Bump versions.

Default keep_summary_html:true to now,
Changes to the AO3, ficbook.net, ficwad.com adapters for summary HTML.
Add options to strip and add chapter numbers to chapter titles.

app.yaml

@@ -1,6 +1,6 @@
 # ffd-retief-hrd fanfictiondownloader
 application: fanfictiondownloader
-version: 4-4-29
+version: 4-4-33
 runtime: python27
 api_version: 1
 threadsafe: true

calibre-plugin/__init__.py

@@ -27,7 +27,7 @@ class FanFictionDownLoaderBase(InterfaceActionBase):
     description         = 'UI plugin to download FanFiction stories from various sites.'
     supported_platforms = ['windows', 'osx', 'linux']
     author              = 'Jim Miller'
-    version             = (1, 6, 14)
+    version             = (1, 6, 18)
     minimum_calibre_version = (0, 8, 57)
 
     #: This field defines the GUI plugin class that contains all the code

calibre-plugin/jobs.py

@@ -126,6 +126,7 @@ def do_download_for_worker(book,options):
         adapter.is_adult = book['is_adult'] 
         adapter.username = book['username'] 
         adapter.password = book['password']
+        adapter.setChaptersRange(book['begin'],book['end'])
         
         story = adapter.getStoryMetadataOnly()
         if 'calibre_series' in book:
@@ -148,8 +149,6 @@ def do_download_for_worker(book,options):
         elif options['collision'] in (ADDNEW, SKIP, OVERWRITE, OVERWRITEALWAYS) or \
                 ('epub_for_update' not in book and options['collision'] in (UPDATE, UPDATEALWAYS)):
 
-            adapter.setChaptersRange(book['begin'],book['end'])
-            
             print("write to %s"%outfile)
             writer.writeStory(outfilename=outfile, forceOverwrite=True)
             book['comment'] = 'Download %s completed, %s chapters.'%(options['fileform'],story.getMetadata("numChapters"))

downloader.py

@@ -158,6 +158,8 @@ def main():
 
        adapter = adapters.getAdapter(configuration,url)
 
+       adapter.setChaptersRange(options.begin,options.end)
+           
        ## Check for include_images and absence of PIL, give warning.
        if adapter.getConfig('include_images'):
            try:
@@ -221,8 +223,6 @@ def main():
            if options.metaonly:
                print adapter.getStoryMetadataOnly()
            
-           adapter.setChaptersRange(options.begin,options.end)
-           
            output_filename=writeStory(configuration,adapter,options.format,options.metaonly)
        
        if not options.metaonly and adapter.getConfig("post_process_cmd"):

