Integrate merlinfic.dtwins.co.uk, bump versions.

New adapter for merlinfic.dtwins.co.uk
Add a BBCode lib for summaries on fimfic(needed to mod for unicode),
2026-09-15 11:36:30 +08:00 · 2012-09-14 12:11:41 -05:00 · 2012-09-13 00:11:12 -04:00 · 2012-09-12 18:03:30 -05:00 · 2012-09-10 22:53:30 -05:00 · 2012-09-06 17:24:02 -05:00
86 changed files with 3601 additions and 397 deletions
@@ -1,6 +1,6 @@
 # ffd-retief-hrd fanfictiondownloader
 application: fanfictiondownloader
-version: 4-4-22
+version: 4-4-25
 runtime: python27
 api_version: 1
 threadsafe: true
@@ -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, 3)
+    version             = (1, 6, 9)
    minimum_calibre_version = (0, 8, 57)

    #: This field defines the GUI plugin class that contains all the code
@@ -4,7 +4,7 @@
 '<a href="http://www.mobileread.com/forums/showthread.php?t=134856">Reading List</a>',
 '<a href="http://www.mobileread.com/forums/showthread.php?t=126727">Extract ISBN</a>' and
 '<a href="http://www.mobileread.com/forums/showthread.php?t=134000">Count Pages</a>'
-plugins.</p>
+plugins.  bbcodeutils code contributed by Pau Sanchez.</p>

 <p>
 Calibre officially distributes plugins from the mobileread.com forum site.
@@ -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)
@@ -715,6 +715,7 @@ permitted_values = {
                     'language',
                     'series',
                     'characters',
+                     'ships',
                     'status',
                     'datePublished',
                     'dateUpdated',
@@ -751,6 +752,7 @@ titleLabels = {
    'status-I':'Status:In-Progress',
    'series':'Series',
    'characters':'Characters',
+    'ships':'Relationships',
    'datePublished':'Published',
    'dateUpdated':'Updated',
    'dateCreated':'Packaged',
@@ -793,6 +795,15 @@ class CustomColumnsTab(QWidget):
        self.custcol_dropdowns = {}
        self.custcol_newonlycheck = {}

+        scrollable = QScrollArea()
+        scrollcontent = QWidget()
+        scrollable.setWidget(scrollcontent)
+        scrollable.setWidgetResizable(True)
+        self.l.addWidget(scrollable)
+
+        self.sl = QVBoxLayout()
+        scrollcontent.setLayout(self.sl)
+        
        for key, column in custom_columns.iteritems():

            if column['datatype'] in permitted_values:
@@ -823,9 +834,9 @@ class CustomColumnsTab(QWidget):
                    newonlycheck.setChecked(prefs['custom_cols_newonly'][key])
                horz.addWidget(newonlycheck)
                
-                self.l.addLayout(horz)
+                self.sl.addLayout(horz)
        
-        self.l.insertStretch(-1)
+        self.sl.insertStretch(-1)

        self.l.addSpacing(5)
        label = QLabel("Special column:")
@@ -847,8 +858,7 @@ class CustomColumnsTab(QWidget):
        self.errorcol.setCurrentIndex(self.errorcol.findData(QVariant(prefs['errorcol'])))
        horz.addWidget(self.errorcol)
        self.l.addLayout(horz)
-        
-        
+
        #print("prefs['custom_cols'] %s"%prefs['custom_cols'])


@@ -7,7 +7,7 @@ __license__   = 'GPL v3'
 __copyright__ = '2012, Jim Miller'
 __docformat__ = 'restructuredtext en'

-import time, os, copy, threading, re
+import time, os, copy, threading, re, platform
 from ConfigParser import SafeConfigParser
 from StringIO import StringIO
 from functools import partial
@@ -28,6 +28,7 @@ from calibre.gui2 import error_dialog, warning_dialog, question_dialog, info_dia
 from calibre.gui2.dialogs.message_box import ViewLog
 from calibre.gui2.dialogs.confirm_delete import confirm
 from calibre.utils.date import local_tz
+from calibre.library.comments import sanitize_comments_html

 # The class that all interface action plugins must inherit from
 from calibre.gui2.actions import InterfaceAction
@@ -36,7 +37,7 @@ from calibre_plugins.fanfictiondownloader_plugin.common_utils import (set_plugin
                                         create_menu_action_unique, get_library_uuid)

 from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader import adapters, writers, exceptions
-from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.htmlcleanup import stripHTML
+#from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.htmlcleanup import stripHTML
 from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.epubutils import get_dcsource, get_dcsource_chaptercount, get_story_url_from_html
 from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.geturls import get_urls_from_page

@@ -143,8 +144,6 @@ 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 +163,34 @@ 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))
+            # print("platform.system():%s"%platform.system())
+            # print("platform.mac_ver()[0]:%s"%platform.mac_ver()[0])
+            if not platform.mac_ver()[0]: # Some macs crash on these menu items for unknown reasons.
+                self.menu.addSeparator()
+                self.config_action = self.create_menu_item_ex(self.menu, '&Configure Plugin',
+                                                              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',
+                                                             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 +216,12 @@ 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):
@@ -435,13 +433,6 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
        print("url:%s"%url)
        skip_date_update = False
        
-        ## was self.ffdlconfig, but we need to be able to change it
-        ## when doing epub update.
-        ffdlconfig = SafeConfigParser()
-        ffdlconfig.readfp(StringIO(get_resources("plugin-defaults.ini")))
-        ffdlconfig.readfp(StringIO(prefs['personal.ini']))
-        adapter = adapters.getAdapter(ffdlconfig,url,fileform)
-
        options['personal.ini'] = prefs['personal.ini']
        if prefs['includeimages']:
            # this is a cheat to make it easier for users.
@@ -451,6 +442,13 @@ keep_summary_html:true
 make_firstimage_cover:true
 ''' + options['personal.ini']

