Update CLI download zip.

Also don't retry 404 errors and bump versions.

app.yaml

@@ -1,6 +1,6 @@
 # ffd-retief-hrd fanfictiondownloader
 application: fanfictiondownloader
-version: 4-4-85
+version: 4-4-95
 runtime: python27
 api_version: 1
 threadsafe: true

calibre-plugin/__init__.py

@@ -42,8 +42,8 @@ class FanFictionDownLoaderBase(InterfaceActionBase):
     description         = _('UI plugin to download FanFiction stories from various sites.')
     supported_platforms = ['windows', 'osx', 'linux']
     author              = 'Jim Miller'
-    version             = (1, 8, 01)
-    minimum_calibre_version = (0, 8, 57)
+    version             = (1, 8, 14)
+    minimum_calibre_version = (1, 13, 0)
 
     #: This field defines the GUI plugin class that contains all the code
     #: that actually does something. Its format is module_path:class_name

calibre-plugin/config.py

@@ -55,7 +55,7 @@ from calibre_plugins.fanfictiondownloader_plugin.dialogs \
             EditTextDialog, RejectUrlEntry)
     
 from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.adapters \
-    import (getConfigSections, getNormalStoryURL)
+    import getConfigSections
 
 from calibre_plugins.fanfictiondownloader_plugin.common_utils \
     import ( KeyboardConfigDialog, PrefsViewerDialog )
@@ -209,6 +209,7 @@ class ConfigWidget(QWidget):
         prefs['suppresstitlesort'] = self.basic_tab.suppresstitlesort.isChecked()
         prefs['mark'] = self.basic_tab.mark.isChecked()
         prefs['showmarked'] = self.basic_tab.showmarked.isChecked()
+        prefs['autoconvert'] = self.basic_tab.autoconvert.isChecked()
         prefs['urlsfromclip'] = self.basic_tab.urlsfromclip.isChecked()
         prefs['updatedefault'] = self.basic_tab.updatedefault.isChecked()
         prefs['deleteotherforms'] = self.basic_tab.deleteotherforms.isChecked()
@@ -248,6 +249,7 @@ class ConfigWidget(QWidget):
                 #print("gc_site_settings[%s]:%s"%(site,gc_site_settings[site]))
         prefs['gc_site_settings'] = gc_site_settings
         prefs['allow_gc_from_ini'] = self.generatecover_tab.allow_gc_from_ini.isChecked()
+        prefs['gc_polish_cover'] = self.generatecover_tab.gc_polish_cover.isChecked()
 
         # Count Pages tab
         countpagesstats = []
@@ -422,6 +424,11 @@ class BasicTab(QWidget):
         self.showmarked.setChecked(prefs['showmarked'])
         self.l.addWidget(self.showmarked)
 
+        self.autoconvert = QCheckBox(_("Automatically Convert new/update books?"),self)
+        self.autoconvert.setToolTip(_("Automatically call calibre's Convert for new/update books.\nConverts to the current output format as chosen in calibre's\nPreferences->Behavior settings."))
+        self.autoconvert.setChecked(prefs['autoconvert'])
+        self.l.addWidget(self.autoconvert)
+
         gui_gb = groupbox = QGroupBox(_("GUI Options"))
         self.l = QVBoxLayout()
         groupbox.setLayout(self.l)
@@ -747,6 +754,11 @@ class GenerateCoverTab(QWidget):
         self.allow_gc_from_ini.setChecked(prefs['allow_gc_from_ini'])
         self.l.addWidget(self.allow_gc_from_ini)
             
+        self.gc_polish_cover = QCheckBox(_("Use calibre's Polish feature to inject/update the cover"),self)
+        self.gc_polish_cover.setToolTip(_("Calibre's Polish feature will be used to inject or update the generated cover into the ebook, EPUB only."))
+        self.gc_polish_cover.setChecked(prefs['gc_polish_cover'])
+        self.l.addWidget(self.gc_polish_cover)
+            
 class CountPagesTab(QWidget):
 
     def __init__(self, parent_dialog, plugin_action):

calibre-plugin/dialogs.py

@@ -136,7 +136,8 @@ class RejectUrlEntry:
     def fullnote(self):
         retval = ""
         if self.title and self.auth:
-            retval = retval + _("%s by %s")%(self.title,self.auth)
+            # don't translate--ends up being saved and confuses regex above.
+            retval = retval + "%s by %s"%(self.title,self.auth)
             if self.note:
                 retval = retval + " - "
                 

calibre-plugin/ffdl_plugin.py

@@ -13,7 +13,7 @@ logger = logging.getLogger(__name__)
 import time, os, copy, threading, re, platform, sys
 from StringIO import StringIO
 from functools import partial
-from datetime import datetime
+from datetime import datetime, time
 from string import Template
 import urllib
 import email
@@ -32,6 +32,7 @@ from calibre.ebooks.metadata.meta import get_metadata
 from calibre.gui2 import error_dialog, warning_dialog, question_dialog, info_dialog
 from calibre.gui2.dialogs.message_box import ViewLog
 from calibre.gui2.dialogs.confirm_delete import confirm
+from calibre.utils.config import prefs as calibre_prefs
 from calibre.utils.date import local_tz
 from calibre.library.comments import sanitize_comments_html
 from calibre.constants import config_dir as calibre_config_dir
@@ -660,13 +661,13 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         #print("update_dialog()")
         
         db = self.gui.current_db
-        book_list = map( self.make_book_id_only, id_list )
+        books = map( self.make_book_id_only, id_list )
 
-        for j, book in enumerate(book_list):
+        for j, book in enumerate(books):
             book['listorder'] = j
-            
+
         LoopProgressDialog(self.gui,
-                           book_list,
+                           books,
                            partial(self.populate_book_from_calibre_id, db=self.gui.current_db),
                            self.update_dialog_finish,
                            init_label=_("Collecting stories for update..."),
@@ -718,6 +719,9 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             url_list = split_text_to_urls(books)
             books = self.convert_urls_to_books(url_list)
 
+        ## for tweak_fg_sleep
+        options['ffnetcount']=len(filter(lambda x : x['site']=='www.fanfiction.net', books))
+
         options['version'] = self.version
         logger.debug(self.version)
         
@@ -815,6 +819,18 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         
         options['personal.ini'] = get_ffdl_personalini()
         adapter = get_ffdl_adapter(url,fileform)
+        # reduce foreground sleep time for ffnet when few books.
+        if 'ffnetcount' in options and \
+                adapter.getConfig('tweak_fg_sleep') and \
+                adapter.getSiteDomain() == 'www.fanfiction.net':
+            minslp = float(adapter.getConfig('min_fg_sleep'))
+            maxslp = float(adapter.getConfig('max_fg_sleep'))
+            dwnlds = float(adapter.getConfig('max_fg_sleep_at_downloads'))
+            m = (maxslp-minslp) / (dwnlds-1)
+            b = minslp - m
+            slp = min(maxslp,m*float(options['ffnetcount'])+b)
+            #print("m:%s b:%s = %s"%(m,b,slp))
+            adapter.set_sleep(slp)
 
         ## three tries, that's enough if both user/pass & is_adult needed,
         ## or a couple tries of one or the other
@@ -841,7 +857,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         series = story.getMetadata('series')
         if not merge and series and prefs['checkforseriesurlid']:
             # try to find *series anthology* by *seriesUrl* identifier url or uri first.
-            searchstr = 'identifiers:"~ur(i|l):=%s"'%story.getMetadata('seriesUrl').replace(":","|")
+            searchstr = 'identifiers:"~ur(i|l):~^%s$"'%re.sub(r'https?\\:','https?(\:|\|)',re.escape(story.getMetadata('seriesUrl')))
             identicalbooks = db.search_getting_ids(searchstr, None)
             # print("searchstr:%s"%searchstr)
             # print("identicalbooks:%s"%identicalbooks)
@@ -918,8 +934,10 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                 logger.debug("from URL(%s)"%url)
     
                 # try to find by identifier url or uri first.
-                searchstr = 'identifiers:"~ur(i|l):=%s"'%url.replace(":","|")
+                searchstr = 'identifiers:"~ur(i|l):~^%s$"'%re.sub(r'https?\:','https?(\:|\|)',url)
                 identicalbooks = db.search_getting_ids(searchstr, None)
+                # print("searchstr:%s"%searchstr)
+                # print("identicalbooks:%s"%identicalbooks)
                 if len(identicalbooks) < 1:
                     # find dups
                     authlist = story.getList("author", removeallentities=True)
@@ -943,7 +961,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                     raise NotGoingToDownload(_("Skipping duplicate story."),"list_remove.png")
     
                 if len(identicalbooks) > 1:
-                    raise NotGoingToDownload("More than one identical book by Identifer URL or title/author(s)--can't tell which book to update/overwrite.","minusminus.png")
+                    raise NotGoingToDownload(_("More than one identical book by Identifer URL or title/author(s)--can't tell which book to update/overwrite."),"minusminus.png")
     
                 ## changed: add new book when CALIBREONLY if none found.
                 if collision == CALIBREONLY and not identicalbooks:
@@ -1029,10 +1047,16 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                 if collision == OVERWRITE and \
                         db.has_format(book_id,formmapping[fileform],index_is_id=True):
                     # check make sure incoming is newer.
-                    lastupdated=story.getMetadataRaw('dateUpdated').date()
-                    fileupdated=datetime.fromtimestamp(os.stat(db.format_abspath(book_id, formmapping[fileform], index_is_id=True))[8]).date()
-                    if fileupdated > lastupdated:
+                    lastupdated=story.getMetadataRaw('dateUpdated')
+                    fileupdated=datetime.fromtimestamp(os.stat(db.format_abspath(book_id, formmapping[fileform], index_is_id=True))[8])
+
+                    # updated doesn't have time (or is midnight), use dates only.
+                    # updated does have time, use full timestamps.
+                    if (lastupdated.time() == time.min and fileupdated.date() > lastupdated.date()) or \
+                            (lastupdated.time() != time.min and fileupdated > lastupdated):
                         raise NotGoingToDownload(_("Not Overwriting, web site is not newer."),'edit-undo.png')
+                    
+                    
         
                 # For update, provide a tmp file copy of the existing epub so
                 # it can't change underneath us.  Now also overwrite for logpage preserve.
@@ -1130,6 +1154,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                 func, args=args,
                 description=desc)
         
+        self.gui.jobs_pointer.start()
         self.gui.status_bar.show_message(_('Starting %d FanFictionDownLoads')%len(book_list),3000)
 
     def update_books_loop(self,book,db=None,
@@ -1224,6 +1249,10 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             cp_plugin = self.gui.iactions['Count Pages']
             cp_plugin.count_statistics(all_ids,prefs['countpagesstats'])
 
+        if prefs['autoconvert'] and options['collision'] != CALIBREONLY:
+            self.gui.status_bar.show_message(_('Starting auto conversion of %d books.')%(len(all_ids)), 3000)
+            self.gui.iactions['Convert Books'].auto_convert_auto_add(all_ids)
+
     def download_list_completed(self, job, options={},merge=False):
         if job.failed:
             self.gui.job_exception(job, dialog_title='Failed to Download Stories')
@@ -1327,7 +1356,6 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         bad_list = sorted(bad_list,key=lambda x : x['listorder'])
         
         self.gui.status_bar.show_message(_('Merging %s books.')%total_good)
-
         
         existingbook = None
         if 'mergebook' in options:
@@ -1385,7 +1413,10 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         if prefs['mark'] or (prefs['errorcol'] != '' and prefs['errorcol'] in custom_columns):
             self.previous = self.gui.library_view.currentIndex() # used by update_books_finish.
             self.gui.status_bar.show_message(_('Adding/Updating %s BAD books.')%len(book_list))
-            label = custom_columns[prefs['errorcol']]['label']
+            if (prefs['errorcol'] != '' and prefs['errorcol'] in custom_columns):
+                label = custom_columns[prefs['errorcol']]['label']
+            else:
+                label = None
             LoopProgressDialog(self.gui,
                                book_list,
                                partial(self.update_error_column_loop, db=self.gui.current_db, label=label),
@@ -1394,12 +1425,10 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                                win_title=_("Update calibre for BAD FanFiction stories"),
                                status_prefix=_("Updated"))
 
-    def update_error_column_loop(self,book,db=None,label='errorcol'):
-        if book['calibre_id']:
-            custom_columns = self.gui.library_view.model().custom_columns
-            if (prefs['errorcol'] != '' and prefs['errorcol'] in custom_columns):
-                logger.debug("add/update bad %s %s %s"%(book['title'],book['url'],book['comment']))
-                db.set_custom(book['calibre_id'], book['comment'], label=label, commit=True)
+    def update_error_column_loop(self,book,db=None,label=None):
+        if book['calibre_id'] and label:
+            logger.debug("add/update bad %s %s %s"%(book['title'],book['url'],book['comment']))
+            db.set_custom(book['calibre_id'], book['comment'], label=label, commit=True)
 
     def add_book_or_update_format(self,book,options,prefs,mi=None):
         db = self.gui.current_db
@@ -1428,8 +1457,18 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             fmts = db.formats(book['calibre_id'], index_is_id=True).split(',')
             for fmt in fmts:
                 if fmt != formmapping[options['fileform']]:
-                    logger.debug("remove f:"+fmt)
+                    logger.debug("deleteotherforms remove f:"+fmt)
                     db.remove_format(book['calibre_id'], fmt, index_is_id=True)#, notify=False
+        elif prefs['autoconvert']:
+            ## 'Convert Book'.auto_convert_auto_add doesn't convert if
+            ## the format is already there.
+            fmt = calibre_prefs['output_format']
+            # delete if there, but not if the format we just made.
+            if fmt != formmapping[options['fileform']] and \
+                    db.has_format(book_id,fmt,index_is_id=True):
+                logger.debug("autoconvert remove f:"+fmt)
+                db.remove_format(book['calibre_id'], fmt, index_is_id=True)#, notify=False
+                
 
         return book_id
 
@@ -1537,8 +1576,15 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                         (custcol,flag) = map( lambda x: x.strip(), custcol.split(",") )
 
                     if meta not in book['all_metadata']:
-                        logger.debug("No value for %s, skipping custom column(%s) update."%(meta,custcol))
-                        continue
+                        # if double quoted, use as a literal value.
+                        if meta[0] == '"' and meta[-1] == '"':
+                            val = meta[1:-1]
+                            logger.debug("No metadata value for %s, setting custom column(%s) literally to %s."%(meta,custcol,val))
+                        else:
+                            logger.debug("No value for %s, skipping custom column(%s) update."%(meta,custcol))
+                            continue
+                    else:
+                        val = book['all_metadata'][meta]    
                     
                     if custcol not in custom_columns:
                         continue
@@ -1550,12 +1596,19 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                         if coldef['datatype'] in ('int','float'): # for favs, etc--site specific metadata.
                             if 'anthology_meta_list' in book and meta in book['anthology_meta_list']:
                                 # re-split list, strip commas, convert to floats, sum up.
-                                val = sum([ float(x.replace(",","")) for x in book['all_metadata'][meta].split(", ") ])
+                                val = sum([ float(x.replace(",","")) for x in val.split(", ") ])
                             else:
-                                val = unicode(book['all_metadata'][meta]).replace(",","")
+                                val = unicode(val).replace(",","")
                         else:
-                            val = book['all_metadata'][meta]
+                            val = val
                         if val != '':
+                            if coldef['datatype'] == 'bool':
+                                if val.lower() in ('t','true','1','yes','y'):
+                                    val = True
+                                elif val.lower() in ('f','false','0','no','n'):
+                                    val = False
+                                else:
+                                    val = None # for tri-state 'booleans'. Yes/No/Null
                             db.set_custom(book_id, val, label=label, commit=False)
 
                     if flag == 'a':
@@ -1569,8 +1622,8 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                         except:
                             pass
 
