Fix ffnet genre, characters, status.

phoenixsong.net, dramione.org, and walkingtheplank.org
Plus a quick correction to checkmated.com

app.yaml

@@ -1,6 +1,6 @@
 # ffd-retief-hrd fanfictiondownloader
 application: fanfictiondownloader
-version: 4-4-8
+version: 4-4-12
 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, 5, 18)
+    version             = (1, 5, 25)
     minimum_calibre_version = (0, 8, 30)
 
     #: This field defines the GUI plugin class that contains all the code

calibre-plugin/config.py

@@ -19,7 +19,7 @@ from calibre.gui2.ui import get_gui
 from calibre_plugins.fanfictiondownloader_plugin.dialogs \
     import (UPDATE, UPDATEALWAYS, OVERWRITE, collision_order)
 
-from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.adapters import getSiteDomains
+from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.adapters import getConfigSections
 
 from calibre_plugins.fanfictiondownloader_plugin.common_utils \
     import ( get_library_uuid, KeyboardConfigDialog )
@@ -47,6 +47,8 @@ all_prefs.defaults['collision'] = OVERWRITE
 all_prefs.defaults['deleteotherforms'] = False
 all_prefs.defaults['adddialogstaysontop'] = False
 all_prefs.defaults['includeimages'] = False
+all_prefs.defaults['lookforurlinhtml'] = False
+all_prefs.defaults['injectseries'] = False
 
 all_prefs.defaults['send_lists'] = ''
 all_prefs.defaults['read_lists'] = ''
@@ -54,6 +56,7 @@ all_prefs.defaults['addtolists'] = False
 all_prefs.defaults['addtoreadlists'] = False
 all_prefs.defaults['addtolistsonread'] = False
 
+all_prefs.defaults['gcnewonly'] = False
 all_prefs.defaults['gc_site_settings'] = {}
 all_prefs.defaults['allow_gc_from_ini'] = True
 
@@ -72,6 +75,9 @@ copylist = ['personal.ini',
             'deleteotherforms',
             'adddialogstaysontop',
             'includeimages',
+            'lookforurlinhtml',
+            'injectseries',
+            'gcnewonly',
             'gc_site_settings',
             'allow_gc_from_ini']
 
@@ -176,6 +182,8 @@ class ConfigWidget(QWidget):
         prefs['deleteotherforms'] = self.basic_tab.deleteotherforms.isChecked()
         prefs['adddialogstaysontop'] = self.basic_tab.adddialogstaysontop.isChecked()
         prefs['includeimages'] = self.basic_tab.includeimages.isChecked()
+        prefs['lookforurlinhtml'] = self.basic_tab.lookforurlinhtml.isChecked()
+        prefs['injectseries'] = self.basic_tab.injectseries.isChecked()
 
         if self.readinglist_tab:
             # lists
@@ -196,6 +204,7 @@ class ConfigWidget(QWidget):
             prefs['personal.ini'] = get_resources('plugin-example.ini')
 
         # Generate Covers tab
+        prefs['gcnewonly'] = self.generatecover_tab.gcnewonly.isChecked()
         gc_site_settings = {}
         for (site,combo) in self.generatecover_tab.gc_dropdowns.iteritems():
             val = unicode(combo.itemData(combo.currentIndex()).toString())
@@ -309,6 +318,16 @@ class BasicTab(QWidget):
         self.includeimages.setChecked(prefs['includeimages'])
         self.l.addWidget(self.includeimages)
 
+        self.lookforurlinhtml = QCheckBox("Search EPUB text for Story URL?",self)
+        self.lookforurlinhtml.setToolTip("Look for first valid story URL inside EPUB text if not found in metadata.\nSomewhat risky, could find wrong URL depending on EPUB content.\nAlso finds and corrects bad ffnet URLs from ficsaver.com files.")
+        self.lookforurlinhtml.setChecked(prefs['lookforurlinhtml'])
+        self.l.addWidget(self.lookforurlinhtml)
+
+        self.injectseries = QCheckBox("Inject calibre Series when none found?",self)
+        self.injectseries.setToolTip("If no series is found, inject the calibre series (if there is one) so it appears on the FFDL title page(not cover).")
+        self.injectseries.setChecked(prefs['injectseries'])
+        self.l.addWidget(self.injectseries)
+
         self.l.insertStretch(-1)
         
     def set_collisions(self):
@@ -486,7 +505,7 @@ class GenerateCoverTab(QWidget):
         
         self.gc_dropdowns = {}
 
-        sitelist = getSiteDomains()
+        sitelist = getConfigSections()
         sitelist.sort()
         sitelist.insert(0,u"Default")
         for site in sitelist:
@@ -511,6 +530,11 @@ class GenerateCoverTab(QWidget):
             horz.addWidget(dropdown)
             self.sl.addLayout(horz)
         
+        self.gcnewonly = QCheckBox("Run Generate Cover Only on New Books",self)
+        self.gcnewonly.setToolTip("Default is to run GC any time the calibre metadata is updated.")
+        self.gcnewonly.setChecked(prefs['gcnewonly'])
+        self.l.addWidget(self.gcnewonly)
+
         self.allow_gc_from_ini = QCheckBox('Allow generate_cover_settings from personal.ini to override.',self)
         self.allow_gc_from_ini.setToolTip("The INI parameter generate_cover_settings allows you to choose a GC setting based on metadata rather than site,\nbut it's much more complex.  generate_cover_settings is ignored when this is off.")
         self.allow_gc_from_ini.setChecked(prefs['allow_gc_from_ini'])

calibre-plugin/ffdl_plugin.py

@@ -36,7 +36,7 @@ from calibre_plugins.fanfictiondownloader_plugin.common_utils import (set_plugin
 
 from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader import adapters, writers, exceptions
 from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.htmlcleanup import stripHTML
-from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.epubutils import get_dcsource, get_dcsource_chaptercount
+from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.epubutils import get_dcsource, get_dcsource_chaptercount, get_story_url_from_html
 
 from calibre_plugins.fanfictiondownloader_plugin.config import (prefs, permitted_values)
 from calibre_plugins.fanfictiondownloader_plugin.dialogs import (
@@ -572,7 +572,13 @@ make_firstimage_cover:true
             # this behavior matches how epubs come out when imported
             # dateCreated == packaged--epub/etc created.
             book['timestamp'] = story.getMetadataRaw('dateCreated').replace(tzinfo=local_tz)
-        
+
+        if book_id != None and prefs['injectseries']:
+            mi = db.get_metadata(book_id,index_is_id=True)
+            if not book['series'] and mi.series != None:
+                book['calibre_series'] = (mi.series,mi.series_index)
+                print("calibre_series:%s [%s]"%book['calibre_series'])
+            
         if book['good']: # there shouldn't be any !'good' books at this point.
             # if still 'good', make a temp file to write the output to.
             tmp = PersistentTemporaryFile(prefix='new-%s-'%book['calibre_id'],
@@ -795,7 +801,7 @@ make_firstimage_cover:true
             coldef = custom_columns[col]
             if not meta.startswith('status-') and meta not in book['all_metadata'] or \
                     meta.startswith('status-') and 'status' not in book['all_metadata']:
-                print("No value for %s, skipping."%meta)
+                print("No value for %s, skipping custom column(%s) update."%(meta,coldef['name']))
                 continue
             if meta not in permitted_values[coldef['datatype']]:
                 print("%s not a valid column type for %s, skipping."%(col,meta))
@@ -815,8 +821,7 @@ make_firstimage_cover:true
 
         db.commit()
         
-        if 'Generate Cover' in self.gui.iactions:
-
+        if 'Generate Cover' in self.gui.iactions and (book['added'] or not prefs['gcnewonly']):
             gc_plugin = self.gui.iactions['Generate Cover']
             setting_name = None
             if prefs['allow_gc_from_ini']:
@@ -1018,8 +1023,12 @@ make_firstimage_cover:true
                 if 'url' in identifiers:
                     #print("url from epub:"+identifiers['url'].replace('|',':'))
                     return identifiers['url'].replace('|',':')
-                # look for dc:source
-                return get_dcsource(existingepub)
+                # look for dc:source first, then scan HTML if 
+                link = get_dcsource(existingepub)
+                if link:
+                    return link
+                elif prefs['lookforurlinhtml']:
+                    return get_story_url_from_html(existingepub,self._is_good_downloader_url)
         return None
 
     def _is_good_downloader_url(self,url):

calibre-plugin/jobs.py

@@ -113,6 +113,11 @@ def do_download_for_worker(book,options):
         adapter.password = book['password']
         
         story = adapter.getStoryMetadataOnly()
+        if 'calibre_series' in book:
+            print("calibre_series:%s [%d]"%book['calibre_series'])
+            adapter.setSeries(book['calibre_series'][0],book['calibre_series'][1])
+        else:
+            print("no calibre_series")
         writer = writers.getWriter(options['fileform'],adapter.config,adapter)
 
         outfile = book['outfile']

defaults.ini

@@ -306,6 +306,16 @@ extratags: FanFiction,Testing,Text
 [test1.com:html]
 extratags: FanFiction,Testing,HTML
 
