Shortcuts for config/about for Mac. Handle tags inside metadata on ksarchivecom.

Some Mac versions crash if there are menu items set to not have shortcuts.
Also accept https, but change to http.

app.yaml

@@ -1,6 +1,6 @@
 # ffd-retief-hrd fanfictiondownloader
 application: fanfictiondownloader
-version: 4-4-21
+version: 4-4-23
 runtime: python27
 api_version: 1
 threadsafe: true

calibre-plugin/__init__.py

@@ -27,7 +27,7 @@ class FanFictionDownLoaderBase(InterfaceActionBase):
     description         = 'UI plugin to download FanFiction stories from various sites.'
     supported_platforms = ['windows', 'osx', 'linux']
     author              = 'Jim Miller'
-    version             = (1, 6, 2)
+    version             = (1, 6, 7)
     minimum_calibre_version = (0, 8, 57)
 
     #: This field defines the GUI plugin class that contains all the code

calibre-plugin/config.py

@@ -628,27 +628,27 @@ class CountPagesTab(QWidget):
         self.l.addSpacing(5)
         
         # 'PageCount', 'WordCount', 'FleschReading', 'FleschGrade', 'GunningFog'
-        self.pagecount = QCheckBox('PageCount',self)
+        self.pagecount = QCheckBox('Page Count',self)
         self.pagecount.setToolTip('Which column and algorithm to use are configured in Count Pages.')
         self.pagecount.setChecked('PageCount' in prefs['countpagesstats'])
         self.l.addWidget(self.pagecount)
             
-        self.wordcount = QCheckBox('WordCount',self)
+        self.wordcount = QCheckBox('Word Count',self)
         self.wordcount.setToolTip('Which column and algorithm to use are configured in Count Words.\nWill overwrite word count from FFDL metadata if set to update the same custom column.')
         self.wordcount.setChecked('WordCount' in prefs['countpagesstats'])
         self.l.addWidget(self.wordcount)
 
-        self.fleschreading = QCheckBox('FleschReading',self)
+        self.fleschreading = QCheckBox('Flesch Reading Ease',self)
         self.fleschreading.setToolTip('Which column and algorithm to use are configured in Count Pages.')
         self.fleschreading.setChecked('FleschReading' in prefs['countpagesstats'])
         self.l.addWidget(self.fleschreading)
         
-        self.fleschgrade = QCheckBox('Fleschgrade',self)
+        self.fleschgrade = QCheckBox('Flesch-Kincaid Grade Level',self)
         self.fleschgrade.setToolTip('Which column and algorithm to use are configured in Count Pages.')
-        self.fleschgrade.setChecked('Fleschgrade' in prefs['countpagesstats'])
+        self.fleschgrade.setChecked('FleschGrade' in prefs['countpagesstats'])
         self.l.addWidget(self.fleschgrade)
         
-        self.gunningfog = QCheckBox('GunningFog',self)
+        self.gunningfog = QCheckBox('Gunning Fog Index',self)
         self.gunningfog.setToolTip('Which column and algorithm to use are configured in Count Pages.')
         self.gunningfog.setChecked('GunningFog' in prefs['countpagesstats'])
         self.l.addWidget(self.gunningfog)

calibre-plugin/dialogs.py

@@ -172,15 +172,17 @@ class FakeLineEdit():
     def text(self):
         pass
     
-class CollectURLDialog(QDialog):
+class CollectURLDialog(SizePersistedDialog):
     '''
     Collect single url for get urls.
     '''
-    def __init__(self, gui, title):
-        QDialog.__init__(self, gui)
+    def __init__(self, gui, title, url_text): 
+        SizePersistedDialog.__init__(self, gui, 'FanFictionDownLoader plugin:get story urls')
         self.gui = gui
         self.status=False
 
+        self.setMinimumWidth(300)
+        
         self.l = QGridLayout()
         self.setLayout(self.l)
 
@@ -189,6 +191,7 @@ class CollectURLDialog(QDialog):
         
         self.l.addWidget(QLabel("URL:"),1,0)
         self.url = QLineEdit(self)
+        self.url.setText(url_text)
         self.l.addWidget(self.url,1,1)
    
         self.ok_button = QPushButton('OK', self)
@@ -199,15 +202,16 @@ class CollectURLDialog(QDialog):
         self.cancel_button.clicked.connect(self.cancel)
         self.l.addWidget(self.cancel_button,2,1)
 
-        self.resize(self.sizeHint())
+        # restore saved size.
+        self.resize_dialog()
 
     def ok(self):
         self.status=True
-        self.hide()
+        self.accept()
 
     def cancel(self):
         self.status=False
-        self.hide()
+        self.reject()
 
 class UserPassDialog(QDialog):
     '''

calibre-plugin/ffdl_plugin.py

@@ -143,8 +143,6 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                                                        triggered=self.add_dialog )
 
             self.update_action = self.create_menu_item_ex(self.menu, '&Update Existing FanFiction Book(s)', image='plusplus.png',
-                                                          unique_name='Update Existing FanFiction Book(s)',
-                                                          shortcut_name='Update Existing FanFiction Book(s)',
                                                           triggered=self.update_existing)
 
             if 'Reading List' in self.gui.iactions and (prefs['addtolists'] or prefs['addtoreadlists']) :
@@ -164,37 +162,31 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
 
                 if addmenutxt:
                     self.add_send_action = self.create_menu_item_ex(self.menu, addmenutxt, image='plusplus.png',
-                                                                    unique_name=addmenutxt,
-                                                                    shortcut_name=addmenutxt,
                                                                     triggered=partial(self.update_lists,add=True))
 
                 if rmmenutxt:
                     self.add_remove_action = self.create_menu_item_ex(self.menu, rmmenutxt, image='minusminus.png',
-                                                                      unique_name=rmmenutxt,
-                                                                      shortcut_name=rmmenutxt,
                                                                       triggered=partial(self.update_lists,add=False))
                 
             self.menu.addSeparator()
             self.get_list_action = self.create_menu_item_ex(self.menu, 'Get URLs from Selected Books', image='bookmarks.png',
-                                                            unique_name='Get URLs from Selected Books',
-                                                            shortcut_name='Get URLs from Selected Books',
                                                             triggered=self.get_list_urls)
 