-                        if book['all_metadata'][meta]:
-                            vallist = [book['all_metadata'][meta]]
+                        if val:
+                            vallist = [val]
                             
                         db.set_custom(book_id, ", ".join(vallist), label=label, commit=False)
 
@@ -1602,7 +1655,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
 
         if 'Generate Cover' in self.gui.iactions and (book['added'] or not prefs['gcnewonly']):
 
-            logger.debug("Do Generate Cover added:%s gcnewonly:%s"%(book['added'],prefs['gcnewonly']))
+            #logger.debug("Do Generate Cover added:%s gcnewonly:%s"%(book['added'],prefs['gcnewonly']))
             
             # force a refresh if generating cover so complex composite
             # custom columns are current and correct
@@ -1645,6 +1698,28 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                 realmi = db.get_metadata(book_id, index_is_id=True)
                 gc_plugin.generate_cover_for_book(realmi,saved_setting_name=setting_name)
 
+                if prefs['gc_polish_cover'] and \
+                        options['fileform'] == "epub" and calibre_version >= (0, 9, 39):
+                    # set cover inside epub from calibre's polish feature
+                    from calibre.ebooks.oeb.polish.main import polish, ALL_OPTS
+                    from calibre.utils.logging import Log
+                    from collections import namedtuple
+
+                    # Couldn't find a better way to get the cover path.
+                    cover_path = os.path.join(db.library_path, db.path(book_id, index_is_id=True), 'cover.jpg')
+                    data = {'cover':cover_path}
+                    #print("cover_path:%s"%cover_path)
+                    opts = ALL_OPTS.copy()
+                    opts.update(data)
+                    O = namedtuple('Options', ' '.join(ALL_OPTS.iterkeys()))
+                    opts = O(**opts)
+                
+                    log = Log(level=Log.DEBUG)
+                    outfile = db.format_abspath(book_id, formmapping[options['fileform']], index_is_id=True)
+                    #print("polish cover outfile:%s"%outfile)
+                    polish({outfile:outfile}, opts, log, logger.info)
+                
+
     def get_clean_reading_lists(self,lists):
         if lists == None or lists.strip() == "" :
             return []
@@ -1733,6 +1808,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         book['end'] = None
         book['comment'] = '' # note this is a comment on the d/l or update.
         book['url'] = ''
+        book['site'] = ''
         book['added'] = False
         return book
     
@@ -1809,13 +1885,15 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             book['status'] = _('Not Found')
         else:
             # get normalized url or None.
-            book['url'] = self.is_good_downloader_url(url)
-            if book['url'] == None:
+            urlsitetuple = adapters.getNormalStoryURLSite(url)
+            if urlsitetuple == None:
                 book['url'] = url
                 book['comment'] = _("URL is not a valid story URL.")
                 book['good'] = False
                 book['icon']='dialog_error.png'
                 book['status'] = _('Bad URL')
+            else:
+                (book['url'],book['site'])=urlsitetuple
     
     def get_story_url(self, db, book_id=None, path=None):
         if book_id == None:

calibre-plugin/jobs.py

@@ -93,16 +93,13 @@ def do_download_worker(book_list, options,
         logger.info('Logfile for book ID %s (%s)'%(book_id, job._book['title']))
         logger.info(job.details)
 
+
+
         if count >= total:
-            # All done!  Output some lists for convenience of some users.
-            logger.info("Successfully downloaded:")
-            for book in book_list:
-                if book['good']:
-                    logger.info("%s %s"%(book['title'],book['url']))
-            logger.info("\nUnsuccessful:")
-            for book in book_list:
-                if not book['good']:
-                    logger.info("%s %s"%(book['title'],book['url']))
+            logger.info("\nSuccessful:\n%s\n"%("\n".join([book['url'] for book in 
+                                                      filter(lambda x: x['good'], book_list) ] ) ) )
+            logger.info("\nUnsuccessful:\n%s\n"%("\n".join([book['url'] for book in 
+                                                        filter(lambda x: not x['good'], book_list) ] ) ) )
             break
 
     server.close()

calibre-plugin/prefs.py

@@ -34,6 +34,7 @@ default_prefs['suppressauthorsort'] = False
 default_prefs['suppresstitlesort'] = False
 default_prefs['mark'] = False
 default_prefs['showmarked'] = False
+default_prefs['autoconvert'] = False
 default_prefs['urlsfromclip'] = True
 default_prefs['updatedefault'] = True
 default_prefs['fileform'] = 'epub'
@@ -56,6 +57,7 @@ default_prefs['addtolistsonread'] = False
 default_prefs['gcnewonly'] = False
 default_prefs['gc_site_settings'] = {}
 default_prefs['allow_gc_from_ini'] = True
+default_prefs['gc_polish_cover'] = False
 
 default_prefs['countpagesstats'] = []
 

defaults.ini

@@ -182,6 +182,11 @@ extratags: FanFiction
 ## useful if pulling large numbers of stories or if the site is slow.
 #slow_down_sleep_time:0.5
 
+## How long to wait for each HTTP connection to finish.  Longer times
+## are better for sites that are slow to respond.  Shorter times
+## prevent excessive wait when your network or the site is down.
+connect_timeout:60.0
+
 ## For use only with stand-alone CLI version--run a command on the
 ## generated file after it's produced.  All of the titlepage_entries
 ## values are available, plus output_filename.
@@ -538,6 +543,13 @@ extratags: FanFiction,Testing,HTML
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+## archiveofourown.org stories allow chapters to be added out of
+## order.  So the newest chapter may not be the last one.  FFDL update
+## doesn't like that.  If do_update_hook is uncommented and set true,
+## the adapter will discard all existing chapters from the newest one
+## on when updating to enforce accurate chapters.
+#do_update_hook:false
+
 ## AO3 adapter defines a few extra metadata entries.
 ## If there's ever more than 4 series, add series04,series04Url etc.
 extra_valid_entries:fandoms,freeformtags,freefromtags,ao3categories,comments,kudos,hits,bookmarks,collections,series00,series01,series02,series03,series00Url,series01Url,series02Url,series03Url
@@ -562,11 +574,6 @@ include_in_freefromtags:freeformtags
 #extra_subject_tags:fandoms,freeformtags,ao3categories
 
 [ashwinder.sycophanthex.com]
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-extracharacters:Severus Snape,Hermione Granger
-extraships:Severus Snape/Hermione Granger
-
 ## 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
@@ -574,6 +581,11 @@ extraships:Severus Snape/Hermione Granger
 #username:YourName
 #password:yourpassword
 
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+extracharacters:Severus Snape,Hermione Granger
+extraships:Severus Snape/Hermione Granger
+
 [asr3.slashzone.org]
 ## Site dedicated to these categories/characters/ships
 extracategories:The Sentinel
@@ -584,9 +596,6 @@ extracategories:The Sentinel
 #is_adult:true
 
 [bloodties-fans.com]
-## Site dedicated to these categories/characters/ships
-extracategories:Blood Ties
-
 ## 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
@@ -599,6 +608,9 @@ extracategories:Blood Ties
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Blood Ties
+
 [buffynfaith.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:Buffy: The Vampire Slayer
@@ -609,9 +621,6 @@ extracategories:Buffy: The Vampire Slayer
 #is_adult:true
 
 [castlefans.org]
-## Site dedicated to these categories/characters/ships
-extracategories:Castle
-
 ## 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
@@ -624,6 +633,9 @@ extracategories:Castle
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Castle
+
 [chaos.sycophanthex.com]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
@@ -636,10 +648,23 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 
 [dark-solace.org]
 ## Site dedicated to these categories/characters/ships
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Some sites also require the user to confirm they are adult for
+## adult content.  In commandline version, this should go in your
+## personal.ini, not defaults.ini.
+#is_adult:true
+
 extracategories:Buffy: The Vampire Slayer
 extracharacters:Buffy, Spike
 extraships:Spike/Buffy
 
+[dramione.org]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
 ## commandline version, this should go in your personal.ini, not
@@ -652,24 +677,11 @@ extraships:Spike/Buffy
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
-[dramione.org]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
 extracharacters:Draco Malfoy,Hermione Granger
 extraships:Draco Malfoy/Hermione Granger
 
-## Some sites require login (or login for some rated stories) The
-## program can prompt you, or you can save it in config.  In
-## commandline version, this should go in your personal.ini, not
-## defaults.ini.
-#username:YourName
-#password:yourpassword
-
-## Some sites also require the user to confirm they are adult for
-## adult content.  In commandline version, this should go in your
-## personal.ini, not defaults.ini.
-#is_adult:true
-
 ## some sites include images that we don't ever want becoming the
 ## cover image.  This lets you exclude them.
 cover_exclusion_regexp:/images/.*?ribbon.gif
@@ -712,22 +724,19 @@ cliches_label:Character Cliches
 extracategories:Lord of the Rings
 
 [erosnsappho.sycophanthex.com]
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 ## some sites include images that we don't ever want becoming the
 ## cover image.  This lets you exclude them.
 cover_exclusion_regexp:/images/.*?ribbon.gif
 
 [fanfiction.mugglenet.com]
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-
 ## 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.
@@ -740,10 +749,10 @@ extracategories:Harry Potter
 #username:YourName
 #password:yourpassword
 
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 [fanfic.potterheadsanonymous.com]
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-
 ## 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.
@@ -756,16 +765,19 @@ extracategories:Harry Potter
 #username:YourName
 #password:yourpassword
 
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 [fanfiction.portkey.org]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
 extraships:Harry Potter/Hermione Granger
 
-## 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
-
 [fanfiction.tenhawkpresents.com]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -810,18 +822,26 @@ dislikes_label:Dislikes
 ## Clear FanFiction from defaults, site is original fiction.
 extratags:
 
-extra_valid_entries:size,universe,codes
-#extra_titlepage_entries:size,universe,codes
+extra_valid_entries:size,universe,universeUrl,universeHTML,codes,notice
+#extra_titlepage_entries:size,universeHTML,codes,notice
 
 size_label:Size
 universe_label:Universe
+universeUrl_label:Universe URL
+universeHTML_label:Universe
 codes_label:Codes
+notice_label:Notice
+
+## 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
 
 [grangerenchanted.com]
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-extracharacters:Hermione Granger
-
 ## 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
@@ -834,6 +854,10 @@ extracharacters:Hermione Granger
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+extracharacters:Hermione Granger
+
 ## Extra metadata that this adapter knows about.  See [dramione.org]
 ## for examples of how to use them.
 extra_valid_entries:read,reviews
@@ -870,18 +894,15 @@ extracharacters:Kirk,Spock
 extraships:Kirk/Spock
 
 [lumos.sycophanthex.com]
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-
 ## 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
 
-[merlinfic.dtwins.co.uk]
 ## Site dedicated to these categories/characters/ships
-extracategories:Merlin
+extracategories:Harry Potter
 
+[merlinfic.dtwins.co.uk]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
 ## commandline version, this should go in your personal.ini, not
@@ -894,6 +915,9 @@ extracategories:Merlin
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Merlin
+
 [national-library.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:West Wing
@@ -905,24 +929,32 @@ extracategories:NCIS
 [netraptor.org]
 
 [nfacommunity.com]
-## Site dedicated to these categories/characters/ships
-extracategories:NCIS
-
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:NCIS
+
 [nha.magical-worlds.us]
 ## Site dedicated to these categories/characters/ships
 extracategories:Buffy: The Vampire Slayer
 extracharacters:Willow
 
 [occlumency.sycophanthex.com]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
 extracharacters:Severus Snape
 
+[onedirectionfanfiction.com]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
 ## commandline version, this should go in your personal.ini, not
@@ -930,10 +962,15 @@ extracharacters:Severus Snape
 #username:YourName
 #password:yourpassword
 
-[onedirectionfanfiction.com]
+## Some sites also require the user to confirm they are adult for
+## adult content.  In commandline version, this should go in your
+## personal.ini, not defaults.ini.
+#is_adult:true
+
 ## Site dedicated to these categories/characters/ships
 extracategories:One Direction
 
+[pommedesang.com]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
 ## commandline version, this should go in your personal.ini, not
@@ -946,40 +983,27 @@ extracategories:One Direction
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
-[pommedesang.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Anita Blake Vampire Hunter 
 
-## Some sites require login (or login for some rated stories) The
-## program can prompt you, or you can save it in config.  In
-## commandline version, this should go in your personal.ini, not
-## defaults.ini.
-#username:YourName
-#password:yourpassword
-
-## Some sites also require the user to confirm they are adult for
-## adult content.  In commandline version, this should go in your
-## personal.ini, not defaults.ini.
+[ponyfictionarchive.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
 
-[ponyfictionarchive.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:My Little Pony: Friendship is Magic
 
+[pretendercentre.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
 
-[pretendercentre.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:The Pretender
 
-## 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
-
 [samdean.archive.nu]
 ## Site dedicated to these categories/characters/ships
 extracategories:Supernatural
@@ -987,9 +1011,6 @@ extracharacters:Sam,Dean
 extraships:Sam/Dean
 
 [scarhead.net]
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-
 ## 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
@@ -1002,6 +1023,9 @@ extracategories:Harry Potter
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 [sg1-heliopolis.com]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
@@ -1032,9 +1056,6 @@ extracharacters:Draco Malfoy,Harry Potter
 extraships:Harry Potter/Draco Malfoy
 
 [thehookupzone.net]
-## Site dedicated to these categories/characters/ships
-extracategories:Criminal Minds
-
 ## 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
@@ -1047,6 +1068,9 @@ extracategories:Criminal Minds
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Criminal Minds
+
 [themasque.net]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -1061,9 +1085,6 @@ extracategories:Criminal Minds
 #is_adult:true
 
 [thequidditchpitch.org]
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-
 ## 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
@@ -1076,50 +1097,71 @@ extracategories:Harry Potter
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 [tokra.fandomnet.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
 ## Site dedicated to these categories/characters/ships
 extracategories:Stargate: SG-1
 
-## 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.
+[trekiverse.org]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Some sites also require the user to confirm they are adult for
+## adult content.  In commandline version, this should go in your
+## personal.ini, not defaults.ini.
 #is_adult:true
 
-[www.adastrafanfic.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Star Trek
 
+extra_valid_entries:awards
+awards_label:Awards
+
+cover_exclusion_regexp:art/.*Awards.jpg
+
+[www.adastrafanfic.com]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Star Trek
+
 [www.dracoandginny.com]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Some sites also require the user to confirm they are adult for
+## adult content.  In commandline version, this should go in your
+## personal.ini, not defaults.ini.
+#is_adult:true
+
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
 extracharacters:Draco Malfoy,Ginny Weasley
 extraships:Draco Malfoy/Ginny Weasley
 
-## Some sites require login (or login for some rated stories) The
-## program can prompt you, or you can save it in config.  In
-## commandline version, this should go in your personal.ini, not
-## defaults.ini.
-#username:YourName
-#password:yourpassword
-
-## Some sites also require the user to confirm they are adult for
-## adult content.  In commandline version, this should go in your
-## personal.ini, not defaults.ini.
-#is_adult:true
-
 [www.thealphagate.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Stargate: SG-1
 
 [www.checkmated.com]
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-
 ## 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
@@ -1127,6 +1169,9 @@ extracategories:Harry Potter
 #username:YourName
 #password:yourpassword
 
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 [www.destinysgateway.com]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
@@ -1134,11 +1179,6 @@ extracategories:Harry Potter
 #is_adult:true
 
 [www.dokuga.com]
-## Site dedicated to these categories/characters/ships
-extracategories:InuYasha
-extracharacters:Sesshoumaru,Kagome
-extraships:Sesshoumaru/Kagome
-
 ## 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
@@ -1146,6 +1186,11 @@ extraships:Sesshoumaru/Kagome
 #username:YourName
 #password:yourpassword
 
+## Site dedicated to these categories/characters/ships
+extracategories:InuYasha
+extracharacters:Sesshoumaru,Kagome
+extraships:Sesshoumaru/Kagome
+
 [www.dotmoon.net]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -1175,6 +1220,11 @@ user_agent:
 ## Change this to false to use them anyway.
 never_make_cover: true
 