+[archive.skyehawke.com]
+
+[ashwinder.sycophanthex.com]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
 [castlefans.org]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -319,6 +329,39 @@ extratags: FanFiction,Testing,HTML
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+[chaos.sycophanthex.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
+## some sites include images that we don't ever want becoming the
+## cover image.  This lets you exclude them.
+cover_exclusion_regexp:/images/.*?ribbon.gif
+
+[dramione.org]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Some sites also require the user to confirm they are adult for
+## adult content.  In commandline version, this should go in your
+## personal.ini, not defaults.ini.
+#is_adult:true
+
+[erosnsappho.sycophanthex.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
+## some sites include images that we don't ever want becoming the
+## cover image.  This lets you exclude them.
+cover_exclusion_regexp:/images/.*?ribbon.gif
+
 [fanfiction.mugglenet.com]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -346,16 +389,27 @@ extratags: FanFiction,Testing,HTML
 #username:YourName
 #password:yourpassword
 
+[lumos.sycophanthex.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
 [nfacommunity.com]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
-## Some sites also require the user to confirm they are adult for
-## adult content.  In commandline version, this should go in your
-## personal.ini, not defaults.ini.
-#is_adult:true
+[occlumency.sycophanthex.com]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+[thehexfiles.net]
 
 [thequidditchpitch.org]
 ## Some sites require login (or login for some rated stories) The
@@ -377,11 +431,19 @@ extratags: FanFiction,Testing,HTML
 #is_adult:true
 
 [www.archiveofourown.org]
-## Some sites also require the user to confirm they are adult for
-## adult content.  In commandline version, this should go in your
-## personal.ini, not defaults.ini.
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+[www.checkmated.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.fanfiction.net]
 
 [www.ficbook.net]
@@ -430,6 +492,12 @@ extratags:
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+[www.libraryofmoria.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
 [www.mediaminer.org]
 
 [www.midnightwhispers.ca]
@@ -442,10 +510,29 @@ extratags:
 ## cover image.  This lets you exclude them.
 cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
 
+[www.phoenixsong.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
+
 [www.potionsandsnitches.net]
 
 [www.siye.co.uk]
 
+[www.squidge.org/peja]
+# www.squidge.org/peja calls it Fandom <shrug>
+category_label:Fandom
+# Remove numWords -- www.squidge.org/peja word counts are inaccurate
+titlepage_entries: series,category,genre,language,characters,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,description
+
+[www.squidge.org/peja:txt]
+## Add URLs since there aren't links.
+# Remove numWords -- www.squidge.org/peja word counts are inaccurate
+titlepage_entries: series,category,genre,language,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,storyUrl, authorUrl, description
+
 [www.thewriterscoffeeshop.com]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -497,8 +584,20 @@ collect_series: false
 ## twiwrite.net (ab)uses series as personal reading lists.
 collect_series: false
 
+[www.walkingtheplank.org]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
 [www.whofic.com]
 
+[www.wraithbait.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
 [overrides]
 ## It may sometimes be useful to override all of the specific format,
 ## site and site:format sections in your private configuration.  For

fanficdownloader/adapters/__init__.py

@@ -52,6 +52,19 @@ 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
 
 ## This bit of complexity allows adapters to be added by just adding
 ## importing.  It eliminates the long if/else clauses we used to need
@@ -95,13 +108,13 @@ def getAdapter(config,url,fileform=None):
         fixedurl = fixedurl.replace("http://","http://www.")
     if cls:
         adapter = cls(config,fixedurl) # raises InvalidStoryURL
-        adapter.setSectionOrder(adapter.getSiteDomain(),fileform)
+        adapter.setSectionOrder(adapter.getConfigSection(),fileform)
         return adapter
     # No adapter found.
     raise exceptions.UnknownSite( url, [cls.getSiteDomain() for cls in __class_list] )
 
-def getSiteDomains():
-    return [cls.getSiteDomain() for cls in __class_list]
+def getConfigSections():
+    return [cls.getConfigSection() for cls in __class_list]
 
 def getClassFor(domain):
     for cls in __class_list:

fanficdownloader/adapters/adapter_ashwindersycophanthexcom.py

@@ -0,0 +1,257 @@
+# -*- 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
+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 AshwinderSycophantHexComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class AshwinderSycophantHexComAdapter(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])
+        logging.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','asph')
+
+        # If all stories from the site fall into the same category,
+        # the site itself isn't likely to label them as such, so we
+        # do.
+        self.story.addToList("category","Harry Potter")
+
+        # 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 'ashwinder.sycophanthex.com'
+
+    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 'This story contains adult content and/or themes.' in data \
+                or "That password doesn't match the one in our database" in data:
+            return True
+        else:
+            return False
+        
+    def performLogin(self, url):
+        params = {}
+
+        if self.password:
+            params['penname'] = self.username
+            params['password'] = self.password
+        else:
+            params['penname'] = self.getConfig("username")
+            params['password'] = self.getConfig("password")
+        params['rememberme'] = '1'
+        params['sid'] = ''
+        params['intent'] = ''
+        params['submit'] = 'Submit'
+    
+        loginUrl = 'http://' + self.getSiteDomain() + '/user.php'
+        logging.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
+                                                              params['penname']))
+    
+        d = self._fetchUrl(loginUrl, params)
+    
+        if "User Account Page" not in d : #Member Account
+            logging.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):
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url
+        logging.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.
+            
+        # 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)
+        asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
+		
+        try:
+            # in case link points somewhere other than the first chapter
+            a = soup.findAll('option')[1]['value']
+            self.story.setMetadata('storyId',a.split('=',)[1])
+            url = 'http://'+self.host+'/'+a
+            soup = bs.BeautifulSoup(self._fetchUrl(url))
+        except:
+            pass
+		
+        for info in asoup.findAll('table', {'bordercolor' : '#1A1919'}):
+            a = info.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+            if a != None:
+                self.story.setMetadata('title',a.text)
+                break
+		
+
+        # Find the chapters:
+        chapters=soup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+&i=1$'))
+        if len(chapters) == 0:
+            self.chapterUrls.append((self.story.getMetadata('title'),url))
+        else:
+            for chapter in chapters:
+                # just in case there's tags, like <i> in chapter titles.
+                self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+
+        # utility method
+        def defaultGetattr(d):
+            try:
+                return d.name
+            except:
+                return ""
+				
+        cats = info.findAll('a',href=re.compile('categories.php'))
+        for cat in cats:
+            self.story.addToList('category',cat.string)
+					
+			
+        a = info.find('a', href=re.compile(r'reviews.php\?sid='+self.story.getMetadata('storyId')))
+        val = a.nextSibling
+        svalue = ""
+        while not defaultGetattr(val) == 'br':
+            val = val.nextSibling
+        val = val.nextSibling
+        while not defaultGetattr(val) == 'table':
+            svalue += str(val)
+            val = val.nextSibling
+        self.setDescription(url,svalue)
+
+        # <span class="label">Rated:</span> NC-17<br /> etc
+        labels = info.findAll('b')
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = stripHTML(labelspan)
+
+            if 'Rating' in label:
+                self.story.setMetadata('rating', value)
+
+            if 'Word Count' in label:
+                self.story.setMetadata('numWords', value)
+
+            if 'Genres' in label:
+                genres = value.string.split(', ')
+                for genre in genres:
+                    if genre != 'none':
+                        self.story.addToList('genre',genre)
+
+            if 'Warnings' in label:
+                warnings = value.string.split(', ')
+                for warning in warnings:
+                    if warning != ' none':
+                        self.story.addToList('warnings',warning)
+
+            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))
+
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logging.debug('Getting chapter text from: %s' % url)
+		
+        data = self._fetchUrl(url)
+
+        soup = bs.BeautifulSoup(data, selfClosingTags=('br','hr','span','center')) # some chapters seem to be hanging up on those tags, so it is safer to close them
+        
+        story = soup.find('div', {"align" : "left"})
+
+        if None == story:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,story)

