Update CLI download zip.

app.yaml

@@ -1,6 +1,6 @@
 # ffd-retief-hrd fanfictiondownloader
 application: fanfictiondownloader
-version: 4-4-97
+version: 4-5-05
 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, 16)
+    version             = (1, 8, 24)
     minimum_calibre_version = (1, 13, 0)
 
     #: This field defines the GUI plugin class that contains all the code

calibre-plugin/ffdl_plugin.py

@@ -970,7 +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>
@@ -1984,11 +1985,12 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             for (k,v) in b['all_metadata'].iteritems():
                 #print("merge_meta_books v:%s k:%s"%(v,k))
                 if k in ('numChapters','numWords'):
-                    if k not in book['all_metadata']:
-                        book['all_metadata'][k] = b['all_metadata'][k]
-                    else:
-                        # lot of work for a simple add.
-                        book['all_metadata'][k] = unicode(int(book['all_metadata'][k].replace(',',''))+int(b['all_metadata'][k].replace(',','')))
+                    if k in b['all_metadata'] and b['all_metadata'][k]:
+                        if k not in book['all_metadata']:
+                            book['all_metadata'][k] = b['all_metadata'][k]
+                        else:
+                            # lot of work for a simple add.
+                            book['all_metadata'][k] = unicode(int(book['all_metadata'][k].replace(',',''))+int(b['all_metadata'][k].replace(',','')))
                 elif k in ('dateUpdated','datePublished','dateCreated',
                            'series','status','title'):
                     pass # handled above, below or skip these for now, not going to do anything with them.
@@ -2003,7 +2005,9 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                         # cust cols can convert back to numbers and
                         # add.
                         book['anthology_meta_list'][k]=True
-    
+
+        print("book['url']:%s"%book['url'])
+        configuration = get_ffdl_config(book['url'],fileform)
         if existingbook:
             book['title'] = deftitle = existingbook['title']
             book['comments'] = existingbook['comments']
@@ -2022,7 +2026,6 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                         book['title'] = deftitle
                         break
             
-            configuration = get_ffdl_config(book['url'],fileform)
             logger.debug("anthology_title_pattern:%s"%configuration.getConfig('anthology_title_pattern'))
             if configuration.getConfig('anthology_title_pattern'):
                 tmplt = Template(configuration.getConfig('anthology_title_pattern'))
@@ -2038,7 +2041,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         for v in ['Completed','In-Progress']:
             if v in book['tags']:
                 book['tags'].remove(v)
-        book['tags'].append('Anthology')
+        book['tags'].extend(configuration.getConfigList('anthology_tags'))
         book['all_metadata']['anthology'] = "true"
         
         return book

defaults.ini

@@ -219,7 +219,32 @@ connect_timeout:60.0
 # .*-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.)
@@ -601,6 +626,29 @@ extracategories:The Sentinel
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+[bloodshedverse.com]
+## website encoding(s) In theory, each website reports the character
+## encoding they use for each page.  In practice, some sites report it
+## incorrectly.  Each adapter has a default list, usually "utf8,
+## Windows-1252" or "Windows-1252, utf8", but this will let you
+## explicitly set the encoding and order if you need to.  The special
+## value 'auto' will call chardet and use the encoding it reports if
+## it has +90% confidence.  'auto' is not reliable.
+website_encodings:ISO-8859-1,auto
+
+## Extra metadata that this adapter knows about.  See [dramione.org]
+## for examples of how to use them.
+extra_valid_entries:warnings,reviews
+reviews_label:Reviews
+
+## Site dedicated to these categories/characters/ships
+extracharacters:Spike,Buffy
+extracategories:Buffy the Vampire Slayer
+
+## Strips links found in the story text
+## Specific to bloodshedverse.com
+strip_text_links:true
+
 [bloodties-fans.com]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -742,6 +790,38 @@ extracategories:Harry Potter
 ## cover image.  This lets you exclude them.
 cover_exclusion_regexp:/images/.*?ribbon.gif
 
+[fanfiction.csodaidok.hu]
+## website encoding(s) In theory, each website reports the character
+## encoding they use for each page.  In practice, some sites report it
+## incorrectly.  Each adapter has a default list, usually "utf8,
+## Windows-1252" or "Windows-1252, utf8", but this will let you
+## explicitly set the encoding and order if you need to.  The special
+## value 'auto' will call chardet and use the encoding it reports if
+## it has +90% confidence.  'auto' is not reliable.
+website_encodings:ISO-8859-2,auto
+
+## Extra metadata that this adapter knows about.  See [dramione.org]
+## for examples of how to use them.
+extra_valid_entries:reviews,challenge
+reviews_label:Reviews
+challenge_label:Challenge
+
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
+[fanfic.hu]
+## website encoding(s) In theory, each website reports the character
+## encoding they use for each page.  In practice, some sites report it
+## incorrectly.  Each adapter has a default list, usually "utf8,
+## Windows-1252" or "Windows-1252, utf8", but this will let you
+## explicitly set the encoding and order if you need to.  The special
+## value 'auto' will call chardet and use the encoding it reports if
+## it has +90% confidence.  'auto' is not reliable.
+website_encodings:ISO-8859-1,auto
+
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 [fanfiction.mugglenet.com]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
@@ -792,6 +872,14 @@ extraships:Harry Potter/Hermione Granger
 #username:YourName
 #password:yourpassword
 
+[ficwad.com]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
 [fictionpad.com]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -948,6 +1036,17 @@ extracategories:NCIS
 extracategories:Buffy: The Vampire Slayer
 extracharacters:Willow
 
+[nocturnal-light.net]
+## Extra metadata that this adapter knows about.  See [dramione.org]
+## for examples of how to use them.
+extra_valid_entries:readings,reviews
+readings_label:Readings
+reviews_label:Reviews
+
+## Site dedicated to these categories/characters/ships
+extracharacters:Spike,Buffy
+extracategories:Buffy the Vampire Slayer
+
 [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
@@ -1038,6 +1137,16 @@ extracategories:Harry Potter
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+[spikeluver.com]
+## Extra metadata that this adapter knows about.  See [dramione.org]
+## for examples of how to use them.
+extra_valid_entries:warnings,reviews
+reviews_label:Reviews
+
+## Site dedicated to these categories/characters/ships
+extracharacters:Spike,Buffy
+extracategories:Buffy the Vampire Slayer
+
 [stargate-atlantis.org]
 ## Site dedicated to these categories/characters/ships
 extracategories:Stargate: Atlantis
@@ -1136,6 +1245,13 @@ awards_label:Awards
 
 cover_exclusion_regexp:art/.*Awards.jpg
 
+[voracity2.e-fic.com]
+## Extra metadata that this adapter knows about.  See [dramione.org]
+## for examples of how to use them.
+extra_valid_entries:reviews,readings
+reviews_label:Reviews
+readings_label:Readings
+
 [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,
@@ -1288,14 +1404,6 @@ extratags:
 ## for examples of how to use them.
 extra_valid_entries:reviews,favs,follows
 
-[ficwad.com]
-## Some sites require login (or login for some rated stories) The
-## program can prompt you, or you can save it in config.  In
-## commandline version, this should go in your personal.ini, not
-## defaults.ini.
-#username:YourName
-#password:yourpassword
-
 [www.fimfiction.net]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
@@ -1314,6 +1422,11 @@ 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

@@ -23,6 +23,7 @@ import getpass
 import string
 import ConfigParser
 from subprocess import call
+import pprint
 
 import logging
 if sys.version_info >= (2, 7):
@@ -292,7 +293,7 @@ def main(argv,
        else:
            # regular download
            if options.metaonly:
-               print adapter.getStoryMetadataOnly()
+               pprint.pprint(adapter.getStoryMetadataOnly().getAllMetadata())
            
            output_filename=writeStory(configuration,adapter,options.format,options.metaonly)
        

fanficdownloader/adapters/__init__.py

@@ -123,6 +123,12 @@ import adapter_fictionpadcom
 import adapter_storiesonlinenet
 import adapter_trekiverseorg
 import adapter_literotica
+import adapter_voracity2eficcom
+import adapter_spikeluvercom
+import adapter_bloodshedversecom
+import adapter_nocturnallightnet
+import adapter_fanfichu
+import adapter_fanfictioncsodaidokhu
 
