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: 4-4-91
+version: 4-5-01
 runtime: python27
 api_version: 1
 threadsafe: true

calibre-plugin/__init__.py

@@ -42,7 +42,7 @@ class FanFictionDownLoaderBase(InterfaceActionBase):
     description         = _('UI plugin to download FanFiction stories from various sites.')
     supported_platforms = ['windows', 'osx', 'linux']
     author              = 'Jim Miller'
-    version             = (1, 8, 10)
+    version             = (1, 8, 20)
     minimum_calibre_version = (1, 13, 0)
 
     #: This field defines the GUI plugin class that contains all the code

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 )
@@ -249,6 +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 = []
@@ -753,6 +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/ffdl_plugin.py

@@ -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$"'%re.sub(r'https?\:','https?(\:|\|)',re.escape(story.getMetadata('seriesUrl')))
+            searchstr = 'identifiers:"~ur(i|l):~^%s$"'%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)
@@ -925,13 +941,6 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                 if len(identicalbooks) < 1:
                     # find dups
                     authlist = story.getList("author", removeallentities=True)
-                    if len(authlist) > 100 and calibre_version < (0, 8, 61):
-                        ## should be fixed from 0.8.61 on.  In the
-                        ## meantime, if it matches the title *and* first
-                        ## 100 authors, I'm prepared to assume it's a
-                        ## match.
-                        logger.debug("reduce author list to 100 only when calibre < 0.8.61")
-                        authlist = authlist[:100]
                     mi = MetaInformation(story.getMetadata("title", removeallentities=True),
                                          authlist)
                     identicalbooks = db.find_identical_books(mi)
@@ -961,7 +970,8 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                 if book_id and mi: # book_id and mi only set if matched by title/author.
                     liburl = self.get_story_url(db,book_id)
                     if book['url'] != liburl and prefs['checkforurlchange'] and \
-                        not (book['url'].replace('https','http') == liburl and 'fanfiction.net' in liburl):
+                        not (book['url'].replace('https','http') == liburl): # several sites have been changing to
+                                                                             # https now.  Don't flag when that's the only change.
                         # special case for ffnet urls change to https.
                         if not question_dialog(self.gui, _('Change Story URL?'),'''
                                                   <h3>%s</h3>
@@ -1138,6 +1148,7 @@ 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,
@@ -1232,7 +1243,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             cp_plugin = self.gui.iactions['Count Pages']
             cp_plugin.count_statistics(all_ids,prefs['countpagesstats'])
 
-        if prefs['autoconvert']:
+        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)
 
@@ -1339,7 +1350,6 @@ 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:
@@ -1441,8 +1451,18 @@ 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
 
@@ -1576,6 +1596,13 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                         else:
                             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':
@@ -1599,30 +1626,23 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         if 'authorUrl' in book['all_metadata']:
             authurls = book['all_metadata']['authorUrl'].split(", ")
             authorlist = [ a.replace('&',';') for a in book['author'] ]
-            if hasattr(db, 'new_api'): # new_api starts in calibre 1.0.0
-                authorids = db.new_api.get_item_ids('authors',authorlist)
-                authordata = db.new_api.author_data(authorids.values())
-                # print("\n\nauthorids:%s"%authorids)
-                # print("authordata:%s"%authordata)
+            authorids = db.new_api.get_item_ids('authors',authorlist)
+            authordata = db.new_api.author_data(authorids.values())
+            # print("\n\nauthorids:%s"%authorids)
+            # print("authordata:%s"%authordata)
 
-                author_id_to_link_map = dict()
-                for i, author in enumerate(authorlist):
-                    author_id_to_link_map[authorids[author]] = authurls[i]
+            author_id_to_link_map = dict()
+            for i, author in enumerate(authorlist):
+                author_id_to_link_map[authorids[author]] = authurls[i]
 
