exist.
+minimum_threadmarks:2
+
+## When 'first post' (or post URL) is being added as a chapter, give
+## the chapter this title.
+first_post_title:First Post
+
+## In normal operation, if given a post URL or a thread URL with less
+## than minimum_threadmarks, the given post or the first post of the
+## thread will be included as the first chapter (with chapter title
+## from first_post_title) unless that post is explicitly linked to in
+## the collected chapter list.  First post is not included when using
+## thread marks.
+##
+## If always_include_first_post:true, then the given or first post
+## will be included as above even if it is a link in the post or even
+## if threadmarks are used.  Can result in a duplicated chapter.
+always_include_first_post:false
+
+## In normal operation, forumtags will only be populated when
+## threadmarks are used for chapters (see minimum_threadmarks above).
+## When always_use_forumtags:true, always populate forumtags.
+always_use_forumtags:false
+
 ## Each output format has a section that overrides [defaults]
 [html]
 
@@ -848,6 +875,12 @@ 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
@@ -1181,14 +1214,41 @@ dislikes_label:Dislikes
 ## program can prompt you, or you can save it in config.  In
 ## commandline version, this should go in your personal.ini, not
 ## defaults.ini.
-#username:YourName
+## finestories.com has started requiring login by email rather than
+## pen name.
+#username:youremail@yourdomain.dom
 #password:yourpassword
 
-# shows size as "10 KB", not word count
-extra_valid_entries:size
+## Clear FanFiction from defaults, site is original fiction.
+extratags:
 
-# don't show twitter icon.
-cover_exclusion_regexp:/res/css/bir.png
+extra_valid_entries:size,universe,universeUrl,universeHTML,sitetags,notice,codes,score
+#extra_titlepage_entries:size,universeHTML,sitetags,notice,score
+include_in_codes:sitetags
+
+## adds to include_subject_tags instead of replacing it.
+#extra_subject_tags:sitetags
+
+size_label:Size
+universe_label:Universe
+universeUrl_label:Universe URL
+universeHTML_label:Universe
+sitetags_label:Site Tags
+notice_label:Notice
+score_label:Score
+
+## Assume entryUrl, apply to "<a class='%slink' href='%s'>%s</a>" to
+## make entryHTML.
+make_linkhtml_entries:universe
+
+## storiesonline.net stories can be in a series or a universe, but not
+## both.  By default, universe will be populated in 'series' with
+## index=0
+universe_as_series: true
+
+## some sites include images that we don't ever want becoming the
+## cover image.  This lets you exclude them.
+cover_exclusion_regexp:/css/bir.png
 
 [forums.spacebattles.com]
 ## see [base_xenforoforum]
@@ -1268,9 +1328,21 @@ crossoverfandom_label:Crossover Fandom
 extra_titlepage_entries:universe,crossoverfandom
 
 [literotica.com]
-extra_valid_entries:eroticatags
+extra_valid_entries:eroticatags,averrating
 eroticatags_label:Erotica Tags
-extra_titlepage_entries: eroticatags
+averrating_label:Average Rating
+extra_titlepage_entries:eroticatags,averrating
+
+## Extract more erotica_tags from the meta tag of each chapter
+use_meta_keywords: true
+
+## For multiple chapter stories, attempt to clean up the chapter title. This will
+## remove the story title and change "Ch. 01" to "Chapter 1", "Pt. 01" to "Part 1"
+## or just use the text. If this can't be done, the full title is used.
+clean_chapter_titles: false
+
+## Add the chapter description at the start of each chapter.
+description_in_chapter: false
 
 [lotrfanfiction.com]
 extra_valid_entries: readings
@@ -1770,6 +1842,10 @@ 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
@@ -1891,6 +1967,9 @@ extracategories:Harry Potter
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
 
+extra_valid_entries:reads,reviews
+reads_label:Total Read Count
+
 [www.hpfanficarchive.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
@@ -2209,6 +2288,96 @@ extracategories:Stargate: Atlantis
 extra_valid_entries:reviews
 reviews_label:Reviews
 