 ## This bit of complexity allows adapters to be added by just adding
 ## importing.  It eliminates the long if/else clauses we used to need
@@ -206,7 +212,7 @@ def getClassFor(url):
         fixedurl = "http://%s"%url
     ## remove any trailing '#' locations.
     fixedurl = re.sub(r"#.*$","",fixedurl)
-    
+
     parsedUrl = up.urlparse(fixedurl)
     domain = parsedUrl.netloc.lower()
     if( domain != parsedUrl.netloc ):

fanficdownloader/adapters/adapter_archiveofourownorg.py

@@ -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'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)

fanficdownloader/adapters/adapter_bloodshedversecom.py

@@ -0,0 +1,192 @@
+from datetime import timedelta
+import re
+import urllib2
+import urlparse
+
+from .. import BeautifulSoup
+
+from base_adapter import BaseSiteAdapter, makeDate
+from .. import exceptions
+
+
+def getClass():
+    return BloodshedverseComAdapter
+
+
+def _get_query_data(url):
+    components = urlparse.urlparse(url)
+    query_data = urlparse.parse_qs(components.query)
+    return dict((key, data[0]) for key, data in query_data.items())
+
+
+class BloodshedverseComAdapter(BaseSiteAdapter):
+    SITE_ABBREVIATION = 'bvc'
+    SITE_DOMAIN = 'bloodshedverse.com'
+
+    BASE_URL = 'http://' + SITE_DOMAIN + '/'
+    READ_URL_TEMPLATE = BASE_URL + 'stories.php?go=read&no=%s'
+
+    STARTED_DATETIME_FORMAT = '%m/%d/%Y'
+    UPDATED_DATETIME_FORMAT = '%m/%d/%Y %I:%M'
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        query_data = urlparse.parse_qs(self.parsedUrl.query)
+        story_no = query_data['no'][0]
+
+        self.story.setMetadata('storyId', story_no)
+        self._setURL(self.READ_URL_TEMPLATE % story_no)
+        self.story.setMetadata('siteabbrev', self.SITE_ABBREVIATION)
+
+    def _customized_fetch_url(self, url, exception=None, parameters=None):
+        if exception:
+            try:
+                data = self._fetchUrl(url, parameters)
+            except urllib2.HTTPError:
+                raise exception(self.url)
+        # Just let self._fetchUrl throw the exception, don't catch and
+        # customize it.
+        else:
+            data = self._fetchUrl(url, parameters)
+
+        return BeautifulSoup.BeautifulSoup(data)
+
+    @staticmethod
+    def getSiteDomain():
+        return BloodshedverseComAdapter.SITE_DOMAIN
+
+    @classmethod
+    def getSiteExampleURLs(cls):
+        return cls.READ_URL_TEMPLATE % 1234
+
+    def getSiteURLPattern(self):
+        return re.escape(self.BASE_URL + 'stories.php?go=') + r'(read|chapters)\&no=\d+$'
+
+    # Override stripURLParameters so the "no" parameter won't get stripped
+    @classmethod
+    def stripURLParameters(cls, url):
+        return url
+
+    def extractChapterUrlsAndMetadata(self):
+        soup = self._customized_fetch_url(self.url)
+
+        # Since no 404 error code we have to raise the exception ourselves.
+        # A title that is just 'by' indicates that there is no author name
+        # and no story title available.
+        if soup.title.string.strip() == 'by':
+            raise exceptions.StoryDoesNotExist(self.url)
+
+        for option in soup.find('select', {'name': 'chapter'}):
+            title = option.string.strip()
+            url = self.READ_URL_TEMPLATE % option['value']
+            self.chapterUrls.append((title, url))
+
+        # Get the URL to the author's page and find the correct story entry to
+        # scrape the metadata
+        author_url = urlparse.urljoin(self.url, soup.find('a', {'class': 'headline'})['href'])
+        soup = self._customized_fetch_url(author_url)
+
+        story_no = self.story.getMetadata('storyId')
+        # Ignore first list_box div, it only contains the author information
+        for list_box in soup('div', {'class': 'list_box'})[1:]:
+            url = list_box.find('a', {'class': 'fictitle'})['href']
+            query_data = _get_query_data(url)
+
+            # Found the div containing the story's metadata; break the loop and
+            # parse the element
+            if query_data['no'] == story_no:
+                break
+        else:
+            raise exceptions.FailedToDownload(self.url)
+
+        title_anchor = list_box.find('a', {'class': 'fictitle'})
+        self.story.setMetadata('title', title_anchor.string.strip())
+
+        author_anchor = title_anchor.findNextSibling('a')
+        self.story.setMetadata('author', author_anchor.string.strip())
+        self.story.setMetadata('authorId', _get_query_data(author_anchor['href'])['who'])
+        self.story.setMetadata('authorUrl', urlparse.urljoin(self.url, author_anchor['href']))
+
+        list_review = list_box.find('div', {'class': 'list_review'})
+        reviews = list_review.a.string.strip().split(' ', 1)[0]
+        self.story.setMetadata('reviews', reviews)
+
+        summary_div = list_box.find('div', {'class': 'list_summary'})
+        if not self.getConfig('keep_summary_html'):
+            summary = ''.join(summary_div(text=True))
+        else:
+            summary = self.utf8FromSoup(author_url, summary_div)
+
+        self.story.setMetadata('description', summary)
+
+        # I'm assuming this to be the category, not sure what else it could be
+        first_listinfo = list_box.find('div', {'class': 'list_info'})
+        self.story.addToList('category', first_listinfo.a.string.strip())
+
+        for list_info in first_listinfo.findNextSiblings('div', {'class': 'list_info'}):
+            for b_tag in list_info('b'):
+                key = b_tag.string.strip(': ')
+                # Strip colons from the beginning, superfluous spaces and minus
+                # characters from the end, and possibly trailing commas from
+                # the warnings if only one is present
+                value = b_tag.nextSibling.string.strip(': -,')
+
+                if key == 'Genre':
+                    for genre in value.split(', '):
+                        # Ignore the "none" genre
+                        if not genre == 'none':
+                            self.story.addToList('genre', genre)
+
+                elif key == 'Rating':
+                    self.story.setMetadata('rating', value)
+
+                elif key == 'Complete':
+                    self.story.setMetadata('status', 'Completed' if value == 'Yes' else 'In-Progress')
+
+                elif key == 'Warning':
+                    for warning in value.split(', '):
+                        # The string here starts with ", " before the actual list
+                        # of values sometimes, so check for an empty warning
+                        # and ignore the "none" warning.
+                        if not warning or warning == 'none':
+                            continue
+
+                        self.story.addToList('warnings', warning)
+
+                elif key == 'Chapters':
+                    self.story.setMetadata('numChapters', int(value))
+
+                elif key == 'Words':
+                    # Apparently only numChapters need to be an integer for
+                    # some strange reason. Remove possible ',' characters as to
+                    # not confuse the codebase down the line
+                    self.story.setMetadata('numWords', value.replace(',', ''))
+
+                elif key == 'Started':
+                    self.story.setMetadata('datePublished', makeDate(value, self.STARTED_DATETIME_FORMAT))
+
+                elif key == 'Updated':
+                    date_string, period = value.rsplit(' ', 1)
+                    date = makeDate(date_string, self.UPDATED_DATETIME_FORMAT)
+
+                    # Rather ugly hack to work around Calibre's changing of
+                    # Python's locale setting, causing am/pm to not be properly
+                    # parsed by strptime() when using a non-english locale
+                    if period == 'pm':
+                        date += timedelta(hours=12)
+                    self.story.setMetadata('dateUpdated', date)
+
+        if self.story.getMetadata('rating') == 'NC-17' and not (self.is_adult or self.getConfig('is_adult')):
+            raise exceptions.AdultCheckRequired(self.url)
+
+    def getChapterText(self, url):
+        soup = self._customized_fetch_url(url)
+        storytext_div = soup.find('div', {'class': 'storytext'})
+
+        if self.getConfig('strip_text_links'):
+            for anchor in storytext_div('a', {'class': 'FAtxtL'}):
+                navigable_string = BeautifulSoup.NavigableString(anchor.string)
+                anchor.replaceWith(navigable_string)
+
+        return self.utf8FromSoup(url, storytext_div)

fanficdownloader/adapters/adapter_darksolaceorg.py

@@ -182,6 +182,11 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
 
         # first a tag in pagetitle is title
         self.story.setMetadata('title',stripHTML(div.find('a')))
+        div.find('a').extract()
+        # only thing left in div(pagetitle) now should be 'by' and rating.
+        rating = stripHTML(div)
+        if '[' in rating:
+            self.story.setMetadata('rating', rating[rating.index('[')+1:-1])
 
         for chapa in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+
                                                        self.story.getMetadata('storyId')+'&chapter=\d+')):
@@ -234,31 +239,28 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
                 self.setDescription(url,svalue)
                 #self.story.setMetadata('description',stripHTML(svalue))
 
-            if 'Rated' in label:
-                self.story.setMetadata('rating', value[:len(value)-2])
-
             if 'Word count' in label:
                 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_fanfichu.py