+        ## was self.ffdlconfig, but we need to be able to change it
+        ## when doing epub update.
+        ffdlconfig = SafeConfigParser()
+        ffdlconfig.readfp(StringIO(get_resources("plugin-defaults.ini")))
+        ffdlconfig.readfp(StringIO(options['personal.ini']))
+        adapter = adapters.getAdapter(ffdlconfig,url,fileform)
+
        ## three tries, that's enough if both user/pass & is_adult needed,
        ## or a couple tries of one or the other
        for x in range(0,2):
@@ -478,9 +476,9 @@ make_firstimage_cover:true
        book['title'] = story.getMetadata("title", removeallentities=True)
        book['author_sort'] = book['author'] = story.getList("author", removeallentities=True)
        book['publisher'] = story.getMetadata("site")
-        book['tags'] = writer.getTags() # getTags could be moved up into adapter now.  Adapter didn't used to know the fileform
-        book['comments'] = stripHTML(story.getMetadata("description")) #, removeallentities=True) comments handles entities better.
-        book['series'] = story.getMetadata("series")
+        book['tags'] = writer.getTags(removeallentities=True) # getTags could be moved up into adapter now.  Adapter didn't used to know the fileform
+        book['comments'] = sanitize_comments_html(story.getMetadata("description"))        
+        book['series'] = story.getMetadata("series", removeallentities=True)
        
        # adapter.opener is the element with a threadlock.  But del
        # adapter.opener doesn't work--subproc fails when it tries
@@ -777,20 +775,20 @@ 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>'
        
@@ -902,18 +900,6 @@ make_firstimage_cover:true
                db.set_link_field_for_author(autid, unicode(authurls[i]),
                                             commit=False, notify=False)

-        # mi.title = oldmi.title
-        # mi.authors = oldmi.authors
-        # mi.publisher = oldmi.publisher
-        # mi.tags = oldmi.tags
-        # mi.languages = oldmi.languages
-        # mi.pubdate = oldmi.pubdate
-        # mi.timestamp = oldmi.timestamp
-        # mi.comments = oldmi.comments
-        # mi.series = oldmi.series
-                
-        # mi.set_identifiers(oldmi.get_identifiers())
-
        # implement 'newonly' flags here by setting to the current
        # value again.
        if not book['added']:
@@ -109,6 +109,9 @@ def do_download_for_worker(book,options):
    when run as a worker job
    '''
    try:
+        # import logging
+        # logging.basicConfig(level=logging.DEBUG,format="%(levelname)s:%(filename)s(%(lineno)d):%(message)s")
+        
        book['comment'] = 'Download started...'

        ffdlconfig = SafeConfigParser()
@@ -117,6 +120,11 @@ def do_download_for_worker(book,options):
        
        if not options['updateepubcover'] and 'epub_for_update' in book and options['collision'] in (UPDATE, UPDATEALWAYS):
            ffdlconfig.set("overrides","never_make_cover","true")
+
+        # images only for epub, even if the user mistakenly turned it
+        # on else where.
+        if options['fileform'] != "epub":
+            ffdlconfig.set("overrides","include_images","false")
        
        adapter = adapters.getAdapter(ffdlconfig,book['url'],options['fileform'])
        adapter.is_adult = book['is_adult'] 
@@ -38,6 +38,7 @@ category_label:Category
 genre_label:Genre
 language_label:Language
 characters_label:Characters
+ships_label:Relationships
 series_label:Series
 ## Completed/In-Progress
 status_label:Status
@@ -70,7 +71,7 @@ version_label:FFDL Version
 ## You can include extra text or HTML that will be included as-is in
 ## the title page. Eg: titlepage_entries: ...,<br />,summary,<br />,...
 ## All current formats already include title and author.
-titlepage_entries: series,category,genre,language,characters,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,numWords,site,description
+titlepage_entries: series,category,genre,language,characters,ships,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,numWords,site,description

 ## Try to collect series name and number of this story in series.
 ## Some sites (ab)use 'series' for reading lists and personal
@@ -121,11 +122,20 @@ allow_unsafe_filename: false

 ## entries to make epub subjects and calibre tags
 ## lastupdate creates two tags: "Last Update Year/Month: %Y/%m" and "Last Update: %Y/%m/%d"
-include_subject_tags: extratags, genre, category, characters, lastupdate, status
+include_subject_tags: extratags, genre, category, characters, ships, lastupdate, status

 ## extra tags (comma separated) to include, primarily for epub.
 extratags: FanFiction

+## extra categories, genres, characters, ships and warnings can be
+## configured.  Used primarily for sites that are dedicated to a genre
+## or 'ship and so don't included it for every story.
+#extracategories:
+#extragenres:
+#extracharacters:
+#extraships:
+#extrawarnings:
+
 ## number of seconds to sleep between calls to the story site.  May by
 ## useful if pulling large numbers of stories or if the site is slow.
 #slow_down_sleep_time:0.5
@@ -154,6 +164,45 @@ extratags: FanFiction
 ## doesn't work on some devices either.)
 #replace_hr: false