fanficdownloader/adapters/__init__.py

@@ -1,179 +1,183 @@
-# -*- coding: utf-8 -*-
-
-# Copyright 2011 Fanficdownloader team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-#
-
-import os, re, sys, glob, types
-from os.path import dirname, basename, normpath
-import logging
-import urlparse as up
-
-logger = logging.getLogger(__name__)
-
-from .. import exceptions as exceptions
-
-## must import each adapter here.
-
-import adapter_test1
-import adapter_fanfictionnet
-import adapter_castlefansorg
-import adapter_fictionalleyorg
-import adapter_fictionpresscom
-import adapter_ficwadcom
-import adapter_fimfictionnet
-import adapter_harrypotterfanfictioncom
-import adapter_mediaminerorg
-import adapter_potionsandsnitchesnet
-import adapter_tenhawkpresentscom
-import adapter_adastrafanficcom
-import adapter_thewriterscoffeeshopcom
-import adapter_tthfanficorg
-import adapter_twilightednet
-import adapter_twiwritenet
-import adapter_whoficcom
-import adapter_siyecouk
-import adapter_archiveofourownorg
-import adapter_ficbooknet
-import adapter_portkeyorg
-import adapter_mugglenetcom
-import adapter_hpfandomnet
-import adapter_thequidditchpitchorg
-import adapter_nfacommunitycom
-import adapter_midnightwhispersca
-import adapter_ksarchivecom
-import adapter_archiveskyehawkecom
-import adapter_squidgeorgpeja
-import adapter_libraryofmoriacom
-import adapter_wraithbaitcom
-import adapter_checkmatedcom
-import adapter_chaossycophanthexcom
-import adapter_dramioneorg
-import adapter_erosnsapphosycophanthexcom
-import adapter_lumossycophanthexcom
-import adapter_occlumencysycophanthexcom
-import adapter_phoenixsongnet
-import adapter_walkingtheplankorg
-import adapter_ashwindersycophanthexcom
-import adapter_thehexfilesnet
-import adapter_dokugacom
-import adapter_iketernalnet
-import adapter_onedirectionfanfictioncom
-import adapter_prisonbreakficnet
-import adapter_storiesofardacom
-import adapter_yourfanfictioncom
-import adapter_samdeanarchivenu
-import adapter_destinysgatewaycom
-import adapter_ncisfictioncom
-import adapter_stargateatlantisorg
-import adapter_thealphagatecom
-import adapter_fanfiktionde
-import adapter_ponyfictionarchivenet
-import adapter_sg1heliopoliscom
-import adapter_ncisficcom
-import adapter_nationallibrarynet
-import adapter_themasquenet
-import adapter_pretendercentrecom
-import adapter_darksolaceorg
-import adapter_finestoriescom
-import adapter_hpfanficarchivecom
-import adapter_svufictioncom
-import adapter_twilightarchivescom
-import adapter_wizardtalesnet
-import adapter_nhamagicalworldsus
-import adapter_hlfictionnet
-import adapter_grangerenchantedcom
-import adapter_dracoandginnycom
-import adapter_scarvesandcoffeenet
-import adapter_thepetulantpoetesscom
-import adapter_wolverineandroguecom
-import adapter_sinfuldesireorg
-import adapter_merlinficdtwinscouk
-import adapter_thehookupzonenet
-import adapter_bloodtiesfancom
-import adapter_qafficcom
-
-## This bit of complexity allows adapters to be added by just adding
-## importing.  It eliminates the long if/else clauses we used to need
-## to pick out the adapter.
-    
-## List of registered site adapters.
-__class_list = []
-
-def imports():
-    for name, val in globals().items():
-        if isinstance(val, types.ModuleType):
-            yield val.__name__
-
-for x in imports():
-    if "fanficdownloader.adapters.adapter_" in x:
-        #print x
-        __class_list.append(sys.modules[x].getClass())
-
-def getAdapter(config,url):
-
-    logger.debug("trying url:"+url)
-    (cls,fixedurl) = getClassFor(url)
-    logger.debug("fixedurl:"+fixedurl)
-    if cls:
-        adapter = cls(config,fixedurl) # raises InvalidStoryURL
-        return adapter
-    # No adapter found.
-    raise exceptions.UnknownSite( url, [cls.getSiteDomain() for cls in __class_list] )
-
-def getConfigSections():
-    return [cls.getConfigSection() for cls in __class_list]
-
-def getConfigSectionFor(url):
-    (cls,fixedurl) = getClassFor(url)
-    if cls:
-        return cls.getConfigSection()
-    
-    # No adapter found.
-    raise exceptions.UnknownSite( url, [cls.getSiteDomain() for cls in __class_list] )
-
-def getClassFor(url):
-    ## fix up leading protocol.
-    fixedurl = re.sub(r"(?i)^[htps]+[:/]+","http://",url.strip())
-    if not fixedurl.startswith("http"):
-        fixedurl = "http://%s"%url
-    ## remove any trailing '#' locations.
-    fixedurl = re.sub(r"#.*$","",fixedurl)
-    
-    ## remove any trailing '&' parameters--?sid=999 will be left.
-    ## that's all that any of the current adapters need or want.
-    fixedurl = re.sub(r"&.*$","",fixedurl)
-    
-    parsedUrl = up.urlparse(fixedurl)
-    domain = parsedUrl.netloc.lower()
-    if( domain != parsedUrl.netloc ):
-        fixedurl = fixedurl.replace(parsedUrl.netloc,domain)
-
-    cls = getClassFromList(domain)
-    if not cls and domain.startswith("www."):
-        domain = domain.replace("www.","")
-        logger.debug("trying site:without www: "+domain)
-        cls = getClassFromList(domain)
-        fixedurl = fixedurl.replace("http://www.","http://")
-    if not cls:
-        logger.debug("trying site:www."+domain)
-        cls = getClassFromList("www."+domain)
-        fixedurl = fixedurl.replace("http://","http://www.")
-        
-    return (cls,fixedurl)
-    
-def getClassFromList(domain):
-    for cls in __class_list:
-        if cls.matchesSite(domain):
-            return cls
+# -*- coding: utf-8 -*-
+
+# Copyright 2011 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import os, re, sys, glob, types
+from os.path import dirname, basename, normpath
+import logging
+import urlparse as up
+
+logger = logging.getLogger(__name__)
+
+from .. import exceptions as exceptions
+
+## must import each adapter here.
+
+import adapter_test1
+import adapter_fanfictionnet
+import adapter_castlefansorg
+import adapter_fictionalleyorg
+import adapter_fictionpresscom
+import adapter_ficwadcom
+import adapter_fimfictionnet
+import adapter_harrypotterfanfictioncom
+import adapter_mediaminerorg
+import adapter_potionsandsnitchesnet
+import adapter_tenhawkpresentscom
+import adapter_adastrafanficcom
+import adapter_thewriterscoffeeshopcom
+import adapter_tthfanficorg
+import adapter_twilightednet
+import adapter_twiwritenet
+import adapter_whoficcom
+import adapter_siyecouk
+import adapter_archiveofourownorg
+import adapter_ficbooknet
+import adapter_portkeyorg
+import adapter_mugglenetcom
+import adapter_hpfandomnet
+import adapter_thequidditchpitchorg
+import adapter_nfacommunitycom
+import adapter_midnightwhispersca
+import adapter_ksarchivecom
+import adapter_archiveskyehawkecom
+import adapter_squidgeorgpeja
+import adapter_libraryofmoriacom
+import adapter_wraithbaitcom
+import adapter_checkmatedcom
+import adapter_chaossycophanthexcom
+import adapter_dramioneorg
+import adapter_erosnsapphosycophanthexcom
+import adapter_lumossycophanthexcom
+import adapter_occlumencysycophanthexcom
+import adapter_phoenixsongnet
+import adapter_walkingtheplankorg
+import adapter_ashwindersycophanthexcom
+import adapter_thehexfilesnet
+import adapter_dokugacom
+import adapter_iketernalnet
+import adapter_onedirectionfanfictioncom
+import adapter_prisonbreakficnet
+import adapter_storiesofardacom
+import adapter_yourfanfictioncom
+import adapter_samdeanarchivenu
+import adapter_destinysgatewaycom
+import adapter_ncisfictionnet
+import adapter_stargateatlantisorg
+import adapter_thealphagatecom
+import adapter_fanfiktionde
+import adapter_ponyfictionarchivenet
+import adapter_sg1heliopoliscom
+import adapter_ncisficcom
+import adapter_nationallibrarynet
+import adapter_themasquenet
+import adapter_pretendercentrecom
+import adapter_darksolaceorg
+import adapter_finestoriescom
+import adapter_hpfanficarchivecom
+import adapter_svufictioncom
+import adapter_twilightarchivescom
+import adapter_wizardtalesnet
+import adapter_nhamagicalworldsus
+import adapter_hlfictionnet
+import adapter_grangerenchantedcom
+import adapter_dracoandginnycom
+import adapter_scarvesandcoffeenet
+import adapter_thepetulantpoetesscom
+import adapter_wolverineandroguecom
+import adapter_sinfuldesireorg
+import adapter_merlinficdtwinscouk
+import adapter_thehookupzonenet
+import adapter_bloodtiesfancom
+import adapter_indeathnet
+import adapter_jlaunlimitedcom
+import adapter_qafficcom
+import adapter_efpfanficnet
+
+
+## This bit of complexity allows adapters to be added by just adding
+## importing.  It eliminates the long if/else clauses we used to need
+## to pick out the adapter.
+    
+## List of registered site adapters.
+__class_list = []
+
+def imports():
+    for name, val in globals().items():
+        if isinstance(val, types.ModuleType):
+            yield val.__name__
+
+for x in imports():
+    if "fanficdownloader.adapters.adapter_" in x:
+        #print x
+        __class_list.append(sys.modules[x].getClass())
+
+def getAdapter(config,url):
+
+    logger.debug("trying url:"+url)
+    (cls,fixedurl) = getClassFor(url)
+    logger.debug("fixedurl:"+fixedurl)
+    if cls:
+        adapter = cls(config,fixedurl) # raises InvalidStoryURL
+        return adapter
+    # No adapter found.
+    raise exceptions.UnknownSite( url, [cls.getSiteDomain() for cls in __class_list] )
+
+def getConfigSections():
+    return [cls.getConfigSection() for cls in __class_list]
+
+def getConfigSectionFor(url):
+    (cls,fixedurl) = getClassFor(url)
+    if cls:
+        return cls.getConfigSection()
+    
+    # No adapter found.
+    raise exceptions.UnknownSite( url, [cls.getSiteDomain() for cls in __class_list] )
+
+def getClassFor(url):
+    ## fix up leading protocol.
+    fixedurl = re.sub(r"(?i)^[htps]+[:/]+","http://",url.strip())
+    if not fixedurl.startswith("http"):
+        fixedurl = "http://%s"%url
+    ## remove any trailing '#' locations.
+    fixedurl = re.sub(r"#.*$","",fixedurl)
+    
+    ## remove any trailing '&' parameters--?sid=999 will be left.
+    ## that's all that any of the current adapters need or want.
+    fixedurl = re.sub(r"&.*$","",fixedurl)
+    
+    parsedUrl = up.urlparse(fixedurl)
+    domain = parsedUrl.netloc.lower()
+    if( domain != parsedUrl.netloc ):
+        fixedurl = fixedurl.replace(parsedUrl.netloc,domain)
+
+    cls = getClassFromList(domain)
+    if not cls and domain.startswith("www."):
+        domain = domain.replace("www.","")
+        logger.debug("trying site:without www: "+domain)
+        cls = getClassFromList(domain)
+        fixedurl = fixedurl.replace("http://www.","http://")
+    if not cls:
+        logger.debug("trying site:www."+domain)
+        cls = getClassFromList("www."+domain)
+        fixedurl = fixedurl.replace("http://","http://www.")
+        
+    return (cls,fixedurl)
+    
+def getClassFromList(domain):
+    for cls in __class_list:
+        if cls.matchesSite(domain):
+            return cls