fanficdownloader/adapters/adapter_chaossycophanthexcom.py

@@ -0,0 +1,239 @@
+# -*- 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
+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 ChaosSycophantHexComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class ChaosSycophantHexComAdapter(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])
+        logging.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','csph')
+
+        # If all stories from the site fall into the same category,
+        # the site itself isn't likely to label them as such, so we
+        # do.
+        #self.story.addToList("category","Harry Potter")
+
+        # 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 'chaos.sycophanthex.com'
+
+    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+$"
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        if self.is_adult or self.getConfig("is_adult"):
+            # Weirdly, different sites use different warning numbers.
+            # If the title search below fails, there's a good chance
+            # you need a different number.  print data at that point
+            # and see what the 'click here to continue' url says.
+            addurl = "&ageconsent=ok&warning=19"
+        else:
+            addurl=""
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'+addurl
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        # The actual text that is used to announce you need to be an
+        # adult varies from site to site.  Again, print data before
+        # the title search to troubleshoot.
+        if "Age Consent Required" in data:
+            raise exceptions.AdultCheckRequired(self.url)
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title
+        pt = soup.find('div', {'id' : 'pagetitle'})
+        a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        self.story.setMetadata('title',a.text)
+        
+        # Find authorid and URL from... author url.
+        a = pt.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)
+
+        rating=pt.text.split('(')[1].split(')')[0]
+        self.story.setMetadata('rating', rating)
+
+        # 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+'/'+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'})
+		
+        value = labels[0].previousSibling
+        svalue = ""
+        while value != None:
+            val = value
+            value = value.previousSibling
+        while not defaultGetattr(val,'class') == 'label':
+            svalue += str(val)
+            val = val.nextSibling
+        self.setDescription(url,svalue)
+		
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.string
+
+            if 'Word count' in label:
+                self.story.setMetadata('numWords', value.split(' -')[0])
+
+            if 'Categories' in label:
+                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:
+                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:
+                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:
+                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 'Complete' 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.split(' -')[0]), 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+'/'+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):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(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_checkmatedcom.py

@@ -0,0 +1,239 @@
+# -*- 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
+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 CheckmatedComAdapter
+
+
+class CheckmatedComAdapter(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])
+        logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        self._setURL('http://' + self.getSiteDomain() + '/story.php?story='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','chm')
+
+        # If all stories from the site fall into the same category,
+        # the site itself isn't likely to label them as such, so we
+        # do.
+        self.story.addToList("category","Harry Potter")
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%b %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.checkmated.com'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/story.php?story=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/story.php?story=")+r"\d+$"
+
+    ## Login seems to be reasonably standard across eFiction sites. This story is in The Bedchamber
+    def needToLoginCheck(self, data):
+        if 'This story is in The Bedchamber' in data \
+                or 'That username is not in our database' in data \
+                or "That password is not correct, please try again" in data:
+            return True
+        else:
+            return False
+        
+    def performLogin(self, url):
+        params = {}
+
+        if self.password:
+            params['name'] = self.username
+            params['pass'] = self.password
+        else:
+            params['name'] = self.getConfig("username")
+            params['pass'] = self.getConfig("password")
+        params['login'] = 'yes'
+        params['submit'] = 'login'	
+	
+        loginUrl = 'http://' + self.getSiteDomain()+'/login.php'
+        d = self._fetchUrl(loginUrl,params)
+        e = self._fetchUrl(url)
+
+        if "Welcome back," not in d : #Member Account
+            logging.info("Failed to login to URL %s as %s" % (loginUrl,
+                                                              params['name']))
+            raise exceptions.FailedToLogin(url,params['name'])
+            return False
+        elif "This story is in The Bedchamber" in e:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Your account does not have sufficient priviliges to read this story.")
+            return False
+        else:
+            return True
+
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url
+        logging.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)
+
+        # The actual text that is used to announce you need to be an
+        # adult varies from site to site.  Again, print data before
+        # the title search to troubleshoot.
+            
+        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.findAll('span', {'class' : 'storytitle'})
+        self.story.setMetadata('title',a[0].string)
+        
+        # Find authorid and URL from... author url.
+        a = a[1].find('a', href=re.compile(r"authors.php\?name\=\w+"))
+        self.story.setMetadata('authorId',a['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('author',a.string)
+			
+        a = soup.find('select', {'name' : 'chapter'})
+        if a == None:
+            self.chapterUrls.append((self.story.getMetadata('title'),url))
+        else:
+            for chapter in a.findAll('option'):
+                self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/story.php?story='+self.story.getMetadata('storyId')+'&chapter='+chapter['value']))
+			
+        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 ""
+
+				
+        # website does not keep track of word count, and there is no convenient way to calculate it
+
+        summary = soup.find('fieldset')
+        summary.find('legend').extract()
+        summary.name='div'
+        self.setDescription(url,summary)
+
+		
+        # <span class="label">Rated:</span> NC-17<br /> etc
+        table = soup.findAll('div', {'class' : 'text'})[1]
+        for labels in table.findAll('tr'):
+            value = labels.findAll('td')[1]
+            label = labels.findAll('td')[0]
+
+			
+            if 'Rating' in stripHTML(label):
+                self.story.setMetadata('rating', stripHTML(value))
+
+            if 'Ship' in stripHTML(label):
+                for char in value.string.split('/'):
+                    if char != 'none':
+                        self.story.addToList('characters',char)		
+
+            if 'Status' in stripHTML(label):
+                if value.find('img', {'src' : 'img/incomplete.gif'}) == None:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+
+            if 'Published' in stripHTML(label):
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            
+            if 'Updated' in stripHTML(label):
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+			
+        a = self._fetchUrl(self.story.getMetadata('authorUrl')+'&cat=stories')	
+        for story in bs.BeautifulSoup(a).findAll('table', {'class' : 'storyinfo'}):
+            a = story.find('a', href=re.compile(r"review.php\?s\="+self.story.getMetadata('storyId')+'&act=view'))
+            if a != None:
+                for labels in story.findAll('tr'):
+                    value = labels.findAll('td')[1]
+                    label = labels.findAll('td')[0]
+                    if 'genre' in stripHTML(label):
+                        for genre in value.findAll('img'):
+                            self.story.addToList('genre',genre['title'])
+        
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logging.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' : 'resizeableText'})
+        div.find('div', {'class' : 'storyTools'}).extract()
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_dramioneorg.py

@@ -0,0 +1,271 @@
+# -*- 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
+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 DramioneOrgAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class DramioneOrgAdapter(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])
+        logging.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','drmn')
+
+        # If all stories from the site fall into the same category,
+        # the site itself isn't likely to label them as such, so we
+        # do.
+        self.story.addToList("category","Harry Potter")
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%dth %B %Y"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'dramione.org'
+
+    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 'Registered Users Only' in data \
+                or 'There is no such account on our website' in data \
+                or "That password doesn't match the one in our database" in data:
+            return True
+        else:
+            return False
+        
+    def performLogin(self, url):
+        params = {}
+
+        if self.password:
+            params['penname'] = self.username
+            params['password'] = self.password
+        else:
+            params['penname'] = self.getConfig("username")
+            params['password'] = self.getConfig("password")
+        params['cookiecheck'] = '1'
+        params['submit'] = 'Submit'
+    
+        loginUrl = 'http://' + self.getSiteDomain() + '/user.php?action=login'
+        logging.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
+                                                              params['penname']))
+    
+        d = self._fetchUrl(loginUrl, params)
+    
+        if "Member Account" not in d : #Member Account
+            logging.info("Failed to login to URL %s as %s" % (loginUrl,
+                                                              params['penname']))
+            raise exceptions.FailedToLogin(url,params['penname'])
+            return False
+        else:
+            return True
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        if self.is_adult or self.getConfig("is_adult"):
+            # Weirdly, different sites use different warning numbers.
+            # If the title search below fails, there's a good chance
+            # you need a different number.  print data at that point
+            # and see what the 'click here to continue' url says.
+            addurl = "&warning=5"
+        else:
+            addurl=""
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+addurl
+        logging.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)
+
+        # The actual text that is used to announce you need to be an
+        # adult varies from site to site.  Again, print data before
+        # the title search to troubleshoot.
+        if "Stories that are suitable for ages 16 and older" in data:
+            raise exceptions.AdultCheckRequired(self.url)
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # 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+'/'+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.
+		
+        genres=soup.findAll('a', {'class' : "tag-1"})
+        for genre in genres:
+            self.story.addToList('genre',genre.string)
+
+        warnings=soup.findAll('a', {'class' : "tag-2"})
+        for warning in warnings:
+            self.story.addToList('warnings',warning.string)
+
+        # 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'))
+                for cat in cats:
+                    self.story.addToList('category',cat.string)
+
+            if 'Characters' in label:
+                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+                for char in chars:
+                    self.story.addToList('characters',char.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:
+                value=value.replace('st','th').replace('nd','th').replace('rd','th')
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            
+            if 'Updated' in label:
+                value=value.replace('st','th').replace('nd','th').replace('rd','th')
+                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+'/'+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):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(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_erosnsapphosycophanthexcom.py