+## If set false, the summary will have all html stripped.
+## Both this and include_images must be true to get images in the
+## summary.
+keep_summary_html:true
+
+## Don't like the numbers at the start of chapter titles on some
+## sites?  You can use strip_chapter_numbers to strip them off.  Just
+## want to make them all look the same?  Strip them off, then add them
+## back on with add_chapter_numbers.  Don't like the way it strips
+## numbers or adds them back?  See chapter_title_strip_pattern and
+## chapter_title_add_pattern.
+strip_chapter_numbers:false
+add_chapter_numbers:false
+
+## (Two versions of chapter_title_strip_pattern are shown below.  You
+## should only have one uncommented.)
+## This version will remove the leading number from:
+## "1." => ""
+## "1. The Beginning" => "The Beginning"
+## "1: Start" => "Start"
+## "2, Chapter the second" => "Chapter the second"
+## etc
+chapter_title_strip_pattern:^[0-9]+[\.: -]+
+
+## This version will strip all of the above *plus* remove 'Chapter 1':
+## "Chapter 1" => ""
+## "1. Chapter 1" => ""
+## "1. Chapter 1, Bob's First Clue" => "Bob's First Clue"
+## "Chapter 2 - Pirates Place" => "Pirates Place"
+## etc
+#chapter_title_strip_pattern:^([0-9]+[\.: -]+)?(Chapter *[0-9]+[\.:, -]*)?
+
+## Uses a python template substitution.  The ${index} is the 'chapter'
+## number and ${title} is the chapter title, after applying
+## chapter_title_strip_pattern.  Those are the only variables available.
+## "The Beginning" => "1. The Beginning" 
+chapter_title_add_pattern:${index}. ${title}
+
+
 ## Each output format has a section that overrides [defaults]
 [html]

@@ -229,10 +278,12 @@ 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; }
@@ -259,11 +310,6 @@ output_css:
 ## stories.  Images will be converted to jpg for size if possible.
 #include_images:false

-## If not set, the summary will have all html stripped for safety.
-## Both this and include_images must be true to get images in the
-## summary.
-#keep_summary_html:false
-
 ## If set, the first image found will be made the cover image.  If
 ## keep_summary_html is true, any images in summary will be before any
 ## in chapters.
@@ -316,6 +362,11 @@ nook_img_fix:true
 ## URLs like: http://test1.com?sid=12345
 [test1.com]
 extratags: FanFiction,Testing
+extracategories:Fafner
+extragenres:Romance,Fluff
+extracharacters:Reginald Smythe-Smythe,Mokona
+extraships:Smythe-Smythe/Mokona
+extrawarnings:Extreme Bogosity

 ## If necessary, you can define [<site>:<format>] sections to
 ## customize the formats differently for the same site.  Overrides
@@ -342,6 +393,11 @@ extratags: FanFiction,Testing,HTML
 #is_adult:true

 [ashwinder.sycophanthex.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+extracharacters:Severus Snape,Hermione Granger
+extraships:Severus Snape/Hermione Granger
+
 ## 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
@@ -350,6 +406,9 @@ extratags: FanFiction,Testing,HTML
 #password:yourpassword

 [castlefans.org]
+## Site dedicated to these categories/characters/ships
+extracategories:Castle
+
 ## 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
@@ -373,6 +432,11 @@ extratags: FanFiction,Testing,HTML
 cover_exclusion_regexp:/images/.*?ribbon.gif

 [dark-solace.org]
+## Site dedicated to these categories/characters/ships
+extracategories:Buffy: The Vampire Slayer
+extracharacters:Buffy, Spike
+extraships:Spike/Buffy
+
 ## 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
@@ -381,6 +445,11 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 #password:yourpassword

 [dramione.org]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+extracharacters:Draco Malfoy,Hermione Granger
+extraships:Draco Malfoy/Hermione Granger
+
 ## 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
@@ -394,6 +463,9 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 #is_adult:true

 [erosnsappho.sycophanthex.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 ## 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.
@@ -404,6 +476,9 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 cover_exclusion_regexp:/images/.*?ribbon.gif

 [fanfiction.mugglenet.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 ## 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
@@ -417,6 +492,10 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 #is_adult:true

 [fanfiction.portkey.org]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+extraships:Harry Potter/Hermione Granger
+
 ## 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.
@@ -439,6 +518,10 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 #password:yourpassword

 [grangerenchanted.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+extracharacters:Hermione Granger
+
 ## 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
@@ -452,26 +535,67 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 #is_adult:true

 [hlfiction.net]
+## Site dedicated to these categories/characters/ships
+extracategories:Highlander
+
+[ksarchive.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Star Trek
+extracharacters:Kirk,Spock
+extraships:Kirk/Spock

 [lumos.sycophanthex.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 ## 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

+[merlinfic.dtwins.co.uk]
+## Site dedicated to these categories/characters/ships
+extracategories:Merlin
+
+## 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
+
 [national-library.net]
+## Site dedicated to these categories/characters/ships
+extracategories:West Wing

 [ncisfic.com]
+## Site dedicated to these categories/characters/ships
+extracategories:NCIS

 [nfacommunity.com]
+## Site dedicated to these categories/characters/ships
+extracategories:NCIS
+
 ## 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

 [nha.magical-worlds.us]
+## Site dedicated to these categories/characters/ships
+extracategories:Buffy: The Vampire Slayer
+extracharacters:Willow

 [occlumency.sycophanthex.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+extracharacters:Severus Snape
+
 ## 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
@@ -480,6 +604,9 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 #password:yourpassword

 [onedirectionfanfiction.com]
+## Site dedicated to these categories/characters/ships
+extracategories:One Direction
+
 ## 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
@@ -493,18 +620,28 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 #is_adult:true

 [ponyfictionarchive.net]
+## Site dedicated to these categories/characters/ships
+extracategories:My Little Pony: Friendship is Magic
+
 ## 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