+[buffygiles.velocitygrass.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Site dedicated to these categories/characters/ships
+extracharacters:Buffy,Giles
+
+[fanfiction.lucifael.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+[www.andromeda-web.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Site dedicated to these categories/characters/ships
+extracategories:Andromeda
+
+[www.artemis-fowl.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Site dedicated to these categories/characters/ships
+extracategories:Artemis Fowl
+
+[www.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,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+
+
 [overrides]
 ## It may sometimes be useful to override all of the specific format,
 ## site and site:format sections in your private configuration.  For

fanficfare/epubutils.py

@@ -84,8 +84,7 @@ def get_update_data(inputio,
                 oldcover = (oldcoverhtmlhref,oldcoverhtmltype,oldcoverhtmldata,oldcoverimghref,oldcoverimgtype,oldcoverimgdata)
             except Exception as e:
                 logger.warn("Cover Image %s not found"%src)
-                logger.warn("Exception: %s"%(unicode(e)))
-                traceback.print_exc()
+                logger.warn("Exception: %s"%(unicode(e)),exc_info=True)
 
     filecount = 0
     soups = [] # list of xhmtl blocks
@@ -127,8 +126,7 @@ 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)))
-                                    traceback.print_exc()
+                                    logger.warn("Exception: %s"%(unicode(e)),exc_info=True)
                         bodysoup = soup.find('body')
                         # ffdl epubs have chapter title h3
                         h3 = bodysoup.find('h3')

fanficfare/geturls.py

@@ -35,7 +35,7 @@ from exceptions import UnknownSite
 def get_urls_from_page(url,configuration=None,normalize=False):
 
     if not configuration:
-        configuration = Configuration("test1.com","EPUB")
+        configuration = Configuration(["test1.com"],"EPUB",lightweight=True)
 
     data = None
     adapter = None
@@ -84,7 +84,7 @@ def get_urls_from_html(data,url=None,configuration=None,normalize=False,restrict
     urls = collections.OrderedDict()
 
     if not configuration:
-        configuration = Configuration("test1.com","EPUB")
+        configuration = Configuration(["test1.com"],"EPUB",lightweight=True)
 
     soup = BeautifulSoup(data,"html5lib")
     if restrictsearch:
@@ -128,7 +128,7 @@ def get_urls_from_text(data,configuration=None,normalize=False):
     data=unicode(data)
 
     if not configuration:
-        configuration = Configuration("test1.com","EPUB")
+        configuration = Configuration(["test1.com"],"EPUB",lightweight=True)
     
     for href in re.findall('http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', data):
         # this (should) catch normal story links, some javascript

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

@@ -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.
@@ -380,8 +380,8 @@ def set_in_ex_clude(setting):
 ## metakey[,metakey]=>pattern=>replacement[&&metakey=>regexp]
 def make_replacements(replace):
     retval=[]
-    for fullline in replace.splitlines():
-        line=fullline
+    for repl_line in replace.splitlines():
+        line=repl_line
         try:
             (metakeys,regexp,replacement,condkey,condregexp)=(None,None,None,None,None)
             if "&&" in line:
@@ -403,10 +403,10 @@ def make_replacements(replace):
                 # replacement string.  The .ini parser eats any
                 # trailing spaces.
                 replacement=replacement.replace(SPACE_REPLACE,' ')
-                retval.append([metakeys,regexp,replacement,condkey,condregexp])
+                retval.append([repl_line,metakeys,regexp,replacement,condkey,condregexp])
         except Exception as e:
-            logger.error("Problem with Replacement Line:%s"%fullline)
-            raise exceptions.PersonalIniFailed(e,'replace_metadata unpacking failed',fullline)
+            logger.error("Problem with Replacement Line:%s"%repl_line)
+            raise exceptions.PersonalIniFailed(e,'replace_metadata unpacking failed',repl_line)
 #            raise
     return retval
 