fanficdownloader/adapters/adapter_efpfanficnet.py

@@ -0,0 +1,296 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2012 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+logger = logging.getLogger(__name__)
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return EFPFanFicNet
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class EFPFanFicNet(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','efp')
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%d/%m/%y"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'www.efpfanfic.net'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
+
+    ## Login seems to be reasonably standard across eFiction sites.
+    def needToLoginCheck(self, data):
+        if 'Fai il login e leggi la storia!' in data:
+            return True
+        else:
+            return False
+        
+    def performLogin(self, url):
+        params = {}
+
+        if self.password:
+            params['penname'] = self.username
+            params['password'] = self.password
+        else:
+            params['penname'] = self.getConfig("username")
+            params['password'] = self.getConfig("password")
+        params['cookiecheck'] = '1'
+        params['submit'] = 'Invia'
+
+        loginUrl = 'http://' + self.getSiteDomain() + '/user.php?sid='+self.story.getMetadata('storyId')
+        logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
+                                                              params['penname']))
+    
+        d = self._fetchUrl(loginUrl, params)
+    
+        if '<a class="menu" href="newaccount.php">' in d : # register for new account link
+            logger.info("Failed to login to URL %s as %s" % (loginUrl,
+                                                              params['penname']))
+            raise exceptions.FailedToLogin(url,params['penname'])
+            return False
+        else:
+            return True
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        url = self.url
+        logger.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        if self.needToLoginCheck(data):
+            # need to log in for this one.
+            self.performLogin(url)
+            data = self._fetchUrl(url)
+
+        # if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+        #     raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+
+        ## Title
+        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        self.story.setMetadata('title',stripHTML(a))
+        
+        # Find authorid and URL from... author url.
+        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        self.story.setMetadata('authorId',a['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('author',a.string)
+
+        # Find the chapter selector 
+        select = soup.find('select', { 'name' : 'sid' } )
+    	 
+        if select is None:
+    	   # no selector found, so it's a one-chapter story.
+    	   self.chapterUrls.append((self.story.getMetadata('title'),url))
+        else:
+            allOptions = select.findAll('option', {'value' : re.compile(r'viewstory')})
+            for o in allOptions:
+                url = u'http://%s/%s' % ( self.getSiteDomain(),
+                                          o['value'])
+                # just in case there's tags, like <i> in chapter titles.
+                title = stripHTML(o)
+                self.chapterUrls.append((title,url))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+        
+        # normalize story URL to first chapter if later chapter URL was given:
+        url = self.chapterUrls[0][1].replace('&i=1','')
+        logger.debug("Normalizing to URL: "+url)
+        self._setURL(url)
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+
+        storya = None
+        authsoup = None
+        authurl = self.story.getMetadata('authorUrl')
+        
+        ## author can have more than one page of stories.
+        while storya == None:
+
+            # no storya, but do have authsoup--we're looping on author pages.
+            if authsoup != None:
+                # last author link with offset should be the 'next' link.
+                authurl = u'http://%s/%s' % ( self.getSiteDomain(),
+                                              authsoup.findAll('a',href=re.compile(r'viewuser\.php\?uid=\d+&catid=&offset='))[-1]['href'] )
+            
+            # Need author page for most of the metadata.
+            logger.debug("fetching author page: (%s)"%authurl)
+            authsoup = bs.BeautifulSoup(self._fetchUrl(authurl))
+            #print("authsoup:%s"%authsoup)
+        
+            storya = authsoup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+r'&i=1$'))
+        
+        storyblock = storya.parent.parent.parent
+
+        self.setDescription(url,storyblock.find('div', {'class':'introbloc'}))
+
+        noteblock = storyblock.find('div', {'class':'notebloc'})
+        #print("%s"%noteblock)
+        notetext = ("%s" % noteblock).replace("<br />"," |")
+        # <div class="notebloc">Autore: <a href="viewuser.php?uid=243036">Cendrillon89</a> | Pubblicata: 23/10/12 | Aggiornata: 30/10/12 | Rating: Arancione | Genere: Drammatico, Sentimentale | Capitoli: 10 | Completa<br />␍
+        # Tipo di coppia: Het |  Personaggi: Akasuna no Sasori , Akatsuki, Nuovo Personaggio |   Note: OOC | Avvertimenti: Tematiche delicate<br />␍
+        # Categoria: <a href="categories.php?catid=1&amp;parentcatid=1">Anime & Manga</a> > <a href="categories.php?catid=108&amp;parentcatid=108">Naruto</a> | Contesto: Naruto Shippuuden | Leggi le <a href="reviews.php?sid=1331275&amp;a=">3</a> recensioni</div>
+
+        cats = noteblock.findAll('a',href=re.compile(r'browse.php\?type=categories'))
+        for cat in cats:
+            self.story.addToList('category',cat.string)
+            
+        for item in notetext.split("|"):
+            if ":" in item:
+                (label,value) = item.split(":")
+                label=label.strip()
+                value=value.strip()
+            else:
+                label=value=item.strip()
+
+            if 'Pubblicata' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            
+            if 'Aggiornata' in label:
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+
+            if label == "Completa":
+                self.story.setMetadata('status', 'Completed')
+            
+            if label == "In corso":
+                self.story.setMetadata('status', 'In-Progress')
+
+            if 'Rating' in label:
+                self.story.setMetadata('rating', value)
+
+            if 'Personaggi' in label:
+                for val in value.split(","):
+                    self.story.addToList('characters',val)
+                    
+            if 'Genere' in label:
+                for val in value.split(","):
+                    self.story.addToList('genre',val)
+                    
+            if 'Coppie' in label:
+                for val in value.split(","):
+                    self.story.addToList('ships',val)
+
+            if 'Avvertimenti' in label:
+                for val in value.split(","):
+                    if val != "None":
+                        self.story.addToList('warnings',val)
+
+            # 'extra' metadata for this adapter:
+                    
+            if 'Tipo di coppia' in label:
+                for val in value.split(","):
+                    self.story.addToList('type',val)
+                    
+            if 'Note' in label:
+                for val in value.split(","):
+                    if val != "None":
+                        self.story.addToList('notes',val)
+                    
+            if 'Contesto' in label:
+                self.story.setMetadata('context', value)
+
+            ## Note--efp doesn't provide word count.
+                
+        try:
+            # Find Series name from series URL.
+            a = soup.find('a', href=re.compile(r"viewseries.php\?ssid=\d+&i=1"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            # can't use ^viewstory...$ in case of higher rated stories with javascript href.
+            storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+&i=1'))
+            i=1
+            for a in storyas:
+                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId'))+'&i=1':
+                    self.setSeries(series_name, i)
+                    break
+                i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logger.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulSoup(self._fetchUrl(url))
+        
+        div = soup.find('div', {'class' : 'storia'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_fanfiktionde.py