 [pretendercentre.com]
+## Site dedicated to these categories/characters/ships
+extracategories:The Pretender
+
 ## 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

 [samdean.archive.nu]
+## Site dedicated to these categories/characters/ships
+extracategories:Supernatural
+extracharacters:Sam,Dean
+extraships:Sam/Dean

 [sg1-heliopolis.com]
 ## Some sites do not require a login, but do require the user to
@@ -513,6 +650,8 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 #is_adult:true

 [stargate-atlantis.org]
+## Site dedicated to these categories/characters/ships
+extracategories:Stargate: Atlantis

 [svufiction.com]
 ## Some sites require login (or login for some rated stories) The
@@ -528,6 +667,10 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 #is_adult:true

 [thehexfiles.net]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+extracharacters:Draco Malfoy,Harry Potter
+extraships:Harry Potter/Draco Malfoy

 [themasque.net]
 ## Some sites require login (or login for some rated stories) The
@@ -543,6 +686,9 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 #is_adult:true

 [thequidditchpitch.org]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 ## 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
@@ -556,14 +702,40 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 #is_adult:true

 [www.adastrafanfic.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Star Trek
+
 ## 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.dracoandginny.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+extracharacters:Draco Malfoy,Ginny Weasley
+extraships:Draco Malfoy/Ginny Weasley
+
+## 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]
+## Site dedicated to these categories/characters/ships
+extracategories:Stargate: SG-1

 [www.checkmated.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 ## 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
@@ -578,6 +750,10 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 #is_adult:true

 [www.dokuga.com]
+## Site dedicated to these categories/characters/ships
+extracategories:InuYasha
+extracharacters:Sesshoumaru,Kagome
+extraships:Sesshoumaru/Kagome

 [www.fanfiction.net]
 ## fanfiction.net's 'cover' images are really just tiny thumbnails.
@@ -595,6 +771,9 @@ never_make_cover: true
 [www.ficbook.net]

 [www.fictionalley.org]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 ## 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.
@@ -616,6 +795,9 @@ extratags:
 #password:yourpassword

 [www.fimfiction.net]
+## Site dedicated to these categories/characters/ships
+extracategories:My Little Pony: Friendship is Magic
+
 ## 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.
@@ -627,20 +809,33 @@ extratags:
 #fail_on_password: false

 [www.harrypotterfanfiction.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 ## 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.hpfandom.net]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 ## 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.hpfanficarchive.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter

 [www.ik-eternal.net]
+## Site dedicated to these categories/characters/ships
+extracategories:InuYasha
+extracharacters:InuYasha,Kagome
+extraships:InuYasha/Kagome
+
 ## 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
@@ -654,6 +849,9 @@ extratags:
 #is_adult:true

 [www.libraryofmoria.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Lord of the Rings
+
 ## 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.
@@ -662,6 +860,9 @@ extratags:
 [www.mediaminer.org]

 [www.midnightwhispers.ca]
+## Site dedicated to these categories/characters/ships
+extracategories:Queer as Folk
+
 ## 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.
@@ -672,8 +873,14 @@ extratags:
 cover_exclusion_regexp:/stories/999/images/.*?_trophy.png

 [www.ncisfiction.com]
+## Site dedicated to these categories/characters/ships
+extracategories:NCIS

 [www.phoenixsong.net]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+extraships:Harry Potter/Ginny Weasley
+
 ## 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
@@ -682,16 +889,43 @@ cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
 #password:yourpassword

 [www.potionsandsnitches.net]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter

 [www.prisonbreakfic.net]
+## Site dedicated to these categories/characters/ships
+extracategories:Prison Break
+
+[www.scarvesandcoffee.net]
+## Site dedicated to these categories/characters/ships
+extracategories:Glee
+extracharacters:Kurt Hummel,Blaine Anderson
+
+## 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]
+## Site dedicated to these categories/characters/ships
+extracategories:Supernatural
+
+## 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]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+extracharacters:Harry Potter,Ginny Weasley
+extraships:Harry Potter/Ginny Weasley

 [www.squidge.org/peja]
 # www.squidge.org/peja calls it Fandom <shrug>
 category_label:Fandom
 # Remove numWords -- www.squidge.org/peja word counts are inaccurate
-titlepage_entries: series,category,genre,language,characters,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,description
+titlepage_entries: series,category,genre,language,characters,ships,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,description

 [www.squidge.org/peja:txt]
 ## Add URLs since there aren't links.
@@ -699,6 +933,16 @@ titlepage_entries: series,category,genre,language,characters,status,datePublishe
 titlepage_entries: series,category,genre,language,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,storyUrl, authorUrl, description

 [www.storiesofarda.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Lord of the Rings
+
+[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
@@ -730,8 +974,13 @@ collect_series: false
 #password:yourpassword

 [www.twilightarchives.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Twilight

 [www.twilighted.net]
+## Site dedicated to these categories/characters/ships
+extracategories:Twilight
+
 ## 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
@@ -743,6 +992,9 @@ collect_series: false
 collect_series: false

 [www.twiwrite.net]
+## Site dedicated to these categories/characters/ships
+extracategories:Twilight
+
 ## 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
@@ -754,6 +1006,11 @@ collect_series: false
 collect_series: false

 [www.walkingtheplank.org]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+extracharacters:Severus Snape,Harry Potter
+extraships:Severus Snape/Harry Potter
+
 ## 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.
@@ -774,7 +1031,15 @@ collect_series: false
 ## personal.ini, not defaults.ini.
 #is_adult:true

+[www.wolverineandrogue.com]
+## Site dedicated to these categories/characters/ships
+extracategories:X-Men Movie
+extracharacters:Wolverine,Rogue
+
 [www.wraithbait.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Stargate: Atlantis
+
 ## 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.
@@ -121,6 +121,11 @@ def main():

   if options.update and not options.updatecover:
       config.set("overrides","never_make_cover","true")
+
+   # images only for epub, even if the user mistakenly turned it
+   # on else where.
+   if options.format != "epub":
+       config.set("overrides","include_images","false")
       
   if options.options:
       for opt in options.options:
@@ -1,5 +1,5 @@
 ## This is an example of what your personal configuration might look
-## like.
+## like.  Uncomment options by removing the '#' in front of them.