@@ -419,38 +419,51 @@ class Story(Configurable):
             self.metadata = {'version':os.environ['CURRENT_VERSION_ID']}
         except:
             self.metadata = {'version':'4.4'}
+        self.replacements = []
         self.in_ex_cludes = {}
         self.chapters = [] # chapters will be namedtuple of Chapter(url,title,html,etc)
         self.chapter_first = None
         self.chapter_last = None
         self.imgurls = []
         self.imgtuples = []
+        # save processed metadata, dicts keyed by 'key', then (removeentities,dorepl)
+        # {'key':{(removeentities,dorepl):"value",(...):"value"},'key':... }
+        self.processed_metadata_cache = {}
 
         self.cover=None # *href* of new cover image--need to create html.
         self.oldcover=None # (oldcoverhtmlhref,oldcoverhtmltype,oldcoverhtmldata,oldcoverimghref,oldcoverimgtype,oldcoverimgdata)
         self.calibrebookmark=None # cheesy way to carry calibre bookmark file forward across update.
         self.logfile=None # cheesy way to carry log file forward across update.
 
-        ## Look for config parameter, split and add each to metadata field.
-        for (config,metadata) in [("extracategories","category"),
-                                  ("extragenres","genre"),
-                                  ("extracharacters","characters"),
-                                  ("extraships","ships"),
-                                  ("extrawarnings","warnings")]:
-            for val in self.getConfigList(config):
-                self.addToList(metadata,val)
+        self.replacements_prepped = False
 
-        self.replacements = make_replacements(self.getConfig('replace_metadata'))
-
-        in_ex_clude_list = ['include_metadata_pre','exclude_metadata_pre',
-                            'include_metadata_post','exclude_metadata_post']
-        for ie in in_ex_clude_list:
-            ies = self.getConfig(ie)
-            # print("%s %s"%(ie,ies))
-            if ies:
-                iel = []
-                self.in_ex_cludes[ie] = set_in_ex_clude(ies)
+    def prepare_replacements(self):
+        if not self.replacements_prepped and not self.is_lightweight():
+            # logger.debug("prepare_replacements")
+            # logger.debug("sections:%s"%self.configuration.sectionslist)
+            
+            ## Look for config parameter, split and add each to metadata field.
+            for (config,metadata) in [("extracategories","category"),
+                                      ("extragenres","genre"),
+                                      ("extracharacters","characters"),
+                                      ("extraships","ships"),
+                                      ("extrawarnings","warnings")]:
+                for val in self.getConfigList(config):
+                    self.addToList(metadata,val)
+    
+            self.replacements =  make_replacements(self.getConfig('replace_metadata'))
+    
+            in_ex_clude_list = ['include_metadata_pre','exclude_metadata_pre',
+                                'include_metadata_post','exclude_metadata_post']
+            for ie in in_ex_clude_list:
+                ies = self.getConfig(ie)
+                # print("%s %s"%(ie,ies))
+                if ies:
+                    iel = []
+                    self.in_ex_cludes[ie] = set_in_ex_clude(ies)
+            self.replacements_prepped = True
 
+    
     def set_chapters_range(self,first=None,last=None):
         self.chapter_first=first
         self.chapter_last=last
@@ -460,6 +473,9 @@ class Story(Configurable):
 
     def setMetadata(self, key, value, condremoveentities=True):
 
+        # delete 
+        if key in self.processed_metadata_cache:
+            del self.processed_metadata_cache[key]
         # keep as list type, but set as only value.
         if self.isList(key):
             self.addToList(key,value,condremoveentities=condremoveentities,clear=True)
@@ -482,8 +498,18 @@ class Story(Configurable):
             self.addToList('lastupdate',value.strftime("Last Update Year/Month: %Y/%m"),clear=True)
             self.addToList('lastupdate',value.strftime("Last Update: %Y/%m/%d"))
 
+        if key == 'storyUrl' and value:
+            self.addUrlConfigSection(value) # adapter/writer share the
+                                            # same configuration.
+                                            # ignored if config
+                                            # is_lightweight()
+            self.replacements_prepped = False
 
     def do_in_ex_clude(self,which,value,key):
+        # sets self.replacements and self.in_ex_cludes if needed
+        # do_in_ex_clude is always called from doReplacements, so redundant.
+        # self.prepare_replacements()
+        
         if value and which in self.in_ex_cludes:
             include = 'include' in which
             keyfound = False
@@ -512,8 +538,10 @@ class Story(Configurable):
                 value = None
         return value
 