@@ -26,6 +26,7 @@ from .. import BeautifulSoup as bs
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
+
 from base_adapter import BaseSiteAdapter,  makeDate
 
 def getClass():
@@ -140,7 +141,7 @@ class FanFiktionDeAdapter(BaseSiteAdapter):
         self.story.setMetadata('title',a.string)
         
         # Find authorid and URL from... author url.
-        head = soup.find('div', {'style' : 'width:85%;float:left;'})
+        head = soup.find('div', {'class' : 'story-metadata-left-top'})
         a = head.find('a')
         self.story.setMetadata('authorId',a['href'].split('/')[2])
         self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
@@ -176,7 +177,7 @@ class FanFiktionDeAdapter(BaseSiteAdapter):
         self.setDescription(url,a['onmouseover'].split("', '")[1])
         
         td = tr[i].findAll('td')
-        self.story.addToList('category',td[1].string)
+        self.story.addToList('category',stripHTML(td[1]))
         self.story.setMetadata('rating', td[4].string)
         self.story.setMetadata('numWords', td[5].string)
  

fanficdownloader/adapters/adapter_fictionalleyorg.py

@@ -223,7 +223,16 @@ class FictionAlleyOrgSiteAdapter(BaseSiteAdapter):
             
         if not data or not text:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
+        # not sure how, but we can get html, etc tags still in some
+        # stories.  That breaks later updates because it confuses
+        # epubutils.py
+        for tag in text.findAll('head'):
+            tag.extract()
+        
+        for tag in text.findAll('body') + text.findAll('html'):
+            tag.name = 'div'
+            
         return self.utf8FromSoup(url,text)
 
 def getClass():

fanficdownloader/adapters/adapter_fimfictionnet.py

@@ -159,7 +159,7 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
         self.story.setMetadata("datePublished", datetime.fromtimestamp(rawDatePublished))
         rawDateUpdated = storyMetadata["date_modified"]
         self.story.setMetadata("dateUpdated", datetime.fromtimestamp(rawDateUpdated))
-        
+
         soup = bs.BeautifulSoup(data).find("div", {"class":"story"})
         # fimfic stopped putting the char name on or around the char
         # icon now for some reason.  Pull it from the image name with
@@ -174,6 +174,15 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
                 char = "Cutie Mark Crusaders"
             self.story.addToList("characters", char)
             
+        # extra site specific metadata
+        extralist = ["likes","dislikes","views","total_views","short_description"]
+        for metakey in extralist:
+            if metakey in storyMetadata:
+                value = storyMetadata[metakey]
+                if not isinstance(value,basestring):
+                    value = unicode(value)
+                self.story.setMetadata(metakey, value)
+        
             
     def getChapterText(self, url):
         logger.debug('Getting chapter text from: %s' % url)

fanficdownloader/adapters/adapter_hpfandomnet.py

@@ -181,21 +181,22 @@ class HPFandomNetAdapterAdapter(BaseSiteAdapter): # XXX
             value = td.nextSibling.string
             #print("\nlabel:%s\nvalue:%s\n"%(label,value))
 
-            if 'Category' in label:
+            if 'Category' in label and value:
                 cats = td.parent.findAll('a',href=re.compile(r'categories.php'))
                 catstext = [cat.string for cat in cats]
                 for cat in catstext:
                     self.story.addToList('category',cat.string)
 
-            if 'Characters' in label:
+            if 'Characters' in label and value: # this site can have Character label with no
+                                                # values, apparently.  Others as a precaution.
                 for char in value.split(','):
                     self.story.addToList('characters',char.strip())
 
-            if 'Genre' in label:
+            if 'Genre' in label and value:
                 for genre in value.split(','):
                     self.story.addToList('genre',genre.strip())
 
-            if 'Warnings' in label:
+            if 'Warnings' in label and value:
                 for warning in value.split(','):
                     if warning.strip() != 'none':
                         self.story.addToList('warnings',warning.strip())

fanficdownloader/adapters/adapter_indeathnet.py

@@ -0,0 +1,179 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2012 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+logger = logging.getLogger(__name__)
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return InDeathNetAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class InDeathNetAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+		
+		  # get storyId from url--url validation guarantees query correct
+        m = re.match(self.getSiteURLPattern(),url)
+        if m:
+            self.story.setMetadata('storyId',m.group('id'))
+            logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+            # normalized story URL.
+            self._setURL('http://www.' + self.getSiteDomain() + '/blog/archive/'+self.story.getMetadata('storyId')+'-'+m.group('name')+'/')
+        else:
+            raise exceptions.InvalidStoryURL(url,
+                                             self.getSiteDomain(),
+                                             self.getSiteExampleURLs())
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','idn')
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%d %B %Y"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'indeath.net'
+
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/blog/archive/123-story-in-death/"
+
+    def getSiteURLPattern(self):
+        # http://www.indeath.net/blog/archive/169-ransom-in-death/
+        return re.escape("http://")+re.escape(self.getSiteDomain())+r"/blog/(archive/)?(?P<id>\d+)\-(?P<name>[a-z0-9\-]*)/?$"     
+        
+            
+    def getDateFromComponents(self, postmonth, postday):
+        ym = re.search("Entries\ in\ (?P<mon>January|February|March|April|May|June|July|August|September|October|November|December)\ (?P<year>\d{4})",postmonth)
+        d = re.search("(?P<day>\d{2})\ (Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)",postday)
+        postdate = makeDate(d.group('day')+' '+ym.group('mon')+' '+ym.group('year'),self.dateformat)
+        return postdate
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        url = self.url
+        try:
+            data = self._fetchUrl(url)
+            
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.meta)
+            else:
+                raise e
+                
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title
+        h = soup.find('a', id="blog_title")
+        t = h.find('span')
+        self.story.setMetadata('title',t.contents[0].string.strip())
+		
+        s = t.find('div')        
+        if s != None:
+            self.setDescription(url,s)
+		
+        # Find authorid and URL from first link in Recent Entries (don't yet reference 'recent entries' - let's see if that is required)
+        a = soup.find('a', href=re.compile(r"http://www.indeath.net/user/\d+\-[a-z0-9]+/$"))		#http://www.indeath.net/user/9083-cyrex/
+        m = re.search('http://www.indeath.net/user/(?P<id>\d+)\-(?P<name>[a-z0-9]*)/$',a['href'])
+        self.story.setMetadata('authorId',m.group('id'))
+        self.story.setMetadata('authorUrl',a['href'])
+        self.story.setMetadata('author',m.group('name'))
+
+
+
+
+        # Find the chapters:
+        chapters=soup.findAll('a', title="View entry", href=re.compile(r'http://www.indeath.net/blog/'+self.story.getMetadata('storyId')+"/entry\-(\d+)\-([^/]*)/$"))
+
+        #reverse the list since newest at the top
+        chapters.reverse()
+        
+        # Get date published & updated from first & last entries
+        posttable=soup.find('div', id="main_column")
+        
+        postmonths=posttable.findAll('th', text=re.compile(r'Entries\ in\ '))
+        postmonths.reverse()
+        
+        postdates=posttable.findAll('span', _class="desc", text=re.compile('\d{2}\ (Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)'))
+        postdates.reverse()
+        
+        self.story.setMetadata('datePublished',self.getDateFromComponents(postmonths[0],postdates[0]))
+        self.story.setMetadata('dateUpdated',self.getDateFromComponents(postmonths[len(postmonths)-1],postdates[len(postdates)-1]))
+        
+        # Process List of Chapters              
+        self.story.setMetadata('numChapters',len(chapters))
+        logger.debug("numChapters: (%s)"%self.story.getMetadata('numChapters'))
+        for x in range(0,len(chapters)):
+            # just in case there's tags, like <i> in chapter titles.
+            chapter=chapters[x]
+            if len(chapters)==1:
+                self.chapterUrls.append((self.story.getMetadata('title'),chapter['href']))
+            else:
+            	ct = stripHTML(chapter)
+            	tnew = re.match("(?i)"+self.story.getMetadata('title')+r" - (?P<newtitle>.*)$",ct)
+            	if tnew:
+            		chaptertitle = tnew.group('newtitle')
+            	else:
+            		chaptertitle = ct
+                self.chapterUrls.append((chaptertitle,chapter['href']))
+	
+		
+        
+        
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+        logger.debug('Getting chapter text from: %s' % url)
+		
+        #chapter=bs.BeautifulSoup('<div class="story"></div>')
+        data = self._fetchUrl(url)
+        soup = bs.BeautifulSoup(data,selfClosingTags=('br','hr','span','center'))
+
+        chapter = soup.find("div", "entry_content")
+        
+        if None == chapter:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+
+        return self.utf8FromSoup(url,chapter)
+