+## fanfiction.net is blocking people more aggressively.  If you
+## download fewer stories less often you can likely get by with
+## reducing this sleep.
+slow_down_sleep_time:4
+
 ## Extra metadata that this adapter knows about.  See [dramione.org]
 ## for examples of how to use them.
 extra_valid_entries:reviews,favs,follows
@@ -1183,13 +1233,20 @@ extra_valid_entries:reviews,favs,follows
 ## to be romantic pairings.
 ships_label:Pairings
 
-## Date formats used by FFDL.  Published and Update don't have time.
+## Date formats used by FFDL.  Published and Update don't usually have
+## time, but they do now on ffnet.
 ## See http://docs.python.org/library/datetime.html#strftime-strptime-behavior
 ## Note that ini format requires % to be escaped as %%.
 #dateCreated_format:%%Y-%%m-%%d %%H:%%M:%%S
 datePublished_format:%%Y-%%m-%%d %%H:%%M:%%S
 dateUpdated_format:%%Y-%%m-%%d %%H:%%M:%%S
 
+## ffnet used to have a tendency to send out update notices in email
+## before all their servers were showing the update on the first
+## chapter.  It generates another server request and doesn't seem to
+## be needed lately, so now default it to off.
+check_next_chapter:false
+
 [www.fanfiktion.de]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -1201,14 +1258,14 @@ dateUpdated_format:%%Y-%%m-%%d %%H:%%M:%%S
 [www.ficbook.net]
 
 [www.fictionalley.org]
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 ## fictionally.org storyIds are not unique.  Combine with authorId.
 output_filename: ${title}-${siteabbrev}_${authorId}_${storyId}${formatext}
 
@@ -1234,19 +1291,6 @@ extra_valid_entries:reviews,favs,follows
 #password:yourpassword
 
 [www.fimfiction.net]
-## Site dedicated to these categories/characters/ships
-extracategories:My Little Pony: Friendship is Magic
-
-## Extra metadata that this adapter knows about.  See [dramione.org]
-## for examples of how to use them.
-extra_valid_entries:likes,dislikes,views,total_views,short_description,groups
-likes_label:Likes
-dislikes_label:Dislikes
-views_label:Highest Single Chapter Views
-total_views_label:Total Views
-short_description_label:Short Summary
-groups_label:Groups
-
 ## 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.
@@ -1264,38 +1308,63 @@ groups_label:Groups
 ## when updating to enforce accurate chapters.
 #do_update_hook:false
 
-[www.harrypotterfanfiction.com]
 ## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
+extracategories:My Little Pony: Friendship is Magic
 
+## Extra metadata that this adapter knows about.  See [dramione.org]
+## for examples of how to use them.
+extra_valid_entries:likes,dislikes,views,total_views,short_description,groups,groupsUrl,groupsHTML,prequel,prequelUrl,prequelHTML,sequels,sequelsUrl,sequelsHTML
+likes_label:Likes
+dislikes_label:Dislikes
+views_label:Highest Single Chapter Views
+total_views_label:Total Views
+short_description_label:Short Summary
+groups_label:Groups
+groupsUrl_label:Groups URLs
+groupsHTML_label:Groups
+prequel_label:Prequel
+prequelUrl_label:Prequel URL
+prequelHTML_label:Prequel
+sequels_label:Sequels
+sequelsUrl_label:Sequel URLs
+sequelsHTML_label:Sequels
+
+keep_in_order_sequels:true
+keep_in_order_sequelsUrl:true
+keep_in_order_groups:true
+keep_in_order_groupsUrl:true
+
+## Assume entryUrl, apply to "<a class='%slink' href='%s'>%s</a>" to
+## make entryHTML.
+make_linkhtml_entries:prequel,sequels,groups
+
+[www.harrypotterfanfiction.com]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 [www.henneth-annun.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:The Hobbit
 
 [www.hpfandom.net]
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 [www.hpfanficarchive.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
 
 [www.ik-eternal.net]
-## Site dedicated to these categories/characters/ships
-extracategories:InuYasha
-extracharacters:InuYasha,Kagome
-extraships:InuYasha/Kagome
-
 ## 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
@@ -1308,30 +1377,35 @@ extraships:InuYasha/Kagome
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:InuYasha
+extracharacters:InuYasha,Kagome
+extraships:InuYasha/Kagome
+
 [www.jlaunlimited.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:JLA
 
 [www.libraryofmoria.com]
-## Site dedicated to these categories/characters/ships
-extracategories:Lord of the Rings
-
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Lord of the Rings
+
 [www.mediaminer.org]
 
 [www.midnightwhispers.ca]
-## Site dedicated to these categories/characters/ships
-extracategories:Queer as Folk
-
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Queer as Folk
+
 ## some sites include images that we don't ever want becoming the
 ## cover image.  This lets you exclude them.
 cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
@@ -1346,10 +1420,6 @@ extracategories:CSI
 extraships:Nick Stokes/Greg Sanders
 
 [www.phoenixsong.net]
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-extraships:Harry Potter/Ginny Weasley
-
 ## 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
@@ -1360,9 +1430,13 @@ extraships:Harry Potter/Ginny Weasley
 ## phoenixsong.net, oddly, can have high rated chapters (login
 ## required) in the middle of a lower rated story.  Use this to force
 ## FFDL to always login to phoenixsong.net so those stories download
-## correctly.
+## correctly.  If you have a login, this is recommended.
 #force_login:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+extraships:Harry Potter/Ginny Weasley
+
 [www.potionsandsnitches.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
@@ -1385,17 +1459,15 @@ extracategories:Psych
 #is_adult:true
 
 [www.qaf-fic.com]
-## Site dedicated to these categories/characters/ships
-extracategories:Queer as Folk
-
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Queer as Folk
+
 [www.restrictedsection.org]
-extracategories:Harry Potter
-extragenres:Erotica
 ## 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
@@ -1403,20 +1475,21 @@ extragenres:Erotica
 #username:YourName
 #password:yourpassword
 
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+extragenres:Erotica
+
 [www.scarvesandcoffee.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
+
 ## Site dedicated to these categories/characters/ships
 extracategories:Glee
 extracharacters:Kurt Hummel,Blaine Anderson
 
-## 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.simplyundeniable.com]
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-
 ## 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
@@ -1424,15 +1497,18 @@ extracategories:Harry Potter
 #username:YourName
 #password:yourpassword
 
-[www.sinful-desire.org]
 ## Site dedicated to these categories/characters/ships
-extracategories:Supernatural
+extracategories:Harry Potter
 
+[www.sinful-desire.org]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Supernatural
+
 [www.siye.co.uk]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
@@ -1440,25 +1516,26 @@ extracharacters:Harry Potter,Ginny Weasley
 extraships:Harry Potter/Ginny Weasley
 
 [www.squidge.org/peja]
-# www.squidge.org/peja calls it Fandom <shrug>
+## www.squidge.org/peja calls it Fandom <shrug>
 category_label:Fandom
-# Remove numWords -- www.squidge.org/peja word counts are inaccurate
+
+## Remove numWords -- www.squidge.org/peja word counts are inaccurate
 titlepage_entries: seriesHTML,category,genre,language,characters,ships,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,description
 
 [www.squidge.org/peja:txt]
-## Add URLs since there aren't links.
-# Remove numWords -- www.squidge.org/peja word counts are inaccurate
+## Add URLs since there aren't links and remove numWords --
+## www.squidge.org/peja word counts are inaccurate
 titlepage_entries: series,seriesUrl,category,genre,language,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,storyUrl, authorUrl, description
 
 [www.storiesofarda.com]
-## Site dedicated to these categories/characters/ships
-extracategories:Lord of the Rings
-
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Lord of the Rings
+
 [www.thepetulantpoetess.com]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -1501,9 +1578,6 @@ collect_series: false
 extracategories:Twilight
 
 [www.twilighted.net]
-## Site dedicated to these categories/characters/ships
-extracategories:Twilight
-
 ## 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
@@ -1511,13 +1585,13 @@ extracategories:Twilight
 #username:YourName
 #password:yourpassword
 
+## Site dedicated to these categories/characters/ships
+extracategories:Twilight
+
 ## twilighted.net (ab)uses series as personal reading lists.
 collect_series: false
 
 [www.twiwrite.net]
-## Site dedicated to these categories/characters/ships
-extracategories:Twilight
-
 ## 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
@@ -1525,20 +1599,23 @@ extracategories:Twilight
 #username:YourName
 #password:yourpassword
 
+## Site dedicated to these categories/characters/ships
+extracategories:Twilight
+
 ## twiwrite.net (ab)uses series as personal reading lists.
 collect_series: false
 
 [www.walkingtheplank.org]
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-extracharacters:Severus Snape,Harry Potter
-extraships:Severus Snape/Harry Potter
-
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+extracharacters:Severus Snape,Harry Potter
+extraships:Severus Snape/Harry Potter
+
 [www.whofic.com]
 
 [www.wizardtales.net]
@@ -1560,14 +1637,14 @@ extracategories:X-Men Movie
 extracharacters:Wolverine,Rogue
 
 [www.wraithbait.com]
-## Site dedicated to these categories/characters/ships
-extracategories:Stargate: Atlantis
-
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Stargate: Atlantis
+
 [overrides]
 ## It may sometimes be useful to override all of the specific format,
 ## site and site:format sections in your private configuration.  For

fanficdownloader/adapters/__init__.py

@@ -121,6 +121,8 @@ import adapter_simplyundeniablecom
 import adapter_scarheadnet
 import adapter_fictionpadcom
 import adapter_storiesonlinenet
+import adapter_trekiverseorg
+import adapter_literotica
 
 ## This bit of complexity allows adapters to be added by just adding
 ## importing.  It eliminates the long if/else clauses we used to need
@@ -144,6 +146,13 @@ for x in imports():
             __domain_map[site]=cls
 
 def getNormalStoryURL(url):
+    r = getNormalStoryURLSite(url)
+    if r:
+        return r[0]
+    else:
+        return None
+
+def getNormalStoryURLSite(url):
     if not getNormalStoryURL.__dummyconfig:
         getNormalStoryURL.__dummyconfig = Configuration("test1.com","EPUB")
     # pulling up an adapter is pretty low over-head.  If
@@ -151,10 +160,11 @@ def getNormalStoryURL(url):
     try:
         adapter = getAdapter(getNormalStoryURL.__dummyconfig,url)
         url = adapter.url
+        site = adapter.getSiteDomain()
         del adapter
-        return url
+        return (url,site)
     except:
-        return None;
+        return None
 
 # kludgey function static/singleton
 getNormalStoryURL.__dummyconfig = None
@@ -191,7 +201,7 @@ def getConfigSectionFor(url):
 
 def getClassFor(url):
     ## fix up leading protocol.
-    fixedurl = re.sub(r"(?i)^[htps]+[:/]+","http://",url.strip())
+    fixedurl = re.sub(r"(?i)^[htp]+(s?)[:/]+",r"http\1://",url.strip())
     if not fixedurl.startswith("http"):
         fixedurl = "http://%s"%url
     ## remove any trailing '#' locations.

fanficdownloader/adapters/adapter_archiveofourownorg.py

@@ -77,14 +77,14 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
         # The site domain.  Does have www here, if it uses it.
         return 'archiveofourown.org'
 
-    @classmethod
+    @classmethod
     def getSiteExampleURLs(self):
         return "http://"+self.getSiteDomain()+"/works/123456 http://"+self.getSiteDomain()+"/collections/Some_Archive/works/123456 http://"+self.getSiteDomain()+"/works/123456/chapters/78901"
 
     def getSiteURLPattern(self):
         # http://archiveofourown.org/collections/Smallville_Slash_Archive/works/159770
         # Discard leading zeros from story ID numbers--AO3 doesn't use them in it's own chapter URLs.
-        return re.escape("http://")+re.escape(self.getSiteDomain())+r"(/collections/[^/]+)?/works/0*(?P<id>\d+)"
+        return r"https?://"+re.escape(self.getSiteDomain())+r"(/collections/[^/]+)?/works/0*(?P<id>\d+)"
         
     ## Login
     def needToLoginCheck(self, data):
@@ -177,19 +177,28 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
                 self.story.addToList('authorUrl','http://'+self.host+a['href'])
                 self.story.addToList('author',a.text)
 
+        newestChapter = None
+        self.newestChapterNum = None # save for comparing during update.
+        # Scan all chapters to find the oldest and newest, on AO3 it's
+        # possible for authors to insert new chapters out-of-order or
+        # change the dates of earlier ones by editing them--That WILL
+        # break epub update.
         # Find the chapters:
         chapters=soup.findAll('a', href=re.compile(r'/works/'+self.story.getMetadata('storyId')+"/chapters/\d+$"))
         self.story.setMetadata('numChapters',len(chapters))
         logger.debug("numChapters: (%s)"%self.story.getMetadata('numChapters'))
-        for x in range(0,len(chapters)):
-            # just in case there's tags, like <i> in chapter titles.
-            chapter=chapters[x]
-            if len(chapters)==1:
-                self.chapterUrls.append((self.story.getMetadata('title'),'http://'+self.host+chapter['href']+addurl))
-            else:
+        if len(chapters)==1:
+            self.chapterUrls.append((self.story.getMetadata('title'),'http://'+self.host+chapters[0]['href']+addurl))
+        else:
+            for index, chapter in enumerate(chapters):
+                # strip just in case there's tags, like <i> in chapter titles.
                 self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+chapter['href']+addurl))
-
-
+                # (2013-09-21)
+                date = stripHTML(chapter.findNext('span'))[1:-1]
+                chapterDate = makeDate(date,self.dateformat)
+                if newestChapter == None or chapterDate > newestChapter:
+                    newestChapter = chapterDate
+                    self.newestChapterNum = index
 
         a = metasoup.find('blockquote',{'class':'userstuff'})
         if a != None:
@@ -299,6 +308,12 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
                     self.setSeries(series_name, series_index)
                     self.story.setMetadata('seriesUrl',series_url)
 
+    def hookForUpdates(self,chaptercount):
+        if self.oldchapters and len(self.oldchapters) > self.newestChapterNum:
+            print("Existing epub has %s chapters\nNewest chapter is %s.  Discarding old chapters from there on."%(len(self.oldchapters), self.newestChapterNum+1))
+            self.oldchapters = self.oldchapters[:self.newestChapterNum]
+        return len(self.oldchapters)
+            
     # grab the text for an individual chapter.
     def getChapterText(self, url):
         logger.debug('Getting chapter text from: %s' % url)

fanficdownloader/adapters/adapter_buffynfaithnet.py

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

fanficdownloader/adapters/adapter_fanfictionnet.py

@@ -57,6 +57,8 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
             ## accept m(mobile)url, but use www.
             self.origurl = self.origurl.replace("https://m.","https://www.")
 