@@ -0,0 +1,185 @@
+# coding=utf-8
+
+import re
+import urllib2
+import urlparse
+
+from .. import BeautifulSoup
+
+from base_adapter import BaseSiteAdapter, makeDate
+from .. import exceptions
+
+
+_SOURCE_CODE_ENCODING = 'utf-8'
+
+
+def getClass():
+    return FanficHuAdapter
+
+
+def _get_query_data(url):
+    components = urlparse.urlparse(url)
+    query_data = urlparse.parse_qs(components.query)
+    return dict((key, data[0]) for key, data in query_data.items())
+
+
+class FanficHuAdapter(BaseSiteAdapter):
+    SITE_ABBREVIATION = 'ffh'
+    SITE_DOMAIN = 'fanfic.hu'
+    SITE_LANGUAGE = 'Hungarian'
+
+    BASE_URL = 'http://' + SITE_DOMAIN + '/merengo/'
+    VIEW_STORY_URL_TEMPLATE = BASE_URL + 'viewstory.php?sid=%s'
+
+    DATE_FORMAT = '%m/%d/%Y'
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        query_data = urlparse.parse_qs(self.parsedUrl.query)
+        story_id = query_data['sid'][0]
+
+        self.story.setMetadata('storyId', story_id)
+        self._setURL(self.VIEW_STORY_URL_TEMPLATE % story_id)
+        self.story.setMetadata('siteabbrev', self.SITE_ABBREVIATION)
+        self.story.setMetadata('language', self.SITE_LANGUAGE)
+
+    def _customized_fetch_url(self, url, exception=None, parameters=None):
+        if exception:
+            try:
+                data = self._fetchUrl(url, parameters)
+            except urllib2.HTTPError:
+                raise exception(self.url)
+        # Just let self._fetchUrl throw the exception, don't catch and
+        # customize it.
+        else:
+            data = self._fetchUrl(url, parameters)
+
+        return BeautifulSoup.BeautifulSoup(data)
+
+    @staticmethod
+    def getSiteDomain():
+        return FanficHuAdapter.SITE_DOMAIN
+
+    @classmethod
+    def getSiteExampleURLs(cls):
+        return cls.VIEW_STORY_URL_TEMPLATE % 1234
+
+    def getSiteURLPattern(self):
+        return re.escape(self.VIEW_STORY_URL_TEMPLATE[:-2]) + r'\d+$'
+
+    def extractChapterUrlsAndMetadata(self):
+        soup = self._customized_fetch_url(self.url + '&i=1')
+
+        if soup.title.string.encode(_SOURCE_CODE_ENCODING).strip(' :') == 'írta':
+            raise exceptions.StoryDoesNotExist(self.url)
+
+        chapter_options = soup.find('form', action='viewstory.php').select('option')
+        # Remove redundant "Fejezetek" option
+        chapter_options.pop(0)
+
+        # If there is still more than one entry remove chapter overview entry
+        if len(chapter_options) > 1:
+            chapter_options.pop(0)
+
+        for option in chapter_options:
+            url = urlparse.urljoin(self.url, option['value'])
+            self.chapterUrls.append((option.string, url))
+
+        author_url = urlparse.urljoin(self.BASE_URL, soup.find('a', href=lambda href: href and href.startswith('viewuser.php?uid='))['href'])
+        soup = self._customized_fetch_url(author_url)
+
+        story_id = self.story.getMetadata('storyId')
+        for table in soup('table', {'class': 'mainnav'}):
+            title_anchor = table.find('span', {'class': 'storytitle'}).a
+            href = title_anchor['href']
+            if href.startswith('javascript:'):
+                href = href.rsplit(' ', 1)[1].strip("'")
+            query_data = _get_query_data(href)
+
+            if query_data['sid'] == story_id:
+                break
+        else:
+            # This should never happen, the story must be found on the author's
+            # page.
+            raise exceptions.FailedToDownload(self.url)
+
+        self.story.setMetadata('title', title_anchor.string)
+
+        rows = table('tr')
+
+        anchors = rows[0].div('a')
+        author_anchor = anchors[1]
+        query_data = _get_query_data(author_anchor['href'])
+        self.story.setMetadata('author', author_anchor.string)
+        self.story.setMetadata('authorId', query_data['uid'])
+        self.story.setMetadata('authorUrl', urlparse.urljoin(self.BASE_URL, author_anchor['href']))
+        self.story.setMetadata('reviews', anchors[3].string)
+
+        if self.getConfig('keep_summary_html'):
+            self.story.setMetadata('description', self.utf8FromSoup(author_url, rows[1].td))
+        else:
+            self.story.setMetadata('description', ''.join(rows[1].td(text=True)))
+
+        for row in rows[3:]:
+            index = 0
+            cells = row('td')
+
+            while index < len(cells):
+                cell = cells[index]
+                key = cell.b.string.encode(_SOURCE_CODE_ENCODING).strip(':')
+                try:
+                    value = cells[index+1].string.encode(_SOURCE_CODE_ENCODING)
+                except AttributeError:
+                    value = None
+
+                if key == 'Kategória':
+                    for anchor in cells[index+1]('a'):
+                        self.story.addToList('category', anchor.string)
+
+                elif key == 'Szereplõk':
+                    if cells[index+1].string:
+                        for name in cells[index+1].string.split(', '):
+                            self.story.addToList('character', name)
+
+                elif key == 'Korhatár':
+                    if value != 'nem korhatáros':
+                        self.story.setMetadata('rating', value)
+
+                elif key == 'Figyelmeztetések':
+                    for b_tag in cells[index+1]('b'):
+                        self.story.addToList('warnings', b_tag.string)
+
+                elif key == 'Jellemzõk':
+                    for genre in cells[index+1].string.split(', '):
+                        self.story.addToList('genre', genre)
+
+                elif key == 'Fejezetek':
+                    self.story.setMetadata('numChapters', int(value))
+
+                elif key == 'Megjelenés':
+                    self.story.setMetadata('datePublished', makeDate(value, self.DATE_FORMAT))
+
+                elif key == 'Frissítés':
+                    self.story.setMetadata('dateUpdated', makeDate(value, self.DATE_FORMAT))
+
+                elif key == 'Szavak':
+                    self.story.setMetadata('numWords', value)
+
+                elif key == 'Befejezett':
+                    self.story.setMetadata('status', 'Completed' if value == 'Nem' else 'In-Progress')
+
+                index += 2
+
+        if self.story.getMetadata('rating') == '18':
+            if not (self.is_adult or self.getConfig('is_adult')):
+                raise exceptions.AdultCheckRequired(self.url)
+
+    def getChapterText(self, url):
+        soup = self._customized_fetch_url(url)
+        story_cell = soup.find('form', action='viewstory.php').parent.parent
+
+        for div in story_cell('div'):
+            div.extract()
+
+        return self.utf8FromSoup(url, story_cell)