             self.get_list_url_action = self.create_menu_item_ex(self.menu, 'Get Story URLs from Web Page', image='view.png',
-                                                                unique_name='Get Story URLs from Web Page',
-                                                                shortcut_name='Get Story URLs from Web Page',
                                                                 triggered=self.get_urls_from_page)
 
             self.menu.addSeparator()
-            self.config_action = create_menu_action_unique(self, self.menu, '&Configure Plugin', shortcut=False,
-                                                           image= 'config.png',
-                                                           unique_name='Configure FanFictionDownLoader',
-                                                           triggered=partial(do_user_config,parent=self.gui))
+            self.config_action = self.create_menu_item_ex(self.menu, '&Configure Plugin', #shortcut=False, # causes crashes on some Macs.  
+                                                          image= 'config.png',
+                                                          unique_name='Configure FanFictionDownLoader',
+                                                          shortcut_name='Configure FanFictionDownLoader',
+                                                          triggered=partial(do_user_config,parent=self.gui))
             
-            self.about_action = create_menu_action_unique(self, self.menu, 'About Plugin', shortcut=False,
-                                                          image= 'images/icon.png',
-                                                          unique_name='About FanFictionDownLoader',
-                                                          triggered=self.about)
+            self.about_action = self.create_menu_item_ex(self.menu, 'About Plugin', #shortcut=False, # causes crashes on some Macs.  
+                                                         image= 'images/icon.png',
+                                                         unique_name='About FanFictionDownLoader', 
+                                                         shortcut_name='About FanFictionDownLoader', 
+                                                         triggered=self.about)
             
             # Before we finalize, make sure we delete any actions for menus that are no longer displayed
             for menu_id, unique_name in self.old_actions_unique_map.iteritems():
@@ -220,10 +212,12 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
     def create_menu_item_ex(self, parent_menu, menu_text, image=None, tooltip=None,
                            shortcut=None, triggered=None, is_checked=None, shortcut_name=None,
                            unique_name=None):
+        #print("create_menu_item_ex before %s"%menu_text)
         ac = create_menu_action_unique(self, parent_menu, menu_text, image, tooltip,
                                        shortcut, triggered, is_checked, shortcut_name, unique_name)
         self.actions_unique_map[ac.calibre_shortcut_unique_name] = ac.calibre_shortcut_unique_name
         self.menu_actions.append(ac)
+        #print("create_menu_item_ex after %s"%menu_text)
         return ac
 
     def plugin_button(self):
@@ -238,13 +232,23 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             self._update_reading_lists(self.gui.library_view.get_selected_ids(),add)
 
     def get_urls_from_page(self):
-        d = CollectURLDialog(self.gui,"Get Story URLs from Web Page")
+
+        if prefs['urlsfromclip']:
+            try:
+                urltxt = self.get_urls_clip(storyurls=False)[0]
+            except:
+                urltxt = ""
+        
+        d = CollectURLDialog(self.gui,"Get Story URLs from Web Page",urltxt)
         d.exec_()
         if not d.status:
             return
-        print("URL:%s"%d.url.text())
+        print("get_urls_from_page URL:%s"%d.url.text())
 
-        url_list = get_urls_from_page("%s"%d.url.text())
+        ffdlconfig = SafeConfigParser()
+        ffdlconfig.readfp(StringIO(get_resources("plugin-defaults.ini")))
+        ffdlconfig.readfp(StringIO(prefs['personal.ini']))
+        url_list = get_urls_from_page("%s"%d.url.text(),ffdlconfig)
 
         if url_list:
             d = ViewLog(_("List of URLs"),"\n".join(url_list),parent=self.gui)
@@ -361,13 +365,14 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             options['version'] = self.version
             print(self.version)
             self.start_downloads( options, update_books )
-        
-    def get_urls_clip(self):
+            
+    def get_urls_clip(self,storyurls=True):
         url_list = []
         if prefs['urlsfromclip']:
             for url in unicode(QApplication.instance().clipboard().text()).split():
-                if( self._is_good_downloader_url(url) ):
+                if not storyurls or self._is_good_downloader_url(url):
                     url_list.append(url)
+                    
         return url_list
 
     def apply_settings(self):
@@ -766,20 +771,20 @@ make_firstimage_cover:true
 <p>Proceed with updating your library?</p>
 '''%(len(good_list),len(bad_list))
 
-        htmllog='<html><body><table border="1"><tr><th>Status</th><th>Title</th><th>Author</th><th>URL</th><th>Comment</th></tr>'
+        htmllog='<html><body><table border="1"><tr><th>Status</th><th>Title</th><th>Author</th><th>Comment</th><th>URL</th></tr>'
         for book in good_list:
             if 'status' in book:
                 status = book['status']
             else:
                 status = 'Good'
-            htmllog = htmllog + '<tr><td>' + '</td><td>'.join([status,book['title'],", ".join(book['author']),book['url'],book['comment']]) + '</td></tr>'
+            htmllog = htmllog + '<tr><td>' + '</td><td>'.join([status,book['title'],", ".join(book['author']),book['comment'],book['url']]) + '</td></tr>'
         
         for book in bad_list:
             if 'status' in book:
                 status = book['status']
             else:
                 status = 'Bad'
-            htmllog = htmllog + '<tr><td>' + '</td><td>'.join([status,book['title'],", ".join(book['author']),book['url'],book['comment']]) + '</td></tr>'
+            htmllog = htmllog + '<tr><td>' + '</td><td>'.join([status,book['title'],", ".join(book['author']),book['comment'],book['url']]) + '</td></tr>'
         
         htmllog = htmllog + '</table></body></html>'
         

calibre-plugin/jobs.py

@@ -154,11 +154,13 @@ def do_download_for_worker(book,options):
             # update now handled by pre-populating the old images and
             # chapters in the adapter rather than merging epubs.
             urlchaptercount = int(story.getMetadata('numChapters'))
-            (url,chaptercount,
+            (url,
+             chaptercount,
              adapter.oldchapters,
              adapter.oldimgs,
              adapter.oldcover,
-             adapter.calibrebookmark) = get_update_data(book['epub_for_update'])
+             adapter.calibrebookmark,
+             adapter.logfile) = get_update_data(book['epub_for_update'])
 
             print("Do update - epub(%d) vs url(%d)" % (chaptercount, urlchaptercount))
             print("write to %s"%outfile)

defaults.ini

@@ -197,9 +197,24 @@ windows_eol: true
 zip_output: false
 
 ## epub carries the TOC in metadata.
-## mobi generated from epub will have a TOC at the end.
+## mobi generated from epub by calibre will have a TOC at the end.
 include_tocpage: false
 