@@ -0,0 +1,255 @@
+# -*- 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
+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 ErosnSapphoSycophantHexComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class ErosnSapphoSycophantHexComAdapter(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])
+        logging.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','essph')
+
+        # If all stories from the site fall into the same category,
+        # the site itself isn't likely to label them as such, so we
+        # do.
+        self.story.addToList("category","Harry Potter")
+
+        # 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 'erosnsappho.sycophanthex.com'
+
+    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+$"
+
+    ## 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=18"
+        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
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        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
+                logging.debug("URL 2nd try: "+url)
+
+                try:
+                    data = self._fetchUrl(url)
+                except urllib2.HTTPError, e:
+                    if e.code == 404:
+                        raise exceptions.StoryDoesNotExist(self.url)
+                    else:
+                        raise e    
+            else:
+                raise exceptions.AdultCheckRequired(self.url)
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title
+        pt = soup.find('div', {'id' : 'pagetitle'})
+        a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        self.story.setMetadata('title',a.text)
+        
+        # Find authorid and URL from... author url.
+        a = pt.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)
+
+        rating=pt.text.split('(')[1].split(')')[0]
+        self.story.setMetadata('rating', rating)
+
+        # 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+'/'+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'})
+		
+        value = labels[0].previousSibling
+        svalue = ""
+        while value != None:
+            val = value
+            value = value.previousSibling
+        while not defaultGetattr(val,'class') == 'label':
+            svalue += str(val)
+            val = val.nextSibling
+        self.setDescription(url,svalue)
+		
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.string
+
+            if 'Word count' in label:
+                self.story.setMetadata('numWords', value.split(' -')[0])
+
+            if 'Categories' in label:
+                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:
+                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:
+                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:
+                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 'Complete' 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.split(' -')[0]), 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+'/'+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):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(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_fanfictionnet.py

@@ -205,21 +205,29 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         if metatext == None: # indicates there's no Reviews, look for id: instead.
             metatext = a.findNext(text=re.compile(r' - id:'))
 
+        m = re.match(r" - (?P<lang>[^ ]+)",metatext)
+        if m.group('lang') != None:
+            self.story.setMetadata('language',m.group('lang'))
+                    
         # after Rating, the same bit of text containing id:123456 contains
         # Complete--if completed.
-        if 'Complete' in a.findNext(text=re.compile(r'id:'+self.story.getMetadata('storyId'))):
+        if 'Complete' in soup.find(text=re.compile(r'id:'+self.story.getMetadata('storyId'))):
             self.story.setMetadata('status', 'Completed')
         else:
             self.story.setMetadata('status', 'In-Progress')
 
+
         # Parse genre(s) from <meta name="description" content="..."
         # <meta name="description" content="A Transformers/Beast Wars  - Humor fanfiction with characters Prowl & Sideswipe. Story summary: Sideswipe is bored. Prowl appears to be so, too  or at least, Sideswipe thinks he looks bored . So Sideswipe entertains them. After all, what's more fun than a race? Song-fic.">
         # <meta name="description" content="Chapter 1 of a Transformers/Beast Wars  - Adventure/Friendship fanfiction with characters Bumblebee. TFA: What would you do if you was being abused all you life? Follow NightRunner as she goes through her spark breaking adventure of getting away from her father..">
         # (fp)<meta name="description" content="Chapter 1 of a Sci-Fi  - Adventure/Humor fiction. Felix Max was just your regular hyperactive kid until he accidently caused his own fathers death. Now he has meta-humans trying to hunt him down with a corrupt goverment to back them up. Oh, and did I mention he has no Powers yet?.">
         # <meta name="description" content="Chapter 1 of a Bleach  - Adventure/Angst fanfiction with characters Ichigo K. & Neliel T. O./Nel. Time travel with a twist. Time can be a real bi***. Ichigo finds that fact out when he accidentally goes back in time. Is this his second chance or is fate just screwing with him. Not a crack fic.IchixNelXHime.">
         # <meta name="description" content="Chapter 1 of a Harry Potter and Transformers  - Humor/Adventure crossover fanfiction  with characters: Harry P. & Ironhide. IT’s one thing to be tossed thru the Veil for something he didn’t do. It was quite another to wake in his animigus form in a world not his own. Harry just knew someone was laughing at him somewhere. Mech/Mech pairings inside..">
-        m = re.match(r"^(?:Chapter \d+ of a|A) (?:.*?)  (?:- (?P<genres>.*?) )?(?:crossover )?(?:fan)?fiction(?P<chars>[ ]+with characters)?",
+        # <meta name="description" content="Chapter 1 of a SpongeBob SquarePants - Romance/Humor fanfiction with characters SpongeBob. Bob Esponja tiene un admirador secreto ¿quien será?.">
+        # Chapter 1 of a SpongeBob SquarePants - Romance/Humor fanfiction with characters SpongeBob. Bob Esponja tiene un admirador secreto ¿quien será?.  update existing id:1684
+        m = re.match(r"^(?:Chapter \d+ of a|A) (?:.*?)  ?(?:- (?P<genres>.*?) )?(?:crossover )?(?:fan)?fiction(?P<chars>[ ]+with characters)?",
                      soup.find('meta',{'name':'description'})['content'])
+        #print("meta desc:%s"%soup.find('meta',{'name':'description'})['content'])
         if m != None:
             genres=m.group('genres')
             if genres != None:
@@ -238,15 +246,13 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
                 # - English -  Shinji H. - Updated: 01-13-12 - Published: 12-20-11 - id:7654123
                 # - English - Adventure/Angst -  Ichigo K. & Neliel T. O./Nel - Reviews:
                 # - English - Humor/Adventure -  Harry P. & Ironhide - Reviews:
-                mc = re.match(r" - (?P<lang>[^ ]+ - )(?P<genres>[^ ]+ - )? (?P<chars>.+?) - (Reviews|Updated|Published)",
+                # - Spanish - Romance/Humor - SpongeBob - Reviews:
+                #print("metatext:%s"%metatext)
+                mc = re.match(r" - (?P<lang>[^ ]+ - )(?P<genres>[^ ]+ - )? ?(?P<chars>.+?) - (Reviews|Updated|Published)",
                               metatext)
                 chars = mc.group("chars")
-                for c in chars.split(' & '):
-                    self.story.addToList('characters',c)
-        m = re.match(r" - (?P<lang>[^ ]+)",metatext)
-        if m.group('lang') != None:
-            self.story.setMetadata('language',m.group('lang'))
-                    
+                for c in chars.split('&'):
+                    self.story.addToList('characters',c.strip())
         return
 
     def getChapterText(self, url):

fanficdownloader/adapters/adapter_libraryofmoriacom.py

@@ -0,0 +1,250 @@
+# -*- 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
+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 LibraryOfMoriaComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class LibraryOfMoriaComAdapter(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])
+        logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/a/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','lom')
+
+        # If all stories from the site fall into the same category,
+        # the site itself isn't likely to label them as such, so we
+        # do.
+        self.story.addToList("category","Lord of the Rings")
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%B %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.libraryofmoria.com'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/a/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/a/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"):
+            addurl = "&ageconsent=ok&warning=3"
+        else:
+            addurl=""
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+addurl
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        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
+                logging.debug("URL 2nd try: "+url)
+
+                try:
+                    data = self._fetchUrl(url)
+                except urllib2.HTTPError, e:
+                    if e.code == 404:
+                        raise exceptions.StoryDoesNotExist(self.url)
+                    else:
+                        raise e    
+            else:
+                raise exceptions.AdultCheckRequired(self.url)
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # 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+'/a/'+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)
+
+            if 'Type' in label:
+                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 'Warning' in label:
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=5'))
+                for warning in warnings:
+                    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+'/a/'+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):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(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_lumossycophanthexcom.py

@@ -0,0 +1,239 @@
+# -*- 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
+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 LumosSycophantHexComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class LumosSycophantHexComAdapter(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])
+        logging.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','lsph')
+
+        # If all stories from the site fall into the same category,
+        # the site itself isn't likely to label them as such, so we
+        # do.
+        self.story.addToList("category","Harry Potter")
+
+        # 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 'lumos.sycophanthex.com'
+
+    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+$"
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        if self.is_adult or self.getConfig("is_adult"):
+            # Weirdly, different sites use different warning numbers.
+            # If the title search below fails, there's a good chance
+            # you need a different number.  print data at that point
+            # and see what the 'click here to continue' url says.
+            addurl = "&ageconsent=ok&warning=19"
+        else:
+            addurl=""
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'+addurl
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        # The actual text that is used to announce you need to be an
+        # adult varies from site to site.  Again, print data before
+        # the title search to troubleshoot.
+        if "Age Consent Required" in data:
+            raise exceptions.AdultCheckRequired(self.url)
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title
+        pt = soup.find('div', {'id' : 'pagetitle'})
+        a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        self.story.setMetadata('title',a.text)
+        
+        # Find authorid and URL from... author url.
+        a = pt.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)
+
+        rating=pt.text.split('(')[1].split(')')[0]
+        self.story.setMetadata('rating', rating)
+
+        # 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+'/'+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'})
+		
+        value = labels[0].previousSibling
+        svalue = ""
+        while value != None:
+            val = value
+            value = value.previousSibling
+        while not defaultGetattr(val,'class') == 'label':
+            svalue += str(val)
+            val = val.nextSibling
+        self.setDescription(url,svalue)
+		
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.string
+
+            if 'Word count' in label:
+                self.story.setMetadata('numWords', value.split(' -')[0])
+
+            if 'Categories' in label:
+                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:
+                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:
+                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:
+                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 'Complete' 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.split(' -')[0]), 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+'/'+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):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(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_occlumencysycophanthexcom.py