 [defaults]
 ## Some sites also require the user to confirm they are adult for
@@ -7,34 +7,86 @@
 ## personal.ini, not defaults.ini.
 #is_adult:true

+[epub]
+## include images from img tags in the body and summary of stories.
+## Images will be converted to jpg for size if possible.  Images work
+## in epub format only.  To get mobi or other format with images,
+## download as epub and use Calibre to convert.
+#include_images:true
+
+## If not set, the summary will have all html stripped for safety.
+## Both this and include_images must be true to get images in the
+## summary.
+#keep_summary_html:true
+
+## If set, the first image found will be made the cover image.  If
+## keep_summary_html is true, any images in summary will be before any
+## in chapters.
+#make_firstimage_cover:true
+
+## Resize images down to width, height, preserving aspect ratio.
+## Nook size, with margin.
+#image_max_size: 580, 725
+
+## Change image to grayscale, if graphics library allows, to save
+## space.
+#grayscale_images: false
+
+
 ## Most common, I expect will be using this to save username/passwords
-## for different sites.
+## for different sites.  Here are a few examples.
+
 [www.twilighted.net]
 #username:YourPenname
 #password:YourPassword
+## default is false
+#collect_series: true

 [www.ficwad.com]
 #username:YourUsername
 #password:YourPassword

+[www.twiwrite.net]
+#username:YourName
+#password:yourpassword
+## default is false
+#collect_series: true
+
 [www.adastrafanfic.com]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.
 #is_adult:true

-## The [defaults] section here will override the system [defaults],
-## but not format, site for site:format sections.
-[defaults]
-## Directories only useful in commandline or zip files.
-#output_filename: books/${title}-${siteabbrev}_${storyId}${formatext}
-#output_filename: books/${site}/${authorId}/${title}-${storyId}${formatext}
+[www.thewriterscoffeeshop.com]
+#username:YourName
+#password:yourpassword
+#is_adult:true
+## default is false
+#collect_series: true
+
+[www.fictionalley.org]
+#is_adult:true
+
+[www.harrypotterfanfiction.com]
+#is_adult:true
+
+[www.fimfiction.net]
+#is_adult:true
+#fail_on_password: false
+
+[www.tthfanfic.org]
+#is_adult:true
+## tth is a little unusual--it doesn't require user/pass, but the site
+## keeps track of which chapters you've read and won't send another
+## update until it thinks you're up to date.  This way, on download,
+## it thinks you're up to date.
+#username:YourName
+#password:yourpassword

-## For example, zip_output here will turn on zip for html and txt, but
-## not epub because the system [epub] section explicitly says
-## zip_output: false (epubs *are* specially formated zip files.)
-#zip_output: true
-#zip_filename: ${title}-${siteabbrev}_${storyId}${formatext}.zip

 ## This section will override anything in the system defaults or other
 ## sections here.
 [overrides]
+## default varies by site.  Set true here to force all sites to
+## collect series.
+#collect_series: true
@@ -92,6 +92,12 @@ import adapter_wizardtalesnet
 import adapter_nhamagicalworldsus
 import adapter_hlfictionnet
 import adapter_grangerenchantedcom
+import adapter_dracoandginnycom
+import adapter_scarvesandcoffeenet
+import adapter_thepetulantpoetesscom
+import adapter_wolverineandroguecom
+import adapter_sinfuldesireorg
+import adapter_merlinficdtwinscouk

 ## 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 +118,7 @@ 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.
@@ -37,7 +37,6 @@ class AdAstraFanficComSiteAdapter(BaseSiteAdapter):
                               # Most sites that claim to be
                               # iso-8859-1 (and some that claim to be
                               # utf8) are really windows-1252.
-        self.story.addToList("category","Star Trek")
        self.is_adult=False
        
        # get storyId from url--url validation guarantees query is only sid=1234
@@ -191,7 +191,7 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):

        a = metasoup.find('blockquote',{'class':'userstuff'})
        if a != None:
-            self.setDescription(url,a.text)
+            self.setDescription(url,a)
            #self.story.setMetadata('description',a.text)
 		
        a = metasoup.find('dd',{'class':"rating tags"})
@@ -231,9 +231,9 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
                self.story.addToList('characters',char.string)
        a = metasoup.find('dd',{'class':"relationship tags"})
        if a != None:
-            chars = a.findAll('a',{'class':"tag"})
-            for char in chars:
-                self.story.addToList('characters',char.string)
+            ships = a.findAll('a',{'class':"tag"})
+            for ship in ships:
+                self.story.addToList('ships',ship.string)
 		

        stats = metasoup.find('dl',{'class':'stats'})
@@ -56,11 +56,6 @@ class AshwinderSycophantHexComAdapter(BaseSiteAdapter):
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','asph')