+## include a Update Log page before the story text.  If included, the
+## log will be updated each time the epub is an all the metadata
+## fields that have changed since the last update (typically
+## dateUpdated,numChapters,numWords at a minimum) will be shown.
+## Great for tracking when chapters came out and when the description,
+## etc changed.
+include_logpage: false
+
+## items to include in the log page Empty metadata entries, or those
+## that haven't changed since the last update, will *not* appear, even
+## if in the list.  You can include extra text or HTML that will be
+## included as-is in each log entry. Eg: logpage_entries: ...,<br />,
+## summary,<br />,...
+logpage_entries: dateCreated,datePublished,dateUpdated,numChapters,numWords,status,title,author,description,category,genre,rating,warnings
+
 ## epub->mobi conversions typically don't like tables.
 titlepage_use_table: false
 
@@ -214,10 +229,12 @@ background_color: ffffff
 ## Allow customization of CSS.  Make sure to keep at least one space
 ## at the start of each line and to escape % to %%.  Also need
 ## background_color to be in the same section, if included in CSS.
+## 'adobe-text-layout: optimizeSpeed;' prevents hyphenation on newer Nooks
 output_css: 
  body { background-color: #%(background_color)s;
         text-align: justify;
-        margin: 2%%; }
+        margin: 2%%;
+	adobe-text-layout: optimizeSpeed; }
  pre { font-size: x-small; }
  sml { font-size: small; }
  h1 { text-align: center; }
@@ -546,6 +563,19 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+[www.dracoandginny.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
+
+## 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
+
 [www.thealphagate.com]
 
 [www.checkmated.com]
@@ -670,6 +700,18 @@ cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
 
 [www.prisonbreakfic.net]
 
+[www.scarvesandcoffee.net]
+## 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.sinful-desire.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.siye.co.uk]
 
 [www.squidge.org/peja]
@@ -685,6 +727,14 @@ titlepage_entries: series,category,genre,language,status,datePublished,dateUpdat
 
 [www.storiesofarda.com]
 
+[www.thepetulantpoetess.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.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
@@ -759,6 +809,8 @@ collect_series: false
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+[www.wolverineandrogue.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,

downloader.py

@@ -128,7 +128,7 @@ def main():
            config.set("overrides",var,val)
 
    if options.list:
-       retlist = get_urls_from_page(args[0])
+       retlist = get_urls_from_page(args[0], config)
        print "\n".join(retlist)
                
        return
@@ -193,11 +193,13 @@ def main():
                    # update now handled by pre-populating the old
                    # images and chapters in the adapter rather than
                    # merging epubs.
-                   (url,chaptercount,
+                   (url,
+                    chaptercount,
                     adapter.oldchapters,
                     adapter.oldimgs,
                     adapter.oldcover,
-                    adapter.calibrebookmark) = get_update_data(args[0])
+                    adapter.calibrebookmark,
+                    adapter.logfile) = get_update_data(args[0])
 
                    writeStory(config,adapter,"epub")
                    

fanficdownloader/adapters/__init__.py

@@ -92,6 +92,11 @@ import adapter_wizardtalesnet
 import adapter_nhamagicalworldsus
 import adapter_hlfictionnet
 import adapter_grangerenchantedcom
+import adapter_dracoandginnycom
+import adapter_scarvesandcoffeenet
+import adapter_thepetulantpoetesscom
+import adapter_wolverineandroguecom
+import adapter_sinfuldesireorg
 
 ## This bit of complexity allows adapters to be added by just adding
 ## importing.  It eliminates the long if/else clauses we used to need
@@ -112,7 +117,7 @@ for x in imports():
             
 def getAdapter(config,url,fileform=None):
     ## fix up leading protocol.
-    fixedurl = re.sub(r"(?i)^[htp]+[:/]+","http://",url.strip())
+    fixedurl = re.sub(r"(?i)^[htps]+[:/]+","http://",url.strip())
     if not fixedurl.startswith("http"):
         fixedurl = "http://%s"%url
     ## remove any trailing '#' locations.
@@ -127,7 +132,7 @@ def getAdapter(config,url,fileform=None):
     if( domain != parsedUrl.netloc ):
         fixedurl = fixedurl.replace(parsedUrl.netloc,domain)
 
-    logging.debug("site:"+domain)
+    logging.debug("trying url:"+url)
     cls = getClassFor(domain)
     if not cls and domain.startswith("www."):
         domain = domain.replace("www.","")

fanficdownloader/adapters/adapter_archiveofourownorg.py

@@ -50,8 +50,17 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
         self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2])
         logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
         
-        # normalized story URL.
-        self._setURL('http://' + self.getSiteDomain() + '/works/'+self.story.getMetadata('storyId'))
+        # get storyId from url--url validation guarantees query correct
+        m = re.match(self.getSiteURLPattern(),url)
+        if m:
+            self.story.setMetadata('storyId',m.group('id'))
+            logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+            # normalized story URL.
+            self._setURL('http://' + self.getSiteDomain() + '/works/'+self.story.getMetadata('storyId'))
+        else:
+            raise exceptions.InvalidStoryURL(url,
+                                             self.getSiteDomain(),
+                                             self.getSiteExampleURLs())
         
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','ao3')
@@ -70,10 +79,11 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
         return ['www.archiveofourown.org','archiveofourown.org']
 
     def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/works/123456"
+        return "http://"+self.getSiteDomain()+"/works/123456 http://"+self.getSiteDomain()+"/collections/Some_Archive/works/123456"
 
     def getSiteURLPattern(self):
-        return re.escape("http://")+"(www\.)?"+re.escape(self.getSiteDomain()+"/works/")+r"\d+(/chapters/\d+)?/?$"
+        # http://archiveofourown.org/collections/Smallville_Slash_Archive/works/159770
+        return re.escape("http://")+"(www.)?"+re.escape(self.getSiteDomain())+r"(/collections/[^/]+)?/works/(?P<id>\d+)(/chapters/\d+)?/?$"
         