+        self.opener.addheaders.append(('Referer',self.origurl))
+
     @staticmethod
     def getSiteDomain():
         return 'www.fanfiction.net'
@@ -72,6 +74,13 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
     def getSiteURLPattern(self):
         return r"https?://(www|m)?\.fanfiction\.net/s/\d+(/\d+)?(/|/[^/]+)?/?$"
 
+    def _fetchUrl(self,url):
+        time.sleep(1.0) ## ffnet(and, I assume, fpcom) tends to fail
+                        ## more if hit too fast.  This is in
+                        ## additional to what ever the
+                        ## slow_down_sleep_time setting is.
+        return BaseSiteAdapter._fetchUrl(self,url)
+
     def extractChapterUrlsAndMetadata(self):
 
         # fetch the chapter.  From that we will get almost all the
@@ -98,28 +107,31 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         if "not found. Please check to see you are not using an outdated url." in data:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  'Chapter not found. Please check to see you are not using an outdated url.'" % url)
 
-        try:
-            # rather nasty way to check for a newer chapter.  ffnet has a
-            # tendency to send out update notices in email before all
-            # their servers are showing the update on the first chapter.
+        if self.getConfig('check_next_chapter'):
             try:
-                chapcount = len(soup.find('select', { 'name' : 'chapter' } ).findAll('option'))
-            # get chapter part of url.
+                ## ffnet used to have a tendency to send out update
+                ## notices in email before all their servers were
+                ## showing the update on the first chapter.  It
+                ## generates another server request and doesn't seem
+                ## to be needed lately, so now default it to off.
+                try:
+                    chapcount = len(soup.find('select', { 'name' : 'chapter' } ).findAll('option'))
+                # get chapter part of url.
+                except:
+                    chapcount = 1
+                chapter = url.split('/',)[5]
+                tryurl = "https://%s/s/%s/%d/"%(self.getSiteDomain(),
+                                                self.story.getMetadata('storyId'),
+                                                chapcount+1)
+                logger.debug('=Trying newer chapter: %s' % tryurl)
+                newdata = self._fetchUrl(tryurl)
+                if "not found. Please check to see you are not using an outdated url." \
+                        not in newdata:
+                    logger.debug('=======Found newer chapter: %s' % tryurl)
+                    soup = bs.BeautifulSoup(newdata)
             except:
-                chapcount = 1
-            chapter = url.split('/',)[5]
-            tryurl = "https://%s/s/%s/%d/"%(self.getSiteDomain(),
-                                            self.story.getMetadata('storyId'),
-                                            chapcount+1)
-            logger.debug('=Trying newer chapter: %s' % tryurl)
-            newdata = self._fetchUrl(tryurl)
-            if "not found. Please check to see you are not using an outdated url." \
-                    not in newdata:
-                logger.debug('=======Found newer chapter: %s' % tryurl)
-                soup = bs.BeautifulSoup(newdata)
-        except:
-            pass
-        
+                pass
+            
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"^/u/\d+"))
         self.story.setMetadata('authorId',a['href'].split('/')[2])
@@ -157,7 +169,7 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
                 
                 
             
-        a = soup.find('a', href='http://www.fictionratings.com/')
+        a = soup.find('a', href=re.compile(r'https?://www\.fictionratings\.com/'))
         rating = a.string
         if 'Fiction' in rating: # if rating has 'Fiction ', strip that out for consistency with past.
             rating = rating[8:]
@@ -275,7 +287,7 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         return
 
     def getChapterText(self, url):
-        time.sleep(5.0) ## ffnet(and, I assume, fpcom) tends to fail
+        time.sleep(4.0) ## ffnet(and, I assume, fpcom) tends to fail
                         ## more if hit too fast.  This is in
                         ## additional to what ever the
                         ## slow_down_sleep_time setting is.

fanficdownloader/adapters/adapter_fimfictionnet.py

@@ -101,7 +101,7 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
         # if "/images/missing_story.png" in data:
         #     raise exceptions.StoryDoesNotExist(self.url)
         
-        if "This story has been marked as having adult content." in data:
+        if "This story has been marked as having adult content. Please click below to confirm you are of legal age to view adult material in your country." in data:
             raise exceptions.AdultCheckRequired(self.url)
         
         if self.password:
@@ -249,11 +249,35 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
                     value = unicode(value)
                 self.story.setMetadata(metakey, value)
 
-        rawGroupList = soup.find('ul', {'id':'story_group_list'})
-        if rawGroupList is not None:
-            for groupName in rawGroupList.findAll('a', {'href':re.compile('^/group/')}):
+        ## Groups and sequels code from FaceDeer
+        allGroupLists = soup.findAll('ul', {'id':'story_group_list'})
+        for groupList in allGroupLists:
+            for groupName in groupList.findAll('a', {'href':re.compile('^/group/')}):
+                self.story.addToList("groupsUrl", 'http://'+self.host+groupName["href"]) 
                 self.story.addToList("groups",stripHTML(groupName).replace(',', ';'))
-            
+
+        sequelStoryHeader = soup.find('h1', {'class':'header-stories'}, text="Sequels")
+        if not sequelStoryHeader == None:
+            sequelContainer = sequelStoryHeader.parent.parent
+            for sequel in sequelContainer.findAll('a', {'class':'story_link'}):
+                self.story.addToList("sequelsUrl", 'http://'+self.host+sequel["href"]) 
+                self.story.addToList("sequels", stripHTML(sequel).replace(',', ';'))
+                
+        #The link to the prequel is embedded in the description text, so erring
+        #on the side of caution and wrapping this whole thing in a try block.
+        #If anything goes wrong this probably wasn't a valid prequel link.
+        try:
+            description = soup.find('div', {'class':'description'})
+            firstHR = description.find("hr")
+            nextSib = firstHR.nextSibling
+            if "This story is a sequel to" in nextSib.string:
+                link = nextSib.nextSibling
+                if link.name == "a":
+                    self.story.setMetadata("prequelUrl", 'http://'+self.host+link["href"])
+                    self.story.setMetadata("prequel", stripHTML(link))
+        except:
+            pass
+        
     def hookForUpdates(self,chaptercount):
         if self.oldchapters and len(self.oldchapters) > self.newestChapterNum:
             print("Existing epub has %s chapters\nNewest chapter is %s.  Discarding old chapters from there on."%(len(self.oldchapters), self.newestChapterNum+1))

fanficdownloader/adapters/adapter_finestoriescom.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2012 Fanficdownloader team
+# Copyright 2013 Fanficdownloader team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -37,11 +37,6 @@ class FineStoriesComAdapter(BaseSiteAdapter):
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
 
-        self.decode = ["Windows-1252",
-                       "utf8"] # 1252 is a superset of iso-8859-1.
-                               # Most sites that claim to be
-                               # iso-8859-1 (and some that claim to be
-                               # utf8) are really windows-1252.
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
@@ -51,7 +46,6 @@ class FineStoriesComAdapter(BaseSiteAdapter):
         if 'storyInfo' in self.story.getMetadata('storyId'):
             self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
         
-        
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/s/storyInfo.php?id='+self.story.getMetadata('storyId'))
         

fanficdownloader/adapters/adapter_hpfanficarchivecom.py

@@ -128,23 +128,22 @@ class HPFanficArchiveComAdapter(BaseSiteAdapter):
         # <span class="label">Rated:</span> NC-17<br /> etc
         labels = soup.findAll('span',{'class':'label'})
         for labelspan in labels:
-            value = labelspan.nextSibling
+            val = labelspan.nextSibling
+            value = unicode('')
+            while val and not defaultGetattr(val,'class') == 'label':
+                value += unicode(val)
+                val = val.nextSibling
             label = labelspan.string
+            #print("label:%s\nvalue:%s"%(label,value))
 
             if 'Summary' in label:
-                ## Everything until the next span class='label'
-                svalue = ""
-                while not defaultGetattr(value,'class') == 'label':
-                    svalue += str(value)
-                    value = value.nextSibling
-                self.setDescription(url,svalue)
-                #self.story.setMetadata('description',stripHTML(svalue))
+                self.setDescription(url,value)
 
             if 'Rated' in label:
-                self.story.setMetadata('rating', value)
+                self.story.setMetadata('rating', stripHTML(value))
 
             if 'Word count' in label:
-                self.story.setMetadata('numWords', value)
+                self.story.setMetadata('numWords', stripHTML(value))
 
             if 'Categories' in label:
                 cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
@@ -167,7 +166,7 @@ class HPFanficArchiveComAdapter(BaseSiteAdapter):
                     self.story.addToList('warnings',warning.string)
 
             if 'Completed' in label:
-                if 'Yes' in value:
+                if 'Yes' in stripHTML(value):
                     self.story.setMetadata('status', 'Completed')
                 else:
                     self.story.setMetadata('status', 'In-Progress')

fanficdownloader/adapters/adapter_literotica.py

@@ -0,0 +1,237 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2013 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+logger = logging.getLogger(__name__)
+import re
+import urllib2
+import urlparse
+import time
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter, makeDate
+
+class LiteroticaSiteAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["utf8",
+                       "Windows-1252"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        
+        self.story.setMetadata('siteabbrev','litero')
+
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2])
+        
+        self.origurl = url
+        if "http://www.i." in self.origurl:
+            ## accept m(mobile)url, but use www.
+            self.origurl = self.origurl.replace("http://www.i.","http://www.")
+
+        # normalized story URL.
+        self._setURL("http://"+self.getSiteDomain()\
+                         +"/s/"+self.story.getMetadata('storyId'))
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = '%m/%d/%y'
+        
+    @staticmethod
+    def getSiteDomain():
+        return 'www.literotica.com'
+
+    @classmethod
+    def getAcceptDomains(cls):
+        return ['www.literotica.com', 'www.i.literotica.com']
+
+    @classmethod
+    def getSiteExampleURLs(self):
+        #return "http://www.literotica.com/s/story-title http://www.literotica.com/stories/showstory.php?id=1234 http://www.i.literotica.com/stories/showstory.php?id=1234"
+        return "http://www.literotica.com/s/story-title"
+
+    def getSiteURLPattern(self):
+        return r"http://www(\.i)?\.literotica\.com/s/([a-zA-Z0-9_-]+)"
+
+    def extractChapterUrlsAndMetadata(self):
+
+        if not (self.is_adult or self.getConfig("is_adult")):
+            raise exceptions.AdultCheckRequired(self.url)
+        
+        url1 = self.origurl
+        logger.debug("first page URL: "+url1)
+
+        try:
+            data1 = self._fetchUrl(url1)
+            soup1 = bs.BeautifulSoup(data1)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(url1)
+            else:
+                raise e
+
+        #strip comments from soup
+        [comment.extract() for comment in soup1.findAll(text=lambda text:isinstance(text, bs.Comment))]
+
+        # author
+        a = soup1.find("span", "b-story-user-y")
+        self.story.setMetadata('authorId', urlparse.parse_qs(a.a['href'].split('?')[1])['uid'])
+        self.story.setMetadata('authorUrl', a.a['href'])
+        self.story.setMetadata('author', a.text)
+
+        # get the author page
+        try:
+            dataAuth = self._fetchUrl(a.a['href'])
+            soupAuth = bs.BeautifulSoup(dataAuth)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(a.a['href'])
+            else:
+                raise e
+
+        storyLink = soupAuth.find('a', href=url1)
+
+        if storyLink is not None:
+            # pull the published date from the author page
+            # default values from single link.  Updated below if multiple chapter.
+            date = storyLink.parent.parent.findAll('td')[-1].text
+            self.story.setMetadata('datePublished', makeDate(date, self.dateformat))
+            self.story.setMetadata('dateUpdated',makeDate(date, self.dateformat))
+
+        # find num of pages
+        # find a "3 Pages:" string on the page and parse it
+        pgs = soup1.find("span", "b-pager-caption-t r-d45").string.split(' ')[0]
+
+        # If there are multiple pages, find and request the last page
+        if "1" != pgs:
+            logger.debug("last page number: "+pgs)
+            try:
+                data2 = self._fetchUrl(url1, {'page': pgs})
+                soup2 = bs.BeautifulSoup(data2)
+                [comment.extract() for comment in soup2.findAll(text=lambda text:isinstance(text, bs.Comment))]
+            except urllib2.HTTPError, e:
+                if e.code == 404:
+                    # TODO: Probably should reformat this
+                    raise exceptions.StoryDoesNotExist(url1, {'page': pgs})
+                else:
+                    raise e
+        else:
+            #If we're already on the last page, copy the soup
+            soup2 = soup1
+
+        # parse out the list of chapters
+        chaps = soup2.find('div', id='b-series')
+        if chaps:  # may be one post only
+            #self.chapterUrls = [(ch.a.text, ch.a['href']) for ch in chaps.findAll('li')]
+
+            # if there are chapters, lets pull them and title from the
+            # author page because *this* chapter is omitted from the
+            # list on the last page.
+            row = storyLink.parent.parent.previousSibling
+            while row['class'] != 'ser-ttl':
+                row = row.previousSibling
+
+            seriesTitle = stripHTML(row)
+            if seriesTitle:
+                # this regex is deliberately greedy. We want to get the biggest match before a ':'
+                self.story.setMetadata('title', re.match('(.*):[^:]*$', seriesTitle).group(1))
+            else:
+                self.story.setMetadata('title', soup1.h1.string)
+
+            # now chapter list.  Assumed oldest to newest.
+            self.chapterUrls = []
+            row = row.nextSibling
+                
+            self.story.setMetadata('datePublished',makeDate(stripHTML(row.find('td',{'class':'dt'})), self.dateformat))
+            while row['class'] == 'sl':
+                # pages include full URLs.
+                self.chapterUrls.append((row.a.string,row.a['href']))
+                if not row.nextSibling:
+                    break
+                row = row.nextSibling
+
+            row = row.previousSibling
+            self.story.setMetadata('dateUpdated',makeDate(stripHTML(row.find('td',{'class':'dt'})), self.dateformat))
+                
+        else:  # if one post only
+            self.chapterUrls = [(soup1.h1.string, url1)]
+            self.story.setMetadata('title', soup1.h1.string)
+
+        # 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))
+
+        self.story.setMetadata('category', soup1.find('div', 'b-breadcrumbs').findAll('a')[1].string)
+        self.story.setMetadata('description', soup1.find('meta', {'name': 'description'})['content'])
+
+        return
+
+    def getChapterText(self, url):
+        logger.debug('Getting chapter text from: %s' % url)
+        time.sleep(0.5)
+        data1 = self._fetchUrl(url)
+        soup1 = bs.BeautifulSoup(data1)
+
+        #strip comments from soup
+        [comment.extract() for comment in soup1.findAll(text=lambda text:isinstance(text, bs.Comment))]
+
+        # get story text
+        story1 = soup1.find('div', 'b-story-body-x').p
+        story1.name='div'
+        story1.append('<br>')
+        storytext = self.utf8FromSoup(url,story1)
+
+        # find num pages
+        pgs = int(soup1.find("span", "b-pager-caption-t r-d45").string.split(' ')[0])
+        logger.debug("pages: "+str(pgs))
+
+        # get all the pages
+        for i in xrange(2, pgs+1):
+            try:
+                logger.debug("fetching page "+str(i))
+                time.sleep(0.5)
+                data2 = self._fetchUrl(url, {'page': i})
+                soup2 = bs.BeautifulSoup(data2)
+                [comment.extract() for comment in soup2.findAll(text=lambda text:isinstance(text, bs.Comment))]
+                story2 = soup2.find('div', 'b-story-body-x').p
+                story2.name='div'
+                story2.append('<br>')
+                storytext += self.utf8FromSoup(url,story2)
+            except urllib2.HTTPError, e:
+                if e.code == 404:
+                    raise exceptions.StoryDoesNotExist(url)
+                else:
+                    raise e
+        return storytext
+
+
+def getClass():
+    return LiteroticaSiteAdapter
+
+
+

fanficdownloader/adapters/adapter_potionsandsnitchesnet.py

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

fanficdownloader/adapters/adapter_storiesonlinenet.py

@@ -37,11 +37,6 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
 
-        self.decode = ["Windows-1252",
-                       "utf8"] # 1252 is a superset of iso-8859-1.
-                               # Most sites that claim to be
-                               # iso-8859-1 (and some that claim to be
-                               # utf8) are really windows-1252.
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
@@ -147,6 +142,10 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
         a = soup.find('h1')
         self.story.setMetadata('title',stripHTML(a))
         