fanficdownloader/adapters/adapter_fanfictioncsodaidokhu.py

@@ -0,0 +1,218 @@
+# coding=utf-8
+
+import re
+import urllib2
+import urlparse
+
+from .. import BeautifulSoup
+
+from base_adapter import BaseSiteAdapter, makeDate
+from .. import exceptions
+
+
+_SOURCE_CODE_ENCODING = 'utf-8'
+
+
+def getClass():
+    return FanfictionCsodaidokHuAdapter
+
+
+def _get_query_data(url):
+    components = urlparse.urlparse(url)
+    query_data = urlparse.parse_qs(components.query)
+    return dict((key, data[0]) for key, data in query_data.items())
+
+
+# yields Tag _and_ NavigableString siblings from the given tag. The
+# BeautifulSoup findNextSiblings() method for some reasons only returns either
+# NavigableStrings _or_ Tag objects, not both.
+def _yield_next_siblings(tag):
+    sibling = tag.nextSibling
+    while sibling:
+        yield sibling
+        sibling = sibling.nextSibling
+
+
+class FanfictionCsodaidokHuAdapter(BaseSiteAdapter):
+    _SITE_DOMAIN = 'fanfiction.csodaidok.hu'
+    _BASE_URL = 'http://' + _SITE_DOMAIN + '/'
+    _VIEW_STORY_URL_TEMPLATE = _BASE_URL + 'viewstory.php?sid=%s'
+    _VIEW_CHAPTER_URL_TEMPLATE = _VIEW_STORY_URL_TEMPLATE + '&chapter=%s'
+
+    _STORY_DOES_NOT_EXIST_PAGE_TITLE = 'Cím:  Szerző:'
+    _DATE_FORMAT = '%Y.%m.%d'
+    _SITE_LANGUAGE = 'Hungarian'
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        query_data = urlparse.parse_qs(self.parsedUrl.query)
+        story_id = query_data['sid'][0]
+
+        self.story.setMetadata('storyId', story_id)
+        self._setURL(self._VIEW_STORY_URL_TEMPLATE % story_id)
+        self.story.setMetadata('siteabbrev', self._SITE_DOMAIN)
+        self.story.setMetadata('language', self._SITE_LANGUAGE)
+
+    def _customized_fetch_url(self, url, exception=None, parameters=None):
+        if exception:
+            try:
+                data = self._fetchUrl(url, parameters)
+            except urllib2.HTTPError:
+                raise exception(self.url)
+        # Just let self._fetchUrl throw the exception, don't catch and
+        # customize it.
+        else:
+            data = self._fetchUrl(url, parameters)
+
+        return BeautifulSoup.BeautifulSoup(data)
+
+    @staticmethod
+    def getSiteDomain():
+        return FanfictionCsodaidokHuAdapter._SITE_DOMAIN
+
+    @classmethod
+    def getSiteExampleURLs(cls):
+        return cls._VIEW_STORY_URL_TEMPLATE % 1234
+
+    def getSiteURLPattern(self):
+        return re.escape(self._VIEW_STORY_URL_TEMPLATE[:-2]) + r'\d+$'
+
+    def extractChapterUrlsAndMetadata(self):
+        soup = self._customized_fetch_url(self.url + '&chapter=1')
+
+        element = soup.find('div', id='pagetitle')
+        page_title = ''.join(element(text=True)).encode(_SOURCE_CODE_ENCODING)
+        if page_title == self._STORY_DOES_NOT_EXIST_PAGE_TITLE:
+            raise exceptions.StoryDoesNotExist(self.url)
+
+        author_url = urlparse.urljoin(self.url, element.a['href'])
+
+        story_id = self.story.getMetadata('storyId')
+        element = soup.find('select', {'name': 'chapter'})
+        if element:
+            for option in element('option'):
+                title = option.string
+                url = self._VIEW_CHAPTER_URL_TEMPLATE % (story_id, option['value'])
+                self.chapterUrls.append((title, url))
+
+        soup = self._customized_fetch_url(author_url)
+        story_id = self.story.getMetadata('storyId')
+
+        for listbox_div in soup('div', {'class': lambda klass: klass and 'listbox' in klass}):
+            a = listbox_div.div.a
+            if not a['href'].startswith('viewstory.php?sid='):
+                continue
+
+            query_data = _get_query_data(a['href'])
+            if query_data['sid'] == story_id:
+                break
+        else:
+            raise exceptions.FailedToDownload(self.url)
+
+        title = ''.join(a(text=True))
+        self.story.setMetadata('title', title)
+        if not self.chapterUrls:
+            self.chapterUrls.append((title, self.url))
+
+        element = a.findNextSibling('a')
+        self.story.setMetadata('author', element.string)
+        query_data = _get_query_data(element['href'])
+        self.story.setMetadata('authorId', query_data['uid'])
+        self.story.setMetadata('authorUrl', author_url)
+
+        element = element.findNextSibling('span')
+        rating = element.nextSibling.strip(' [')
+
+        if rating.encode(_SOURCE_CODE_ENCODING) != 'Korhatár nélkül':
+            self.story.setMetadata('rating', rating)
+
+        if rating == '18':
+            raise exceptions.AdultCheckRequired(self.url)
+
+        element = element.findNextSiblings('a')[1]
+        self.story.setMetadata('reviews', element.string)
+
+        sections = listbox_div('div', {'class': lambda klass: klass and klass in ['content', 'tail']})
+        for section in sections:
+            for element in section('span', {'class': 'classification'}):
+                key = element.string.encode(_SOURCE_CODE_ENCODING).strip(' :')
+                try:
+                    value = element.nextSibling.string.encode(_SOURCE_CODE_ENCODING).strip()
+                except AttributeError:
+                    value = None
+
+                if key == 'Tartalom':
+                    contents = []
+                    keep_summary_html = self.getConfig('keep_summary_html')
+
+                    for sibling in _yield_next_siblings(element):
+                        if isinstance(sibling, BeautifulSoup.Tag):
+                            if sibling.name == 'span' and sibling.get('class', None) == 'classification':
+                                break
+
+                            if keep_summary_html:
+                                contents.append(self.utf8FromSoup(author_url, sibling))
+                            else:
+                                contents.append(''.join(sibling(text=True)))
+                        else:
+                            contents.append(sibling)
+                    self.story.setMetadata('description', ''.join(contents))
+
+                elif key == 'Kategória':
+                    for sibling in element.findNextSiblings(['a', 'span']):
+                        if sibling.name == 'span':
+                            break
+
+                        self.story.addToList('category', sibling.string)
+
+                elif key == 'Szereplők':
+                    for name in value.split(', '):
+                        self.story.addToList('characters', name)
+
+                elif key == 'Műfaj':
+                    if value != 'Nincs':
+                        self.story.setMetadata('genre', value)
+
+                elif key == 'Figyelmeztetés':
+                    if value != 'Nincs':
+                        for warning in value.split(', '):
+                            self.story.addToList('warnings', warning)
+
+                elif key == 'Kihívás':
+                    if value != 'Nincs':
+                        self.story.setMetadata('challenge', value)
+
+                elif key == 'Sorozat':
+                    if value != 'Nincs':
+                        self.story.setMetadata('series', value)
+
+                elif key == 'Fejezetek':
+                    self.story.setMetadata('numChapters', int(value))
+
+                elif key == 'Befejezett':
+                    self.story.setMetadata('status', 'Completed' if value == 'Nem' else 'In-Progress')
+
+                elif key == 'Szavak száma':
+                    self.story.setMetadata('numWords', value)
+
+                elif key == 'Feltöltve':
+                    self.story.setMetadata('datePublished', makeDate(value, self._DATE_FORMAT))
+
+                elif key == 'Frissítve':
+                    self.story.setMetadata('dateUpdated', makeDate(value, self._DATE_FORMAT))
+
+    def getChapterText(self, url):
+        soup = self._customized_fetch_url(url)
+        contents = []
+
+        notes_div = soup.find('div', id='notes')
+        if notes_div:
+            contents.append(self.utf8FromSoup(url, notes_div))
+            story_div = notes_div.findNextSibling('div')
+        else:
+            element = soup.find('div', {'class': 'jumpmenu'})
+            story_div = element.findNextSibling('div')
+
+        contents.append(self.utf8FromSoup(url, story_div.span))
+        return ''.join(contents)

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_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:
@@ -283,12 +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_literotica.py

@@ -42,16 +42,19 @@ class LiteroticaSiteAdapter(BaseSiteAdapter):
         
         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])
+        # normalize to first chapter.  Not sure if they ever have more than 2 digits.
+        storyid = self.parsedUrl.path.split('/',)[2]
+        if re.match(r'-ch\d\d$',storyid):
+            storyid = storyid[:-2]+'01'
+        self.story.setMetadata('storyId',storyid)
         
         self.origurl = url
-        if "http://www.i." in self.origurl:
+        if "//www.i." in self.origurl:
             ## accept m(mobile)url, but use www.
-            self.origurl = self.origurl.replace("http://www.i.","http://www.")
+            self.origurl = self.origurl.replace("//www.i.","//www.")
 
         # normalized story URL.
-        self._setURL("http://"+self.getSiteDomain()\
+        self._setURL(url[:url.index('//')+2]+self.getSiteDomain()\
                          +"/s/"+self.story.getMetadata('storyId'))
 
         # The date format will vary from site to site.
@@ -69,10 +72,10 @@ class LiteroticaSiteAdapter(BaseSiteAdapter):
     @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"
+        return "http://www.literotica.com/s/story-title https://www.literotica.com/s/story-title"
 
     def getSiteURLPattern(self):
-        return r"http://www(\.i)?\.literotica\.com/s/([a-zA-Z0-9_-]+)"
+        return r"https?://www(\.i)?\.literotica\.com/s/([a-zA-Z0-9_-]+)"
 
     def extractChapterUrlsAndMetadata(self):
 
@@ -97,20 +100,24 @@ class LiteroticaSiteAdapter(BaseSiteAdapter):
         # 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'])
+        authorurl = a.a['href']
+        if authorurl.startswith('//'):
+            authorurl = self.parsedUrl.scheme+':'+authorurl
+        self.story.setMetadata('authorUrl', authorurl)
         self.story.setMetadata('author', a.text)
 
         # get the author page
         try:
-            dataAuth = self._fetchUrl(a.a['href'])
+            dataAuth = self._fetchUrl(authorurl)
             soupAuth = bs.BeautifulSoup(dataAuth)
         except urllib2.HTTPError, e:
             if e.code == 404:
-                raise exceptions.StoryDoesNotExist(a.a['href'])
+                raise exceptions.StoryDoesNotExist(authorurl)
             else:
                 raise e
 
-        storyLink = soupAuth.find('a', href=url1)
+        ## site has started using //domain.name/asdf urls remove https?: from front
+        storyLink = soupAuth.find('a', href=url1[url1.index(':')+1:])
 
         if storyLink is not None:
             # pull the published date from the author page
@@ -166,7 +173,10 @@ class LiteroticaSiteAdapter(BaseSiteAdapter):
             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']))
+                chapurl = row.a['href']
+                if chapurl.startswith('//'):
+                    chapurl = self.parsedUrl.scheme+':'+chapurl
+                self.chapterUrls.append((row.a.string,chapurl))
                 if not row.nextSibling:
                     break
                 row = row.nextSibling
@@ -203,7 +213,7 @@ 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 +230,7 @@ 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_nocturnallightnet.py