-        # If all stories from the site fall into the same category,
-        # the site itself isn't likely to label them as such, so we
-        # do.
-        self.story.addToList("category","Harry Potter")
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%m/%d/%Y"
@@ -80,11 +80,6 @@ class CastleFansOrgAdapter(BaseSiteAdapter): # XXX
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','cslf') # XXX

-        # 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","Castle") # XXX
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%b %d, %Y" # XXX
@@ -56,11 +56,6 @@ class ChaosSycophantHexComAdapter(BaseSiteAdapter):
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','csph')

-        # If all stories from the site fall into the same category,
-        # the site itself isn't likely to label them as such, so we
-        # do.
-        #self.story.addToList("category","Harry Potter")
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%m/%d/%Y"
@@ -44,25 +44,20 @@ class CheckmatedComAdapter(BaseSiteAdapter):
        self.username = "" # if left empty, site doesn't return any message at all.
        self.password = ""
        self.is_adult=False
-        
+
        # get storyId from url--url validation guarantees query is only sid=1234
        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
        logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
-        
+
        self._setURL('http://' + self.getSiteDomain() + '/story.php?story='+self.story.getMetadata('storyId'))
-        
+
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','chm')

-        # If all stories from the site fall into the same category,
-        # the site itself isn't likely to label them as such, so we
-        # do.
-        self.story.addToList("category","Harry Potter")
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%b %d, %Y"
-            
+
    @staticmethod # must be @staticmethod, don't remove it.
    def getSiteDomain():
        # The site domain.  Does have www here, if it uses it.
@@ -82,7 +77,7 @@ class CheckmatedComAdapter(BaseSiteAdapter):
            return True
        else:
            return False
-        
+
    def performLogin(self, url):
        params = {}

@@ -93,8 +88,8 @@ class CheckmatedComAdapter(BaseSiteAdapter):
            params['name'] = self.getConfig("username")
            params['pass'] = self.getConfig("password")
        params['login'] = 'yes'
-        params['submit'] = 'login'	
-	
+        params['submit'] = 'login'
+
        loginUrl = 'http://' + self.getSiteDomain()+'/login.php'
        d = self._fetchUrl(loginUrl,params)
        e = self._fetchUrl(url)
@@ -135,33 +130,33 @@ class CheckmatedComAdapter(BaseSiteAdapter):
        # The actual text that is used to announce you need to be an
        # adult varies from site to site.  Again, print data before
        # the title search to troubleshoot.
-            
+
        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
+
        # use BeautifulSoup HTML parser to make everything easier to find.
        soup = bs.BeautifulSoup(data)
        # print data

        # Now go hunting for all the meta data and the chapter list.
-        
+
        ## Title
        a = soup.findAll('span', {'class' : 'storytitle'})
        self.story.setMetadata('title',a[0].string)
-        
+
        # Find authorid and URL from... author url.
        a = a[1].find('a', href=re.compile(r"authors.php\?name\=\w+"))
        self.story.setMetadata('authorId',a['href'].split('=')[1])
        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
        self.story.setMetadata('author',a.string)
-			
+
        a = soup.find('select', {'name' : 'chapter'})
        if a == None:
            self.chapterUrls.append((self.story.getMetadata('title'),url))
        else:
            for chapter in a.findAll('option'):
                self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/story.php?story='+self.story.getMetadata('storyId')+'&chapter='+chapter['value']))
-			
+
        self.story.setMetadata('numChapters',len(self.chapterUrls))

        # eFiction sites don't help us out a lot with their meta data
@@ -174,7 +169,7 @@ class CheckmatedComAdapter(BaseSiteAdapter):
            except:
                return ""

-				
+
        # website does not keep track of word count, and there is no convenient way to calculate it

        summary = soup.find('fieldset')
@@ -182,21 +177,23 @@ class CheckmatedComAdapter(BaseSiteAdapter):
        summary.name='div'
        self.setDescription(url,summary)

-		
+
        # <span class="label">Rated:</span> NC-17<br /> etc
        table = soup.findAll('div', {'class' : 'text'})[1]
        for labels in table.findAll('tr'):
            value = labels.findAll('td')[1]
            label = labels.findAll('td')[0]

-			
+
            if 'Rating' in stripHTML(label):
                self.story.setMetadata('rating', stripHTML(value))

            if 'Ship' in stripHTML(label):
+                if value.string != "none/none":
+                    self.story.addToList('ships',value.string)
                for char in value.string.split('/'):
                    if char != 'none':
-                        self.story.addToList('characters',char)		
+                        self.story.addToList('characters',char)

            if 'Status' in stripHTML(label):
                if value.find('img', {'src' : 'img/incomplete.gif'}) == None:
@@ -206,11 +203,11 @@ class CheckmatedComAdapter(BaseSiteAdapter):

            if 'Published' in stripHTML(label):
                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
+
            if 'Updated' in stripHTML(label):
                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
-			
-        a = self._fetchUrl(self.story.getMetadata('authorUrl')+'&cat=stories')	
+
+        a = self._fetchUrl(self.story.getMetadata('authorUrl')+'&cat=stories')
        for story in bs.BeautifulSoup(a).findAll('table', {'class' : 'storyinfo'}):
            a = story.find('a', href=re.compile(r"review.php\?s\="+self.story.getMetadata('storyId')+'&act=view'))
            if a != None:
@@ -220,8 +217,8 @@ class CheckmatedComAdapter(BaseSiteAdapter):
                    if 'genre' in stripHTML(label):
                        for genre in value.findAll('img'):
                            self.story.addToList('genre',genre['title'])
-        
-            
+
+
    # grab the text for an individual chapter.
    def getChapterText(self, url):