@@ -0,0 +1,265 @@
+# -*- 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
+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 OcclumencySycophantHexComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class OcclumencySycophantHexComAdapter(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])
+        logging.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','osph')
+
+        # If all stories from the site fall into the same category,
+        # the site itself isn't likely to label them as such, so we
+        # do.
+        self.story.addToList("category","Harry Potter")
+
+        # 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 'occlumency.sycophanthex.com'
+
+    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 'This story contains adult content and/or themes.' in data \
+                or "That password doesn't match the one in our database" in data:
+            return True
+        else:
+            return False
+        
+    def performLogin(self, url):
+        params = {}
+
+        if self.password:
+            params['penname'] = self.username
+            params['password'] = self.password
+        else:
+            params['penname'] = self.getConfig("username")
+            params['password'] = self.getConfig("password")
+        params['rememberme'] = '1'
+        params['sid'] = ''
+        params['intent'] = ''
+        params['submit'] = 'Submit'
+    
+        loginUrl = 'http://' + self.getSiteDomain() + '/user.php'
+        logging.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
+                                                              params['penname']))
+    
+        d = self._fetchUrl(loginUrl, params)
+    
+        if "Logout" not in d : #Member Account
+            logging.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):
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url
+        logging.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.
+        
+        
+        # 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)
+        asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
+		
+        try:
+            # in case link points somewhere other than the first chapter
+            a = soup.findAll('option')[1]['value']
+            self.story.setMetadata('storyId',a.split('=',)[1])
+            url = 'http://'+self.host+'/'+a
+            soup = bs.BeautifulSoup(self._fetchUrl(url))
+        except:
+            pass
+		
+        for info in asoup.findAll('table', {'class' : 'border'}):
+            a = info.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+            if a != None:
+                self.story.setMetadata('title',a.text)
+                break
+		
+
+        # Find the chapters:
+        chapters=soup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+&i=1$'))
+        if len(chapters) == 0:
+            self.chapterUrls.append((self.story.getMetadata('title'),url))
+        else:
+            for chapter in chapters:
+                # just in case there's tags, like <i> in chapter titles.
+                self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+
+        # utility method
+        def defaultGetattr(d):
+            try:
+                return d.name
+            except:
+                return ""
+				
+        cats = info.findAll('a',href=re.compile('categories.php'))
+        for cat in cats:
+            self.story.addToList('category',cat.string)
+					
+			
+        a = info.find('a', href=re.compile(r'reviews.php\?sid='+self.story.getMetadata('storyId')))
+        val = a.nextSibling
+        svalue = ""
+        while not defaultGetattr(val) == 'br':
+            val = val.nextSibling
+        val = val.nextSibling
+        while not defaultGetattr(val) == 'table':
+            svalue += str(val)
+            val = val.nextSibling
+        self.setDescription(url,svalue)
+
+        # <span class="label">Rated:</span> NC-17<br /> etc
+        labels = info.findAll('b')
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = stripHTML(labelspan)
+
+            if 'Rating' in label:
+                self.story.setMetadata('rating', value)
+
+            if 'Word Count' in label:
+                self.story.setMetadata('numWords', value)
+
+            if 'Genres' in label:
+                genres = value.string.split(', ')
+                for genre in genres:
+                    if genre != 'none':
+                        self.story.addToList('genre',genre)
+						
+            if 'Characters' in label:
+                chars = value.string.split(', ')
+                for char in chars:
+                    if char != 'none':
+                        self.story.addToList('characters',char)
+
+            if 'Warnings' in label:
+                warnings = value.string.split(', ')
+                for warning in warnings:
+                    if warning != ' none':
+                        self.story.addToList('warnings',warning)
+
+            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))
+
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logging.debug('Getting chapter text from: %s' % url)
+		
+        data = self._fetchUrl(url)
+        data = data.replace('<div align="left"', '<div align="left">')
+
+        soup = bs.BeautifulSoup(data, selfClosingTags=('br','hr'))
+        
+        story = soup.find('div', {"align" : "left"})
+
+        if None == story:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,story)

fanficdownloader/adapters/adapter_phoenixsongnet.py

@@ -0,0 +1,242 @@
+# -*- 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
+import re
+import urllib2, urllib, cookielib
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return PhoenixSongNetAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class PhoenixSongNetAdapter(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.path.split('/',)[3])
+        logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/fanfiction/story/' +self.story.getMetadata('storyId')+'/')
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','phs')
+
+        # If all stories from the site fall into the same category,
+        # the site itself isn't likely to label them as such, so we
+        # do.
+        self.story.addToList("category","Harry Potter")
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%B %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.phoenixsong.net'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/fanfiction/story/1234/"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/fanfiction/story/")+r"\d+/?$"
+
+    ## Login seems to be reasonably standard across eFiction sites.
+    def needToLoginCheck(self, data):
+        if 'Please login to continue.' in data:
+            return True
+        else:
+            return False
+        
+    def performLogin(self, url):
+        params = {}
+		
+        if self.password:
+            params['txtusername'] = self.username
+            params['txtpassword'] = self.password
+        else:
+            params['txtusername'] = self.getConfig("username")
+            params['txtpassword'] = self.getConfig("password")
+        #params['remember'] = '1'
+        params['login'] = 'Login'
+    
+        loginUrl = 'http://' + self.getSiteDomain() + '/users/processlogin.php'
+        logging.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
+                                                              params['txtusername']))
+        d = self._fetchUrl(loginUrl, params)
+    
+        if 'Please login to continue.' in d : #Member Account
+            logging.info("Failed to login to URL %s as %s" % (loginUrl,
+                                                              params['txtusername']))
+            raise exceptions.FailedToLogin(url,params['txtusername'])
+            return False
+        else:
+            return True
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url
+        logging.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)
+			
+            
+        # 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
+        b = soup.find('div', {'id' : 'nav25'})
+        a = b.find('a', href=re.compile(r'fanfiction/story/'+self.story.getMetadata('storyId')+"/$"))
+        self.story.setMetadata('title',a.string)
+        
+        # Find authorid and URL from... author url.  /fanfiction/stories.php?psid=125
+        a = b.find('a', href=re.compile(r"/fanfiction/stories.php\?psid=\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:
+        chapters = soup.find('select')
+        if chapters == None:
+            self.chapterUrls.append((self.story.getMetadata('title'),url))
+            for b in soup.findAll('b'):
+                if b.text == "Updated":
+                    date = b.nextSibling.string.split(': ')[1].split(',')
+                    self.story.setMetadata('datePublished', makeDate(date[0]+date[1], self.dateformat))
+                    self.story.setMetadata('dateUpdated', makeDate(date[0]+date[1], self.dateformat))
+        else:
+            i = 0
+            chapters = chapters.findAll('option')
+            for chapter in chapters:
+                self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+chapter['value']))
+                if i == 0:
+                    self.story.setMetadata('storyId',chapter['value'].split('/')[3])
+                    head = bs.BeautifulSoup(self._fetchUrl('http://'+self.host+chapter['value'])).findAll('b')
+                    for b in head:
+                        if b.text == "Updated":
+                            date = b.nextSibling.string.split(': ')[1].split(',')
+                            self.story.setMetadata('datePublished', makeDate(date[0]+date[1], self.dateformat))
+                            
+                if  i == (len(chapters)-1):
+                    head = bs.BeautifulSoup(self._fetchUrl('http://'+self.host+chapter['value'])).findAll('b')
+                    for b in head:
+                        if b.text == "Updated":
+                            date = b.nextSibling.string.split(': ')[1].split(',')
+                            self.story.setMetadata('dateUpdated', makeDate(date[0]+date[1], self.dateformat))
+                i = i+1
+				
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))        	
+				
+        asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
+        
+        info = asoup.find('a', href=re.compile(r'fanfiction/story/'+self.story.getMetadata('storyId')+"/$"))
+        while info != None:
+            info = info.findNext('div')
+            b = info.find('b')
+            val = b.nextSibling
+            
+            if 'Rating' in b.string:
+                self.story.setMetadata('rating', val.string.split(': ')[1])
+				
+            if 'Words' in b.string:
+                self.story.setMetadata('numWords', val.string.split(': ')[1])
+				
+            if 'Setting' in b.string:
+                self.story.addToList('category', val.string.split(': ')[1])
+				
+            if 'Status' in b.string:
+                if 'Completed' in val:
+                    val = 'Completed'
+                else:
+                    val = 'In-Progress'
+                self.story.setMetadata('status', val)
+            
+            if 'Summary' in b.string:
+                b.extract()
+                info.find('br').extract()
+                self.setDescription(url,info)
+                break
+	
+	
+	# grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+
+        chapter=bs.BeautifulSoup('<div class="story"></div>')
+        for p in soup.findAll('p'):
+            if "This is for problems with the formatting or the layout of the chapter." in stripHTML(p):
+                break
+            chapter.append(p)
+			
+        for a in chapter.findAll('div'):
+            a.extract()
+        for a in chapter.findAll('table'):
+            a.extract()
+        for a in chapter.findAll('script'):
+            a.extract()
+        for a in chapter.findAll('form'):
+            a.extract()
+        for a in chapter.findAll('textarea'):
+            a.extract()
+
+
+        if None == chapter:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,chapter)