fanficdownloader/adapters/adapter_jlaunlimitedcom.py

@@ -0,0 +1,259 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2011 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+logger = logging.getLogger(__name__)
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+
+def getClass():
+    return JLAUnlimitedComAdapter
+
+
+class JLAUnlimitedComAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+
+        self._setURL('http://' + self.getSiteDomain() + '/eFiction1.1/viewstory.php?sid='+self.story.getMetadata('storyId'))
+
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','jla')
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%m/%d/%y"
+
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'www.jlaunlimited.com'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/eFiction1.1/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/eFiction1.1/viewstory.php?sid=")+r"\d+$"
+
+
+
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        if self.is_adult or self.getConfig("is_adult"):
+            # Weirdly, different sites use different warning numbers.
+            # If the title search below fails, there's a good chance
+            # you need a different number.  print data at that point
+            # and see what the 'click here to continue' url says.
+            addurl = "&ageconsent=ok&warning=4" # XXX
+        else:
+            addurl=""
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'+addurl
+        logger.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        # Assume that if there is a url with 'warning=#' in the page then it is a 'check' page
+        m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)",data)
+        if m != None:
+            if self.is_adult or self.getConfig("is_adult"):
+                # We tried the default and still got a warning, so
+                # let's pull the warning number from the 'continue'
+                # link and reload data.
+                addurl = m.group(1)
+                # correct stupid & error in url.
+                addurl = addurl.replace("&","&")
+                url = self.url+'&index=1'+addurl
+                logger.debug("URL 2nd try: "+url)
+
+                try:
+                    data = self._fetchUrl(url)
+                except urllib2.HTTPError, e:
+                    if e.code == 404:
+                        raise exceptions.StoryDoesNotExist(self.url)
+                    else:
+                        raise e    
+            else:
+                raise exceptions.AdultCheckRequired(self.url)
+                
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+
+        ## Title
+        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')))
+        self.story.setMetadata('title',a.string)
+        
+        # Find authorid and URL from... author url.
+        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        self.story.setMetadata('authorId',a['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('author',a.string)
+
+        # Find the chapters:
+        for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+")):
+            # just in case there's tags, like <i> in chapter titles.
+            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/eFiction1.1/'+chapter['href']+addurl))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+
+        # utility method
+        def defaultGetattr(d,k):
+            try:
+                return d[k]
+            except:
+                return ""
+
+        # <span class="label">Rated:</span> NC-17<br /> etc
+        labels = soup.findAll('span',{'class':'label'})
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.string
+
+            if 'Summary' in label:
+                ## Everything until the next span class='label'
+                svalue = ""
+                while not defaultGetattr(value,'class') == 'label':
+                    svalue += str(value)
+                    value = value.nextSibling
+                self.setDescription(url,svalue)
+                #self.story.setMetadata('description',stripHTML(svalue))
+
+            if 'Rated' in label:
+                self.story.setMetadata('rating', value)
+
+            if 'Word count' in label:
+                self.story.setMetadata('numWords', value)
+
+            if 'Categories' in label:
+                cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
+                catstext = [cat.string for cat in cats]
+                for cat in catstext:
+                    self.story.addToList('category',cat.string)
+
+            if 'Characters' in label:
+                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+                charstext = [char.string for char in chars]
+                for char in charstext:
+                    self.story.addToList('characters',char.string)
+
+            ## Not all sites use Genre, but there's no harm to
+            ## leaving it in.  Check to make sure the type_id number
+            ## is correct, though--it's site specific.
+            if 'Genre' in label:
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1')) # XXX
+                genrestext = [genre.string for genre in genres]
+                self.genre = ', '.join(genrestext)
+                for genre in genrestext:
+                    self.story.addToList('genre',genre.string)
+
+            ## Not all sites use Warnings, but there's no harm to
+            ## leaving it in.  Check to make sure the type_id number
+            ## is correct, though--it's site specific.
+            if 'Warnings' in label:
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')) # XXX
+                warningstext = [warning.string for warning in warnings]
+                self.warning = ', '.join(warningstext)
+                for warning in warningstext:
+                    self.story.addToList('warnings',warning.string)
+
+            if 'Completed' in label:
+                if 'Yes' in value:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+
+            if 'Published' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            
+            if 'Updated' in label:
+                # there's a stray [ at the end.
+                #value = value[0:-1]
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+
+        try:
+            # Find Series name from series URL.
+            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/fanfic/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
+            i=1
+            for a in storyas:
+                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                    self.setSeries(series_name, i)
+                    break
+                i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+
+
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logger.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+
+        div = soup.find('div', {'id' : 'story'})
+        
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+
+        return self.utf8FromSoup(url,div)
+

fanficdownloader/adapters/adapter_ncisfictionnet.py

@@ -28,15 +28,20 @@ from .. import exceptions as exceptions
 from base_adapter import BaseSiteAdapter,  makeDate
 
 def getClass():
-    return NCISFictionComAdapter
+    return NCISFictionNetAdapter
 
 # Class name has to be unique.  Our convention is camel case the
 # sitename with Adapter at the end.  www is skipped.
-class NCISFictionComAdapter(BaseSiteAdapter):
+class NCISFictionNetAdapter(BaseSiteAdapter):
 