     ## Login
     def needToLoginCheck(self, data):

fanficdownloader/adapters/adapter_dracoandginnycom.py

@@ -0,0 +1,302 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2012 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+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 DracoAndGinnyComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class DracoAndGinnyComAdapter(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','dcagn')
+
+        # 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")
+        self.story.addToList("characters","Ginny Weasley")
+        self.story.addToList("characters","Draco Malfoy")
+
+        # 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.dracoandginny.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 '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 = "&ageconsent=ok&warning=2"
+        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 self.needToLoginCheck(data):
+            # need to log in for this one.
+            self.performLogin(url)
+            data = self._fetchUrl(url)
+
+        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+'/'+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
+        content=soup.find('div',{'class' : 'listbox'})
+        
+        self.setDescription(url,content.find('blockquote'))
+        
+        for genre in content.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1')):
+            self.story.addToList('genre',genre.string)
+
+        for warning in content.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')):
+            self.story.addToList('warnings',warning.string)
+        
+        labels = content.findAll('b')
+        
+        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)
+
+            if 'Word count' in label:
+                self.story.setMetadata('numWords', value.split(' |')[0])
+                
+            if 'Rating' in label:
+                self.story.setMetadata('rating', 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 '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 '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.nextSibling).split(' |')[0], 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+'/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            # can't use ^viewstory...$ in case of higher rated stories with javascript href.
+            storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+'))
+            i=1
+            for a in storyas:
+                # skip 'report this' and 'TOC' links
+                if 'contact.php' not in a['href'] and 'index' not in a['href']:
+                    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', {'class' : 'listbox'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_ksarchivecom.py

@@ -167,7 +167,7 @@ class KSArchiveComAdapter(BaseSiteAdapter): # XXX
         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)
+        self.story.setMetadata('author',stripHTML(a))
 
         # Find the chapters:
         for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
@@ -190,7 +190,7 @@ class KSArchiveComAdapter(BaseSiteAdapter): # XXX
         labels = soup.findAll('span',{'class':'label'})
         for labelspan in labels:
             value = labelspan.nextSibling
-            label = labelspan.string
+            label = stripHTML(labelspan)
 
             if 'Summary' in label:
                 ## Everything until the next span class='label'
@@ -215,50 +215,50 @@ class KSArchiveComAdapter(BaseSiteAdapter): # XXX
 
             if 'Categories' in label:
                 cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
-                catstext = [cat.string for cat in cats]
+                catstext = [stripHTML(cat) for cat in cats]
                 for cat in catstext:
                     # ran across one story with an empty <a href="browse.php?type=categories&amp;catid=1"></a>
                     # tag in the desc once.
                     if cat and cat.strip() in ('Poetry','Essays'):
-                        self.story.addToList('category',cat.string)
+                        self.story.addToList('category',stripHTML(cat))
 
             if 'Characters' in label:
                 self.story.addToList('characters','Kirk')
                 self.story.addToList('characters','Spock')
                 chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
-                charstext = [char.string for char in chars]
+                charstext = [stripHTML(char) for char in chars]
                 for char in charstext:
-                    self.story.addToList('characters',char.string)
+                    self.story.addToList('characters',stripHTML(char))
 
             ## Not all sites use Genre, but there's no harm to
             ## leaving it in.  Check to make sure the type_id number
             ## is correct, though--it's site specific.
             if 'Genre' in label:
                 genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1')) # XXX
-                genrestext = [genre.string for genre in genres]
+                genrestext = [stripHTML(genre) for genre in genres]
                 self.genre = ', '.join(genrestext)
                 for genre in genrestext:
-                    self.story.addToList('genre',genre.string)
+                    self.story.addToList('genre',stripHTML(genre))
 
             ## In addition to Genre (which is very site specific) KSA
             ## has 'Story Type', which is much more what most sites
             ## call genre.
             if 'Story Type' in label:
                 genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=5')) # XXX
-                genrestext = [genre.string for genre in genres]
+                genrestext = [stripHTML(genre) for genre in genres]
                 self.genre = ', '.join(genrestext)
                 for genre in genrestext:
-                    self.story.addToList('genre',genre.string)
+                    self.story.addToList('genre',stripHTML(genre))
 
             ## Not all sites use Warnings, but there's no harm to
             ## leaving it in.  Check to make sure the type_id number
             ## is correct, though--it's site specific.
             if 'Warnings' in label:
                 warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')) # XXX
-                warningstext = [warning.string for warning in warnings]
+                warningstext = [stripHTML(warning) for warning in warnings]
                 self.warning = ', '.join(warningstext)
                 for warning in warningstext:
-                    self.story.addToList('warnings',warning.string)
+                    self.story.addToList('warnings',stripHTML(warning))
 
             if 'Completed' in label:
                 if 'Yes' in value:
@@ -277,7 +277,7 @@ class KSArchiveComAdapter(BaseSiteAdapter): # XXX
         try:
             # Find Series name from series URL.
             a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
-            series_name = a.string
+            series_name = stripHTML(a)
             series_url = 'http://'+self.host+'/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.

fanficdownloader/adapters/adapter_nhamagicalworldsus.py

@@ -122,7 +122,7 @@ class NHAMagicalWorldsUsAdapter(BaseSiteAdapter):
 		
 
         # Find the chapters:
-        chapters=soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+'&chapter=\d$'))
+        chapters=soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+'&chapter=\d+$'))
         if len(chapters) == 0:
             self.chapterUrls.append((self.story.getMetadata('title'),url))
         else:

fanficdownloader/adapters/adapter_scarvesandcoffeenet.py

@@ -0,0 +1,251 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2012 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+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 ScarvesAndCoffeeNetAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class ScarvesAndCoffeeNetAdapter(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','scacf')
+
+        # 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","Glee")
+        self.story.addToList("characters","Kurt Hummel")
+        self.story.addToList("characters","Blaine Anderson")
+
+        # 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.scarvesandcoffee.net'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
+
+    ## Login seems to be reasonably standard across eFiction sites.
+    def needToLoginCheck(self, data):
+        if '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
+
+    ## 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=20"
+        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
+        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.
+
+        # 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('genre',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:
+                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+'/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            # can't use ^viewstory...$ in case of higher rated stories with javascript href.
+            storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+'))
+            i=1
+            for a in storyas:
+                # skip 'report this' and 'TOC' links
+                if 'contact.php' not in a['href'] and 'index' not in a['href']:
+                    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_sinfuldesireorg.py