-                # print("author_id_to_link_map:%s\n\n"%author_id_to_link_map)
-                db.new_api.set_link_for_authors(author_id_to_link_map)
-            else:
-                # keep for pre-calibre 1.0.0
-                for i, auth in enumerate(authorlist):
-                    #print("===Update author url for %s to %s"%(auth,authurls[i]))
-                    autid=db.get_author_id(auth)
-                    db.set_link_field_for_author(autid, unicode(authurls[i]),
-                                             commit=False, notify=False)
+            # print("author_id_to_link_map:%s\n\n"%author_id_to_link_map)
+            db.new_api.set_link_for_authors(author_id_to_link_map)
+            
         db.commit()
 
         if 'Generate Cover' in self.gui.iactions and (book['added'] or not prefs['gcnewonly']):
 
-            logger.debug("Do Generate Cover added:%s gcnewonly:%s"%(book['added'],prefs['gcnewonly']))
+            #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
@@ -1665,6 +1685,28 @@ 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":
+                    # 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 []
@@ -1753,6 +1795,7 @@ 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
     
@@ -1829,13 +1872,15 @@ 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

@@ -57,6 +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.
@@ -214,7 +219,32 @@ extratags: FanFiction
 # .*-Centered=>
 # characters=>Sam W\.=>Sam Witwicky&&category=>Transformers
 # characters=>Sam W\.=>Sam Winchester&&category=>Supernatural
- 
+
+## Include/Exclude metadata
+##
+## You can use the include/exclude metadata features to either limit
+## the values of particular metadata lists to specific values or to
+## exclude specific values.  Further, you can conditionally apply each
+## line depending on other metadata, use exact strings or regular
+## expressions(regex) to match values, and negate matches.
+##
+## The settings are:
+## include_metadata_pre
+## exclude_metadata_pre
+## include_metadata_post
+## exclude_metadata_post
+##
+## The form of each line is:
+## metakey[,metakey]==exactvalue
+## metakey[,metakey]=~regex
+## metakey[,metakey]==exactvalue&&conditionalkey==exactcondvalue
+## metakey[,metakey]=~regex&&conditionalkey==exactcondvalue
+## metakey[,metakey]==exactvalue&&conditionalkey=~condregex
+##
+## This is fairly complicated, so it's documented on its own wiki
+## page:
+## https://code.google.com/p/fanficdownloader/wiki/InExcludeMetadataFeature
+
 ## Some readers don't show horizontal rule (<hr />) tags correctly.
 ## This replaces them all with a centered '* * *'.  (Note centering
 ## doesn't work on some devices either.)
@@ -568,6 +598,12 @@ include_in_freefromtags:freeformtags
 ## adds to include_subject_tags instead of replacing it.
 #extra_subject_tags:fandoms,freeformtags,ao3categories
 
+## AO3 chapters can include several different types of notes.  We've
+## traditional included them all in the chapter text, but this allows
+## you to customize which you include.  Copy this parameter to your
+## personal.ini and list the ones you don't want.
+#exclude_notes:authorheadnotes,chaptersummary,chapterheadnotes,chapterfootnotes,authorfootnotes
+
 [ashwinder.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
@@ -1215,6 +1251,11 @@ 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
@@ -1223,13 +1264,20 @@ 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
@@ -1291,6 +1339,11 @@ extra_valid_entries:reviews,favs,follows
 ## when updating to enforce accurate chapters.
 #do_update_hook:false
 
+## fimfiction.net is reported to misinterprete some BBCode with
+## blockquotes incorrectly.  This fixes those instances and defaults
+## to on, but can be switched off if it is found to cause problems.
+fix_fimf_blockquotes:true
+
 ## Site dedicated to these categories/characters/ships
 extracategories:My Little Pony: Friendship is Magic
 

downloader.py

@@ -270,31 +270,29 @@ def main(argv,
            elif chaptercount == 0:
                print "%s doesn't contain any recognizable chapters, probably from a different source.  Not updating." % (output_filename)
            else:
-               if not options.metaonly:
+               # update now handled by pre-populating the old
+               # images and chapters in the adapter rather than
+               # merging epubs.
+               (url,
+                chaptercount,
+                adapter.oldchapters,
+                adapter.oldimgs,
+                adapter.oldcover,
+                adapter.calibrebookmark,
+                adapter.logfile) = get_update_data(output_filename)
 