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
 
+        # ncisfiction.net blocks IPs the default user-agent.  However,
+        # when asked, they said it was just general anti-spam, not
+        # targeted at us.  That lets me do this in good conscience:
+        self.opener.addheaders = [('User-agent', 'FFDL/1.6')]
+        
         self.decode = ["iso-8859-1",
                        "Windows-1252"] # 1252 is a superset of iso-8859-1.
                                # Most sites that claim to be
@@ -64,13 +69,21 @@ class NCISFictionComAdapter(BaseSiteAdapter):
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
-        return 'www.ncisfiction.com'
+        return 'www.ncisfiction.net'
+
+    ## Changed from www.ncisfiction.com to www.ncisfiction.net Oct
+    ## 2012 due to the ncisfiction.com domain expiring.  Still accept
+    ## .com domains for existing updates, etc.
+    
+    @classmethod
+    def getAcceptDomains(cls):
+        return ['www.ncisfiction.net','www.ncisfiction.com']
 
     def getSiteExampleURLs(self):
         return "http://"+self.getSiteDomain()+"/story.php?stid=01234 http://"+self.getSiteDomain()+"/chapters.php?stid=1234"
 
     def getSiteURLPattern(self):
-        return "http://"+self.getSiteDomain()+r'/(chapters|story)?.php\?stid=\d+'
+        return r'http://www\.ncisfiction\.(net|com)/(chapters|story)?.php\?stid=\d+'
        
 
     ## Getting the chapter list and the meta data, plus 'is adult' checking.

fanficdownloader/adapters/adapter_ponyfictionarchivenet.py

@@ -237,8 +237,7 @@ class PonyFictionArchiveNetAdapter(BaseSiteAdapter):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        soup = bs.BeautifulSoup(self._fetchUrl(url)) # otherwise soup eats the br/hr tags.
         
         div = soup.find('div', {'id' : 'story'})
 

fanficdownloader/adapters/adapter_potionsandsnitchesnet.py

@@ -162,12 +162,12 @@ class PotionsAndSnitchesNetSiteAdapter(BaseSiteAdapter):
                     self.story.setMetadata('status', 'In-Progress')
 
             if 'Published' in label:
-                self.story.setMetadata('datePublished', makeDate(stripHTML(value), "%b %d %Y"))
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), "%d %b %Y"))
             
             if 'Updated' in label:
                 # there's a stray [ at the end.
                 #value = value[0:-1]
-                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), "%b %d %Y"))
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), "%d %b %Y"))
 
         try:
             # Find Series name from series URL.

fanficdownloader/adapters/adapter_test1.py

@@ -129,7 +129,7 @@ Some more longer description.  "I suck at summaries!"  "Better than it sounds!"
 
         self.story.addToList('genre','Fantasy')
         self.story.addToList('genre','Comedy')
-        self.story.addToList('genre','SF')
+        self.story.addToList('genre','Sci-Fi')
         self.story.addToList('genre','Noir')
         
         self.story.addToList('characters','Bob Smith')

fanficdownloader/adapters/adapter_thehexfilesnet.py

@@ -147,6 +147,7 @@ class TheHexFilesNetAdapter(BaseSiteAdapter):
             self.story.setMetadata('status', 'In-Progress')
 						
         summary = info.find('td', {'class' : 'summary'})
+        summary.name='div' # change td to div so it doesn't mess up the display when using table titlepage.
         self.setDescription(url,summary)
 		
         rating=stripHTML(info.find('td', {'align' : 'left'})).split('(')[1].split(')')[0]

fanficdownloader/adapters/adapter_twiwritenet.py

@@ -139,12 +139,14 @@ class TwiwriteNetSiteAdapter(BaseSiteAdapter):
         # use BeautifulSoup HTML parser to make everything easier to find.
         soup = bs.BeautifulSoup(data)
 
+        pagetitlediv = soup.find('div',id='pagetitle')
+        
         ## Title
-        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        a = pagetitlediv.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',a.string)
         
         # Find authorid and URL from... author url.
-        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        a = pagetitlediv.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
         self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
         self.story.setMetadata('author',a.string)

fanficdownloader/bbcodeutils/bbcodeparser.py

@@ -201,8 +201,11 @@ class bbcodeparser:
     #re_tagArgs = re.compile (r'\s*([^=]*)=(("([^"]+)")|([^\s]+))',  re.DOTALL | re.UNICODE)
     re_tagArgs = re.compile (r'\s*([\w]*)=(("([^"]+)")|([^\s]+))',  re.DOTALL | re.UNICODE)
 
-    # get a unique name and replace escaped braces 
-    unique = hashlib.md5(code).hexdigest()
+    # get a unique name and replace escaped braces encode utf8 to
+    # prevent CLI/Web from barfing on unicode chars.  Not sure why
+    # this even needs to be 'unique' like this, but that's the way
+    # they wrote it.
+    unique = hashlib.md5(code.encode('utf8')).hexdigest()
     code   = code.replace ('\[', unique+'_OPEN_BRACE')
     code   = code.replace ('\]', unique+'_CLOSE_BRACE')
 

fanficdownloader/configurable.py

@@ -134,7 +134,7 @@ class Configurable(object):
         return self.configuration.hasConfig(key)
         
     def getConfig(self, key, default=""):
-        return self.configuration.getConfig(key)
+        return self.configuration.getConfig(key,default)
 
     def getConfigList(self, key):
         return self.configuration.getConfigList(key)

fanficdownloader/story.py

@@ -253,24 +253,40 @@ class Story(Configurable):
     ## Three part effect only those key(s) lists.
     ## pattern=>replacement
     ## metakey,metakey=>pattern=>replacement
+    ## *Five* part lines.  Effect only when trailing conditional key=>regexp matches
+    ## metakey[,metakey]=>pattern=>replacement[&&metakey=>regexp]
     def setReplace(self,replace):
         for line in replace.splitlines():
+            (metakeys,regexp,replacement,condkey,condregexp)=(None,None,None,None,None)
+            if "&&" in line:
+                (line,conditional) = map( lambda x: x.strip(), line.split("&&") )
+                (condkey,condregexp) = map( lambda x: x.strip(), conditional.split("=>") )
             if "=>" in line:
                 parts = map( lambda x: x.strip(), line.split("=>") )
                 if len(parts) > 2:
-                    parts[0] = map( lambda x: x.strip(), parts[0].split(",") )
-                    self.replacements.append(parts)
+                    metakeys = map( lambda x: x.strip(), parts[0].split(",") )
+                    (regexp,replacement)=parts[1:]
                 else:
-                    self.replacements.append([None]+parts)
+                    (regexp,replacement)=parts
+
+            if regexp:
+                regexp = re.compile(regexp)
+                if condregexp:
+                    condregexp = re.compile(condregexp)
+                self.replacements.append([metakeys,regexp,replacement,condkey,condregexp])
     
     def doReplacments(self,value,key):
-        for (keys,p,v) in self.replacements:
-            if (keys == None or key in keys) \
+        for (metakeys,regexp,replacement,condkey,condregexp) in self.replacements:
+            if (metakeys == None or key in metakeys) \
                     and isinstance(value,basestring) \
-                    and re.search(p,value):
-                #pv=value
-                value = re.sub(p,v,value)
-                #print("change:%s => %s === %s => %s "%(p,v,pv,value))
+                    and regexp.search(value):
+                doreplace=True
+                if condkey and condkey != key: # prevent infinite recursion.
+                    condval = self.getMetadata(condkey)
+                    doreplace = condval != None and condregexp.search(condval)
+                    
+                if doreplace:
+                    value = regexp.sub(replacement,value)
         return value
         