-
     def doReplacements(self,value,key,return_list=False,seen_list=[]):
+        # sets self.replacements and self.in_ex_cludes if needed
+        self.prepare_replacements()
+
         value = self.do_in_ex_clude('include_metadata_pre',value,key)
         value = self.do_in_ex_clude('exclude_metadata_pre',value,key)
 
@@ -523,7 +551,7 @@ class Story(Configurable):
                 # print("bailing on %s"%replaceline)
                 continue
             #print("replacement tuple:%s"%replaceline)
-            (metakeys,regexp,replacement,condkey,condregexp) = replaceline
+            (repl_line,metakeys,regexp,replacement,condkey,condregexp) = replaceline
             if (metakeys == None or key in metakeys) \
                     and isinstance(value,basestring) \
                     and regexp.search(value):
@@ -541,21 +569,28 @@ class Story(Configurable):
                     if SPLIT_META in replacement:
                         retlist = []
                         for splitrepl in replacement.split(SPLIT_META):
-                            retlist.extend(self.doReplacements(regexp.sub(splitrepl,value),
+                            try:
+                                tval = regexp.sub(splitrepl,value)
+                            except:
+                                logger.error("Exception with replacement line,value:(%s),(%s)"%(repl_line,value))
+                                raise
+                            retlist.extend(self.doReplacements(tval,
                                                                key,
                                                                return_list=True,
                                                                seen_list=seen_list+[replaceline]))
                         break
                     else:
                         # print("replacement,value:%s,%s->%s"%(replacement,value,regexp.sub(replacement,value)))
-                        value = regexp.sub(replacement,value)
-                        retlist = [value]
+                        try:
+                            value = regexp.sub(replacement,value)
+                            retlist = [value]
+                        except:
+                            logger.error("Exception with replacement line,value:(%s),(%s)"%(repl_line,value))
+                            raise
 
         for val in retlist:
             retlist = map(partial(self.do_in_ex_clude,'include_metadata_post',key=key),retlist)
             retlist = map(partial(self.do_in_ex_clude,'exclude_metadata_post',key=key),retlist)
-        # value = self.do_in_ex_clude('include_metadata_post',value,key)
-        # value = self.do_in_ex_clude('exclude_metadata_post',value,key)
 
         if return_list:
             return retlist
@@ -636,13 +671,16 @@ class Story(Configurable):
         if not self.isValidMetaEntry(key):
             return value
 
-        if self.isList(key):
+        # check for a cached value to speed processing
+        if key in self.processed_metadata_cache \
+                and (removeallentities,doreplacements) in self.processed_metadata_cache[key]:
+            return self.processed_metadata_cache[key][(removeallentities,doreplacements)]
+        elif self.isList(key):
             # join_string = self.getConfig("join_string_"+key,u", ").replace(SPACE_REPLACE,' ')
             # value = join_string.join(self.getList(key, removeallentities, doreplacements=True))
             value = self.join_list(key,self.getList(key, removeallentities, doreplacements=True))
             if doreplacements:
                 value = self.doReplacements(value,key+"_LIST")
-            return value
         elif self.metadata.has_key(key):
             value = self.metadata[key]
             if value:
@@ -667,11 +705,16 @@ class Story(Configurable):
             if doreplacements:
                 value=self.doReplacements(value,key)
             if removeallentities and value != None:
-                return removeAllEntities(value)
-            else:
-                return value
+                value = removeAllEntities(value)
         else: #if self.getConfig("default_value_"+key):
-            return self.getConfig("default_value_"+key)
+            value = self.getConfig("default_value_"+key)
+
+        # save a cached value to speed processing
+        if key not in self.processed_metadata_cache:
+            self.processed_metadata_cache[key] = {}
+        self.processed_metadata_cache[key][(removeallentities,doreplacements)] = value
+        
+        return value
 
     def getAllMetadata(self,
                        removeallentities=False,
@@ -1024,9 +1067,9 @@ class Story(Configurable):
 