@@ -0,0 +1,253 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2012 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+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 SinfulDesireOrgAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class SinfulDesireOrgAdapter(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','snds')
+
+        # 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","Supernatural")
+
+        # 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.sinful-desire.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=5"
+        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
+        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+'/archive/'+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 ""
+
+        # <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 '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)
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=3'))
+                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 '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))
+            # can't use ^viewstory...$ in case of higher rated stories with javascript href.
+            storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+'))
+            i=1
+            for a in storyas:
+                # skip 'report this' and 'TOC' links
+                if 'contact.php' not in a['href'] and 'index' not in a['href']:
+                    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_test1.py

@@ -140,25 +140,25 @@ Some more longer description.  "I suck at summaries!"  "Better than it sounds!"
                             ('Chapter 3, Over Cinnabar',self.url+"&chapter=4"),
                             ('Chapter 4',self.url+"&chapter=5"),
                             ('Chapter 5',self.url+"&chapter=6"),
-                            ('Chapter 6',self.url+"&chapter=6"),
-                            # ('Chapter 7',self.url+"&chapter=6"),
-                            # ('Chapter 8',self.url+"&chapter=6"),
-                            # ('Chapter 9',self.url+"&chapter=6"),
-                            # ('Chapter 0',self.url+"&chapter=6"),
-                            # ('Chapter a',self.url+"&chapter=6"),
-                            # ('Chapter b',self.url+"&chapter=6"),
-                            # ('Chapter c',self.url+"&chapter=6"),
-                            # ('Chapter d',self.url+"&chapter=6"),
-                            # ('Chapter e',self.url+"&chapter=6"),
-                            # ('Chapter f',self.url+"&chapter=6"),
-                            # ('Chapter g',self.url+"&chapter=6"),
-                            # ('Chapter h',self.url+"&chapter=6"),
-                            # ('Chapter i',self.url+"&chapter=6"),
-                            # ('Chapter j',self.url+"&chapter=6"),
-                            # ('Chapter k',self.url+"&chapter=6"),
-                            # ('Chapter l',self.url+"&chapter=6"),
-                            # ('Chapter m',self.url+"&chapter=6"),
-                            # ('Chapter n',self.url+"&chapter=6"),
+                            #('Chapter 6',self.url+"&chapter=7"),
+                            #('Chapter 7',self.url+"&chapter=8"),
+                            #('Chapter 8',self.url+"&chapter=9"),
+                            #('Chapter 9',self.url+"&chapter=0"),
+                            #('Chapter 0',self.url+"&chapter=a"),
+                            #('Chapter a',self.url+"&chapter=b"),
+                            #('Chapter b',self.url+"&chapter=c"),
+                            #('Chapter c',self.url+"&chapter=d"),
+                            #('Chapter d',self.url+"&chapter=e"),
+                            #('Chapter e',self.url+"&chapter=f"),
+                            #('Chapter f',self.url+"&chapter=g"),
+                            #('Chapter g',self.url+"&chapter=h"),
+                            #('Chapter h',self.url+"&chapter=i"),
+                            #('Chapter i',self.url+"&chapter=j"),
+                            #('Chapter j',self.url+"&chapter=k"),
+                            #('Chapter k',self.url+"&chapter=l"),
+                            #('Chapter l',self.url+"&chapter=m"),
+                            #('Chapter m',self.url+"&chapter=n"),
+                            #('Chapter n',self.url+"&chapter=o"),
                             ]
         self.story.setMetadata('numChapters',len(self.chapterUrls))
                             

fanficdownloader/adapters/adapter_thepetulantpoetesscom.py

@@ -0,0 +1,239 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2012 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+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 ThePetulantPoetessComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class ThePetulantPoetessComAdapter(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') +'&i=1')
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','tpp')
+
+        # 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 'www.thepetulantpoetess.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 'You must be a member to read this story.' in data \
+                or "The Ministry of Magic does not have a record of that password. " 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 "My 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)
+
+        # Find the chapters:
+        chapters=soup.find('select', {'name' : 'sid'})
+        if chapters == None:
+            self.chapterUrls.append((self.story.getMetadata('title'),url))
+        else:
+            for chapter in chapters.findAll('option', value=re.compile(r"viewstory.php\?sid=\d+&i=1")):
+                # just in case there's tags, like <i> in chapter titles.
+                self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['value']))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+        
+        # make sure that the story id is from the first chapter
+        self.story.setMetadata('storyId',self.chapterUrls[0][1].split('=')[1].split('&')[0])
+        
+        #locate the story on author's page
+        index = 1
+        found = 0
+        while found == 0:
+            asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')+"&page="+str(index)))
+        
+            for info in asoup.findAll('td', {'class' : 'highlightcolor1'}):
+                a = info.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+                if a != None:
+                    self.story.setMetadata('title',a.text)                
+                    found = 1
+                    break
+            index=index+1
+            
+        # extract metadata
+        b=info.find('b')
+        b.find('a').extract()
+        self.story.setMetadata('rating', b.text.split('[')[1].split(']')[0])
+        
+        info = info.findNext('td', {'colspan' : '2'}) 
+        for label in info.findAll('b'):
+            value = label.nextSibling
+            
+            if "Category" in label.text:
+                for cat in info.findAll('a'):
+                    self.story.addToList('category',cat.string)
+            
+            if "Characters" in label.text:
+                for char in value.split(', '):
+                    self.story.addToList('characters',char)
+                    
+            if "Genres" in label.text:
+                for genre in value.split(', '):
+                    if "General" not in genre:
+                        self.story.addToList('genre',genre)
+                    
+            if "Warnings" in label.text:
+                for warning in value.split(', '):
+                    if "none" not in warning.lower():
+                        self.story.addToList('warnings',warning)
+                        
+                        
+        info = info.findNext('td', {'class' : 'tblborder'}) 
+        info.find('b').extract()
+        self.setDescription(url,info)
+        
+        info = info.findNext('td', {'class' : 'highlightcolor2'}) 
+        for label in info.findAll('b'):
+            value = label.nextSibling
+            
+            if "Completed" in label.text:
+                if 'Yes' in value:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+                    
+            if 'Published' in label.text:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            
+            if 'Updated' in label.text:
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+                
+            if 'Word Count' in label.text:
+                self.story.setMetadata('numWords', value)
+            
+            
+    # 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.findAll('table')[2].findAll('td')[1]
+        for a in div.findAll('div'):
+            a.extract()
+        div.name='div'
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_wolverineandroguecom.py