     def getMetadataRaw(self,key):
@@ -293,7 +309,9 @@ class Story(Configurable):
                     value = commaGroups(value)
                 if key == "numChapters":
                     value = commaGroups("%d"%value)
-                if key in ("dateCreated","datePublished","dateUpdated"):
+                if key in ("dateCreated"):
+                    value = value.strftime(self.getConfig(key+"_format","%Y-%m-%d %H:%M:%S"))
+                if key in ("datePublished","dateUpdated"):
                     value = value.strftime(self.getConfig(key+"_format","%Y-%m-%d"))
 
             if doreplacements:
@@ -450,7 +468,7 @@ class Story(Configurable):
             pattern = re.compile(r"[^a-zA-Z0-9_\. \[\]\(\)&'-]+")
             for k in origvalues.keys():
                 values[k]=re.sub(pattern,'_', removeAllEntities(self.getMetadata(k)))
-
+    
         return string.Template(template).substitute(values).encode('utf8')
 
     # pass fetch in from adapter in case we need the cookies collected

fanficdownloader/writers/writer_epub.py

@@ -192,30 +192,28 @@ div { margin: 0pt; padding: 0pt; }
         string.Template().  START and END are expected to use the same
         names as Story.metadata, but ENTRY should use id, label and value.
         """
-        if self.getConfig("include_logpage"):
+        if self.hasConfig("logpage_start"):
+            START = string.Template(self.getConfig("logpage_start"))
+        else:
+            START = self.EPUB_LOG_PAGE_START
 
-            if self.hasConfig("logpage_start"):
-                START = string.Template(self.getConfig("logpage_start"))
-            else:
-                START = self.EPUB_LOG_PAGE_START
-
-            if self.hasConfig("logpage_end"):
-                END = string.Template(self.getConfig("logpage_end"))
-            else:
-                END = self.EPUB_LOG_PAGE_END
-            
-            # if there's a self.story.logfile, there's an existing log
-            # to add to.
-            if self.story.logfile:
-                logger.debug("existing logfile found, appending")
-                logger.debug("existing data:%s"%self._getLastLogData(self.story.logfile))
-                replace_string = "</body>" # "</h3>"
-                self._write(out,self.story.logfile.replace(replace_string,self._makeLogEntry(self._getLastLogData(self.story.logfile))+replace_string))
-            else:
-                # otherwise, write a new one.
-                self._write(out,START.substitute(self.story.getAllMetadata()))
-                self._write(out,self._makeLogEntry())
-                self._write(out,END.substitute(self.story.getAllMetadata()))
+        if self.hasConfig("logpage_end"):
+            END = string.Template(self.getConfig("logpage_end"))
+        else:
+            END = self.EPUB_LOG_PAGE_END
+        
+        # if there's a self.story.logfile, there's an existing log
+        # to add to.
+        if self.story.logfile:
+            logger.debug("existing logfile found, appending")
+            logger.debug("existing data:%s"%self._getLastLogData(self.story.logfile))
+            replace_string = "</body>" # "</h3>"
+            self._write(out,self.story.logfile.replace(replace_string,self._makeLogEntry(self._getLastLogData(self.story.logfile))+replace_string))
+        else:
+            # otherwise, write a new one.
+            self._write(out,START.substitute(self.story.getAllMetadata()))
+            self._write(out,self._makeLogEntry())
+            self._write(out,END.substitute(self.story.getAllMetadata()))
 
     # self parsing instead of Soup because it should be simple and not
     # worth the overhead.
@@ -494,7 +492,11 @@ div { margin: 0pt; padding: 0pt; }
             items.append(("toc_page","OEBPS/toc_page.xhtml","application/xhtml+xml","Table of Contents"))
             itemrefs.append("toc_page")
 
-        if self.getConfig("include_logpage"):
+        dologpage = ( self.getConfig("include_logpage") == "smart" and \
+                          (self.story.logfile or self.story.getMetadataRaw("status") == "In-Progress") )  \
+                     or self.getConfig("include_logpage") == "true"
+
+        if dologpage:
             items.append(("log_page","OEBPS/log_page.xhtml","application/xhtml+xml","Update Log"))
             itemrefs.append("log_page")
             
@@ -629,12 +631,12 @@ div { margin: 0pt; padding: 0pt; }
             outputepub.writestr("OEBPS/toc_page.xhtml",tocpageIO.getvalue())
         tocpageIO.close()
 
-        # write log page.
-        logpageIO = StringIO.StringIO()
-        self.writeLogPage(logpageIO)
-        if logpageIO.getvalue(): # will be false if no log page.
+        if dologpage:
+            # write log page.
+            logpageIO = StringIO.StringIO()
+            self.writeLogPage(logpageIO)
             outputepub.writestr("OEBPS/log_page.xhtml",logpageIO.getvalue())
-        logpageIO.close()
+            logpageIO.close()
 
         if self.hasConfig('chapter_start'):
             CHAPTER_START = string.Template(self.getConfig("chapter_start"))

index.html

@@ -54,6 +54,10 @@
 	      much easier. </p>
 	  </div>
 	  <!-- put announcements here, h3 is a good title size. -->
+	  <h3>Fixes:</h3>
+	  <p>
+	    Minor fixes for fictionalley.org, thehexfiles.net, ponyfictionarchive.net, and potionsandsnitches.net.
+	  </p>
 	  <p>
 	    Questions?  Check out our 
 	    <a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownloaderFAQs">FAQs</a>.
@@ -62,7 +66,7 @@
 	    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://4-4-28.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
+	    <a href="http://4-4-32.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
 	  </p>
 	  <div id='error'>
 	    {{ error_message }}
@@ -544,8 +548,22 @@
 	    Use the URL of the story's chapter list, such as
 	    <br /><a href="http://www.qaf-fic.com/atp/viewstory.php?sid=1234">http://www.qaf-fic.com/atp/viewstory.php?sid=1234</a>
 	  </dd>
+	  <dt>indeath.net</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://www.indeath.net/blog/25-nightmare-in-death/">http://www.indeath.net/blog/25-nightmare-in-death/</a>
+	  </dd>
+	  <dt>www.jlaunlimited.com</dt>
+	  <dd>
+	    Use the URL of the story's first chapter, such as
+	    <br /><a href="http://www.jlaunlimited.com/eFiction1.1/viewstory.php?sid=1234">http://www.jlaunlimited.com/eFiction1.1/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>www.efpfanfic.net</dt>
+	  <dd>
+	    Use the URL of any story chapter, such as
+	    <br /><a href="http://www.efpfanfic.net/viewstory.php?sid=12345">http://www.efpfanfic.net/viewstory.php?sid=12345</a>
+	  </dd>
 	</dl>
-		    
 