@@ -0,0 +1,177 @@
+import re
+import urllib2
+import urlparse
+
+from .. import BeautifulSoup
+
+from base_adapter import BaseSiteAdapter, makeDate
+from .. import exceptions
+
+
+def getClass():
+    return NocturnalLightNetAdapter
+
+
+# yields Tag _and_ NavigableString siblings from the given tag. The
+# BeautifulSoup findNextSiblings() method for some reasons only returns either
+# NavigableStrings _or_ Tag objects, not both.
+def _yield_next_siblings(tag):
+    sibling = tag.nextSibling
+    while sibling:
+        yield sibling
+        sibling = sibling.nextSibling
+
+
+class NocturnalLightNetAdapter(BaseSiteAdapter):
+    SITE_ABBREVIATION = 'nln'
+    SITE_DOMAIN = 'nocturnal-light.net'
+    BASE_URL = 'http://' + SITE_DOMAIN + '/fanfiction/'
+    STORY_URL_TEMPLATE = BASE_URL + 'story/%s'
+    AUTHORS_URL_TEMPLATE = BASE_URL + 'authors/%s'
+
+    DATETIME_FORMAT = '%m-%d-%y'
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        url_tokens = self.parsedUrl.path.split('/')
+        story_id = url_tokens[url_tokens.index('story') + 1]
+
+        self.story.setMetadata('storyId', story_id)
+        self._setURL(self.STORY_URL_TEMPLATE % story_id)
+        self.story.setMetadata('siteabbrev', self.SITE_ABBREVIATION)
+
+    def _customized_fetch_url(self, url, exception=None, parameters=None):
+        if exception:
+            try:
+                data = self._fetchUrl(url, parameters)
+            except urllib2.HTTPError:
+                raise exception(self.url)
+        # Just let self._fetchUrl throw the exception, don't catch and
+        # customize it.
+        else:
+            data = self._fetchUrl(url, parameters)
+
+        return BeautifulSoup.BeautifulSoup(data)
+
+    @staticmethod
+    def getSiteDomain():
+        return NocturnalLightNetAdapter.SITE_DOMAIN
+
+    @classmethod
+    def getSiteExampleURLs(cls):
+        return cls.STORY_URL_TEMPLATE % 1234
+
+    def getSiteURLPattern(self):
+        return re.escape(self.STORY_URL_TEMPLATE[:-2]) + r'\d+.*$'
+
+    def extractChapterUrlsAndMetadata(self):
+        soup = self._customized_fetch_url(self.url)
+
+        # Since no 404 error code we have to raise the exception ourselves.
+        # A title that is just 'by' indicates that there is no author name
+        # and no story title available.
+        if soup.title.string.strip() == 'by':
+            raise exceptions.StoryDoesNotExist(self.url)
+
+        # "storycontent" is found in a single-chapter story
+        author_anchor = soup.find('div', id=lambda id: id in ('main', 'storycontent')).h1.a
+        self.story.setMetadata('author', author_anchor.string)
+
+        url_tokens = author_anchor['href'].split('/')
+        author_id = url_tokens[url_tokens.index('authors')+1]
+        self.story.setMetadata('authorId', author_id)
+        self.story.setMetadata('authorUrl', self.AUTHORS_URL_TEMPLATE % author_id)
+
+        chapter_anchors = soup('a', href=lambda href: href and href.startswith('/fanfiction/story/'))
+        for chapter_anchor in chapter_anchors:
+            url = urlparse.urljoin(self.BASE_URL, chapter_anchor['href'])
+            self.chapterUrls.append((chapter_anchor.string, url))
+
+        author_url = urlparse.urljoin(self.BASE_URL, author_anchor['href'])
+        soup = self._customized_fetch_url(author_url)
+        story_id = self.story.getMetadata('storyId')
+        for listbox in soup('div', {'class': 'listbox'}):
+            url_tokens = listbox.a['href'].split('/')
+            # Found the div containing the story's metadata; break the loop and
+            # parse the element
+            if story_id == url_tokens[url_tokens.index('story')+1]:
+                break
+        else:
+            raise exceptions.FailedToDownload(self.url)
+
+        title = listbox.a.string
+        self.story.setMetadata('title', title)
+
+        # No chapter anchors found in the original story URL, so the story has
+        # only a single chapter.
+        if not chapter_anchors:
+            self.chapterUrls.append((title, self.url))
+
+        for b_tag in listbox('b'):
+            key = b_tag.string.strip(':')
+            try:
+                value = b_tag.nextSibling.string.replace('•', '').strip(': ')
+            # This can happen with some fancy markup in the summary. Just
+            # ignore this error and set value to None, the summary parsing
+            # takes care of this
+            except AttributeError:
+                value = None
+
+            if key == 'Summary':
+                contents = []
+                keep_summary_html = self.getConfig('keep_summary_html')
+
+                for sibling in _yield_next_siblings(b_tag):
+                    if isinstance(sibling, BeautifulSoup.Tag):
+                        if sibling.name == 'b' and sibling.findPreviousSibling().name == 'br':
+                            break
+
+                        if keep_summary_html:
+                            contents.append(self.utf8FromSoup(author_url, sibling))
+                        else:
+                            contents.append(''.join(sibling(text=True)))
+                    else:
+                        contents.append(sibling)
+
+                # Pop last break line tag
+                contents.pop()
+                self.story.setMetadata('description', ''.join(contents))
+
+            elif key == 'Category':
+                for sibling in b_tag.findNextSiblings(['a', 'b']):
+                    if sibling.name == 'b':
+                        break
+
+                    self.story.addToList('category', sibling.string)
+
+            elif key == 'Rating':
+                self.story.setMetadata('rating', value)
+
+            elif key == 'Chapters':
+                self.story.setMetadata('numChapters', int(value))
+
+                # Also parse reviews number which lies right after the chapters
+                # section
+                reviews_anchor = b_tag.findNextSibling('a')
+                reviews = reviews_anchor.string.split(' ')[1].strip('()')
+                self.story.setMetadata('reviews', reviews)
+
+            elif key == 'Completed':
+                self.story.setMetadata('status', 'Completed' if value == 'Yes' else 'In-Progress')
+
+            elif key == 'Date Added':
+                self.story.setMetadata('datePublished', makeDate(value, self.DATETIME_FORMAT))
+
+            elif key == 'Last Updated':
+                self.story.setMetadata('dateUpdated', makeDate(value, self.DATETIME_FORMAT))
+
+            elif key == 'Read':
+                self.story.setMetadata('readings', value.split()[0])
+
+        if self.story.getMetadata('rating') == 'NC-17' and not (self.is_adult or self.getConfig('is_adult')):
+            raise exceptions.AdultCheckRequired(self.url)
+
+    def getChapterText(self, url):
+        soup = self._customized_fetch_url(url)
+        return self.utf8FromSoup(url, soup.find('div', id='storytext'))