fanficdownloader/adapters/adapter_squidgeorgpeja.py

@@ -0,0 +1,234 @@
+# -*- 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
+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 SquidgeOrgPejaAdapter
+
+## XXX IMPORTANT NOTE!!  This adapter is for squidge.org/peja ONLY!
+## There are lots of other sites and stuff under squidge.org that
+## we're not supporting.  If/When we ever want to support more
+## sections of squidge.org, FFDL will need to be changed more
+## fundamentally to find different adapters under the same domain.
+##
+## For now, I've only implemented the part for ini section names so
+## if/when more adapters under squidge.org come along, existing ini
+## files will still work correctly.
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class SquidgeOrgPejaAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["utf8",
+                       "Windows-1252"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.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])
+        logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # normalized story URL.
+        self._setURL('http://' + 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')
+        
+        # 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.squidge.org'
+    
+    @classmethod # must be @staticmethod, don't remove it.
+    def getConfigSection(cls):
+        # The config section name.  Only override if != site domain.
+        return cls.getSiteDomain()+'/peja'
+    
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/peja/cgi-bin/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/peja/cgi-bin/viewstory.php?sid=")+r"\d+$"        
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        url = self.url
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        data = self._fetchUrl(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.
+        
+        # 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('author',author.string)
+		
+        authorSoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+
+        title = authorSoup.find('a',{'href':'viewstory.php?sid='+self.story.getMetadata('storyId')})
+        self.story.setMetadata('title',title.string)
+        titleblock=title.parent.parent
+        
+        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']))
+        else:
+            self.chapterUrls.append((title,url))
+		
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        
+        # utility method
+        def defaultGetattr(d,k):
+            try:
+                return d[k]
+            except:
+                return ""
+
+        # <span class="classification">Rated:</span> NC-17<br /> etc
+        labels = titleblock.findAll('span',{'class':'classification'})
+        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') == 'classification':
+                    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 'Characters' in label:
+                for char in value.split(','):
+                    self.story.addToList('characters',char.strip())
+
+            if 'Genre' in label:
+                for genre in value.split(','):
+                    if genre.strip() != "None":
+                        self.story.addToList('genre',genre.strip())
+
+            if 'Warnings' in label:
+                for warning in value.split(','):
+                    if warning.strip() != 'None':
+                        self.story.addToList('warnings',warning.strip())
+
+            if 'Word count' in label:
+                self.story.setMetadata('numWords', value)
+
+            if 'Fandoms' in label:
+                cats = labelspan.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 '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.
+            # 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']
+    
+            # 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):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        chaptext = soup.find('div',{'id':"story"}).find('span')
+
+        if None == chaptext:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,chaptext)

fanficdownloader/adapters/adapter_test1.py

@@ -90,17 +90,16 @@ Some more longer description.  "I suck at summaries!"  "Better than it sounds!"
         else:
             self.story.setMetadata('status','Completed')
 
-        langs = {
-            0:"English",
-            1:"Russian",
-            2:"French",
-            3:"German",
-            }
+        # greater than 10, no language or series.
         if idnum < 10:
+            langs = {
+                0:"English",
+                1:"Russian",
+                2:"French",
+                3:"German",
+                }
             self.story.setMetadata('language',langs[idnum%len(langs)])
-        # greater than 10, no language.
-            
-        self.setSeries('The Great Test',idnum)
+            self.setSeries('The Great Test',idnum)
         
         self.story.setMetadata('rating','Tweenie')
         
@@ -161,7 +160,7 @@ Some more longer description.  "I suck at summaries!"  "Better than it sounds!"
             text=u'''
 <div>
 <h3>Prologue</h3>
-<p>This is a fake adapter for testing purposes.  Different storyId's will give different errors:</p>
+<p>This is a fake adapter for testing purposes.  Different sid's will give different errors:</p>
 <p>http://test1.com?sid=664 - Crazy string title</p>
 <p>http://test1.com?sid=665 - raises AdultCheckRequired</p>
 <p>http://test1.com?sid=666 - raises StoryDoesNotExist</p>
@@ -171,18 +170,17 @@ Some more longer description.  "I suck at summaries!"  "Better than it sounds!"
 <p>http://test1.com?sid=670 - Succeeds, but sleeps 2sec on each chapter</p>
 <p>http://test1.com?sid=671 - Succeeds, but sleeps 2sec metadata only</p>
 <p>http://test1.com?sid=672 - Succeeds, quick meta, sleeps 2sec chapters only</p>
-<p>And other storyId will succeed with the same output.</p>
+<p>Odd sid's will be In-Progress, evens complete.  sid&lt;10 will be assigned one of four languages and included in a series.</p>
 </div>
 '''
         else:
             text=u'''
 <div>
 <h3>Chapter title from site</h3>
-<p><center>Centered text</center></p>
 <p>Lorem '''+self.crazystring+u''' <i>italics</i>, <b>bold</b>, <u>underline</u> consectetur adipisicing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.</p>
 br breaks<br><br>
 Puella Magi Madoka Magica/魔法少女まどか★マギカ
-<a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownLoaderPluginWithReadingList" title="Tilt-a-Whirl by Jim &amp; Sarah, on Flickr"><img src="http://i.imgur.com/bo8eD.png"></a><br/>
+<!-- a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownLoaderPluginWithReadingList" title="Tilt-a-Whirl by Jim &amp; Sarah, on Flickr"><img src="http://i.imgur.com/bo8eD.png"></a --><br/>
 br breaks<br><br>
 Don't&#8212e;ver&#8212d;o&#8212;that&#8212a;gain, &#27861; &#xE9;
 <hr>

fanficdownloader/adapters/adapter_thehexfilesnet.py

@@ -0,0 +1,199 @@
+# -*- 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
+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 TheHexFilesNetAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class TheHexFilesNetAdapter(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])
+        logging.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','thf')
+
+        # If all stories from the site fall into the same category,
+        # the site itself isn't likely to label them as such, so we
+        # do.
+        self.story.addToList("category","Harry Potter")
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%Y.%m.%d"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'thehexfiles.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+$"
+
+
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        
+        # Find authorid and URL from... author url.
+        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        self.story.setMetadata('authorId',a['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('author',a.string)
+        asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
+		
+        try:
+            # in case link points somewhere other than the first chapter
+            a = soup.findAll('option')[1]['value']
+            self.story.setMetadata('storyId',a.split('=',)[1])
+            url = 'http://'+self.host+'/'+a
+            soup = bs.BeautifulSoup(self._fetchUrl(url))
+        except:
+            pass
+		
+        for info in asoup.findAll('table', {'cellspacing' : '4'}):
+            a = info.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+            if a != None:
+                self.story.setMetadata('title',a.string)
+                break
+		
+
+        # Find the chapters:
+        chapters=soup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+&i=1$'))
+        if len(chapters) == 0:
+            self.chapterUrls.append((self.story.getMetadata('title'),url))
+        else:
+            for chapter in chapters:
+                # just in case there's tags, like <i> in chapter titles.
+                self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+				
+        cats = info.findAll('a',href=re.compile('categories.php'))
+        for cat in cats:
+            self.story.addToList('category',cat.string)
+			
+        words = info.find(text=re.compile('Words:')).split('|')[1].split(': ')[1]
+        self.story.setMetadata('numWords', words)
+		
+        comp = info.find('span', {'class' : 'completed'}).string.split(': ')[1]
+        if 'Yes' in comp:
+            self.story.setMetadata('status', 'Completed')
+        else:
+            self.story.setMetadata('status', 'In-Progress')
+						
+        summary = info.find('td', {'class' : 'summary'})
+        self.setDescription(url,summary)
+		
+        rating=stripHTML(info.find('td', {'align' : 'left'})).split('(')[1].split(')')[0]
+        self.story.setMetadata('rating', rating)
+
+        labels = info.findAll('td', {'width' : '10%'})
+        values = info.findAll('td', {'width' : '40%'})
+        for i in range(0,len(labels)):
+            value = stripHTML(values[i])
+            label = stripHTML(labels[i])
+
+            if 'Genres' in label:
+                genres = value.split(', ')
+                for genre in genres:
+                    if genre != 'none':
+                        self.story.addToList('genre',genre)
+						
+
+            if 'Warnings' in label:
+                warnings = value.split(', ')
+                for warning in warnings:
+                    if warning != 'none':
+                        self.story.addToList('warnings',warning)
+
+            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))
+
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        for a in soup.findAll('table'):
+            a.extract()
+
+        if None == soup:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,soup)