@@ -229,11 +226,11 @@ class CheckmatedComAdapter(BaseSiteAdapter):

        soup = bs.BeautifulSoup(self._fetchUrl(url),
                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
+
        div = soup.find('div', {'id' : 'resizeableText'})
        div.find('div', {'class' : 'storyTools'}).extract()

        if None == div:
            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
        return self.utf8FromSoup(url,div)
@@ -56,11 +56,6 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','dksl')

-        # 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","Buffy the Vampire Slayer")
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%d %B %Y"
@@ -56,11 +56,6 @@ class DokugaComAdapter(BaseSiteAdapter):
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','dkg')

-        # 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","InuYasha")
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        if 'fanfiction' in self.story.getMetadata('section'):
@@ -0,0 +1,298 @@
+# -*- 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')
+
+        # 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+((?:&amp;ageconsent=ok)?&amp;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 &amp; error in url.
+                addurl = addurl.replace("&amp;","&")
+                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:
+            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)
@@ -55,11 +55,6 @@ class DramioneOrgAdapter(BaseSiteAdapter):
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','drmn')

-        # If all stories from the site fall into the same category,
-        # the site itself isn't likely to label them as such, so we
-        # do.
-        self.story.addToList("category","Harry Potter")
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%d %B %Y"
@@ -56,11 +56,6 @@ class ErosnSapphoSycophantHexComAdapter(BaseSiteAdapter):
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','essph')

-        # If all stories from the site fall into the same category,
-        # the site itself isn't likely to label them as such, so we
-        # do.
-        self.story.addToList("category","Harry Potter")
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%d/%m/%y"
@@ -201,7 +201,7 @@ class FicBookNetAdapter(BaseSiteAdapter):
                break
 				
        summary=soup.find('span', {'class' : 'urlize'})
-        self.setDescription(url,summary.text)
+        self.setDescription(url,summary)
        #self.story.setMetadata('description', summary.text)
            
    # grab the text for an individual chapter.
@@ -37,7 +37,6 @@ class FictionAlleyOrgSiteAdapter(BaseSiteAdapter):
                               # Most sites that claim to be
                               # iso-8859-1 (and some that claim to be
                               # utf8) are really windows-1252.
-        self.story.addToList("category","Harry Potter")
        self.is_adult=False
        
        # get storyId from url--url validation guarantees query correct
@@ -124,7 +124,7 @@ class FicwadComSiteAdapter(BaseSiteAdapter):

        # description
        storydiv = soup.find("div",{"id":"story"})
-        self.setDescription(url,storydiv.find("blockquote",{'class':'summary'}).p.string)
+        self.setDescription(url,storydiv.find("blockquote",{'class':'summary'}).p)
        #self.story.setMetadata('description', storydiv.find("blockquote",{'class':'summary'}).p.string)

        # most of the meta data is here:
@@ -27,6 +27,8 @@ from .. import BeautifulSoup as bs
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions

+from ..bbcodeutils.bbcodeparser import bbcodeparser
+
 from base_adapter import BaseSiteAdapter,  makeDate

 def getClass():
@@ -133,19 +135,23 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
            if storyMetadata["categories"][category]:
                self.story.addToList("genre", category) 

-        self.story.addToList("category", "My Little Pony")
-        
        self.story.setMetadata("numWords", str(storyMetadata["words"]))
        
-        
        # fimfic is the first site with an explicit cover image.
        if self.getConfig('include_images') and "image" in storyMetadata.keys():
-            coverurl = storyMetadata["image"]
+            if "full_image" in storyMetadata:
+                coverurl = storyMetadata["full_image"]
+            else:
+                coverurl = storyMetadata["image"]
            if coverurl.startswith('//static.fimfiction.net'): # fix for img urls missing 'http:'
                coverurl = "http:"+coverurl
            self.story.addImgUrl(self,self.url,coverurl,self._fetchUrlRaw,cover=True)
-            
-        self.setDescription(self.url, storyMetadata["description"])
+
+
+        # the fimfic API gives bbcode for desc, not html.
+        # btw, bbcode honors newlines, html doesn't.  change newlines to br tags.
+        self.setDescription(self.url,
+                            bbcodeparser().parse(storyMetadata["description"]).html(doDeepCopy=False).replace('\r','').replace('\n','<br />'))
        
        # Dates are in Unix time
        # Take the publish date from the first chapter posted
@@ -155,8 +161,18 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
        self.story.setMetadata("dateUpdated", datetime.fromtimestamp(rawDateUpdated))
        
        soup = bs.BeautifulSoup(data).find("div", {"class":"story"})
-        for character in [character_icon["title"] for character_icon in soup.findAll("a", {"class":"character_icon"})]:
-            self.story.addToList("characters", character)
+        # fimfic stopped putting the char name on or around the char
+        # icon now for some reason.  Pull it from the image name with
+        # some heuristics.
+        for character in [character_icon["src"] for character_icon in soup.findAll("img", {"class":"character_icon"})]:
+            # //static.fimfiction.net/images/characters/twilight_sparkle.png
+            # 5th split /, remove last four, replace _, capitolize every word(title())
+            char = character.split('/')[5][:-4].replace('_',' ').title()
+            if char == 'Oc':
+                char = "OC"
+            if char == 'Cmc':
+                char = "Cutie Mark Crusaders"
+            self.story.addToList("characters", char)
            
            
    def getChapterText(self, url):
@@ -60,11 +60,6 @@ class GrangerEnchantedCom(BaseSiteAdapter):
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','gech')