+        notice = soup.find('div', {'class' : 'notice'})
+        if notice:
+            self.story.setMetadata('notice',unicode(notice))
+
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"/a/\w+"))
         self.story.setMetadata('authorId',a['href'].split('/')[2])
@@ -185,23 +184,74 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
         self.story.setMetadata('size', lc2.findNext('td', {'class' : 'num'}).text)
         
         lc4 = lc2.findNext('td', {'class' : 'lc4'})        
-        
+        desc = lc4.contents[0]
+
         try:
             a = lc4.find('a', href=re.compile(r"/library/show_series.php\?id=\d+"))
-            i = a.parent.text.split('(')[1].split(')')[0]
-            self.setSeries(stripHTML(a), i)
-            self.story.setMetadata('seriesUrl','http://'+self.host+a['href'])
+            if a:
+                # if there's a number after the series name, series_contents is a two element list:
+                # [<a href="...">Title</a>, u' (2)']
+                series_contents = a.parent.contents
+                i = 0 if len(series_contents) == 1 else series_contents[1].strip(' ()')
+                seriesUrl = 'http://'+self.host+a['href']
+                self.story.setMetadata('seriesUrl',seriesUrl)
+                series_name = stripHTML(a)
+                logger.debug("Series name= %s" % series_name)
+                series_soup = bs.BeautifulSoup(self._fetchUrl(seriesUrl))
+                if series_soup:
+                    logger.debug("Retrieving Series - looking for name")
+                    series_name = series_soup.find('span', {'id' : 'ptitle'}).text.partition(' — ')[0]
+                    logger.debug("Series name: '{0}'".format(series_name))
+                self.setSeries(series_name, i)
+                desc = lc4.contents[2]
+                # Check if series is in a universe
+                universes_soup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')  + "&type=uni")) 
+#                logger.debug("Universe page=", universes_soup)
+                if universes_soup:
+                    universes = universes_soup.findAll('div', {'class' : 'ser-box'})
+                    logger.debug("Number of Universes: %d" % len(universes))
+                    for universe in universes:
+                        logger.debug("universe.find('a')={0}".format(universe.find('a')))
+                        # The universe id is in an "a" tag that has an id but nothing else. It is the first tag.
+                        # The id is prefixed with the letter "u".
+                        universe_id = universe.find('a')['id'][1:]
+                        logger.debug("universe_id='%s'" % universe_id)
+                        universe_name = universe.find('div', {'class' : 'ser-name'}).text.partition(' ')[2]
+                        logger.debug("universe_name='%s'" % universe_name)
+                        # If there is link to the story, we have the right universe
+                        story_a = universe.find('a', {'href' : '/s/'+self.story.getMetadata('storyId')})
+                        if story_a:
+                            logger.debug("Story is in a series that is in a universe! The universe is '%s'" % universe_name)
+                            self.story.setMetadata("universe", universe_name)
+                            self.story.setMetadata('universeUrl','http://'+self.host+ '/library/universe.php?id=' + universe_id)
+                            break
         except:
             pass
         try:
             a = lc4.find('a', href=re.compile(r"/library/universe.php\?id=\d+"))
             if a:
                 self.story.setMetadata("universe",stripHTML(a))
+                desc = lc4.contents[2]
+                # Assumed only one universe, but it does have a URL--use universeHTML
+                universe_name = stripHTML(a)
+                universeUrl = 'http://'+self.host+a['href']
+                logger.debug("Retrieving Universe - about to get page")
+                universe_soup = bs.BeautifulSoup(self._fetchUrl(universeUrl))
+                logger.debug("Retrieving Universe - have page")
+                if universe_soup:
+                    logger.debug("Retrieving Universe - looking for name")
+                    universe_name = universe_soup.find('span', {'id' : 'ptitle'}).text.partition(' &mdash;')[0]
+                    logger.debug("Universes name: '{0}'".format(universe_name))
+
+                self.story.setMetadata('universeUrl',universeUrl)
+                logger.debug("Setting universe name: '{0}'".format(universe_name))
+                self.story.setMetadata('universe',universe_name)
+                if self.getConfig("universe_as_series"):
+                    self.setSeries(universe_name, 0)
+                    self.story.setMetadata('seriesUrl',universeUrl)
         except:
             pass
-            
 
-        desc = lc4.contents[0]
         self.setDescription('http://'+self.host+'/s/'+self.story.getMetadata('storyId'),desc)
             
         for b in lc4.findAll('b'):
@@ -255,8 +305,18 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
         # some big chapters are split over several pages
         pager = div.find('span', {'class' : 'pager'})
         if pager != None:
+            a = pager.previousSibling
+            while a != None:
+                logger.debug("before pager: {0}".format(a))
+                b = a.previousSibling
+                a.extract()
+                a = b
+
             urls=pager.findAll('a')
             urls=urls[:len(urls)-1]
+            pager.extract()
+            div.contents = div.contents[2:]
+#            logger.debug(div)
                         
             for ur in urls:
                 soup = bs.BeautifulSoup(self._fetchUrl("http://"+self.getSiteDomain()+ur['href']),
@@ -264,38 +324,76 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
         
                 div1 = soup.find('div', {'id' : 'story'})
                 
-                # appending next section
-                last=div.findAll('p')
-                next=div1.find('span', {'class' : 'conTag'}).nextSibling
-            
-                last[len(last)-1]=last[len(last)-1].append(next)
-                div.append(div1)
-            
-        # removing all the left-over stuff    
-        for a in div.findAll('span'):
-            a.extract() 
-            
-        for a in div.findAll('h1'):
-            a.extract()
-        for a in div.findAll('h2'):
-            a.extract()
-        for a in div.findAll('h3'):
-            a.extract()
-        for a in div.findAll('h4'):
-            a.extract()
-        for a in div.findAll('br'):
-            a.extract()
-        for a in div.findAll('div', {'class' : 'date'}):
-            a.extract()
-            
-        a = div.find('form')
-        if a != None:
-            b = a.nextSibling
-            while b != None:
+                # Find the "Continues" marker on the current page and remove everything after that. 
+                continues = div.find('span', {'class' : 'conTag'})
+                if continues != None:
+                    while continues != None:
+#                        logger.debug("removing end: {0}".format(continues))
+                        b = continues.nextSibling
+                        continues.extract()
+                        continues = b
+
+                # Find the "Continued" marker and delete everything before that
+                continued = div1.find('span', {'class' : 'conTag'})
+                if continued != None:
+                    a = continued.previousSibling
+                    while a != None:
+#                        logger.debug("before conTag: {0}".format(a))
+                        b = a.previousSibling
+                        a.extract()
+                        a = b
+                # Remove the pager from the end if this is the last page
+                endPager = div1.find('span', {'class' : 'pager'})
+                if endPager != None:
+                    b = endPager.nextSibling
+                    while endPager != None:
+                        logger.debug("removing end: {0}".format(endPager))
+                        b = endPager.nextSibling
+                        endPager.extract()
+                        endPager = b
+                    div1.contents = div1.contents[:len(div1) - 2]
+#                logger.debug("after removing pager: {0}".format(div1))
+                for tag in div1.contents[2:]:
+                    div.append(tag)
+
+        # If it is a chapter, there are dates at the start for when it was posted or modified. These plus 
+        # everything before them can be discarded. 
+        postedDates = div.findAll('div', {'class' : 'date'})
+        if postedDates:
+            a = postedDates[0].previousSibling
+            while a != None:
+#                logger.debug("before dates: {0}".format(a))
+                b = a.previousSibling
                 a.extract()
-                a=b
-                b=b.nextSibling
-        
+                a = b
+            for a in div.findAll('div', {'class' : 'date'}):
+                a.extract()
+
+        # For single chapter stories, there is a copyright statement. Remove this and everything
+        # before it.
+        copy = div.find('h4', {'class': 'copy'})
+        while copy != None:
+#            logger.debug("before copyright: {0}".format(copy))
+            b = copy.previousSibling
+            copy.extract()
+            copy = b
+
+        # For a story or the last chapter, remove voting form and the in library box
+        a = div.find('div', {'id' : 'vote-form'})
+        if a != None:
+            a.extract()
+        a = div.find('div', {'id' : 'b-man-div'})
+        if a != None:
+            a.extract()
+
+        # Kill the "The End" header and everything after it.
+        a = div.find(['h2', 'h3'], {'class' : 'end'})
+        logger.debug("Chapter end= '{0}'".format(a))
+        while a != None:
+            b = a.nextSibling
+            a.extract()
+            a=b
+
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)

fanficdownloader/adapters/adapter_test1.py

@@ -50,6 +50,7 @@ class TestSiteAdapter(BaseSiteAdapter):
     def extractChapterUrlsAndMetadata(self):
         idstr = self.story.getMetadata('storyId')
         idnum = int(idstr)
+        self.do_sleep()
 
         if idnum >= 1000:
             logger.warn("storyId:%s - Custom INI data will be used."%idstr)
@@ -296,6 +297,7 @@ Some more longer description.  "I suck at summaries!"  "Better than it sounds!"
 
     def getChapterText(self, url):
         logger.debug('Getting chapter text from: %s' % url)
+        self.do_sleep()
         if self.story.getMetadata('storyId').startswith('670') or \
                 self.story.getMetadata('storyId').startswith('672'):
             time.sleep(1.0)

fanficdownloader/adapters/adapter_trekiverseorg.py

@@ -0,0 +1,325 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2013 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+logger = logging.getLogger(__name__)
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return TrekiverseOrgAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class TrekiverseOrgAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["iso-8859-1",
+                       "Windows-1252"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        
+        # normalized story URL.
+        self._setURL("http://"+self.getSiteDomain()\
+                         +"/efiction/viewstory.php?sid="+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','trkvs')
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%d/%m/%Y"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.
+        return 'trekiverse.org'
+
+    @classmethod
+    def getAcceptDomains(cls):
+        return ['trekiverse.org','efiction.trekiverse.org']
+
+    @classmethod
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/efiction/viewstory.php?sid=1234 http://efiction."+self.getSiteDomain()+"/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return r'(http://trekiverse\.org/efiction/viewstory\.php\?sid=\d+|http://efiction\.trekiverse\.org/viewstory\.php\?sid=\d+)'
+       
+    ## Login seems to be reasonably standard across eFiction sites.
+    def needToLoginCheck(self, data):
+        if 'Registered Users Only' in data \
+                or 'There is no such account on our website' in data \
+                or "That password doesn't match the one in our database" in data:
+            return True
+        else:
+            return False
+        
+    def performLogin(self, url):
+        params = {}
+
+        if self.password:
+            params['penname'] = self.username
+            params['password'] = self.password
+        else:
+            params['penname'] = self.getConfig("username")
+            params['password'] = self.getConfig("password")
+        params['cookiecheck'] = '1'
+        params['submit'] = 'Submit'
+    
+        loginUrl = 'http://' + self.getSiteDomain() + '/efiction/user.php?action=login'
+        logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
+                                                              params['penname']))
+    
+        d = self._fetchUrl(loginUrl, params)
+    
+        if "Member Account" not in d : #Member Account
+            logger.info("Failed to login to URL %s as %s" % (loginUrl,
+                                                              params['penname']))
+            raise exceptions.FailedToLogin(url,params['penname'])
+            return False
+        else:
+            return True
+
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        if self.is_adult or self.getConfig("is_adult"):
+            # Weirdly, different sites use different warning numbers.
+            # If the title search below fails, there's a good chance
+            # you need a different number.  print data at that point
+            # and see what the 'click here to continue' url says.
+            addurl = "&index=1&ageconsent=ok&warning=5"
+        else:
+            addurl="&index=1"
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+addurl
+        logger.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        if self.needToLoginCheck(data):
+            # need to log in for this one.
+            self.performLogin(url)
+            data = self._fetchUrl(url)
+            
+        m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
+        if m != None:
+            if self.is_adult or self.getConfig("is_adult"):
+                # We tried the default and still got a warning, so
+                # let's pull the warning number from the 'continue'
+                # link and reload data.
+                addurl = m.group(1)
+                # correct stupid & error in url.
+                addurl = addurl.replace("&","&")
+                url = self.url+'&index=1'+addurl
+                logger.debug("URL 2nd try: "+url)
+
+                try:
+                    data = self._fetchUrl(url)
+                except urllib2.HTTPError, e:
+                    if e.code == 404:
+                        raise exceptions.StoryDoesNotExist(self.url)
+                    else:
+                        raise e    
+            else:
+                raise exceptions.AdultCheckRequired(self.url)
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title and author
+        a = soup.find('div', {'id' : 'pagetitle'})
+        aut = a.find('a', href=re.compile(r"^viewuser\.php\?uid="))
+        self.story.setMetadata('authorId',aut['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/efiction/'+aut['href'])
+        self.story.setMetadata('author',aut.string)
+        
+        ttl = a.find('a', href=re.compile(r'^viewstory.php\?sid=%s$'%self.story.getMetadata('storyId')))
+        self.story.setMetadata('title',ttl.string)
+
+        # Find the chapters:
+        outputdiv = soup.find('div', {'id':'output'})
+        # (amp;)? because it should be &, but is escaped to & in URL.
+        # viewstory.php?sid=35&chapter=3
+        chapters=outputdiv.findAll('a', href=re.compile(r'^viewstory.php\?sid=%s&(amp;)?chapter=\d+$'%self.story.getMetadata('storyId')))
+        if len(chapters)==0:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: No php/html chapters found.")
+        if len(chapters)==1:
+            self.chapterUrls.append((self.story.getMetadata('title'),'http://'+self.host+'/efiction/'+chapters[0]['href']))
+        else:
+            for chapter in chapters:
+                # just in case there's tags, like <i> in chapter titles.
+                self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/efiction/'+chapter['href']))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+
+        def defaultGetattr(d,k):
+            try:
+                return d[k]
+            except:
+                return ""
+        
+        # <span class="label">Rated:</span> NC-17<br /> etc
+        labels = soup.findAll('span',{'class':'label'})
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.string
+
+            if 'Summary' in label:
+                ## Everything until the next span class='label'
+                svalue = ''
+                while value and not defaultGetattr(value,'class') == 'label':
+                    svalue += str(value)
+                    value = value.nextSibling
+                # sometimes poorly formated desc (<p> w/o </p>) leads
+                # to all labels being included.
+                svalue=svalue[:svalue.find('<span class="label">')]
+                self.setDescription(url,svalue)
+                #self.story.setMetadata('description',stripHTML(svalue))
+
+            if 'Rated' in label:
+                self.story.setMetadata('rating', value)
+
+            if 'Word count' in label:
+                self.story.setMetadata('numWords', value)
+
+            if 'Categories' in label:
+                cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
+                catstext = [cat.string for cat in cats]
+                for cat in catstext:
+                    self.story.addToList('category',cat.string)
+
+            if 'Characters' in label:
+                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+                charstext = [char.string for char in chars]
+                for char in charstext:
+                    self.story.addToList('characters',char.string)
+
+            if 'Genre' in label:
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=9'))
+                genrestext = [genre.string for genre in genres]
+                self.genre = ', '.join(genrestext)
+                for genre in genrestext:
+                    self.story.addToList('genre',genre.string)
+
+            if 'Awards' in label:
+                awards = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=12'))
+                awardstext = [award.string for award in awards]
+                self.award = ', '.join(awardstext)
+                for award in awardstext:
+                    self.story.addToList('awards',award.string)
+
+            if 'Pairing' in label:
+                ships = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=10'))
+                shipstext = [ship.string for ship in ships]
+                self.ship = ', '.join(shipstext)
+                for ship in shipstext:
+                    self.story.addToList('ships',ship.string)
+
+            if 'Warnings' in label:
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=11'))
+                warningstext = [warning.string for warning in warnings]
+                self.warning = ', '.join(warningstext)
+                for warning in warningstext:
+                    self.story.addToList('warnings',warning.string)
+
+            if 'Completed' in label:
+                if 'Yes' in value:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+
+            if 'Published' in label:
+                self.story.setMetadata('datePublished', makeDate(value.strip(), "%d %b %Y"))
+            
+            if 'Updated' in label:
+                self.story.setMetadata('dateUpdated', makeDate(value.strip(), "%d %b %Y"))
+                    
+        try:
+            # Find Series name from series URL.
+            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/efiction/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
+            i=1
+            for a in storyas:
+                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                    self.setSeries(series_name, i)
+                    self.story.setMetadata('seriesUrl',series_url)
+                    break
+                i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logger.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulSoup(self._fetchUrl(url)) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('div', {'id' : 'story'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+
+        notesdiv = soup.find('div', {'class':'noteinfo'})
+        if notesdiv != None:
+            div.insert(0,"<hr>")
+            div.insert(0,notesdiv)
+            div.insert(0,"<hr>")
+        
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_tthfanficorg.py