@@ -0,0 +1,223 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2012 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+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 WolverineAndRogueComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class WolverineAndRogueComAdapter(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() + '/wrfa/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','wrfa')
+
+        # 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","X-Men Movie")
+        self.story.addToList("characters","Wolverine")
+        self.story.addToList("characters","Rogue")
+
+        # 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.wolverineandrogue.com'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/wrfa/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/wrfa/viewstory.php?sid=")+r"\d+$"
+
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title
+        pt = soup.find('div', {'id' : 'pagetitle'})
+        a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        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+'/wrfa/'+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+'/wrfa/'+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.
+
+        # <span class="label">Rated:</span> NC-17<br /> etc
+        content=soup.find('div',{'class' : 'content'})
+        labels = soup.findAll('span',{'class':'label'})
+        
+        value = labels[0].previousSibling
+        svalue = ""
+        while value != None:
+            val = value
+            value = value.previousSibling
+        while "Categories" not in str(val):
+            svalue += str(val)
+            val = val.nextSibling
+        self.setDescription(url,svalue)
+        
+        
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.string
+
+            if 'Rated' in label:
+                self.story.setMetadata('rating', value)
+
+            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(value.split(' -')[0], 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+'/wrfa/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            # can't use ^viewstory...$ in case of higher rated stories with javascript href.
+            storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+'))
+            i=1
+            for a in storyas:
+                # skip 'report this' and 'TOC' links
+                if 'contact.php' not in a['href'] and 'index' not in a['href']:
+                    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_yourfanfictioncom.py

@@ -141,7 +141,6 @@ class YourFanfictionComAdapter(BaseSiteAdapter):
         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.
         # because for some reason, this works while simple 'print data' errors on ascii conversion.
         # loopdata = data
         # chklen=5000
@@ -151,6 +150,7 @@ class YourFanfictionComAdapter(BaseSiteAdapter):
         #     logging.info("loopdata: %s" % loopdata[:chklen])
         #     loopdata = loopdata[chklen:]
             
+        # use BeautifulSoup HTML parser to make everything easier to find.
         soup = bs.BeautifulSoup(data)
 
         # Now go hunting for all the meta data and the chapter list.
@@ -191,9 +191,11 @@ class YourFanfictionComAdapter(BaseSiteAdapter):
             if 'Summary' in label:
                 ## Everything until the next span class='label'
                 svalue = ""
-                while not defaultGetattr(value,'class') == 'label':
+                while value and not defaultGetattr(value,'class') == 'label':
                     svalue += str(value)
                     value = value.nextSibling
+                # sometimes poorly formated desc (<p> w/o </p>) leads
+                # to all labels being included.
                 self.setDescription(url,svalue)
                 #self.story.setMetadata('description',stripHTML(svalue))
 

fanficdownloader/adapters/base_adapter.py

@@ -89,6 +89,7 @@ class BaseSiteAdapter(Configurable):
         self.oldimgs = None
         self.oldcover = None # (data of existing cover html, data of existing cover image)
         self.calibrebookmark = None
+        self.logfile = None
         ## order of preference for decoding.
         self.decode = ["utf8",
                        "Windows-1252"] # 1252 is a superset of
@@ -229,6 +230,8 @@ class BaseSiteAdapter(Configurable):
             # cheesy way to carry calibre bookmark file forward across update.
             if self.calibrebookmark:
                 self.story.calibrebookmark = self.calibrebookmark
+            if self.logfile:
+                self.story.logfile = self.logfile
                 
         return self.story
 

fanficdownloader/epubutils.py

@@ -42,6 +42,7 @@ def get_update_data(inputio,
             
     oldcover = None
     calibrebookmark = None
+    logfile = None
     # Looking for pre-existing cover.
     for item in contentdom.getElementsByTagName("reference"):
         if item.getAttribute("type") == "cover":
@@ -96,6 +97,11 @@ def get_update_data(inputio,
             if( item.getAttribute("media-type") == "application/xhtml+xml" ):
                 href=relpath+item.getAttribute("href")
                 #print("---- item href:%s path part: %s"%(href,get_path_part(href)))
+                if re.match(r'.*/log_page\.x?html',href):
+                    try:
+                        logfile = epub.read(href).decode("utf-8")
+                    except:
+                        pass # corner case I bumped into while testing.
                 if re.match(r'.*/(file|chapter)\d+\.x?html',href):
                     if getsoups:
                         soup = bs.BeautifulSoup(epub.read(href).decode("utf-8"))
@@ -136,7 +142,7 @@ def get_update_data(inputio,
                     
     for k in images.keys():
         print("\tlongdesc:%s\n\tData len:%s\n"%(k,len(images[k])))
-    return (source,filecount,soups,images,oldcover,calibrebookmark)
+    return (source,filecount,soups,images,oldcover,calibrebookmark,logfile)
 
 def get_path_part(n):
     relpath = os.path.dirname(n)