 	<p>
 	  A few additional things to know, which will make your life substantially easier:

plugin-defaults.ini

@@ -131,8 +131,11 @@ extratags: FanFiction
 ## for regexp details.
 ## Make sure to keep at least one space at the start of each line and
 ## to escape % to %%, if used.
-## Two or three part lines.  Two part effect everything.
+## Two, three or five part lines.  Two part effect everything.
 ## Three part effect only those key(s) lists.
+## *Five* part lines.  Effect only when trailing conditional key=>regexp matches
+## metakey[,metakey]=>pattern=>replacement[&&conditionalkey=>regexp]
+## Note that if metakey == conditionalkey the conditional is ignored.
 #replace_metadata:
 # genre,category=>Sci-Fi=>SF
 # Puella Magi Madoka Magica.* => Madoka
@@ -140,7 +143,9 @@ extratags: FanFiction
 # Crossover: (.*)=>\1
 # title=>(.*)Great(.*)=>\1Moderate\2
 # .*-Centered=>
-
+# characters=>Sam W\.=>Sam Witwicky&&category=>Transformers
+# characters=>Sam W\.=>Sam Winchester&&category=>Supernatural
+ 
 ## 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.)
@@ -258,13 +263,17 @@ windows_eol: true
 ## mobi generated from epub by calibre will have a TOC at the end.
 include_tocpage: false
 
-## include a Update Log page before the story text.  If included, the
-## log will be updated each time the epub is an all the metadata
+## include a Update Log page before the story text.  If 'true', the
+## log will be updated each time the epub is and all the metadata
 ## fields that have changed since the last update (typically
 ## dateUpdated,numChapters,numWords at a minimum) will be shown.
 ## Great for tracking when chapters came out and when the description,
 ## etc changed.
 include_logpage: false
+## If set to 'smart', logpage will only be included if the story is
+## status:In-Progress or already had a logpage.  That way you don't
+## end up with Completed stories that have just one logpage entry.
+#include_logpage: smart
 
 ## items to include in the log page Empty metadata entries, or those
 ## that haven't changed since the last update, will *not* appear, even
@@ -372,31 +381,31 @@ nook_img_fix:true
 ## URLs like: http://test1.com?sid=12345
 [test1.com]
 extratags: FanFiction,Testing
-extracategories:Fafner
-extragenres:Romance,Fluff
-extracharacters:Reginald Smythe-Smythe,Mokona,Harry P.
-extraships:Smythe-Smythe/Mokona
-extrawarnings:Extreme Bogosity
+# extracategories:Fafner
+# extragenres:Romance,Fluff
+# extracharacters:Reginald Smythe-Smythe,Mokona,Harry P.
+# extraships:Smythe-Smythe/Mokona
+# extrawarnings:Extreme Bogosity
 
-extra_valid_entries:metaA,metaB,metaC,listX,listY,listZ,compositeJ,compositeK,compositeL
+# extra_valid_entries:metaA,metaB,metaC,listX,listY,listZ,compositeJ,compositeK,compositeL
 
-include_in_compositeJ:dateCreated
-include_in_compositeK:metaC,listX,compositeL,compositeJ,compositeK,listZ
-include_in_compositeL:ships,metaA,listZ,datePublished,dateUpdated,
+# include_in_compositeJ:dateCreated
+# include_in_compositeK:metaC,listX,compositeL,compositeJ,compositeK,listZ
+# include_in_compositeL:ships,metaA,listZ,datePublished,dateUpdated,
 
-extra_titlepage_entries: metaA,metaB,metaC,listX,listY,listZ,compositeJ,compositeK,compositeL
-extra_logpage_entries: metaA,metaB,metaC,listX,listY,listZ,compositeJ,compositeK,compositeL
-extra_subject_tags: metaA,metaB,metaC
+# extra_titlepage_entries: metaA,metaB,metaC,listX,listY,listZ,compositeJ,compositeK,compositeL
+# extra_logpage_entries: metaA,metaB,metaC,listX,listY,listZ,compositeJ,compositeK,compositeL
+# extra_subject_tags: metaA,metaB,metaC
 
-replace_metadata:
- compositeL=>Val=>VALUE
- series,extratags=>Test=>Plan
- Puella Magi Madoka Magica.* => Madoka
- Comedy=>Humor
- Crossover: (.*)=>\1
- (.*)Great(.*)=>\1Moderate\2
- .*-Centered=>
- characters=>Harry P\.=>Harry Potter
+# replace_metadata:
+#  compositeL=>Val=>VALUE
+#  series,extratags=>Test=>Plan
+#  Puella Magi Madoka Magica.* => Madoka
+#  Comedy=>Humor
+#  Crossover: (.*)=>\1
+#  (.*)Great(.*)=>\1Moderate\2
+#  .*-Centered=>
+#  characters=>Harry P\.=>Harry Potter
 
 
 ## If necessary, you can define [<site>:<format>] sections to
@@ -565,9 +574,9 @@ cliches_label:Character Cliches
 ## then the label of the calibre custom column, then (optionally) a
 ## 'mode'.  'r' to Replace any existing values, 'a' to Add to existing
 ## value (use with tag-like columns), and 'n' for setting on New books
-## only.
-## Make sure to keep at least one space at the start of each
-## line.
+## only.  (Default is 'r'.)
+## Each metadata=>column mapping must be on a separate line and each
+## needs to have one space at the start of each line.
 
 #custom_columns_settings:
 # cliches=>#acolumn,r
@@ -650,6 +659,10 @@ extracharacters:Hermione Granger
 ## Site dedicated to these categories/characters/ships
 extracategories:Highlander
 
+[indeath.net]
+## Site dedicated to these categories/characters/ships
+extracategories:In Death
+
 [ksarchive.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Star Trek
@@ -883,6 +896,21 @@ extracategories:InuYasha
 extracharacters:Sesshoumaru,Kagome
 extraships:Sesshoumaru/Kagome
 
+[www.efpfanfic.net]
+## 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
+
+## Extra metadata that this adapter knows about.  See [dramione.org]
+## for examples of how to use them.
+extra_valid_entries:notes,context,type
+notes_label:Notes
+context_label:Context
+type_label:Type of Couple
+
 [www.fanfiction.net]
 ## fanfiction.net's 'cover' images are really just tiny thumbnails.
 ## Change this to false to use them anyway.
@@ -931,6 +959,15 @@ extra_valid_entries:reviews,favs,follows
 ## Site dedicated to these categories/characters/ships
 extracategories:My Little Pony: Friendship is Magic
 
+## Extra metadata that this adapter knows about.  See [dramione.org]
+## for examples of how to use them.
+extra_valid_entries:likes,dislikes,views,total_views,short_description
+likes_label:Likes
+dislikes_label:Dislikes
+views_label:Highest Single Chapter Views
+total_views_label:Total Views
+short_description_label:Short Summary
+
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
 ## this should go in your personal.ini, not defaults.ini.
@@ -981,6 +1018,10 @@ extraships:InuYasha/Kagome
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+[www.jlaunlimited.com]
+## Site dedicated to these categories/characters/ships
+extracategories:JLA
+
 [www.libraryofmoria.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Lord of the Rings
@@ -1005,7 +1046,7 @@ extracategories:Queer as Folk
 ## cover image.  This lets you exclude them.
 cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
 
-[www.ncisfiction.com]
+[www.ncisfiction.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:NCIS