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

fanficdownloader/adapters/base_adapter.py

@@ -76,6 +76,8 @@ class BaseSiteAdapter(Configurable):
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
         self.is_adult=False
+
+        self.override_sleep = None
         
         self.opener = u2.build_opener(u2.HTTPCookieProcessor(),GZipProcessor())
         ## Specific UA because too many sites are blocking the default python UA.
@@ -147,8 +149,7 @@ class BaseSiteAdapter(Configurable):
 
     # Assumes application/x-www-form-urlencoded.  parameters, headers are dict()s
     def _postUrl(self, url, parameters={}, headers={}):
-        if self.getConfig('slow_down_sleep_time'):
-            time.sleep(float(self.getConfig('slow_down_sleep_time')))
+        self.do_sleep()
 
         ## u2.Request assumes POST when data!=None.  Also assumes data
         ## is application/x-www-form-urlencoded.
@@ -159,24 +160,38 @@ class BaseSiteAdapter(Configurable):
         req = u2.Request(url,
                          data=urllib.urlencode(parameters),
                          headers=headers)
-        return self._decode(self.opener.open(req).read())
+        return self._decode(self.opener.open(req,None,float(self.getConfig('connect_timeout',30.0))).read())
 
     def _fetchUrlRaw(self, url, parameters=None):
         if parameters != None:
-            return self.opener.open(url.replace(' ','%20'),urllib.urlencode(parameters)).read()
+            return self.opener.open(url.replace(' ','%20'),urllib.urlencode(parameters),float(self.getConfig('connect_timeout',30.0))).read()
         else:
-            return self.opener.open(url.replace(' ','%20')).read()
+            return self.opener.open(url.replace(' ','%20'),None,float(self.getConfig('connect_timeout',30.0))).read()
+
+    def set_sleep(self,val):
+        print("\n===========\n set sleep time %s\n==========="%val)
+        self.override_sleep = val
     
+    def do_sleep(self):
+        if self.override_sleep:
+            time.sleep(float(self.override_sleep))
+        elif self.getConfig('slow_down_sleep_time'):
+            time.sleep(float(self.getConfig('slow_down_sleep_time')))
+        
     # parameters is a dict()
     def _fetchUrl(self, url, parameters=None):
-        if self.getConfig('slow_down_sleep_time'):
-            time.sleep(float(self.getConfig('slow_down_sleep_time')))
+        self.do_sleep()
 
         excpt=None
         for sleeptime in [0, 0.5, 4, 9]:
             time.sleep(sleeptime)	
             try:
                 return self._decode(self._fetchUrlRaw(url,parameters))
+            except u2.HTTPError, he:
+                if he.code == 404:
+                    logger.warn("Caught an exception reading URL: %s  Exception %s."%(unicode(url),unicode(he)))
+                    excpt=he
+                    break # break out on 404
             except Exception, e:
                 excpt=e
                 logger.warn("Caught an exception reading URL: %s  Exception %s."%(unicode(url),unicode(e)))
@@ -367,7 +382,7 @@ class BaseSiteAdapter(Configurable):
             
         # Don't want body tags in chapter html--writers add them.
         # This is primarily for epub updates.
-        retval = re.sub(r"</?body>\r?\n?","",retval)
+        retval = re.sub(r"</?body[^>]*>\r?\n?","",retval)
         
         if self.getConfig("replace_br_with_p"):
             # Apply heuristic processing to replace <br> paragraph

fanficdownloader/htmlheuristics.py

@@ -137,32 +137,35 @@ def replace_br_with_p(body):
             contentLinesSum += lineLen
             if lineLen > longestLineLength:
                 longestLineLength = lineLen
+                
+    if contentLines == 0:
+        contentLines = 1
 
     averageLineLength = contentLinesSum/contentLines
 
     logger.debug(u'---')
-    logger.debug(u'Lines.............: ' + str(len(lines)))
-    logger.debug(u'contentLines......: ' + str(contentLines))
-    logger.debug(u'contentLinesSum...: ' + str(contentLinesSum))
-    logger.debug(u'longestLineLength.: ' + str(longestLineLength))
-    logger.debug(u'averageLineLength.: ' + str(averageLineLength))
+    logger.debug(u'Lines.............: ' + unicode(len(lines)))
+    logger.debug(u'contentLines......: ' + unicode(contentLines))
+    logger.debug(u'contentLinesSum...: ' + unicode(contentLinesSum))
+    logger.debug(u'longestLineLength.: ' + unicode(longestLineLength))
+    logger.debug(u'averageLineLength.: ' + unicode(averageLineLength))
 
     if breaksMaxIndex == len(breaksCount)-1 and breaksMax < 2:
         breaksMaxIndex = 0
         breaksMax = breaksCount[0]
 
     logger.debug(u'---')
-    logger.debug(u'breaks 1: ' + str(breaksCount[0]))
-    logger.debug(u'breaks 2: ' + str(breaksCount[1]))
-    logger.debug(u'breaks 3: ' + str(breaksCount[2]))
-    logger.debug(u'breaks 4: ' + str(breaksCount[3]))
-    logger.debug(u'breaks 5: ' + str(breaksCount[4]))
-    logger.debug(u'breaks 6: ' + str(breaksCount[5]))
-    logger.debug(u'breaks 7: ' + str(breaksCount[6]))
-    logger.debug(u'breaks 8: ' + str(breaksCount[7]))
+    logger.debug(u'breaks 1: ' + unicode(breaksCount[0]))
+    logger.debug(u'breaks 2: ' + unicode(breaksCount[1]))
+    logger.debug(u'breaks 3: ' + unicode(breaksCount[2]))
+    logger.debug(u'breaks 4: ' + unicode(breaksCount[3]))
+    logger.debug(u'breaks 5: ' + unicode(breaksCount[4]))
+    logger.debug(u'breaks 6: ' + unicode(breaksCount[5]))
+    logger.debug(u'breaks 7: ' + unicode(breaksCount[6]))
+    logger.debug(u'breaks 8: ' + unicode(breaksCount[7]))
     logger.debug(u'----')
-    logger.debug(u'max found: ' + str(breaksMax))
-    logger.debug(u'max Index: ' + str(breaksMaxIndex))
+    logger.debug(u'max found: ' + unicode(breaksMax))
+    logger.debug(u'max Index: ' + unicode(breaksMaxIndex))
     logger.debug(u'----')
 
     if breaksMaxIndex > 0 and breaksCount[0] > breaksMax and averageLineLength < 90:
@@ -173,13 +176,13 @@ def replace_br_with_p(body):
     for i in range(len(breaksCount)):
         # if i > 0 or breaksMaxIndex == 0:
         if i <= breaksMaxIndex:
-            logger.debug(str(i) + u' <= breaksMaxIndex (' + str(breaksMaxIndex) + u')')
+            logger.debug(unicode(i) + u' <= breaksMaxIndex (' + unicode(breaksMaxIndex) + u')')
             body = breaksRegexp[i].sub(r'\1</p>\n<p>\3', body)
         elif i == breaksMaxIndex+1:
-            logger.debug(str(i) + u' == breaksMaxIndex+1 (' + str(breaksMaxIndex+1) + u')')
+            logger.debug(unicode(i) + u' == breaksMaxIndex+1 (' + unicode(breaksMaxIndex+1) + u')')
             body = breaksRegexp[i].sub(r'\1</p>\n<p><br/></p>\n<p>\3', body)
         else:
-            logger.debug(str(i) + u' > breaksMaxIndex+1 (' + str(breaksMaxIndex+1) + u')')
+            logger.debug(unicode(i) + u' > breaksMaxIndex+1 (' + unicode(breaksMaxIndex+1) + u')')
             body = breaksRegexp[i].sub(r'\1</p>\n<hr />\n<p>\3', body)
 
     body = breaksRegexp[8].sub(r'</p>\n<hr />\n<p>', body)
@@ -230,7 +233,7 @@ def replace_br_with_p(body):
     return tag_sanitizer(body)
 
 def is_valid_block(block):
-    return str(block).find('<') == 0 and str(block).find('<!') != 0
+    return unicode(block).find('<') == 0 and unicode(block).find('<!') != 0
 
 def soup_up_div(body):
     blockTags = ['address', 'blockquote', 'del', 'div', 'dl', 'fieldset', 'form', 'ins', 'noscript', 'ol', 'p', 'pre', 'table', 'ul']
@@ -247,8 +250,8 @@ def soup_up_div(body):
     lastElement = 1 # 1 = block, 2 = nested, 3 = invalid
 
     for i in soup.contents[0]:
-        if str(i).strip().__len__() > 0:
-            s = str(i)
+        if unicode(i).strip().__len__() > 0:
+            s = unicode(i)
             if  type(i) == bs.Tag:
                 if  i.name in blockTags:
                     if lastElement > 1:
@@ -308,7 +311,7 @@ def tag_sanitizer(html):
         is_closed = is_closed_tag(rTag[0]) or is_comment_tag(rTag[0])
 
         # is_comment = is_comment_tag(rTag[0])
-        # logger.debug(u'%s >  isEnd: %s >  isClosed: %s >  isComment: %s'%(name, str(is_end), str(is_closed), str(is_comment)))
+        # logger.debug(u'%s >  isEnd: %s >  isClosed: %s >  isComment: %s'%(name, unicode(is_end), unicode(is_closed), unicode(is_comment)))
         # logger.debug(u'> %s%s\n'%(rTag[0], rTag[1]))
 
         if name in blockTags:

fanficdownloader/story.py

@@ -30,7 +30,7 @@ from configurable import Configurable
 
 # Create convert_image method depending on which graphics lib we can
 # load.  Preferred: calibre, PIL, none
-        
+
 imagetypes = {
     'jpg':'image/jpeg',
     'jpeg':'image/jpeg',
@@ -48,14 +48,14 @@ try:
         export = False
         img = Image()
         img.load(data)
-        
+
         owidth, oheight = img.size
         nwidth, nheight = sizes
         scaled, nwidth, nheight = fit_image(owidth, oheight, nwidth, nheight)
         if scaled:
             img.size = (nwidth, nheight)
             export = True
-            
+
         if normalize_format_name(img.format) != imgtype:
             export = True
 
@@ -65,7 +65,7 @@ try:
             canvas.compose(img)
             img = canvas
             export = True
-            
+
         if grayscale and img.type != "GrayscaleType":
             img.type = "GrayscaleType"
             export = True
@@ -75,7 +75,7 @@ try:
         else:
             logger.debug("image used unchanged")
             return (data,imgtype,imagetypes[imgtype])
-        
+
 except:
 
     # No calibre routines, try for PIL for CLI.
@@ -87,14 +87,14 @@ except:
                           removetrans,imgtype="jpg",background='#ffffff'):
             export = False
             img = Image.open(StringIO(data))
-            
+
             owidth, oheight = img.size
             nwidth, nheight = sizes
             scaled, nwidth, nheight = fit_image(owidth, oheight, nwidth, nheight)
             if scaled:
                 img = img.resize((nwidth, nheight),Image.ANTIALIAS)
                 export = True
-                
+
             if normalize_format_name(img.format) != imgtype:
                 if img.mode == "P":
                     # convert pallete gifs to RGB so jpg save doesn't fail.
@@ -119,7 +119,7 @@ except:
             else:
                 logger.debug("image used unchanged")
                 return (data,imgtype,imagetypes[imgtype])
-        
+
     except:
         # No calibre or PIL, simple pass through with mimetype.
         def convert_image(url,data,sizes,grayscale,
@@ -129,16 +129,16 @@ except:
 ## also used for explicit no image processing.
 def no_convert_image(url,data):
     parsedUrl = up.urlparse(url)
-    
+
     ext=parsedUrl.path[parsedUrl.path.rfind('.')+1:].lower()
-    
+
     if ext not in imagetypes:
         logger.debug("no_convert_image url:%s - no known extension"%url)
         # doesn't have extension? use jpg.
         ext='jpg'
-        
+
     return (data,ext,imagetypes[ext])
-        
+
 def normalize_format_name(fmt):
     if fmt:
         fmt = fmt.lower()
@@ -222,7 +222,7 @@ langs = {
     }
 
 class Story(Configurable):
-    
+
     def __init__(self, configuration):
         Configurable.__init__(self, configuration)
         try:
@@ -234,7 +234,7 @@ class Story(Configurable):
         self.chapters = [] # chapters will be tuples of (title,html)
         self.imgurls = []
         self.imgtuples = []
-        
+
         self.cover=None # *href* of new cover image--need to create html.
         self.oldcover=None # (oldcoverhtmlhref,oldcoverhtmltype,oldcoverhtmldata,oldcoverimghref,oldcoverimgtype,oldcoverimgdata)
         self.calibrebookmark=None # cheesy way to carry calibre bookmark file forward across update.
@@ -251,7 +251,7 @@ class Story(Configurable):
                 self.addToList(metadata,val)
 
         self.setReplace(self.getConfig('replace_metadata'))
-        
+
     def setMetadata(self, key, value, condremoveentities=True):
         ## still keeps < < and &
         if condremoveentities:
@@ -297,9 +297,9 @@ class Story(Configurable):
                 # A way to explicitly include spaces in the
                 # replacement string.  The .ini parser eats any
                 # trailing spaces.
-                replacement=replacement.replace('\s',' ') 
+                replacement=replacement.replace('\s',' ')
                 self.replacements.append([metakeys,regexp,replacement,condkey,condregexp])
-    
+
     def doReplacements(self,value,key):
         for (metakeys,regexp,replacement,condkey,condregexp) in self.replacements:
             if (metakeys == None or key in metakeys) \
@@ -309,11 +309,11 @@ class Story(Configurable):
                 if condkey and condkey != key: # prevent infinite recursion.
                     condval = self.getMetadata(condkey)
                     doreplace = condval != None and condregexp.search(condval)
-                    
+
                 if doreplace:
                     value = regexp.sub(replacement,value)
         return value
-        
+
     def getMetadataRaw(self,key):
         if self.isValidMetaEntry(key) and self.metadata.has_key(key):
             return self.metadata[key]
@@ -326,7 +326,7 @@ class Story(Configurable):
             return value
 
         if self.isList(key):
-            join_string = self.getConfig("join_string_"+key,u", ").replace('\s',' ') 
+            join_string = self.getConfig("join_string_"+key,u", ").replace('\s',' ')
             value = join_string.join(self.getList(key, removeallentities, doreplacements=True))
             if doreplacements:
                 value = self.doReplacements(value,key+"_LIST")
@@ -351,7 +351,7 @@ class Story(Configurable):
                 return value
         else: #if self.getConfig("default_value_"+key):
             return self.getConfig("default_value_"+key)
-        
+
     def getAllMetadata(self,
                        removeallentities=False,
                        doreplacements=True,
@@ -360,13 +360,13 @@ class Story(Configurable):
         All single value *and* list value metadata as strings (unless keeplists=True, then keep lists).
         '''
         allmetadata = {}
-        
+
         # special handling for authors/authorUrls
         linkhtml="<a class='%slink' href='%s'>%s</a>"
         if self.isList('author'): # more than one author, assume multiple authorUrl too.
             htmllist=[]
             for i, v in enumerate(self.getList('author')):
-                aurl = self.getList('authorUrl')[i]                    
+                aurl = self.getList('authorUrl')[i]
                 auth = v
                 # make sure doreplacements & removeallentities are honored.
                 if doreplacements:
@@ -375,9 +375,9 @@ class Story(Configurable):
                 if removeallentities:
                     aurl=removeAllEntities(aurl)
                     auth=removeAllEntities(auth)
-                
+
                 htmllist.append(linkhtml%('author',aurl,auth))
-            join_string = self.getConfig("join_string_authorHTML",u", ").replace('\s',' ') 
+            join_string = self.getConfig("join_string_authorHTML",u", ").replace('\s',' ')
             self.setMetadata('authorHTML',join_string.join(htmllist))
         else:
             self.setMetadata('authorHTML',linkhtml%('author',self.getMetadata('authorUrl', removeallentities, doreplacements),
@@ -388,20 +388,43 @@ class Story(Configurable):
                                                     self.getMetadata('series', removeallentities, doreplacements)))
         elif self.getMetadataRaw('series') != None:
             self.setMetadata('seriesHTML',self.getMetadataRaw('series'))
-            
+
+        # logger.debug("make_linkhtml_entries:%s"%self.getConfig('make_linkhtml_entries'))
+        for k in self.getConfigList('make_linkhtml_entries'):
+            # Assuming list, because it has to be site specific and
+            # they are all lists.  Bail if kUrl list not the same
+            # length.
+            # logger.debug("\nk:%s\nlist:%s\nlistURL:%s"%(k,self.getList(k),self.getList(k+'Url')))
+            if len(self.getList(k+'Url')) != len(self.getList(k)):
+                continue
+            htmllist=[]
+            for i, v in enumerate(self.getList(k)):
+                url = self.getList(k+'Url')[i]
+                # make sure doreplacements & removeallentities are honored.
+                if doreplacements:
+                    url=self.doReplacements(url,k+'Url')
+                    v=self.doReplacements(v,k)
+                if removeallentities:
+                    url=removeAllEntities(url)
+                    v=removeAllEntities(v)
+
+                htmllist.append(linkhtml%(k,url,v))
+            join_string = self.getConfig("join_string_"+k+"HTML",u", ").replace('\s',' ')
+            self.setMetadata(k+'HTML',join_string.join(htmllist))
+
         for k in self.getValidMetaList():
             if self.isList(k) and keeplists:
                 allmetadata[k] = self.getList(k, removeallentities, doreplacements)
             else:
                 allmetadata[k] = self.getMetadata(k, removeallentities, doreplacements)
-                
+
         return allmetadata
 