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_spikeluvercom.py

@@ -0,0 +1,206 @@
+import re
+import urllib2
+import urlparse
+
+from .. import BeautifulSoup
+
+from base_adapter import BaseSiteAdapter, makeDate
+from .. import exceptions
+
+
+def getClass():
+    return SpikeluverComAdapter
+
+
+# yields Tag _and_ NavigableString siblings from the given tag. The
+# BeautifulSoup findNextSiblings() method for some reasons only returns either
+# NavigableStrings _or_ Tag objects, not both.
+def _yield_next_siblings(tag):
+    sibling = tag.nextSibling
+    while sibling:
+        yield sibling
+        sibling = sibling.nextSibling
+
+
+class SpikeluverComAdapter(BaseSiteAdapter):
+    SITE_ABBREVIATION = 'slc'
+    SITE_DOMAIN = 'spikeluver.com'
+
+    BASE_URL = 'http://' + SITE_DOMAIN + '/SpuffyRealm/'
+    LOGIN_URL = BASE_URL + 'user.php?action=login'
+    VIEW_STORY_URL_TEMPLATE = BASE_URL + 'viewstory.php?sid=%d'
+    METADATA_URL_SUFFIX = '&index=1'
+    AGE_CONSENT_URL_SUFFIX = '&ageconsent=ok&warning=5'
+
+    DATETIME_FORMAT = '%m/%d/%Y'
+    STORY_DOES_NOT_EXIST_ERROR_TEXT = 'That story does not exist on this archive.  You may search for it or return to the home page.'
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        query_data = urlparse.parse_qs(self.parsedUrl.query)
+        story_id = query_data['sid'][0]
+
+        self.story.setMetadata('storyId', story_id)
+        self._setURL(self.VIEW_STORY_URL_TEMPLATE % int(story_id))
+        self.story.setMetadata('siteabbrev', self.SITE_ABBREVIATION)
+
+    def _customized_fetch_url(self, url, exception=None, parameters=None):
+        if exception:
+            try:
+                data = self._fetchUrl(url, parameters)
+            except urllib2.HTTPError:
+                raise exception(self.url)
+        # Just let self._fetchUrl throw the exception, don't catch and
+        # customize it.
+        else:
+            data = self._fetchUrl(url, parameters)
+
+        return BeautifulSoup.BeautifulSoup(data)
+
+    @staticmethod
+    def getSiteDomain():
+        return SpikeluverComAdapter.SITE_DOMAIN
+
+    @classmethod
+    def getSiteExampleURLs(cls):
+        return cls.VIEW_STORY_URL_TEMPLATE % 1234
+
+    def getSiteURLPattern(self):
+        return re.escape(self.VIEW_STORY_URL_TEMPLATE[:-2]) + r'\d+$'
+
+    def extractChapterUrlsAndMetadata(self):
+        soup = self._customized_fetch_url(self.url + self.METADATA_URL_SUFFIX)
+
+        errortext_div = soup.find('div', {'class': 'errortext'})
+        if errortext_div:
+            error_text = ''.join(errortext_div(text=True)).strip()
+            if error_text == self.STORY_DOES_NOT_EXIST_ERROR_TEXT:
+                raise exceptions.StoryDoesNotExist(self.url)
+
+        # No additional login is required, just check for adult
+        pagetitle_div = soup.find('div', id='pagetitle')
+        if pagetitle_div.a['href'].startswith('javascript:'):
+            if not(self.is_adult or self.getConfig('is_adult')):
+                raise exceptions.AdultCheckRequired(self.url)
+
+        url = ''.join([self.url, self.METADATA_URL_SUFFIX, self.AGE_CONSENT_URL_SUFFIX])
+        soup = self._customized_fetch_url(url)
+
+        pagetitle_div = soup.find('div', id='pagetitle')
+        self.story.setMetadata('title', pagetitle_div.a.string.strip())
+
+        author_anchor = pagetitle_div.a.findNextSibling('a')
+        url = urlparse.urljoin(self.BASE_URL, author_anchor['href'])
+        components = urlparse.urlparse(url)
+        query_data = urlparse.parse_qs(components.query)
+
+        self.story.setMetadata('author', author_anchor.string.strip())
+        self.story.setMetadata('authorId', query_data['uid'])
+        self.story.setMetadata('authorUrl', url)
+
+        sort_div = soup.find('div', id='sort')
+        self.story.setMetadata('reviews', sort_div('a')[1].string.strip())
+
+        listbox_tag = soup.find('div', {'class': 'listbox'})
+        for span_tag in listbox_tag('span'):
+            key = span_tag.string.strip(' :')
+            try:
+                value = span_tag.nextSibling.string.strip()
+            # This can happen with some fancy markup in the summary. Just
+            # ignore this error and set value to None, the summary parsing
+            # takes care of this
+            except AttributeError:
+                value = None
+
+            if key == 'Summary':
+                contents = []
+                keep_summary_html = self.getConfig('keep_summary_html')
+
+                for sibling in _yield_next_siblings(span_tag):
+                    if isinstance(sibling, BeautifulSoup.Tag):
+                        # Encountered next label, break. Not as bad as other
+                        # e-fiction sites, let's hope this is enough for proper
+                        # parsing.
+                        if sibling.name == 'span' and sibling.get('class', None) == 'label':
+                            break
+
+                        if keep_summary_html:
+                            contents.append(self.utf8FromSoup(self.url, sibling))
+                        else:
+                            contents.append(''.join(sibling(text=True)))
+                    else:
+                        contents.append(sibling)
+
+                # Remove the preceding break line tag and other crud
+                contents.pop()
+                contents.pop()
+                self.story.setMetadata('description', ''.join(contents))
+
+            elif key == 'Rated':
+                self.story.setMetadata('rating', value)
+
+            elif key == 'Categories':
+                for sibling in span_tag.findNextSiblings(['a', 'br']):
+                    if sibling.name == 'br':
+                        break
+
+                    self.story.addToList('category', sibling.string.strip())
+
+            # Seems to be always "None" for some reason
+            elif key == 'Characters':
+                for sibling in span_tag.findNextSiblings(['a', 'br']):
+                    if sibling.name == 'br':
+                        break
+                    self.story.addToList('characters', sibling.string.strip())
+
+            elif key == 'Genres':
+                for sibling in span_tag.findNextSiblings(['a', 'br']):
+                    if sibling.name == 'br':
+                        break
+
+                    self.story.addToList('genre', sibling.string.strip())
+
+            elif key == 'Warnings':
+                for sibling in span_tag.findNextSiblings(['a', 'br']):
+                    if sibling.name == 'br':
+                        break
+                    self.story.addToList('warnings', sibling.string.strip())
+
+            # Challenges
+
+            elif key == 'Series':
+                a = span_tag.findNextSibling('a')
+                if not a:
+                    continue
+                self.story.setMetadata('series', a.string.strip())
+                self.story.setMetadata('seriesUrl', urlparse.urljoin(self.BASE_URL, a['href']))
+
+            elif key == 'Chapters':
+                self.story.setMetadata('numChapters', int(value))
+
+            elif key == 'Completed':
+                self.story.setMetadata('status', 'Completed' if value == 'Yes' else 'In-Progress')
+
+            elif key == 'Word count':
+                self.story.setMetadata('numWords', value)
+
+            elif key == 'Published':
+                self.story.setMetadata('datePublished', makeDate(value, self.DATETIME_FORMAT))
+
+            elif key == 'Updated':
+                self.story.setMetadata('dateUpdated', makeDate(value, self.DATETIME_FORMAT))
+
+        for p_tag in listbox_tag.findNextSiblings('p'):
+            chapter_anchor = p_tag.find('a', href=lambda href: href and href.startswith('viewstory.php?sid='))
+            if not chapter_anchor:
+                continue
+
+            title = chapter_anchor.string.strip()
+            url = urlparse.urljoin(self.BASE_URL, chapter_anchor['href'])
+            self.chapterUrls.append((title, url))
+
+    def getChapterText(self, url):
+        url += self.AGE_CONSENT_URL_SUFFIX
+        soup = self._customized_fetch_url(url)
+        return self.utf8FromSoup(url, soup.find('div', id='story'))