fanficdownloader/adapters/adapter_walkingtheplankorg.py

@@ -0,0 +1,233 @@
+# -*- 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
+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 WalkingThePlankOrgAdapter
+
+class WalkingThePlankOrgAdapter(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])
+        logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/archive/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','wtp')
+
+        # If all stories from the site fall into the same category,
+        # the site itself isn't likely to label them as such, so we
+        # do.
+        self.story.addToList("category","Harry Potter")
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%b %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.walkingtheplank.org'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/archive/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/archive/viewstory.php?sid=")+r"\d+$"
+
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        if self.is_adult or self.getConfig("is_adult"):
+            # Weirdly, different sites use different warning numbers.
+            # If the title search below fails, there's a good chance
+            # you need a different number.  print data at that point
+            # and see what the 'click here to continue' url says.
+            addurl = "&warning=4"
+        else:
+            addurl=""
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'+addurl
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+
+        # The actual text that is used to announce you need to be an
+        # adult varies from site to site.  Again, print data before
+        # the title search to troubleshoot.
+    
+        if "By clicking this link, you acknowledge" in data:
+            raise exceptions.AdultCheckRequired(self.url)
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title
+        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        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+'/archive/'+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 ""
+				
+        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)
+
+            if 'Genre' in label:
+                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:
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')) # XXX
+                for warning in warnings:
+                    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:
+                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+'/archive/'+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):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(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_wraithbaitcom.py

@@ -0,0 +1,227 @@
+# -*- 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
+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 WraithBaitComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class WraithBaitComAdapter(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])
+        logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+
+        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','wb')
+
+        # If all stories from the site fall into the same category,
+        # the site itself isn't likely to label them as such, so we
+        # do.
+        self.story.addToList("category","Stargate")
+
+        # 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 'www.wraithbait.com'
+
+    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+$"
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        if self.is_adult or self.getConfig("is_adult"):
+            # Weirdly, different sites use different warning numbers.
+            # If the title search below fails, there's a good chance
+            # you need a different number.  print data at that point
+            # and see what the 'click here to continue' url says.
+            addurl = "&ageconsent=ok&warning=12"
+        else:
+            addurl=""
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'+addurl
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+				
+        if "for adults only" in data:
+            raise exceptions.AdultCheckRequired(self.url)
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title
+        pt = soup.find('div', {'id' : 'pagetitle'})
+        a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        self.story.setMetadata('title',a.string)
+        
+        # Find authorid and URL from... author url.
+        a = pt.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)
+
+        rating=pt.text.split('[')[1].split(']')[0]
+        self.story.setMetadata('rating', rating)
+
+        # 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+'/'+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 ""
+		
+        info = soup.find('div', {'class' : 'small'})
+		
+        word=info.find(text=re.compile("Word count:")).split(':')
+        self.story.setMetadata('numWords', word[1])
+		
+        cats = info.findAll('a',href=re.compile(r'browse.php\?type=categories&id=\d'))
+        for cat in cats:
+            if "General" != cat.string:
+                self.story.addToList('category',cat.string)
+				
+        chars = info.findAll('a',href=re.compile(r'browse.php\?type=characters&charid=\d'))
+        for char in chars:
+            self.story.addToList('characters',char.string)
+			
+        completed=info.find(text=re.compile("Completed: Yes"))
+        if completed != None:
+            self.story.setMetadata('status', 'Completed')
+        else:
+            self.story.setMetadata('status', 'In-Progress')
+			
+        date=soup.find('div',{'class' : 'bottom'})
+        pd=date.find(text=re.compile("Published:")).string.split(': ')
+        self.story.setMetadata('datePublished', makeDate(stripHTML(pd[1].split(' U')[0]), self.dateformat))
+        self.story.setMetadata('dateUpdated', makeDate(stripHTML(pd[2]), self.dateformat))
+		
+        # <span class="label">Rated:</span> NC-17<br /> etc
+        labels = soup.findAll('span',{'class':'label'})
+        pub=0
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.string
+
+            if 'Genres' in label:
+                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:
+                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)
+
+        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+'/'+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
+			
+        info.extract()
+        summary = soup.find('div', {'class' : 'content'})
+        self.setDescription(url,summary)
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(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/base_adapter.py

@@ -70,9 +70,7 @@ class BaseSiteAdapter(Configurable):
     def __init__(self, config, url):
         self.config = config
         Configurable.__init__(self, config)
-        self.setSectionOrder(self.getSiteDomain())
-        # self.addConfigSection(self.getSiteDomain())
-        # self.addConfigSection("overrides")
+        self.setSectionOrder(self.getConfigSection())
         
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
@@ -82,7 +80,7 @@ class BaseSiteAdapter(Configurable):
         self.storyDone = False
         self.metadataDone = False
         self.story = Story()
-        self.story.setMetadata('site',self.getSiteDomain())
+        self.story.setMetadata('site',self.getConfigSection())
         self.story.setMetadata('dateCreated',datetime.datetime.now())
         self.chapterUrls = [] # tuples of (chapter title,chapter url)
         self.chapterFirst = None
@@ -235,6 +233,11 @@ class BaseSiteAdapter(Configurable):
         "Needs to be overriden in each adapter class."
         return 'no such domain'
     
+    @classmethod
+    def getConfigSection(cls):
+        "Only needs to be overriden if != site domain."
+        return cls.getSiteDomain()
+    
     ## URL pattern validation is done *after* picking an adaptor based
     ## on domain instead of *as* the adaptor selector so we can offer
     ## the user example(s) for that particular site.
@@ -262,7 +265,7 @@ class BaseSiteAdapter(Configurable):
     # Just for series, in case we choose to change how it's stored or represented later.
     def setSeries(self,name,num):
         if self.getConfig('collect_series'):
-            self.story.setMetadata('series','%s [%s]'%(name, num))
+            self.story.setMetadata('series','%s [%s]'%(name, int(num)))
 
     def setDescription(self,url,svalue):
         #print("\n\nsvalue:\n%s\n"%svalue)

fanficdownloader/epubutils.py

@@ -94,3 +94,40 @@ def get_path_part(n):
     if( len(relpath) > 0 ):
         relpath=relpath+"/"
     return relpath
+
+def get_story_url_from_html(inputio,_is_good_url=None):
+
+    #print("get_story_url_from_html called")
+    epub = ZipFile(inputio, 'r')
+
+    ## Find the .opf file.
+    container = epub.read("META-INF/container.xml")
+    containerdom = parseString(container)
+    rootfilenodelist = containerdom.getElementsByTagName("rootfile")
+    rootfilename = rootfilenodelist[0].getAttribute("full-path")
+
+    contentdom = parseString(epub.read(rootfilename))
+    #firstmetadom = contentdom.getElementsByTagName("metadata")[0]
+
+    ## Save the path to the .opf file--hrefs inside it are relative to it.
+    relpath = get_path_part(rootfilename)
+            
+    # spin through the manifest--only place there are item tags.
+    for item in contentdom.getElementsByTagName("item"):
+        # First, count the 'chapter' files.  FFDL uses file0000.xhtml,
+        # but can also update epubs downloaded from Twisting the
+        # Hellmouth, which uses chapter0.html.
+        #print("---- item:%s"%item)
+        if( item.getAttribute("media-type") == "application/xhtml+xml" ):
+            filehref=relpath+item.getAttribute("href")
+            soup = bs.BeautifulSoup(epub.read(filehref).decode("utf-8"))
+            for link in soup.findAll('a',href=re.compile(r'^http.*')):
+                ahref=link['href']
+                #print("href:(%s)"%ahref)
+                # hack for bad ficsaver ffnet URLs.
+                m = re.match(r"^http://www.fanfiction.net/s(?P<id>\d+)//$",ahref)
+                if m != None:
+                    ahref="http://www.fanfiction.net/s/%s/1/"%m.group('id')
+                if _is_good_url == None or _is_good_url(ahref):
+                    return ahref
+    return None

fanficdownloader/exceptions.py

@@ -63,6 +63,7 @@ class UnknownSite(Exception):
     def __init__(self,url,supported_sites_list):
         self.url=url
         self.supported_sites_list=supported_sites_list
+        self.supported_sites_list.sort()
 
     def __str__(self):
         return "Unknown Site(%s).  Supported sites: (%s)" % (self.url, ", ".join(self.supported_sites_list))

fanficdownloader/writers/base_writer.py

@@ -38,11 +38,7 @@ class BaseStoryWriter(Configurable):
 
     def __init__(self, config, adapter):
         Configurable.__init__(self, config)
-        self.setSectionOrder(adapter.getSiteDomain(),self.getFormatName())
-        # self.addConfigSection(adapter.getSiteDomain())
-        # self.addConfigSection(self.getFormatName())
-        # self.addConfigSection(adapter.getSiteDomain()+":"+self.getFormatName())
-        # self.addConfigSection("overrides")
+        self.setSectionOrder(adapter.getConfigSection(),self.getFormatName())
         
         self.adapter = adapter
         self.story = adapter.getStoryMetadataOnly() # only cache the metadata initially.