     # just for less clutter in adapters.
     def extendList(self,listname,l):
         for v in l:
             self.addToList(listname,v.strip())
-    
+
     def addToList(self,listname,value):
         if value==None:
             return
@@ -421,24 +444,24 @@ class Story(Configurable):
         return self.hasConfig("include_in_"+listname) or \
             ( self.isValidMetaEntry(listname) and self.metadata.has_key(listname) \
                   and isinstance(self.metadata[listname],list) )
-    
+
     def getList(self,listname,
                 removeallentities=False,
                 doreplacements=True,
                 includelist=[]):
         #print("getList(%s,%s)"%(listname,includelist))
         retlist = []
-        
+
         if not self.isValidMetaEntry(listname):
             return retlist
-        
+
         # includelist prevents infinite recursion of include_in_'s
         if self.hasConfig("include_in_"+listname) and listname not in includelist:
             for k in self.getConfigList("include_in_"+listname):
                 retlist.extend(self.getList(k,removeallentities=False,
                                             doreplacements=doreplacements,includelist=includelist+[listname]))
         else:
-        
+
             if not self.isList(listname):
                 retlist = [self.getMetadata(listname,removeallentities=False,
                                             doreplacements=doreplacements)]
@@ -458,7 +481,7 @@ class Story(Configurable):
         # ships=>[ ]*(/|&amp;|&)[ ]*=>/
         if listname == 'ships' and self.getConfig('sort_ships'):
             retlist = [ '/'.join(sorted(x.split('/'))) for x in retlist ]
-                
+
         if retlist:
             if listname in ('author','authorUrl','authorId') or self.getConfig('keep_in_order_'+listname):
                 # need to retain order for author & authorUrl so the
@@ -473,9 +496,9 @@ class Story(Configurable):
     def getSubjectTags(self, removeallentities=False):
         # set to avoid duplicates subject tags.
         subjectset = set()
-        
+
         tags_list = self.getConfigList("include_subject_tags") + self.getConfigList("extra_subject_tags")
-            
+
         # metadata all go into dc:subject tags, but only if they are configured.
         for (name,value) in self.getAllMetadata(removeallentities=removeallentities,keeplists=True).iteritems():
             if name in tags_list:
@@ -491,7 +514,7 @@ class Story(Configurable):
             subjectset.remove('')
 
         return list(subjectset | set(self.getConfigList("extratags")))
-            
+
     def addChapter(self, url, title, html):
         if self.getConfig('strip_chapter_numbers') and \
                 self.getConfig('chapter_title_strip_pattern'):
@@ -512,7 +535,7 @@ class Story(Configurable):
                                 html) )
         else:
             retval = self.chapters
-            
+
         return retval
 
     def formatFileName(self,template,allowunsafefilename=True):
@@ -526,7 +549,7 @@ class Story(Configurable):
             pattern = re.compile(self.getConfig("output_filename_safepattern",r"[^a-zA-Z0-9_\. \[\]\(\)&'-]+"))
             for k in origvalues.keys():
                 values[k]=re.sub(pattern,'_', removeAllEntities(self.getMetadata(k)))
-    
+
         return string.Template(template).substitute(values).encode('utf8')
 
     # pass fetch in from adapter in case we need the cookies collected
@@ -537,7 +560,7 @@ class Story(Configurable):
         # isn't used anywhere.
         if cover and self.getConfig('never_make_cover'):
             return
-        
+
         url = url.strip() # ran across an image with a space in the
                           # src. Browser handled it, so we'd better, too.
 
@@ -545,12 +568,18 @@ class Story(Configurable):
         # gets too big too fast and breaks things.
         if is_appengine:
             return
-        
+
         if url.startswith("http") or url.startswith("file") or parenturl == None:
             imgurl = url
         else:
             parsedUrl = urlparse.urlparse(parenturl)
-            if url.startswith("/") :
+            if url.startswith("//") :
+                imgurl = urlparse.urlunparse(
+                    (parsedUrl.scheme,
+                     '',
+                     url,
+                     '','',''))
+            elif url.startswith("/") :
                 imgurl = urlparse.urlunparse(
                     (parsedUrl.scheme,
                      parsedUrl.netloc,
@@ -598,7 +627,7 @@ class Story(Configurable):
             except Exception, e:
                 logger.info("Failed to load or convert image, skipping:\n%s\nException: %s"%(imgurl,e))
                 return "failedtoload"
-            
+
             # explicit cover, make the first image.
             if cover and not self.getConfig('never_make_cover'):
                 if len(self.imgtuples) > 0 and 'cover' in self.imgtuples[0]['newsrc']:
@@ -624,19 +653,19 @@ class Story(Configurable):
                     self.cover=newsrc
                     self.imgtuples.append({'newsrc':newsrc,'mime':mime,'data':data})
                     self.imgurls.append(imgurl)
-            
+
                 newsrc = "images/%s-%s.%s"%(
                     prefix,
                     self.imgurls.index(imgurl),
                     ext)
                 self.imgtuples.append({'newsrc':newsrc,'mime':mime,'data':data})
-                
+
             #logger.debug("\nimgurl:%s\nnewsrc:%s\nimage size:%d\n"%(imgurl,newsrc,len(data)))
         else:
             newsrc = self.imgtuples[self.imgurls.index(imgurl)]['newsrc']
-            
+
         #print("===============\n%s\nimg url:%s\n============"%(newsrc,self.imgurls[-1]))
-        
+
         return newsrc
 
     def getImgUrls(self):
@@ -645,9 +674,9 @@ class Story(Configurable):
             #parsedUrl = urlparse.urlparse(url)
             retlist.append(self.imgtuples[i])
         return retlist
-    
+
     def __str__(self):
-        return "Metadata: " +str(self.metadata) 
+        return "Metadata: " +str(self.metadata)
 
 def commaGroups(s):
     groups = []

index.html

@@ -48,13 +48,9 @@
 
           <h3>fanfiction.net / fimfiction.net</h3>
           <p>
-            Fanfiction.net appears to be blocking access from Google
-            App Engine, which prevents this web service.  There's
-            nothing I can do about it.  At the time of writing, the
-            latest CLI and calibre plugin versions worked.
-          </p>
-          <p>It appears that FimFiction.net is also blocking access from Google
-            App Engine now.
+            As of Jan 13, 2014, fanfiction.net &amp; fimfiction.net
+            are working again.  I'd ask that users limit the number of
+            stories they download from those sites, thanks.
           </p>
 	  
       {% if authorized %}
@@ -68,10 +64,10 @@
 	  <h3>Changes:</h3>
 	  <p>
 	    <ul>
-              <li>Additional improvements to the replace_br_with_p heuristic HTML processing feature.</li>
+              <li>Fix potionsandsnitches.net dates.</li>
+              <li>Fix for AO3 https urls.</li>
 	    </ul>
 	  </p>
-          
 	  <p>
 	    Questions?  Check out our 
 	    <a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownloaderFAQs">FAQs</a>.
@@ -80,7 +76,7 @@
 	    If you have any problems with this application, please
 	    report them in
 	    the <a href="http://groups.google.com/group/fanfic-downloader">FanFictionDownLoader Google Group</a>.  The
-	    <a href="http://4-4-84.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
+	    <a href="http://4-4-94.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
 	  </p>
 	  <div id='error'>
 	    {{ error_message }}

plugin-defaults.ini

@@ -154,6 +154,11 @@ extratags: FanFiction
 ## useful if pulling large numbers of stories or if the site is slow.
 #slow_down_sleep_time:0.5
 
+## How long to wait for each HTTP connection to finish.  Longer times
+## are better for sites that are slow to respond.  Shorter times
+## prevent excessive wait when your network or the site is down.
+connect_timeout:60.0
+
 ## Use regular expressions to find and replace (or remove) metadata.
 ## For example, you could change Sci-Fi=>SF, remove *-Centered tags,
 ## etc.  See http://docs.python.org/library/re.html (look for re.sub)
@@ -507,6 +512,13 @@ extratags: FanFiction,Testing,HTML
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+## archiveofourown.org stories allow chapters to be added out of
+## order.  So the newest chapter may not be the last one.  FFDL update
+## doesn't like that.  If do_update_hook is uncommented and set true,
+## the adapter will discard all existing chapters from the newest one
+## on when updating to enforce accurate chapters.
+#do_update_hook:false
+
 ## AO3 adapter defines a few extra metadata entries.
 ## If there's ever more than 4 series, add series04,series04Url etc.
 extra_valid_entries:fandoms,freeformtags,freefromtags,ao3categories,comments,kudos,hits,bookmarks,collections,series00,series01,series02,series03,series00Url,series01Url,series02Url,series03Url
@@ -531,11 +543,6 @@ include_in_freefromtags:freeformtags
 #extra_subject_tags:fandoms,freeformtags,ao3categories
 
 [ashwinder.sycophanthex.com]
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-extracharacters:Severus Snape,Hermione Granger
-extraships:Severus Snape/Hermione Granger
-
 ## 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
@@ -543,6 +550,11 @@ extraships:Severus Snape/Hermione Granger
 #username:YourName
 #password:yourpassword
 
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+extracharacters:Severus Snape,Hermione Granger
+extraships:Severus Snape/Hermione Granger
+
 [asr3.slashzone.org]
 ## Site dedicated to these categories/characters/ships
 extracategories:The Sentinel
@@ -553,9 +565,6 @@ extracategories:The Sentinel
 #is_adult:true
 
 [bloodties-fans.com]
-## Site dedicated to these categories/characters/ships
-extracategories:Blood Ties
-
 ## 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
@@ -568,6 +577,9 @@ extracategories:Blood Ties
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Blood Ties
+
 [buffynfaith.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:Buffy: The Vampire Slayer
@@ -578,9 +590,6 @@ extracategories:Buffy: The Vampire Slayer
 #is_adult:true
 
 [castlefans.org]
-## Site dedicated to these categories/characters/ships
-extracategories:Castle
-
 ## 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
@@ -593,6 +602,9 @@ extracategories:Castle
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Castle
+
 [chaos.sycophanthex.com]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
@@ -605,10 +617,23 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 
 [dark-solace.org]
 ## Site dedicated to these categories/characters/ships
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Some sites also require the user to confirm they are adult for
+## adult content.  In commandline version, this should go in your
+## personal.ini, not defaults.ini.
+#is_adult:true
+
 extracategories:Buffy: The Vampire Slayer
 extracharacters:Buffy, Spike
 extraships:Spike/Buffy
 
+[dramione.org]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
 ## commandline version, this should go in your personal.ini, not
@@ -621,24 +646,11 @@ extraships:Spike/Buffy
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
-[dramione.org]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
 extracharacters:Draco Malfoy,Hermione Granger
 extraships:Draco Malfoy/Hermione Granger
 
-## Some sites require login (or login for some rated stories) The
-## program can prompt you, or you can save it in config.  In
-## commandline version, this should go in your personal.ini, not
-## defaults.ini.
-#username:YourName
-#password:yourpassword
-
-## Some sites also require the user to confirm they are adult for
-## adult content.  In commandline version, this should go in your
-## personal.ini, not defaults.ini.
-#is_adult:true
-
 ## some sites include images that we don't ever want becoming the
 ## cover image.  This lets you exclude them.
 cover_exclusion_regexp:/images/.*?ribbon.gif
@@ -684,35 +696,34 @@ cliches_label:Character Cliches
 ## 'mode'.  'r' to Replace any existing values, 'a' to Add to existing
 ## value (use with tag-like columns), and 'n' for setting on New books
 ## only.  (Default is 'r'.)
+## Literal strings can be set into custom columns using double quotes.
 ## Each metadata=>column mapping must be on a separate line and each
 ## needs to have one space at the start of each line.
 