fanficdownloader/geturls.py

@@ -25,14 +25,38 @@ from gziphttp import GZipProcessor
 
 import adapters
 
-def get_urls_from_page(url):
-    
-    opener = u2.build_opener(u2.HTTPCookieProcessor(),GZipProcessor())
-    soup = BeautifulSoup(opener.open(url).read())
-    
+def get_urls_from_page(url,config=None):
+
     normalized = set() # normalized url
     retlist = [] # orig urls.
-    config = ConfigParser.SafeConfigParser()
+    if not config:
+        config = ConfigParser.SafeConfigParser()
+
+    data = None
+    
+    # special stuff to log into archiveofourown.org, if possible.
+    # Unlike most that show the links to 'adult' stories, but protect
+    # them, AO3 doesn't even show them if not logged in.  Only works
+    # with saved user/pass--not going to prompt for list.
+    if 'archiveofourown.org' in url:
+        ao3adapter = adapters.getAdapter(config,"http://www.archiveofourown.org/works/0","EPUB")
+        if ao3adapter.getConfig("username"):
+            if ao3adapter.getConfig("is_adult"):
+                addurl = "?view_adult=true"
+            else:
+                addurl=""
+            # just to get an authenticity_token.
+            data = ao3adapter._fetchUrl(url+addurl)
+            # login the session.
+            ao3adapter.performLogin(url,data)
+            # get the list page with logged in session.
+            data = ao3adapter._fetchUrl(url)
+
+    if not data:
+        opener = u2.build_opener(u2.HTTPCookieProcessor(),GZipProcessor())
+        data = opener.open(url).read()
+    
+    soup = BeautifulSoup(data)
     
     for a in soup.findAll('a'):
         if a.has_key('href'):

fanficdownloader/story.py

@@ -201,6 +201,7 @@ class Story:
         self.cover=None # *href* of new cover image--need to create html.
         self.oldcover=None # (oldcoverhtmlhref,oldcoverhtmltype,oldcoverhtmldata,oldcoverimghref,oldcoverimgtype,oldcoverimgdata)
         self.calibrebookmark=None # cheesy way to carry calibre bookmark file forward across update.
+        self.logfile=None # cheesy way to carry log file forward across update.
 
     def setMetadata(self, key, value):
         ## still keeps < < and &
@@ -230,6 +231,8 @@ class Story:
             if value:
                 if key == "numWords":
                     value = commaGroups(value)
+                if key == "numChapters":
+                    value = commaGroups("%d"%value)
                 if key == "dateCreated":
                     value = value.strftime("%Y-%m-%d %H:%M:%S")
                 if key == "datePublished" or key == "dateUpdated":
@@ -279,7 +282,7 @@ class Story:
     # just for less clutter in adapters.
     def extendList(self,listname,l):
         for v in l:
-            self.addToList(listname,v)
+            self.addToList(listname,v.strip())
     
     def addToList(self,listname,value):
         if value==None:

fanficdownloader/writers/writer_epub.py

@@ -140,6 +140,101 @@ ${value}<br />
 </html>
 ''')
 
+        self.EPUB_LOG_PAGE_START = string.Template('''<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml">
+<head>
+<title>Update Log</title>
+<link href="stylesheet.css" type="text/css" charset="UTF-8" rel="stylesheet"/>
+</head>
+<body>
+<h3>Update Log</h3>
+''')
+
+        self.EPUB_LOG_ENTRY = string.Template('''
+<b>${label}:</b> <span id="${id}">${value}</span>
+''')
+                          
+        self.EPUB_LOG_PAGE_END = string.Template('''
+</body>
+</html>
+''')
+
+    def writeLogPage(self, out):
+        """
+       XXX 
+
+        
+        Write the log page, but only include entries that there's
+        metadata for.  START, ENTRY and END are expected to already by
+        string.Template().  START and END are expected to use the same
+        names as Story.metadata, but ENTRY should use id, label and value.
+        """
+        if self.getConfig("include_logpage"):
+
+            # if there's a self.story.logfile, there's an existing log
+            # to add to.
+            if self.story.logfile:
+                print("existing logfile found, appending")
+                print("existing data:%s"%self._getLastLogData(self.story.logfile))
+                replace_string = "</body>" # "</h3>"
+                self._write(out,self.story.logfile.replace(replace_string,self._makeLogEntry(self._getLastLogData(self.story.logfile))+replace_string))
+            else:
+                # otherwise, write a new one.
+                self._write(out,self.EPUB_LOG_PAGE_START.substitute(self.story.getAllMetadata()))
+                self._write(out,self._makeLogEntry())
+                self._write(out,self.EPUB_LOG_PAGE_END.substitute(self.story.getAllMetadata()))
+
+    # self parsing instead of Soup because it should be simple and not
+    # worth the overhead.
+    def _getLastLogData(self,logfile):
+        """
+        Make a dict() of the most recent(last) log entry for each piece of metadata.
+        Switch rindex to index to search from top instead of bottom.
+        """
+        values = {}
+        for entry in self.getConfigList("logpage_entries"):
+            if entry in self.validEntries:
+                try:
+                    # <span id="dateUpdated">1975-04-15</span>
+                    span = '<span id="%s">'%entry
+                    idx = logfile.rindex(span)+len(span)
+                    values[entry] = logfile[idx:logfile.index('</span>',idx)]
+                except Exception, e:
+                    #print("e:%s"%e)
+                    pass
+
+        return values
+        
+    def _makeLogEntry(self, oldvalues={}):
+        retval = "<p class='log_entry'>"
+
+        for entry in self.getConfigList("logpage_entries"):
+            if entry in self.validEntries:
+                val = self.story.getMetadata(entry)
+                if val and ( entry not in oldvalues or val != oldvalues[entry] ):
+                    if self.hasConfig(entry+"_label"):
+                        label=self.getConfig(entry+"_label")
+                    else:
+                        print("Using fallback label for %s_label"%entry)
+                        label=self.titleLabels[entry]
+
+                    retval = retval + self.EPUB_LOG_ENTRY.substitute({'id':entry,
+                                                                      'label':label,
+                                                                      'value':val})
+            else:
+                # could be useful for introducing extra text, but
+                # mostly it makes it easy to tell when you get the
+                # keyword wrong.
+                retval = retval + entry
+                
+        retval = retval + "</p><hr />"
+        
+        if self.getConfig('replace_hr'):
+            retval = retval.replace("<hr />","<div class='center'>* * *</div>")
+            
+        return retval
+                
     def writeStoryImpl(self, out):
 