-                   # update now handled by pre-populating the old
-                   # images and chapters in the adapter rather than
-                   # merging epubs.
-                   (url,
-                    chaptercount,
-                    adapter.oldchapters,
-                    adapter.oldimgs,
-                    adapter.oldcover,
-                    adapter.calibrebookmark,
-                    adapter.logfile) = get_update_data(output_filename)
+               print "Do update - epub(%d) vs url(%d)" % (chaptercount, urlchaptercount)
 
-                   print "Do update - epub(%d) vs url(%d)" % (chaptercount, urlchaptercount)
+               if not (options.update and chaptercount == urlchaptercount) \
+                       and adapter.getConfig("do_update_hook"):
+                   chaptercount = adapter.hookForUpdates(chaptercount)
 
-                   if not (options.update and chaptercount == urlchaptercount) \
-                           and adapter.getConfig("do_update_hook"):
-                       chaptercount = adapter.hookForUpdates(chaptercount)
-
-                   writeStory(configuration,adapter,"epub")
+               writeStory(configuration,adapter,"epub")
                    
        else:
            # regular download
            if options.metaonly:
-               print adapter.getStoryMetadataOnly()
+               print adapter.getStoryMetadataOnly().getAllMetadata()
            
            output_filename=writeStory(configuration,adapter,options.format,options.metaonly)
        

fanficdownloader/adapters/__init__.py

@@ -146,6 +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
@@ -153,10 +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
@@ -193,7 +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

@@ -84,7 +84,7 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
     def getSiteURLPattern(self):
         # http://archiveofourown.org/collections/Smallville_Slash_Archive/works/159770
         # Discard leading zeros from story ID numbers--AO3 doesn't use them in it's own chapter URLs.
-        return re.escape("http://")+re.escape(self.getSiteDomain())+r"(/collections/[^/]+)?/works/0*(?P<id>\d+)"
+        return r"https?://"+re.escape(self.getSiteDomain())+r"(/collections/[^/]+)?/works/0*(?P<id>\d+)"
         
     ## Login
     def needToLoginCheck(self, data):
@@ -145,10 +145,13 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
             
         except urllib2.HTTPError, e:
             if e.code == 404:
-                raise exceptions.StoryDoesNotExist(self.meta)
+                raise exceptions.StoryDoesNotExist(self.url)
             else:
                 raise e
-                
+
+        if "Sorry, we couldn&#x27;t find the work you were looking for." in data:
+            raise exceptions.StoryDoesNotExist(self.url)
+            
         if self.needToLoginCheck(data):
             # need to log in for this one.
             self.performLogin(url,data)
@@ -321,25 +324,31 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
         chapter=bs.BeautifulSoup('<div class="story"></div>').find('div')
         data = self._fetchUrl(url)
         soup = bs.BeautifulSoup(data,selfClosingTags=('br','hr'))
-		
-        headnotes = soup.find('div', {'class' : "preface group"}).find('div', {'class' : "notes module"})
-        if headnotes != None:
-            headnotes = headnotes.find('blockquote', {'class' : "userstuff"})
+
+        exclude_notes=self.getConfigList('exclude_notes')
+
+        if 'authorheadnotes' not in exclude_notes:
+            headnotes = soup.find('div', {'class' : "preface group"}).find('div', {'class' : "notes module"})
             if headnotes != None:
-                chapter.append("<b>Author's Note:</b>")
-                chapter.append(headnotes)
+                headnotes = headnotes.find('blockquote', {'class' : "userstuff"})
+                if headnotes != None:
+                    chapter.append("<b>Author's Note:</b>")
+                    chapter.append(headnotes)
         