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_voracity2eficcom.py

@@ -0,0 +1,232 @@
+import re
+import urllib2
+import urlparse
+
+from .. import BeautifulSoup
+
+from base_adapter import BaseSiteAdapter, makeDate
+from .. import exceptions
+
+
+def getClass():
+    return Voracity2EficComAdapter
+
+
+# yields Tag _and_ NavigableString siblings from the given tag. The
+# BeautifulSoup findNextSiblings() method for some reasons only returns either
+# NavigableStrings _or_ Tag objects, not both.
+def _yield_next_siblings(tag):
+    sibling = tag.nextSibling
+    while sibling:
+        yield sibling
+        sibling = sibling.nextSibling
+
+
+class Voracity2EficComAdapter(BaseSiteAdapter):
+    SITE_ABBREVIATION = 'voe'
+    SITE_DOMAIN = 'voracity2.e-fic.com'
+
+    BASE_URL = 'http://' + SITE_DOMAIN + '/'
+    LOGIN_URL = BASE_URL + 'user.php?action=login'
+    VIEW_STORY_URL_TEMPLATE = BASE_URL + 'viewstory.php?sid=%d'
+    METADATA_URL_SUFFIX = '&index=1'
+    AGE_CONSENT_URL_SUFFIX = '&ageconsent=ok&warning=4'
+
+    DATETIME_FORMAT = '%m/%d/%Y'
+    REQUIRED_SKIN = 'Simple Elegance'
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        query_data = urlparse.parse_qs(self.parsedUrl.query)
+        story_id = query_data['sid'][0]
+
+        self.story.setMetadata('storyId', story_id)
+        self._setURL(self.VIEW_STORY_URL_TEMPLATE % int(story_id))
+        self.story.setMetadata('siteabbrev', self.SITE_ABBREVIATION)
+
+        self.is_logged_in = False
+
+    def _login(self):
+        # Apparently self.password is only set when login fails, i.e.
+        # the FailedToLogin exception is raised, so the adapter gets new
+        # login data and tries again
+        if self.password:
+            password = self.password
+            username = self.username
+        else:
+            username = self.getConfig('username')
+            password = self.getConfig('password')
+
+        parameters = {
+            'penname': username,
+            'password': password,
+            'submit': 'Submit'}
+
+        class CustomizedFailedToLogin(exceptions.FailedToLogin):
+            def __init__(self, url, passwdonly=False):
+                # Use username variable from outer scope
+                exceptions.FailedToLogin.__init__(self, url, username, passwdonly)
+
+        soup = self._customized_fetch_url(self.LOGIN_URL, CustomizedFailedToLogin, parameters)
+        div = soup.find('div', id='useropts')
+        if not div:
+            raise CustomizedFailedToLogin(self.LOGIN_URL)
+
+        self.is_logged_in = True
+
+    def _customized_fetch_url(self, url, exception=None, parameters=None):
+        if exception:
+            try:
+                data = self._fetchUrl(url, parameters)
+            except urllib2.HTTPError:
+                raise exception(self.url)
+        # Just let self._fetchUrl throw the exception, don't catch and
+        # customize it.
+        else:
+            data = self._fetchUrl(url, parameters)
+
+        return BeautifulSoup.BeautifulSoup(data)
+
+    @staticmethod
+    def getSiteDomain():
+        return Voracity2EficComAdapter.SITE_DOMAIN
+
+    @classmethod
+    def getSiteExampleURLs(cls):
+        return cls.VIEW_STORY_URL_TEMPLATE % 1234
+
+    def getSiteURLPattern(self):
+        return re.escape(self.VIEW_STORY_URL_TEMPLATE[:-2]) + r'\d+$'
+
+    def extractChapterUrlsAndMetadata(self):
+        soup = self._customized_fetch_url(self.url + self.METADATA_URL_SUFFIX)
+
+        # Check if the story is for "Registered Users Only", i.e. has adult
+        # content. Based on the "is_adult" attributes either login or raise an
+        # error.
+        errortext_div = soup.find('div', {'class': 'errortext'})
+        if errortext_div:
+            error_text = ''.join(errortext_div(text=True)).strip()
+            if error_text == 'Registered Users Only':
+                if not (self.is_adult or self.getConfig('is_adult')):
+                    raise exceptions.AdultCheckRequired(self.url)
+                self._login()
+            else:
+                # This case usually occurs when the story doesn't exist, but
+                # might potentially be something else, so just raise
+                # FailedToDownload exception with the found error text.
+                raise exceptions.FailedToDownload(error_text)
+
+        url = ''.join([self.url, self.METADATA_URL_SUFFIX, self.AGE_CONSENT_URL_SUFFIX])
+        soup = self._customized_fetch_url(url)
+
+        # If logged in and the skin doesn't match the required skin throw an
+        # error
+        if self.is_logged_in:
+            skin = soup.find('select', {'name': 'skin'}).find('option', selected=True)['value']
+            if skin != self.REQUIRED_SKIN:
+                raise exceptions.FailedToDownload('Required skin "%s" must be set in preferences' % self.REQUIRED_SKIN)
+
+        pagetitle_div = soup.find('div', id='pagetitle')
+        self.story.setMetadata('title', pagetitle_div.a.string)
+
+        author_anchor = pagetitle_div.a.findNextSibling('a')
+        url = urlparse.urljoin(self.BASE_URL, author_anchor['href'])
+        components = urlparse.urlparse(url)
+        query_data = urlparse.parse_qs(components.query)
+
+        self.story.setMetadata('author', author_anchor.string)
+        self.story.setMetadata('authorId', query_data['uid'])
+        self.story.setMetadata('authorUrl', url)
+
+        sort_div = soup.find('div', id='sort')
+        self.story.setMetadata('reviews', sort_div('a')[1].string)
+
+        for b_tag in soup.find('div', {'class': 'listbox'})('b'):
+            key = b_tag.string.strip(' :')
+            try:
+                value = b_tag.nextSibling.string.strip()
+            # This can happen with some fancy markup in the summary. Just
+            # ignore this error and set value to None, the summary parsing
+            # takes care of this
+            except AttributeError:
+                value = None
+
+            if key == 'Summary':
+                contents = []
+                keep_summary_html = self.getConfig('keep_summary_html')
+
+                for sibling in _yield_next_siblings(b_tag):
+                    if isinstance(sibling, BeautifulSoup.Tag):
+                        # Encountered next label, break. This method is the
+                        # safest and most reliable I could think of. Blame
+                        # e-fiction sites that allow their users to include
+                        # arbitrary markup into their summaries and the
+                        # horrible HTML markup.
+                        if sibling.name == 'b' and sibling.findPreviousSibling().name == 'br':
+                            break
+
+                        if keep_summary_html:
+                            contents.append(self.utf8FromSoup(self.url, sibling))
+                        else:
+                            contents.append(''.join(sibling(text=True)))
+                    else:
+                        contents.append(sibling)
+
+                # Remove the preceding break line tag and other crud
+                contents.pop()
+                contents.pop()
+                self.story.setMetadata('description', ''.join(contents))
+
+            elif key == 'Rating':
+                self.story.setMetadata('rating', value)
+
+            elif key == 'Category':
+                for sibling in b_tag.findNextSiblings(['a', 'br']):
+                    if sibling.name == 'br':
+                        break
+                    self.story.addToList('category', sibling.string)
+
+            # Seems to be always "None" for some reason
+            elif key == 'Characters':
+                for sibling in b_tag.findNextSiblings(['a', 'br']):
+                    if sibling.name == 'br':
+                        break
+                    self.story.addToList('characters', sibling.string)
+
+            elif key == 'Series':
+                a = b_tag.findNextSibling('a')
+                if not a:
+                    continue
+                self.story.setMetadata('series', a.string)
+                self.story.setMetadata('seriesUrl', urlparse.urljoin(self.BASE_URL, a['href']))
+
+            elif key == 'Chapter':
+                self.story.setMetadata('numChapters', int(value))
+
+            elif key == 'Completed':
+                self.story.setMetadata('status', 'Completed' if value == 'Yes' else 'In-Progress')
+
+            elif key == 'Words':
+                self.story.setMetadata('numWords', value)
+
+            elif key == 'Read':
+                self.story.setMetadata('readings', value)
+
+            elif key == 'Published':
+                self.story.setMetadata('datePublished', makeDate(value, self.DATETIME_FORMAT))
+
+            elif key == 'Updated':
+                self.story.setMetadata('dateUpdated', makeDate(value, self.DATETIME_FORMAT))
+
+        for b_tag in soup.find('div', id='output').findNextSiblings('b'):
+            chapter_anchor = b_tag.a
+            title = chapter_anchor.string
+            url = urlparse.urljoin(self.BASE_URL, chapter_anchor['href'])
+            self.chapterUrls.append((title, url))
+
+    def getChapterText(self, url):
+        url += self.AGE_CONSENT_URL_SUFFIX
+        soup = self._customized_fetch_url(url)
+        return self.utf8FromSoup(url, soup.find('div', id='story'))

fanficdownloader/adapters/base_adapter.py

@@ -188,9 +188,9 @@ class BaseSiteAdapter(Configurable):
             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)))
-                    excpt=he
                     break # break out on 404
             except Exception, e:
                 excpt=e

fanficdownloader/story.py

@@ -28,6 +28,9 @@ import exceptions
 from htmlcleanup import conditionalRemoveEntities, removeAllEntities
 from configurable import Configurable
 
+SPACE_REPLACE=u'\s'
+SPLIT_META=u'\,'
+
 # Create convert_image method depending on which graphics lib we can
 # load.  Preferred: calibre, PIL, none
 
@@ -221,6 +224,65 @@ 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(SPACE_REPLACE,' ')
+            self.regex = re.compile(self.match)
+        elif "!~" in line:
+            (self.keys,self.match) = line.split("!~")
+            self.match = self.match.replace(SPACE_REPLACE,' ')
+            self.regex = re.compile(self.match)
+            self.negate = True
+        elif "==" in line:
+            (self.keys,self.match) = line.split("==")
+            self.match = self.match.replace(SPACE_REPLACE,' ')
+        elif "!=" in line:
+            (self.keys,self.match) = line.split("!=")
+            self.match = self.match.replace(SPACE_REPLACE,' ')
+            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 +293,7 @@ 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 = []
@@ -241,8 +304,7 @@ class Story(Configurable):
         self.logfile=None # cheesy way to carry log file forward across update.
 