         prefix='ffdl'
         if imgurl not in self.imgurls:
-            parsedUrl = urlparse.urlparse(imgurl)
 
             try:
+                parsedUrl = urlparse.urlparse(imgurl)
                 if self.getConfig('no_image_processing'):
                     (data,ext,mime) = no_convert_image(imgurl,
                                                        fetch(imgurl))
@@ -1118,5 +1161,5 @@ def unique_list(seq):
     try:
         return [x for x in seq if not (x in seen or seen_add(x))]
     except:
-        print("unique_list exception seq:%s"%seq)
+        logger.debug("unique_list exception seq:%s"%seq)
         raise

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

@@ -23,7 +23,7 @@ setup(
     # Versions should comply with PEP440.  For a discussion on single-sourcing
     # the version across setup.py and the project code, see
     # https://packaging.python.org/en/latest/single_source_version.html
-    version="2.2.17",
+    version="2.3.2",
 
     description='A tool for downloading fanfiction to eBook formats',
     long_description=long_description,
@@ -81,7 +81,7 @@ 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,

webservice/app.yaml

@@ -1,6 +1,6 @@
 # ffd-retief-hrd fanficfare
 application: fanficfare
-version: 2-2-17
+version: 2-3-02
 runtime: python27
 api_version: 1
 threadsafe: true

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/>
-	Copyright &copy; Fanficdownloader team
+	This is a web front-end to <a href="https://github.com/JimmXinu/FanFicFare/">FanFicFare</a><br/>
+	Copyright &copy; FanFicFare team
       </div>
 
     </div>

webservice/index.html

@@ -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://2-2-16.fanficfare.appspot.com">previous version
+	    <a href="http://2-3-01.fanficfare.appspot.com">previous version
 	    </a> is also available for you to use if necessary.
 	  </p>
 	  <div id='error'>

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

@@ -210,18 +210,18 @@ class FileServer(webapp2.RequestHandler):
             # to hold the whole in memory just for the
             # compress/uncompress
             if download.format != 'epub':
-                def dc(data):
+                def decompress(data):
                     try:
                         return zlib.decompress(data)
                     # if error, assume it's a chunk from before we started compessing.
                     except zlib.error:
                         return data
             else:
-                def dc(data):
+                def decompress(data):
                     return data
 
             for datum in data:
-                self.response.out.write(dc(datum.blob))
+                self.response.out.write(decompress(datum.blob))
 
         except Exception, e:
             fic = DownloadMeta()
@@ -286,8 +286,8 @@ class ClearRecentServer(webapp2.RequestHandler):
             if results:
                 for d in results:
                     d.delete()
-                    for c in d.data_chunks:
-                        c.delete()
+                    for chunk in d.data_chunks:
+                        chunk.delete()
                     num = num + 1
                     logging.debug('Delete '+d.url)
             else:
@@ -494,8 +494,8 @@ class FanfictionDownloaderTask(UserConfigServer):
         # use existing record if available.
         # fileId should have record from /fdown.
         download = getDownloadMeta(id=fileId,url=url,user=user,format=format,new=True)
-        for c in download.data_chunks:
-            c.delete()
+        for chunk in download.data_chunks:
+            chunk.delete()
         download.put()
 
         logging.info('Creating adapter...')
@@ -542,21 +542,22 @@ class FanfictionDownloaderTask(UserConfigServer):
             # compressed individually to avoid having to hold the
             # whole in memory just for the compress/uncompress.
             if format != 'epub':
-                def c(data):
+                def compress(data):
                     return zlib.compress(data)
             else:
-                def c(data):
+                def compress(data):
                     return data
 
             # delete existing chunks first
-            for c in download.data_chunks:
-                c.delete()
+            for chunk in download.data_chunks:
+                chunk.delete()
                 
             index=0
             while( len(data) > 0 ):
+                # logging.info("len(data): %s" % len(data))
                 DownloadData(download=download,
                              index=index,
-                             blob=c(data[:1000000])).put()
+                             blob=compress(data[:1000000])).put()
                 index += 1
                 data = data[1000000:]
             download.completed=True

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>