-        chapsumm = soup.find('div', {'id' : "summary"})
-        if chapsumm != None:
-            chapsumm = chapsumm.find('blockquote')
-            chapter.append("<b>Summary for the Chapter:</b>")
-            chapter.append(chapsumm)
-        chapnotes = soup.find('div', {'id' : "notes"})
-        if chapnotes != None:
-            chapnotes = chapnotes.find('blockquote')
+        if 'chaptersummary' not in exclude_notes:
+            chapsumm = soup.find('div', {'id' : "summary"})
+            if chapsumm != None:
+                chapsumm = chapsumm.find('blockquote')
+                chapter.append("<b>Summary for the Chapter:</b>")
+                chapter.append(chapsumm)
+                
+        if 'chapterheadnotes' not in exclude_notes:
+            chapnotes = soup.find('div', {'id' : "notes"})
             if chapnotes != None:
-                chapter.append("<b>Notes for the Chapter:</b>")
-                chapter.append(chapnotes)
+                chapnotes = chapnotes.find('blockquote')
+                if chapnotes != None:
+                    chapter.append("<b>Notes for the Chapter:</b>")
+                    chapter.append(chapnotes)
 		
         text = soup.find('div', {'class' : "userstuff module"})
         chtext = text.find('h3', {'class' : "landmark heading"})
@@ -347,17 +356,19 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
             chtext.extract()
         chapter.append(text)
 		
-        chapfoot = soup.find('div', {'class' : "end notes module", 'role' : "complementary"})
-        if chapfoot != None:
-            chapfoot = chapfoot.find('blockquote')
-            chapter.append("<b>Notes for the Chapter:</b>")
-            chapter.append(chapfoot)
+        if 'chapterfootnotes' not in exclude_notes:
+            chapfoot = soup.find('div', {'class' : "end notes module", 'role' : "complementary"})
+            if chapfoot != None:
+                chapfoot = chapfoot.find('blockquote')
+                chapter.append("<b>Notes for the Chapter:</b>")
+                chapter.append(chapfoot)
 		
-        footnotes = soup.find('div', {'id' : "work_endnotes"})
-        if footnotes != None:
-            footnotes = footnotes.find('blockquote')
-            chapter.append("<b>Author's Note:</b>")
-            chapter.append(footnotes)
+        if 'authorfootnotes' not in exclude_notes:
+            footnotes = soup.find('div', {'id' : "work_endnotes"})
+            if footnotes != None:
+                footnotes = footnotes.find('blockquote')
+                chapter.append("<b>Author's Note:</b>")
+                chapter.append(footnotes)
 			
         if None == soup:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)

fanficdownloader/adapters/adapter_buffynfaithnet.py

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

fanficdownloader/adapters/adapter_darksolaceorg.py

@@ -241,24 +241,24 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
                 self.story.setMetadata('numWords', value)
 
             if 'Categories' in label:
-                cats = labelspan.parent.findAll('a',href=re.compile(r'categories.php\?catid=\d+'))
+                cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
                 for cat in cats:
                     self.story.addToList('category',cat.string)
 
             if 'Characters' in label:
-                for char in value.string.split(', '):
-                    if not 'None' in char:
-                        self.story.addToList('characters',char)
+                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+                for char in chars:
+                    self.story.addToList('characters',char.string)
 
             if 'Genre' in label:
-                for genre in value.string.split(', '):
-                    if not 'None' in genre:
-                        self.story.addToList('genre',genre)
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
+                for genre in genres:
+                    self.story.addToList('genre',genre.string)
 
             if 'Warnings' in label:
-                for warning in value.string.split(', '):
-                    if not 'None' in warning:
-                        self.story.addToList('warnings',warning)
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2'))
+                for warning in warnings:
+                    self.story.addToList('warnings',warning.string)
 
             if 'Completed' in label:
                 if 'Yes' in value:

fanficdownloader/adapters/adapter_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'
@@ -105,28 +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])

