Bump versions.

app.yaml

@@ -1,6 +1,6 @@
 # ffd-retief-hrd fanfictiondownloader
 application: fanfictiondownloader
-version: 4-4-89
+version: 4-4-90
 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, 06)
+    version             = (1, 8, 07)
     minimum_calibre_version = (1, 13, 0)
 
     #: This field defines the GUI plugin class that contains all the code

calibre-plugin/ffdl_plugin.py

@@ -1393,7 +1393,10 @@ 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),
@@ -1402,12 +1405,10 @@ 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

defaults.ini

@@ -817,12 +817,24 @@ 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]
 ## Some sites require login (or login for some rated stories) The

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_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'):

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 %}
@@ -68,8 +64,9 @@
 	  <h3>Changes:</h3>
 	  <p>
 	    <ul>
-              <li>Alternate URL efiction.trekiverse.org for trekiverse.org/efiction/</li>
-              <li>Minor fixes</li>
+              <li>Change default encoding for finestories.com.</li>
+              <li>Change default encoding and improve metadata for storiesonline.net, thanks davidfor.</li>
+              <li>Fixes for hpfanficarchive.com changes.</li>
 	    </ul>
 	  </p>
           
@@ -81,7 +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://4-4-86.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
+	    <a href="http://4-4-89.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
 	  </p>
 	  <div id='error'>
 	    {{ error_message }}

plugin-defaults.ini

@@ -802,12 +802,24 @@ 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]
 ## Some sites require login (or login for some rated stories) The

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 %}