         ## Python 2.5 ZipFile is rather more primative than later
@@ -349,6 +444,11 @@ div { margin: 0pt; padding: 0pt; }
         if len(self.story.getChapters()) > 1 and self.getConfig("include_tocpage") and not self.metaonly :
             items.append(("toc_page","OEBPS/toc_page.xhtml","application/xhtml+xml","Table of Contents"))
             itemrefs.append("toc_page")
+
+        if self.getConfig("include_logpage"):
+            items.append(("log_page","OEBPS/log_page.xhtml","application/xhtml+xml","Update Log"))
+            itemrefs.append("log_page")
+            
         for index, (title,html) in enumerate(self.story.getChapters()):
             if html:
                 i=index+1
@@ -480,6 +580,13 @@ div { margin: 0pt; padding: 0pt; }
             outputepub.writestr("OEBPS/toc_page.xhtml",tocpageIO.getvalue())
         tocpageIO.close()
 
+        # write log page.
+        logpageIO = StringIO.StringIO()
+        self.writeLogPage(logpageIO)
+        if logpageIO.getvalue(): # will be false if no log page.
+            outputepub.writestr("OEBPS/log_page.xhtml",logpageIO.getvalue())
+        logpageIO.close()
+        
         for index, (title,html) in enumerate(self.story.getChapters()):
             if html:
                 logging.debug('Writing chapter text for: %s' % title)

index.html

@@ -56,10 +56,12 @@
 	  <!-- put announcements here, h3 is a good title size. -->
 	  <h3>New Sites</h3>
 	  <p>
-	    
-	    New sites grangerenchanted.com, hlfiction.net and nha.magical-worlds.us.
-	    <br />Thanks, Ida!
-	    
+	    Now supporing www.dracoandginny.com,
+	    www.scarvesandcoffee.net, www.thepetulantpoetess.com,
+	    www.wolverineandrogue.com and www.sinful-desire.com.  Thanks, Ida!
+	  </p>
+	  <p>
+	    FFDL now supports over 70 different fanfiction sites.
 	  </p>
 	  <p>
 	    Questions?  Check out our 
@@ -69,7 +71,7 @@
 	    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://4-4-20.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
+	    <a href="http://4-4-22.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
 	  </p>
 	  <div id='error'>
 	    {{ error_message }}
@@ -506,6 +508,31 @@
 	    Use the URL of the story's chapter list, such as
 	    <br /><a href="http://nha.magical-worlds.us/viewstory.php?sid=1234">http://nha.magical-worlds.us/viewstory.php?sid=1234</a>
 	  </dd>
+	  <dt>www.dracoandginny.com</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://www.dracoandginny.com/viewstory.php?sid=1234">http://www.dracoandginny.com/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>www.scarvesandcoffee.net</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://www.scarvesandcoffee.net/viewstory.php?sid=1234">http://www.scarvesandcoffee.net/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>www.thepetulantpoetess.com</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://www.thepetulantpoetess.com/viewstory.php?sid=1234">http://www.thepetulantpoetess.com/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>www.wolverineandrogue.com</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://www.wolverineandrogue.com/wrfa/viewstory.php?sid=1234">http://www.wolverineandrogue.com/wrfa/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>www.sinful-desire.org</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://www.sinful-desire.org/archive/viewstory.php?sid=1234">http://www.sinful-desire.org/archive/viewstory.php?sid=1234</a>
+	  </dd>
 	</dl>
 	<p>
 	  A few additional things to know, which will make your life substantially easier:

plugin-defaults.ini

@@ -19,8 +19,7 @@
 ## overridden at several levels
 
 ## 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.
+## adult content.  Uncomment by removing '#' in front of is_adult.
 #is_adult:true
 
 ## All available titlepage_entries and the label used for them:
@@ -183,9 +182,24 @@ windows_eol: true
 [epub]
 
 ## epub carries the TOC in metadata.
-## mobi generated from epub will have a TOC at the end.
+## mobi generated from epub by calibre will have a TOC at the end.
 include_tocpage: false
 
+## include a Update Log page before the story text.  If included, the
+## log will be updated each time the epub is an all the metadata
+## fields that have changed since the last update (typically
+## dateUpdated,numChapters,numWords at a minimum) will be shown.
+## Great for tracking when chapters came out and when the description,
+## etc changed.
+include_logpage: false
+
+## items to include in the log page Empty metadata entries, or those
+## that haven't changed since the last update, will *not* appear, even
+## if in the list.  You can include extra text or HTML that will be
+## included as-is in each log entry. Eg: logpage_entries: ...,<br />,
+## summary,<br />,...
+logpage_entries: dateCreated,datePublished,dateUpdated,numChapters,numWords,status,title,author,description,category,genre,rating,warnings
+
 ## epub->mobi conversions typically don't like tables.
 titlepage_use_table: false
 
@@ -200,10 +214,12 @@ background_color: ffffff
 ## Allow customization of CSS.  Make sure to keep at least one space
 ## at the start of each line and to escape % to %%.  Also need
 ## background_color to be in the same section, if included in CSS.
+## 'adobe-text-layout: optimizeSpeed;' prevents hyphenation on newer Nooks
 output_css: 
  body { background-color: #%(background_color)s;
         text-align: justify;
-        margin: 2%%; }
+        margin: 2%%;
+	adobe-text-layout: optimizeSpeed; }
  pre { font-size: x-small; }
  sml { font-size: small; }
  h1 { text-align: center; }
@@ -532,6 +548,19 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+[www.dracoandginny.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
+
+## 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
+
 [www.thealphagate.com]
 
 [www.checkmated.com]
@@ -653,6 +682,18 @@ cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
 
 [www.prisonbreakfic.net]
 
+[www.scarvesandcoffee.net]
+## 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.sinful-desire.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.siye.co.uk]
 
 [www.squidge.org/peja]
@@ -668,6 +709,14 @@ titlepage_entries: series,category,genre,language,status,datePublished,dateUpdat
 
 [www.storiesofarda.com]
 
+[www.thepetulantpoetess.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.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
@@ -742,6 +791,8 @@ collect_series: false
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+[www.wolverineandrogue.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,

plugin-example.ini

@@ -3,8 +3,7 @@
 
 [defaults]
 ## 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.
+## adult content.
 #is_adult:true
 
 ## include images from img tags in the body and summary of