 #custom_columns_settings:
-# cliches=>#acolumn,r
+# cliches=>#acolumn
 # themes=>#bcolumn,a
 # timeline=>#ccolumn,n
+# "FanFiction"=>#collection
 
 [efiction.esteliel.de]
 ## Site dedicated to these categories/characters/ships
 extracategories:Lord of the Rings
 
 [erosnsappho.sycophanthex.com]
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 ## some sites include images that we don't ever want becoming the
 ## cover image.  This lets you exclude them.
 cover_exclusion_regexp:/images/.*?ribbon.gif
 
 [fanfiction.mugglenet.com]
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-
 ## 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.
@@ -725,10 +736,10 @@ extracategories:Harry Potter
 #username:YourName
 #password:yourpassword
 
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 [fanfic.potterheadsanonymous.com]
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-
 ## 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.
@@ -741,16 +752,19 @@ extracategories:Harry Potter
 #username:YourName
 #password:yourpassword
 
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 [fanfiction.portkey.org]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
 extraships:Harry Potter/Hermione Granger
 
-## 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
-
 [fanfiction.tenhawkpresents.com]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -795,18 +809,26 @@ dislikes_label:Dislikes
 ## Clear FanFiction from defaults, site is original fiction.
 extratags:
 
-extra_valid_entries:size,universe,codes
-#extra_titlepage_entries:size,universe,codes
+extra_valid_entries:size,universe,universeUrl,universeHTML,codes,notice
+#extra_titlepage_entries:size,universeHTML,codes,notice
 
 size_label:Size
 universe_label:Universe
+universeUrl_label:Universe URL
+universeHTML_label:Universe
 codes_label:Codes
+notice_label:Notice
+
+## 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
 
 [grangerenchanted.com]
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-extracharacters:Hermione Granger
-
 ## 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
@@ -819,6 +841,10 @@ extracharacters:Hermione Granger
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+extracharacters:Hermione Granger
+
 ## Extra metadata that this adapter knows about.  See [dramione.org]
 ## for examples of how to use them.
 extra_valid_entries:read,reviews
@@ -855,18 +881,15 @@ extracharacters:Kirk,Spock
 extraships:Kirk/Spock
 
 [lumos.sycophanthex.com]
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-
 ## 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
 
-[merlinfic.dtwins.co.uk]
 ## Site dedicated to these categories/characters/ships
-extracategories:Merlin
+extracategories:Harry Potter
 
+[merlinfic.dtwins.co.uk]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
 ## commandline version, this should go in your personal.ini, not
@@ -879,6 +902,9 @@ extracategories:Merlin
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Merlin
+
 [national-library.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:West Wing
@@ -890,24 +916,32 @@ extracategories:NCIS
 [netraptor.org]
 
 [nfacommunity.com]
-## Site dedicated to these categories/characters/ships
-extracategories:NCIS
-
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:NCIS
+
 [nha.magical-worlds.us]
 ## Site dedicated to these categories/characters/ships
 extracategories:Buffy: The Vampire Slayer
 extracharacters:Willow
 
 [occlumency.sycophanthex.com]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
 extracharacters:Severus Snape
 
+[onedirectionfanfiction.com]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
 ## commandline version, this should go in your personal.ini, not
@@ -915,10 +949,15 @@ extracharacters:Severus Snape
 #username:YourName
 #password:yourpassword
 
-[onedirectionfanfiction.com]
+## Some sites also require the user to confirm they are adult for
+## adult content.  In commandline version, this should go in your
+## personal.ini, not defaults.ini.
+#is_adult:true
+
 ## Site dedicated to these categories/characters/ships
 extracategories:One Direction
 
+[pommedesang.com]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
 ## commandline version, this should go in your personal.ini, not
@@ -931,40 +970,27 @@ extracategories:One Direction
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
-[pommedesang.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Anita Blake Vampire Hunter 
 
-## Some sites require login (or login for some rated stories) The
-## program can prompt you, or you can save it in config.  In
-## commandline version, this should go in your personal.ini, not
-## defaults.ini.
-#username:YourName
-#password:yourpassword
-
-## Some sites also require the user to confirm they are adult for
-## adult content.  In commandline version, this should go in your
-## personal.ini, not defaults.ini.
+[ponyfictionarchive.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
 
-[ponyfictionarchive.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:My Little Pony: Friendship is Magic
 
+[pretendercentre.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
 
-[pretendercentre.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:The Pretender
 
-## 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
-
 [samdean.archive.nu]
 ## Site dedicated to these categories/characters/ships
 extracategories:Supernatural
@@ -972,9 +998,6 @@ extracharacters:Sam,Dean
 extraships:Sam/Dean
 
 [scarhead.net]
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-
 ## 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
@@ -987,6 +1010,9 @@ extracategories:Harry Potter
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 [sg1-heliopolis.com]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
@@ -1017,9 +1043,6 @@ extracharacters:Draco Malfoy,Harry Potter
 extraships:Harry Potter/Draco Malfoy
 
 [thehookupzone.net]
-## Site dedicated to these categories/characters/ships
-extracategories:Criminal Minds
-
 ## 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
@@ -1032,6 +1055,9 @@ extracategories:Criminal Minds
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Criminal Minds
+
 [themasque.net]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -1046,9 +1072,6 @@ extracategories:Criminal Minds
 #is_adult:true
 
 [thequidditchpitch.org]
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-
 ## 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
@@ -1061,50 +1084,71 @@ extracategories:Harry Potter
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 [tokra.fandomnet.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
 ## Site dedicated to these categories/characters/ships
 extracategories:Stargate: SG-1
 
-## 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.
+[trekiverse.org]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Some sites also require the user to confirm they are adult for
+## adult content.  In commandline version, this should go in your
+## personal.ini, not defaults.ini.
 #is_adult:true
 
-[www.adastrafanfic.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Star Trek
 
+extra_valid_entries:awards
+awards_label:Awards
+
+cover_exclusion_regexp:art/.*Awards.jpg
+
+[www.adastrafanfic.com]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Star Trek
+
 [www.dracoandginny.com]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Some sites also require the user to confirm they are adult for
+## adult content.  In commandline version, this should go in your
+## personal.ini, not defaults.ini.
+#is_adult:true
+
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
 extracharacters:Draco Malfoy,Ginny Weasley
 extraships:Draco Malfoy/Ginny Weasley
 
-## Some sites require login (or login for some rated stories) The
-## program can prompt you, or you can save it in config.  In
-## commandline version, this should go in your personal.ini, not
-## defaults.ini.
-#username:YourName
-#password:yourpassword
-
-## Some sites also require the user to confirm they are adult for
-## adult content.  In commandline version, this should go in your
-## personal.ini, not defaults.ini.
-#is_adult:true
-
 [www.thealphagate.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Stargate: SG-1
 
 [www.checkmated.com]
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-
 ## 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
@@ -1112,6 +1156,9 @@ extracategories:Harry Potter
 #username:YourName
 #password:yourpassword
 
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 [www.destinysgateway.com]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
@@ -1119,11 +1166,6 @@ extracategories:Harry Potter
 #is_adult:true
 
 [www.dokuga.com]
-## Site dedicated to these categories/characters/ships
-extracategories:InuYasha
-extracharacters:Sesshoumaru,Kagome
-extraships:Sesshoumaru/Kagome
-
 ## 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
@@ -1131,6 +1173,11 @@ extraships:Sesshoumaru/Kagome
 #username:YourName
 #password:yourpassword
 
+## Site dedicated to these categories/characters/ships
+extracategories:InuYasha
+extracharacters:Sesshoumaru,Kagome
+extraships:Sesshoumaru/Kagome
+
 [www.dotmoon.net]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -1160,6 +1207,20 @@ user_agent:
 ## Change this to false to use them anyway.
 never_make_cover: true
 
+## fanfiction.net is blocking people more aggressively.  If you
+## download fewer stories less often you can likely get by with
+## reducing this sleep.
+slow_down_sleep_time:4
+
+## ffnet is sensitive to too many hits.  Users are sensitive to long
+## waits during the initial metadata collection in the foreground.
+## When used, these settings will speed up metadata downloads in the
+## foreground linearly.
+tweak_fg_sleep:true
+min_fg_sleep:1.0
+max_fg_sleep:4.0
+max_fg_sleep_at_downloads: 10
+
 ## Extra metadata that this adapter knows about.  See [dramione.org]
 ## for examples of how to use them.
 extra_valid_entries:reviews,favs,follows
@@ -1168,13 +1229,20 @@ extra_valid_entries:reviews,favs,follows
 ## to be romantic pairings.
 ships_label:Pairings
 
-## Date formats used by FFDL.  Published and Update don't have time.
+## Date formats used by FFDL.  Published and Update don't usually have
+## time, but they do now on ffnet.
 ## See http://docs.python.org/library/datetime.html#strftime-strptime-behavior
 ## Note that ini format requires % to be escaped as %%.
 #dateCreated_format:%%Y-%%m-%%d %%H:%%M:%%S
 datePublished_format:%%Y-%%m-%%d %%H:%%M:%%S
 dateUpdated_format:%%Y-%%m-%%d %%H:%%M:%%S
 
+## ffnet used to have a tendency to send out update notices in email
+## before all their servers were showing the update on the first
+## chapter.  It generates another server request and doesn't seem to
+## be needed lately, so now default it to off.
+check_next_chapter:false
+
 [www.fanfiktion.de]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -1186,14 +1254,14 @@ dateUpdated_format:%%Y-%%m-%%d %%H:%%M:%%S
 [www.ficbook.net]
 
 [www.fictionalley.org]
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 ## fictionalley.org doesn't have a status metadatum.  If uncommented,
 ## this will be used for status.
 #default_value_status:Unknown
@@ -1216,19 +1284,6 @@ extra_valid_entries:reviews,favs,follows
 #password:yourpassword
 
 [www.fimfiction.net]
-## Site dedicated to these categories/characters/ships
-extracategories:My Little Pony: Friendship is Magic
-
-## Extra metadata that this adapter knows about.  See [dramione.org]
-## for examples of how to use them.
-extra_valid_entries:likes,dislikes,views,total_views,short_description,groups
-likes_label:Likes
-dislikes_label:Dislikes
-views_label:Highest Single Chapter Views
-total_views_label:Total Views
-short_description_label:Short Summary
-groups_label:Groups
-
 ## 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.
@@ -1246,38 +1301,63 @@ groups_label:Groups
 ## when updating to enforce accurate chapters.
 #do_update_hook:false
 
-[www.harrypotterfanfiction.com]
 ## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
+extracategories:My Little Pony: Friendship is Magic
 
+## Extra metadata that this adapter knows about.  See [dramione.org]
+## for examples of how to use them.
+extra_valid_entries:likes,dislikes,views,total_views,short_description,groups,groupsUrl,groupsHTML,prequel,prequelUrl,prequelHTML,sequels,sequelsUrl,sequelsHTML
+likes_label:Likes
+dislikes_label:Dislikes
+views_label:Highest Single Chapter Views
+total_views_label:Total Views
+short_description_label:Short Summary
+groups_label:Groups
+groupsUrl_label:Groups URLs
+groupsHTML_label:Groups
+prequel_label:Prequel
+prequelUrl_label:Prequel URL
+prequelHTML_label:Prequel
+sequels_label:Sequels
+sequelsUrl_label:Sequel URLs
+sequelsHTML_label:Sequels
+
+keep_in_order_sequels:true
+keep_in_order_sequelsUrl:true
+keep_in_order_groups:true
+keep_in_order_groupsUrl:true
+
+## Assume entryUrl, apply to "<a class='%slink' href='%s'>%s</a>" to
+## make entryHTML.
+make_linkhtml_entries:prequel,sequels,groups
+
+[www.harrypotterfanfiction.com]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 [www.henneth-annun.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:The Hobbit
 
 [www.hpfandom.net]
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 [www.hpfanficarchive.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
 
 [www.ik-eternal.net]
-## Site dedicated to these categories/characters/ships
-extracategories:InuYasha
-extracharacters:InuYasha,Kagome
-extraships:InuYasha/Kagome
-
 ## 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
@@ -1290,30 +1370,35 @@ extraships:InuYasha/Kagome
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:InuYasha
+extracharacters:InuYasha,Kagome
+extraships:InuYasha/Kagome
+
 [www.jlaunlimited.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:JLA
 
 [www.libraryofmoria.com]
-## Site dedicated to these categories/characters/ships
-extracategories:Lord of the Rings
-
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Lord of the Rings
+
 [www.mediaminer.org]
 
 [www.midnightwhispers.ca]
-## Site dedicated to these categories/characters/ships
-extracategories:Queer as Folk
-
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Queer as Folk
+
 ## some sites include images that we don't ever want becoming the
 ## cover image.  This lets you exclude them.
 cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
@@ -1328,10 +1413,6 @@ extracategories:CSI
 extraships:Nick Stokes/Greg Sanders
 
 [www.phoenixsong.net]
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-extraships:Harry Potter/Ginny Weasley
-
 ## 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
@@ -1342,9 +1423,13 @@ extraships:Harry Potter/Ginny Weasley
 ## phoenixsong.net, oddly, can have high rated chapters (login
 ## required) in the middle of a lower rated story.  Use this to force
 ## FFDL to always login to phoenixsong.net so those stories download
-## correctly.
+## correctly.  If you have a login, this is recommended.
 #force_login:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+extraships:Harry Potter/Ginny Weasley
+
 [www.potionsandsnitches.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
@@ -1367,17 +1452,15 @@ extracategories:Psych
 #is_adult:true
 
 [www.qaf-fic.com]
-## Site dedicated to these categories/characters/ships
-extracategories:Queer as Folk
-
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Queer as Folk
+
 [www.restrictedsection.org]
-extracategories:Harry Potter
-extragenres:Erotica
 ## 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
@@ -1385,20 +1468,21 @@ extragenres:Erotica
 #username:YourName
 #password:yourpassword
 
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+extragenres:Erotica
+
 [www.scarvesandcoffee.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
+
 ## Site dedicated to these categories/characters/ships
 extracategories:Glee
 extracharacters:Kurt Hummel,Blaine Anderson
 
-## 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.simplyundeniable.com]
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-
 ## 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
@@ -1406,15 +1490,18 @@ extracategories:Harry Potter
 #username:YourName
 #password:yourpassword
 
-[www.sinful-desire.org]
 ## Site dedicated to these categories/characters/ships
-extracategories:Supernatural
+extracategories:Harry Potter
 
+[www.sinful-desire.org]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Supernatural
+
 [www.siye.co.uk]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
@@ -1422,25 +1509,26 @@ extracharacters:Harry Potter,Ginny Weasley
 extraships:Harry Potter/Ginny Weasley
 
 [www.squidge.org/peja]
-# www.squidge.org/peja calls it Fandom <shrug>
+## www.squidge.org/peja calls it Fandom <shrug>
 category_label:Fandom
-# Remove numWords -- www.squidge.org/peja word counts are inaccurate
+
+## Remove numWords -- www.squidge.org/peja word counts are inaccurate
 titlepage_entries: seriesHTML,category,genre,language,characters,ships,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,description
 
 [www.squidge.org/peja:txt]
-## Add URLs since there aren't links.
-# Remove numWords -- www.squidge.org/peja word counts are inaccurate
+## Add URLs since there aren't links and remove numWords --
+## www.squidge.org/peja word counts are inaccurate
 titlepage_entries: series,seriesUrl,category,genre,language,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,storyUrl, authorUrl, description
 
 [www.storiesofarda.com]
-## Site dedicated to these categories/characters/ships
-extracategories:Lord of the Rings
-
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Lord of the Rings
+
 [www.thepetulantpoetess.com]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -1483,9 +1571,6 @@ collect_series: false
 extracategories:Twilight
 
 [www.twilighted.net]
-## Site dedicated to these categories/characters/ships
-extracategories:Twilight
-
 ## 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
@@ -1493,13 +1578,13 @@ extracategories:Twilight
 #username:YourName
 #password:yourpassword
 
+## Site dedicated to these categories/characters/ships
+extracategories:Twilight
+
 ## twilighted.net (ab)uses series as personal reading lists.
 collect_series: false
 
 [www.twiwrite.net]
-## Site dedicated to these categories/characters/ships
-extracategories:Twilight
-
 ## 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
@@ -1507,20 +1592,23 @@ extracategories:Twilight
 #username:YourName
 #password:yourpassword
 
+## Site dedicated to these categories/characters/ships
+extracategories:Twilight
+
 ## twiwrite.net (ab)uses series as personal reading lists.
 collect_series: false
 
 [www.walkingtheplank.org]
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-extracharacters:Severus Snape,Harry Potter
-extraships:Severus Snape/Harry Potter
-
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+extracharacters:Severus Snape,Harry Potter
+extraships:Severus Snape/Harry Potter
+
 [www.whofic.com]
 
 [www.wizardtales.net]
@@ -1542,14 +1630,14 @@ extracategories:X-Men Movie
 extracharacters:Wolverine,Rogue
 
 [www.wraithbait.com]
-## Site dedicated to these categories/characters/ships
-extracategories:Stargate: Atlantis
-
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+## Site dedicated to these categories/characters/ships
+extracategories:Stargate: Atlantis
+
 [overrides]
 ## It may sometimes be useful to override all of the specific format,
 ## site and site:format sections in your private configuration.  For

status.html

@@ -53,13 +53,9 @@
 	  {% if fic.failure %}
           <h3>fanfiction.net / fimfiction.net</h3>
           <p>
-            FYI, fanfiction.net appears to be blocking access from Google
-            App Engine, which prevents this web service.  There's
-            nothing I can do about it.  At the time of writing, the
-            latest CLI and calibre plugin versions worked.
-          </p>
-          <p>It appears that FimFiction.net is also blocking access from Google
-            App Engine now.
+            As of Jan 13, 2014, fanfiction.net &amp; fimfiction.net
+            are working again.  I'd ask that users limit the number of
+            stories they download from those sites, thanks.
           </p>
 	  <span id='error'>{{ fic.failure }}</span>
 	  {% endif %}