fanficdownloader/adapters/adapter_fictionpadcom.py

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

fanficdownloader/adapters/adapter_fictionpresscom.py

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

fanficdownloader/adapters/adapter_fimfictionnet.py

@@ -59,7 +59,7 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
         return "http://www.fimfiction.net/story/1234/story-title-here http://www.fimfiction.net/story/1234/ http://www.fimfiction.com/story/1234/1/ http://mobile.fimfiction.net/story/1234/1/story-title-here/chapter-title-here"
 
     def getSiteURLPattern(self):
-        return r"http://(www|mobile)\.fimfiction\.(net|com)/story/\d+/?.*"
+        return r"https?://(www|mobile)\.fimfiction\.(net|com)/story/\d+/?.*"
         
     def extractChapterUrlsAndMetadata(self):
         
@@ -85,7 +85,7 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
             
             # Unfortunately, we still need to load the story index
             # page to parse the characters.  And chapters, now, too.
-            data = self._fetchUrl(self.url)
+            data = self.do_fix_blockquotes(self._fetchUrl(self.url))
             soup = bs.BeautifulSoup(data)
         except urllib2.HTTPError, e:
             if e.code == 404:
@@ -101,7 +101,7 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
         # if "/images/missing_story.png" in data:
         #     raise exceptions.StoryDoesNotExist(self.url)
         
-        if "This story has been marked as having adult content." in data:
+        if "This story has been marked as having adult content. Please click below to confirm you are of legal age to view adult material in your country." in data:
             raise exceptions.AdultCheckRequired(self.url)
         
         if self.password:
@@ -249,18 +249,20 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
                     value = unicode(value)
                 self.story.setMetadata(metakey, value)
 
-        #Sequel links and group links are each bundled into story_group_list containers.
-        #Rather than mess around examining the header text, which is outside the containers,
-        #one can tell the two link types apart by examining them directly.
+        ## 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(',', ';'))
-            for sequel in groupList.findAll('a', {'class':'story_link'}):
+
+        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.
@@ -281,12 +283,21 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
             print("Existing epub has %s chapters\nNewest chapter is %s.  Discarding old chapters from there on."%(len(self.oldchapters), self.newestChapterNum+1))
             self.oldchapters = self.oldchapters[:self.newestChapterNum]
         return len(self.oldchapters)
-            
+
+    def do_fix_blockquotes(self,data):
+        if self.getConfig('fix_fimf_blockquotes'):
+            # <p class="double"><blockquote>
+            # </blockquote></p>
+            # include > in re groups so there's always something in the group.
+            data = re.sub(r'<p([^>]*>\s*)<blockquote([^>]*>)',r'<blockquote\2<p\1',data)
+            data = re.sub(r'</blockquote(>\s*)</p>',r'</p\1</blockquote>',data)
+        return data
         
     def getChapterText(self, url):
         logger.debug('Getting chapter text from: %s' % url)
-        
-        soup = bs.BeautifulSoup(self._fetchUrl(url),selfClosingTags=('br','hr')).find('div', {'class' : 'chapter_content'})
+
+        data = self.do_fix_blockquotes(self._fetchUrl(url))
+        soup = bs.BeautifulSoup(data,selfClosingTags=('br','hr')).find('div', {'class' : 'chapter_content'})
         if soup == None:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
         return self.utf8FromSoup(url,soup)

fanficdownloader/adapters/adapter_hpfanficarchivecom.py

@@ -160,6 +160,11 @@ class HPFanficArchiveComAdapter(BaseSiteAdapter):
                 for genre in genres:
                     self.story.addToList('genre',genre.string)
 