         ## Look for config parameter, split and add each to metadata field.
-        for (config,metadata) in [("extratags","extratags"),
-                                  ("extracategories","category"),
+        for (config,metadata) in [("extracategories","category"),
                                   ("extragenres","genre"),
                                   ("extracharacters","characters"),
                                   ("extraships","ships"),
@@ -252,6 +314,15 @@ 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 +340,56 @@ 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.
@@ -297,10 +418,13 @@ 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(SPACE_REPLACE,' ')
                 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)
+
         for (metakeys,regexp,replacement,condkey,condregexp) in self.replacements:
             if (metakeys == None or key in metakeys) \
                     and isinstance(value,basestring) \
@@ -311,7 +435,20 @@ class Story(Configurable):
                     doreplace = condval != None and condregexp.search(condval)
 
                 if doreplace:
-                    value = regexp.sub(replacement,value)
+                    # split into more than one list entry if list and
+                    # SPLIT_META present in replacement string.  Split
+                    # first, then regex sub.
+                    if self.isList(key) and SPLIT_META in replacement:
+                        repllist = replacement.split(SPLIT_META)
+                        for repl in repllist[1:]:
+                            self.addToList(key,regexp.sub(repl,value))
+                        value = regexp.sub(repllist[0],value)
+                    else:            
+                        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):
@@ -326,7 +463,7 @@ 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(SPACE_REPLACE,' ')
             value = join_string.join(self.getList(key, removeallentities, doreplacements=True))
             if doreplacements:
                 value = self.doReplacements(value,key+"_LIST")
@@ -377,7 +514,7 @@ class Story(Configurable):
                     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(SPACE_REPLACE,' ')
             self.setMetadata('authorHTML',join_string.join(htmllist))
         else:
             self.setMetadata('authorHTML',linkhtml%('author',self.getMetadata('authorUrl', removeallentities, doreplacements),
@@ -409,7 +546,7 @@ class Story(Configurable):
                     v=removeAllEntities(v)
 
                 htmllist.append(linkhtml%(k,url,v))
-            join_string = self.getConfig("join_string_"+k+"HTML",u", ").replace('\s',' ')
+            join_string = self.getConfig("join_string_"+k+"HTML",u", ").replace(SPACE_REPLACE,' ')
             self.setMetadata(k+'HTML',join_string.join(htmllist))
 
         for k in self.getValidMetaList():

index.html

@@ -46,13 +46,6 @@
       {{yourfile}}
       <!--			</div> -->
 
-          <h3>fanfiction.net / fimfiction.net</h3>
-          <p>
-            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 %}
       <form action="/fdown" method="post">
 	<div id='urlbox'>
@@ -62,9 +55,15 @@
 	  </div>
 	  <!-- put announcements here, h3 is a good title size. -->
 	  <h3>Changes:</h3>
+	  <p>
+            Now supporting over 100 different sites!  Thanks, cryzed, for pushing us over the top.
+	  </p>
 	  <p>
 	    <ul>
-              <li>Add Pairing for hpfanficarchive.com</li>
+              <li>New site: nocturnal-light.net -- Thanks, cryzed!</li>
+              <li>New site: fanfic.hu (Hungarian language) -- Thanks, cryzed!</li>
+              <li>New site: fanfiction.csodaidok.hu (Hungarian language) -- Thanks, cryzed!</li>
+              <li>Improvements &amp; fixes for recently added sites -- Thanks, cryzed!</li>
 	    </ul>
 	  </p>
 	  <p>
@@ -75,7 +74,7 @@
 	    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://4-4-96.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
+	    <a href="http://4-5-03.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
 	  </p>
 	  <div id='error'>
 	    {{ error_message }}

plugin-defaults.ini

@@ -186,7 +186,32 @@ connect_timeout:60.0
 # .*-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.)
@@ -207,6 +232,9 @@ connect_timeout:60.0
 ## Make sure to keep at least one space at the start of each line and
 ## to escape % to %%, if used.
 ## template => regexp to match => GC Setting to use.
+## To use this, make sure you go to the Generate Cover tab in FFDL
+## config and check 'Allow generate_cover_settings from personal.ini
+## to override'
 #generate_cover_settings:
 # ${category} => Buffy:? [tT]he Vampire Slayer => BuffyCover
 # ${category} => Star Trek => StarTrekCover
@@ -264,6 +292,10 @@ chapter_title_add_pattern:${index}. ${title}
 ## anthologies.
 anthology_title_pattern:${title} Anthology
 
+## Add tag(s) for anthology (series) books.  Set to empty to not add
+## any anthology tags.
+anthology_tags:Anthology
+
 ## Reorder ships so b/a and c/b/a become a/b and a/b/c. Only separates
 ## on '/', so use replace_metadata to change separator first if
 ## needed. Something like: ships=>[ ]*(/|&amp;|&)[ ]*=>/ You can use
@@ -570,6 +602,29 @@ extracategories:The Sentinel
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+[bloodshedverse.com]
+## website encoding(s) In theory, each website reports the character
+## encoding they use for each page.  In practice, some sites report it
+## incorrectly.  Each adapter has a default list, usually "utf8,
+## Windows-1252" or "Windows-1252, utf8", but this will let you
+## explicitly set the encoding and order if you need to.  The special
+## value 'auto' will call chardet and use the encoding it reports if
+## it has +90% confidence.  'auto' is not reliable.
+website_encodings:ISO-8859-1,auto
+
+## Extra metadata that this adapter knows about.  See [dramione.org]
+## for examples of how to use them.
+extra_valid_entries:warnings,reviews
+reviews_label:Reviews
+
+## Site dedicated to these categories/characters/ships
+extracharacters:Spike,Buffy
+extracategories:Buffy the Vampire Slayer
+
+## Strips links found in the story text
+## Specific to bloodshedverse.com
+strip_text_links:true
+
 [bloodties-fans.com]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -729,6 +784,38 @@ extracategories:Harry Potter
 ## cover image.  This lets you exclude them.
 cover_exclusion_regexp:/images/.*?ribbon.gif
 
+[fanfiction.csodaidok.hu]
+## website encoding(s) In theory, each website reports the character
+## encoding they use for each page.  In practice, some sites report it
+## incorrectly.  Each adapter has a default list, usually "utf8,
+## Windows-1252" or "Windows-1252, utf8", but this will let you
+## explicitly set the encoding and order if you need to.  The special
+## value 'auto' will call chardet and use the encoding it reports if
+## it has +90% confidence.  'auto' is not reliable.
+website_encodings:ISO-8859-2,auto
+
+## Extra metadata that this adapter knows about.  See [dramione.org]
+## for examples of how to use them.
+extra_valid_entries:reviews,challenge
+reviews_label:Reviews
+challenge_label:Challenge
+
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
+[fanfic.hu]
+## website encoding(s) In theory, each website reports the character
+## encoding they use for each page.  In practice, some sites report it
+## incorrectly.  Each adapter has a default list, usually "utf8,
+## Windows-1252" or "Windows-1252, utf8", but this will let you
+## explicitly set the encoding and order if you need to.  The special
+## value 'auto' will call chardet and use the encoding it reports if
+## it has +90% confidence.  'auto' is not reliable.
+website_encodings:ISO-8859-1,auto
+
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 [fanfiction.mugglenet.com]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
@@ -779,6 +866,14 @@ extraships:Harry Potter/Hermione Granger
 #username:YourName
 #password:yourpassword
 
+[ficwad.com]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
 [fictionpad.com]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -935,6 +1030,17 @@ extracategories:NCIS
 extracategories:Buffy: The Vampire Slayer
 extracharacters:Willow
 
+[nocturnal-light.net]
+## Extra metadata that this adapter knows about.  See [dramione.org]
+## for examples of how to use them.
+extra_valid_entries:readings,reviews
+readings_label:Readings
+reviews_label:Reviews
+
+## Site dedicated to these categories/characters/ships
+extracharacters:Spike,Buffy
+extracategories:Buffy the Vampire Slayer
+
 [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
@@ -1025,6 +1131,16 @@ extracategories:Harry Potter
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+[spikeluver.com]
+## Extra metadata that this adapter knows about.  See [dramione.org]
+## for examples of how to use them.
+extra_valid_entries:warnings,reviews
+reviews_label:Reviews
+
+## Site dedicated to these categories/characters/ships
+extracharacters:Spike,Buffy
+extracategories:Buffy the Vampire Slayer
+
 [stargate-atlantis.org]
 ## Site dedicated to these categories/characters/ships
 extracategories:Stargate: Atlantis
@@ -1123,6 +1239,13 @@ awards_label:Awards
 
 cover_exclusion_regexp:art/.*Awards.jpg
 
+[voracity2.e-fic.com]
+## Extra metadata that this adapter knows about.  See [dramione.org]
+## for examples of how to use them.
+extra_valid_entries:reviews,readings
+reviews_label:Reviews
+readings_label:Readings
+
 [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,
@@ -1281,14 +1404,6 @@ extratags:
 ## for examples of how to use them.
 extra_valid_entries:reviews,favs,follows
 
-[ficwad.com]
-## Some sites require login (or login for some rated stories) The
-## program can prompt you, or you can save it in config.  In
-## commandline version, this should go in your personal.ini, not
-## defaults.ini.
-#username:YourName
-#password:yourpassword
-
 [www.fimfiction.net]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
@@ -1307,6 +1422,11 @@ 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
 

status.html

@@ -51,12 +51,6 @@
 	      by {{ fic.author }} ({{ fic.format }})
 	  {% endif %}
 	  {% if fic.failure %}
-          <h3>fanfiction.net / fimfiction.net</h3>
-          <p>
-            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 %}
 	  {% if  not fic.completed and not fic.failure %}