index.html

@@ -54,14 +54,9 @@
 	      much easier. </p>
 	  </div>
 	  <!-- put announcements here, h3 is a good title size. -->
-	  <h3>Latest Changes</h3>
+	  <h3>Fix for fanfiction.net Genre, Characters and Status</h3>
 	  <p>
-	    Fix for 'Hide this banner' title issue on Archive of Our
-	    Own.
-	  </p>
-	  <p>
-	    Changed implementation of fimfiction to use provided API,
-	    thanks to Althaine.
+	    fanfiction.net changed their format yesterday or today(May 26/27) enough to break capture of Genre, Characters and Status.  This version fixes it.
 	  </p>
 	  <p>
 	    Questions?  Check out our 
@@ -71,7 +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://4-4-7.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
+	    <a href="http://4-4-11.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
 	  </p>
 	  <div id='error'>
 	    {{ error_message }}
@@ -296,6 +291,73 @@
 	    Use the URL of the story's summary, such as
 	    <br /><a href="http://archive.skyehawke.com/story.php?no=17466">http://archive.skyehawke.com/story.php?no=17466</a>.
 	  </dd>
+	  <dt>www.libraryofmoria.com</dt>
+	  <dd>
+	    Use the URL of the story's summary, such as
+	    <br /><a href="http://www.libraryofmoria.com/a/viewstory.php?sid=434">http://www.libraryofmoria.com/a/viewstory.php?sid=434</a>.
+	  </dd>
+	  <dt>www.wraithbait.com</dt>
+	  <dd>
+	    Use the URL of the story's summary, such as
+	    <br /><a href="http://www.wraithbait.com/viewstory.php?sid=14305">http://www.wraithbait.com/viewstory.php?sid=14305</a>.
+	  </dd>
+	  <dt>www.squidge.org/peja (WWOMB)</dt>
+	  <dd>
+	    Use the URL of the story's summary, such as
+	    <br /><a href="http://www.squidge.org/peja/cgi-bin/viewstory.php?sid=1234">http://www.squidge.org/peja/cgi-bin/viewstory.php?sid=1234</a>.<br />
+	    This is <i>only</i> for squidge.org/peja, not other parts of squidge.org.
+	  </dd>
+	  <dt>www.checkmated.com</dt>
+	  <dd>
+	    Use the URL of the story's first chapter, such as
+	    <br /><a href="http://www.checkmated.com/story.php?story=10898">http://www.checkmated.com/story.php?story=10898</a>.
+	  </dd>
+
+	  <dt>ashwinder.sycophanthex.com</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://ashwinder.sycophanthex.com/viewstory.php?sid=1234">http://ashwinder.sycophanthex.com/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>chaos.sycophanthex.com</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://chaos.sycophanthex.com/viewstory.php?sid=1234">http://chaos.sycophanthex.com/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>erosnsappho.sycophanthex.com</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://erosnsappho.sycophanthex.com/viewstory.php?sid=1234">http://erosnsappho.sycophanthex.com/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>lumos.sycophanthex.com</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://lumos.sycophanthex.com/viewstory.php?sid=1234">http://lumos.sycophanthex.com/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>occlumency.sycophanthex.com</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://occlumency.sycophanthex.com/viewstory.php?sid=1234">http://erosnsappho.sycophanthex.com/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>dramione.org</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://dramione.org/viewstory.php?sid=1234">http://dramione.org/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>www.phoenixsong.net</dt>
+	  <dd>
+	    Use the URL of any story chapter, such as
+	    <br /><a href="http://www.phoenixsong.net/fanfiction/story/1234/">http://www.phoenixsong.net/fanfiction/story/1234/</a>
+	  </dd>
+	  <dt>www.walkingtheplank.org</dt>
+	  <dd>
+	    Use the URL of the story's first chapter, such as
+	    <br /><a href="http://www.walkingtheplank.org/archive/viewstory.php?sid=1234">http://www.walkingtheplank.org/archive/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>thehexfiles.net</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://thehexfiles.net/viewstory.php?sid=1234">http://thehexfiles.net/viewstory.php?sid=1234</a>
+	  </dd>
 	</dl>
 	<p>
 	  A few additional things to know, which will make your life substantially easier:

main.py

@@ -418,7 +418,7 @@ class FanfictionDownloader(UserConfigServer):
             template_values = dict(nickname = user.nickname(),
                                    url = url,
                                    format = format,
-                                   site = adapter.getSiteDomain(),
+                                   site = adapter.getConfigSection(),
                                    fic = download,
                                    is_login=is_login,
                                    )

plugin-defaults.ini

@@ -292,6 +292,16 @@ extratags: FanFiction,Testing,Text
 [test1.com:html]
 extratags: FanFiction,Testing,HTML
 
+[archive.skyehawke.com]
+
+[ashwinder.sycophanthex.com]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
 [castlefans.org]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -305,6 +315,39 @@ extratags: FanFiction,Testing,HTML
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+[chaos.sycophanthex.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
+## some sites include images that we don't ever want becoming the
+## cover image.  This lets you exclude them.
+cover_exclusion_regexp:/images/.*?ribbon.gif
+
+[dramione.org]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Some sites also require the user to confirm they are adult for
+## adult content.  In commandline version, this should go in your
+## personal.ini, not defaults.ini.
+#is_adult:true
+
+[erosnsappho.sycophanthex.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
+## some sites include images that we don't ever want becoming the
+## cover image.  This lets you exclude them.
+cover_exclusion_regexp:/images/.*?ribbon.gif
+
 [fanfiction.mugglenet.com]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -332,16 +375,27 @@ extratags: FanFiction,Testing,HTML
 #username:YourName
 #password:yourpassword
 
+[lumos.sycophanthex.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
 [nfacommunity.com]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
-## Some sites also require the user to confirm they are adult for
-## adult content.  In commandline version, this should go in your
-## personal.ini, not defaults.ini.
-#is_adult:true
+[occlumency.sycophanthex.com]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+[thehexfiles.net]
 
 [thequidditchpitch.org]
 ## Some sites require login (or login for some rated stories) The
@@ -363,11 +417,19 @@ extratags: FanFiction,Testing,HTML
 #is_adult:true
 
 [www.archiveofourown.org]
-## Some sites also require the user to confirm they are adult for
-## adult content.  In commandline version, this should go in your
-## personal.ini, not defaults.ini.
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+[www.checkmated.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.fanfiction.net]
 
 [www.ficbook.net]
@@ -413,6 +475,12 @@ extratags:
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+[www.libraryofmoria.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
 [www.mediaminer.org]
 
 [www.midnightwhispers.ca]
@@ -425,10 +493,29 @@ extratags:
 ## cover image.  This lets you exclude them.
 cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
 
+[www.phoenixsong.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
+
 [www.potionsandsnitches.net]
 
 [www.siye.co.uk]
 
+[www.squidge.org/peja]
+# www.squidge.org/peja calls it Fandom <shrug>
+category_label:Fandom
+# Remove numWords -- www.squidge.org/peja word counts are inaccurate
+titlepage_entries: series,category,genre,language,characters,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,description
+
+[www.squidge.org/peja:txt]
+## Add URLs since there aren't links.
+# Remove numWords -- www.squidge.org/peja word counts are inaccurate
+titlepage_entries: series,category,genre,language,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,storyUrl, authorUrl, description
+
 [www.thewriterscoffeeshop.com]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -480,8 +567,20 @@ collect_series: false
 ## twiwrite.net (ab)uses series as personal reading lists.
 collect_series: false
 
+[www.walkingtheplank.org]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
 [www.whofic.com]
 
+[www.wraithbait.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
 [overrides]
 ## It may sometimes be useful to override all of the specific format,
 ## site and site:format sections in your private configuration.  For