+            if 'Pairing' in label:
+                ships = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=4'))
+                for ship in ships:
+                    self.story.addToList('ships',ship.string)
+
             if 'Warnings' in label:
                 warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')) # XXX
                 for warning in warnings:

fanficdownloader/adapters/adapter_literotica.py

@@ -203,7 +203,7 @@ class LiteroticaSiteAdapter(BaseSiteAdapter):
         # get story text
         story1 = soup1.find('div', 'b-story-body-x').p
         story1.name='div'
-        story1.append('<br>')
+        story1.append('<br />')
         storytext = self.utf8FromSoup(url,story1)
 
         # find num pages
@@ -220,7 +220,7 @@ class LiteroticaSiteAdapter(BaseSiteAdapter):
                 [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>')
+                story2.append('<br />')
                 storytext += self.utf8FromSoup(url,story2)
             except urllib2.HTTPError, e:
                 if e.code == 404:

fanficdownloader/adapters/adapter_onedirectionfanfictioncom.py

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

fanficdownloader/adapters/adapter_potionsandsnitchesnet.py

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

fanficdownloader/adapters/adapter_squidgeorgpeja.py

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

fanficdownloader/adapters/adapter_storiesonlinenet.py

@@ -66,7 +66,7 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
         return "http://"+self.getSiteDomain()+"/s/1234 http://"+self.getSiteDomain()+"/s/1234:4010"
 
     def getSiteURLPattern(self):
-        return re.escape("http://"+self.getSiteDomain())+r"/s/\d+((:\d+)?(;\d+)?$|(:i)?$)"
+        return re.escape("http://"+self.getSiteDomain())+r"/s/\d+((:\d+)?(;\d+)?$|(:i)?$)?"
 
     ## Login seems to be reasonably standard across eFiction sites.
     def needToLoginCheck(self, data):
@@ -171,7 +171,7 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
 
             a = asoup.findAll('td', {'class' : 'lc2'})
             for lc2 in a:
-                if lc2.find('a')['href'] == '/s/'+self.story.getMetadata('storyId'):
+                if lc2.find('a', href=re.compile(r'^/s/'+self.story.getMetadata('storyId'))):
                     i=1
                     break
                 if a[len(a)-1] == lc2:

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/base_adapter.py

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

@@ -221,6 +221,65 @@ langs = {
     "Devanagari":"hi",
     }
 
+class InExMatch:
+    keys = []
+    regex = None
+    match = None
+    negate = False
+
+    def  __init__(self,line):
+        if "=~" in line:
+            (self.keys,self.match) = line.split("=~")
+            self.match = self.match.replace('\s',' ')
+            self.regex = re.compile(self.match)
+        elif "!~" in line:
+            (self.keys,self.match) = line.split("!~")
+            self.match = self.match.replace('\s',' ')
+            self.regex = re.compile(self.match)
+            self.negate = True
+        elif "==" in line:
+            (self.keys,self.match) = line.split("==")
+            self.match = self.match.replace('\s',' ')
+        elif "!=" in line:
+            (self.keys,self.match) = line.split("!=")
+            self.match = self.match.replace('\s',' ')
+            self.negate = True
+        self.keys = map( lambda x: x.strip(), self.keys.split(",") )
+
+    # For conditional, only one key
+    def is_key(self,key):
+        return key == self.keys[0]
+
+    # For conditional, only one key
+    def key(self):
+        return self.keys[0]
+
+    def in_keys(self,key):
+        return key in self.keys
+
+    def is_match(self,value):
+        retval = False
+        if self.regex:
+            if self.regex.search(value):
+                retval = True
+            #print(">>>>>>>>>>>>>%s=~%s r: %s,%s=%s"%(self.match,value,self.negate,retval,self.negate != retval))
+        else:
+            retval = self.match == value
+            #print(">>>>>>>>>>>>>%s==%s r: %s,%s=%s"%(self.match,value,self.negate,retval, self.negate != retval))
+            
+        return self.negate != retval
+
+    def __str__(self):
+        if self.negate:
+            f='!'
+        else:
+            f='='
+        if self.regex:
+            s='~'
+        else:
+            s='='
+        return u'InExMatch(%s %s%s %s)'%(self.keys,f,s,self.match)
+
 class Story(Configurable):
 
     def __init__(self, configuration):
@@ -231,6 +290,7 @@ class Story(Configurable):
         except:
             self.metadata = {'version':'4.4'}
         self.replacements = []
+        self.in_ex_cludes = {}
         self.chapters = [] # chapters will be tuples of (title,html)
         self.imgurls = []
         self.imgtuples = []
@@ -252,6 +312,15 @@ class Story(Configurable):
 
         self.setReplace(self.getConfig('replace_metadata'))
 
+        in_ex_clude_list = ['include_metadata_pre','exclude_metadata_pre',
+                            'include_metadata_post','exclude_metadata_post']
+        for ie in in_ex_clude_list:
+            ies = self.getConfig(ie)
+            # print("%s %s"%(ie,ies))
+            if ies:
+                iel = []
+                self.in_ex_cludes[ie] = self.set_in_ex_clude(ies)
+
     def setMetadata(self, key, value, condremoveentities=True):
         ## still keeps < < and &
         if condremoveentities:
@@ -269,6 +338,56 @@ class Story(Configurable):
             self.addToList('lastupdate',value.strftime("Last Update Year/Month: %Y/%m"))
             self.addToList('lastupdate',value.strftime("Last Update: %Y/%m/%d"))
 
+        
+    ## metakey[,metakey]=~pattern
+    ## metakey[,metakey]==string
+    ## *for* part lines.  Effect only when trailing conditional key=~regexp matches
+    ## metakey[,metakey]=~pattern[&&metakey=~regexp]
+    ## metakey[,metakey]==string[&&metakey=~regexp]
+    ## metakey[,metakey]=~pattern[&&metakey==string]
+    ## metakey[,metakey]==string[&&metakey==string]
+    def set_in_ex_clude(self,setting):
+        dest = []
+        # print("set_in_ex_clude:"+setting)
+        for line in setting.splitlines():
+            if line:
+                (match,condmatch)=(None,None)
+                if "&&" in line:
+                    (line,conditional) = line.split("&&")
+                    condmatch = InExMatch(conditional)
+                match = InExMatch(line)
+                dest.append([match,condmatch])
+        return dest
+              
+    def do_in_ex_clude(self,which,value,key):
+        if value and which in self.in_ex_cludes:
+            include = 'include' in which
+            keyfound = False
+            found = False
+            for (match,condmatch) in self.in_ex_cludes[which]:
+                keyfndnow = False
+                if match.in_keys(key):
+                    # key in keys and either no conditional, or conditional matched
+                    if condmatch == None or condmatch.is_key(key):
+                        keyfndnow = True
+                    else:
+                        condval = self.getMetadata(condmatch.key())
+                        keyfndnow = condmatch.is_match(condval)
+                    keyfound |= keyfndnow
+                        # print("match:%s %s\ncondmatch:%s %s\n\tkeyfound:%s\n\tfound:%s"%(
+                        #         match,value,condmatch,condval,keyfound,found))
+                    if keyfndnow:
+                        found = isinstance(value,basestring) and match.is_match(value)
+                    if found:
+                        # print("match:%s %s\n\tkeyfndnow:%s\n\tfound:%s"%(
+                        #         match,value,keyfndnow,found))
+                        if not include:
+                            value = None
+                        break
+            if include and keyfound and not found:
+                value = None
+        return value
+        
 
     ## Two or three part lines.  Two part effect everything.
     ## Three part effect only those key(s) lists.
@@ -301,6 +420,10 @@ class Story(Configurable):
                 self.replacements.append([metakeys,regexp,replacement,condkey,condregexp])
 
     def doReplacements(self,value,key):
+        value = self.do_in_ex_clude('include_metadata_pre',value,key)
+        value = self.do_in_ex_clude('exclude_metadata_pre',value,key)
+        # if key=='characters' and value=='Bilbo':
+        #     value = ''
         for (metakeys,regexp,replacement,condkey,condregexp) in self.replacements:
             if (metakeys == None or key in metakeys) \
                     and isinstance(value,basestring) \
@@ -312,6 +435,8 @@ class Story(Configurable):
 
                 if doreplace:
                     value = regexp.sub(replacement,value)
+        value = self.do_in_ex_clude('include_metadata_post',value,key)
+        value = self.do_in_ex_clude('exclude_metadata_post',value,key)
         return value
 
     def getMetadataRaw(self,key):
@@ -573,7 +698,13 @@ class Story(Configurable):
             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,

index.html

@@ -64,10 +64,12 @@
 	  <h3>Changes:</h3>
 	  <p>
 	    <ul>
-              <li>Fix for possible divide-by-zero in replace_br_with_p.</li>
+              <li>Fix for AO3 story not found.</li>
+              <li>Fix for storiesonline.net changing urls.</li>
+              <li>Fix for fictionpad.com removing 'dislikes' in some(all?) cases.</li>
+              <li>Fix for dark-solace.org metadata parsing.</li>
 	    </ul>
 	  </p>
-          
 	  <p>
 	    Questions?  Check out our 
 	    <a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownloaderFAQs">FAQs</a>.
@@ -76,7 +78,7 @@
 	    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://4-4-90.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
+	    <a href="http://4-5-00.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)
@@ -181,7 +186,32 @@ extratags: FanFiction
 # .*-Centered=>
 # characters=>Sam W\.=>Sam Witwicky&&category=>Transformers
 # characters=>Sam W\.=>Sam Winchester&&category=>Supernatural
- 
+
+## Include/Exclude metadata
+##
+## You can use the include/exclude metadata features to either limit
+## the values of particular metadata lists to specific values or to
+## exclude specific values.  Further, you can conditionally apply each
+## line depending on other metadata, use exact strings or regular
+## expressions(regex) to match values, and negate matches.
+##
+## The settings are:
+## include_metadata_pre
+## exclude_metadata_pre
+## include_metadata_post
+## exclude_metadata_post
+##
+## The form of each line is:
+## metakey[,metakey]==exactvalue
+## metakey[,metakey]=~regex
+## metakey[,metakey]==exactvalue&&conditionalkey==exactcondvalue
+## metakey[,metakey]=~regex&&conditionalkey==exactcondvalue
+## metakey[,metakey]==exactvalue&&conditionalkey=~condregex
+##
+## This is fairly complicated, so it's documented on its own wiki
+## page:
+## https://code.google.com/p/fanficdownloader/wiki/InExcludeMetadataFeature
+
 ## Some readers don't show horizontal rule (<hr />) tags correctly.
 ## This replaces them all with a centered '* * *'.  (Note centering
 ## doesn't work on some devices either.)
@@ -537,6 +567,12 @@ include_in_freefromtags:freeformtags
 ## adds to include_subject_tags instead of replacing it.
 #extra_subject_tags:fandoms,freeformtags,ao3categories
 
+## AO3 chapters can include several different types of notes.  We've
+## traditional included them all in the chapter text, but this allows
+## you to customize which you include.  Copy this parameter to your
+## personal.ini and list the ones you don't want.
+#exclude_notes:authorheadnotes,chaptersummary,chapterheadnotes,chapterfootnotes,authorfootnotes
+
 [ashwinder.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
@@ -1202,6 +1238,20 @@ 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
@@ -1210,13 +1260,20 @@ 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
@@ -1275,6 +1332,11 @@ extra_valid_entries:reviews,favs,follows
 ## when updating to enforce accurate chapters.
 #do_update_hook:false
 
+## fimfiction.net is reported to misinterprete some BBCode with
+## blockquotes incorrectly.  This fixes those instances and defaults
+## to on, but can be switched off if it is found to cause problems.
+fix_fimf_blockquotes:true
+
 ## Site dedicated to these categories/characters/ships
 extracategories:My Little Pony: Friendship is Magic