-        # If all stories from the site fall into the same category,
-        # the site itself isn't likely to label them as such, so we
-        # do.
-        self.story.addToList("category","Harry Potter")
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%d/%b/%Y"
@@ -37,7 +37,6 @@ class HarryPotterFanFictionComSiteAdapter(BaseSiteAdapter):
                               # Most sites that claim to be
                               # iso-8859-1 (and some that claim to be
                               # utf8) are really windows-1252.
-        self.story.addToList("category","Harry Potter")
        self.is_adult=False
        
        # get storyId from url--url validation guarantees query is only psid=1234
@@ -55,11 +55,6 @@ class HLFictionNetAdapter(BaseSiteAdapter):
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','hlf')

-        # 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","Highlander")
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%m/%d/%y"
@@ -60,11 +60,6 @@ class HPFandomNetAdapterAdapter(BaseSiteAdapter): # XXX
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','hpfdm') # XXX

-        # 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") # XXX
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%Y.%m.%d" # XXX
@@ -55,11 +55,6 @@ class HPFanficArchiveComAdapter(BaseSiteAdapter):
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','hpffa')

-        # If all stories from the site fall into the same category,
-        # the site itself isn't likely to label them as such, so we
-        # do.
-        self.story.addToList("category","Harry Potter")
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%B %d, %Y"
@@ -55,11 +55,6 @@ class IkEternalNetAdapter(BaseSiteAdapter):
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','ike')

-        # 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","InuYasha")
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%B %d, %Y"
@@ -60,11 +60,6 @@ class KSArchiveComAdapter(BaseSiteAdapter): # XXX
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','ksa') # XXX

-        # 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","Star Trek") # XXX
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%b/%d/%Y" # XXX
@@ -167,7 +162,7 @@ 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 +185,7 @@ 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 +210,50 @@ 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 +272,7 @@ 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.
@@ -56,11 +56,6 @@ class LibraryOfMoriaComAdapter(BaseSiteAdapter):
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','lom')

-        # If all stories from the site fall into the same category,
-        # the site itself isn't likely to label them as such, so we
-        # do.
-        self.story.addToList("category","Lord of the Rings")
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%B %d, %Y"
@@ -56,11 +56,6 @@ class LumosSycophantHexComAdapter(BaseSiteAdapter):
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','lsph')

-        # If all stories from the site fall into the same category,
-        # the site itself isn't likely to label them as such, so we
-        # do.
-        self.story.addToList("category","Harry Potter")
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%m/%d/%Y"
@@ -0,0 +1,290 @@
+# -*- 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 MerlinFicDtwinsCoUk
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class MerlinFicDtwinsCoUk(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','mrfd')
+
+        # 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 'merlinfic.dtwins.co.uk'
+
+    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=4"
+        else:
+            addurl=""
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'+addurl
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        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+((?:&amp;ageconsent=ok)?&amp;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 &amp; error in url.
+                addurl = addurl.replace("&amp;","&")
+                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('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 'Pairing' in label:
+                ships = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
+                for ship in ships:
+                    self.story.addToList('ships',ship.string)
+
+            if 'Genre' in label:
+                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+'/'+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)
@@ -60,11 +60,6 @@ class MidnightwhispersCaAdapter(BaseSiteAdapter): # XXX
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','mw') # XXX

-        # 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","Queer as Folk") # XXX
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%B %d, %Y" # XXX
@@ -59,11 +59,6 @@ class MuggleNetComAdapter(BaseSiteAdapter): # XXX
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','mgln') # XXX

-        # 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") # XXX
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%m/%d/%y" # XXX
@@ -55,11 +55,6 @@ class NationalLibraryNetAdapter(BaseSiteAdapter):
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','ntlb')

-        # 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","West Wing")
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%m-%d-%y"
@@ -154,6 +149,10 @@ class NationalLibraryNetAdapter(BaseSiteAdapter):
                for char in value.string.split(', '):
                    self.story.addToList('characters',char)
                    
+            if 'Pairing' in label:
+                for char in value.string.split(', '):
+                    self.story.addToList('ships',char)
+                    
            if 'Warnings' in label:
                for warning in value.string.split(', '):
                    self.story.addToList('warnings',warning)
@@ -55,11 +55,6 @@ class NCISFicComAdapter(BaseSiteAdapter):
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','ncisf')

-        # 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","NCIS")
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%m-%d-%y"
@@ -154,6 +149,10 @@ class NCISFicComAdapter(BaseSiteAdapter):
                for char in value.string.split(', '):
                    self.story.addToList('characters',char)
                    
+            if 'Pairing' in label:
+                for char in value.string.split(', '):
+                    self.story.addToList('ships',char)
+                    
            if 'Warnings' in label:
                for warning in value.string.split(', '):
                    self.story.addToList('warnings',warning)
@@ -56,11 +56,6 @@ class NCISFictionComAdapter(BaseSiteAdapter):
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','ncisfn')

-        # 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","NCIS")
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%d/%m/%Y"
@@ -157,6 +152,11 @@ class NCISFictionComAdapter(BaseSiteAdapter):
                for char in chars:
                    self.story.addToList('characters',char.string)

+            if 'Pairing' in label:
+                ships = value.findAll('a')
+                for ship in ships:
+                    self.story.addToList('ships',ship.string)
+
            if 'Genre' in label:
                genres = value.findAll('a')
                for genre in genres:
@@ -60,11 +60,6 @@ class NfaCommunityComAdapter(BaseSiteAdapter): # XXX
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','nfa') # XXX

-        # 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","NCIS") # XXX
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%m/%d/%Y" # XXX
@@ -56,11 +56,6 @@ class NHAMagicalWorldsUsAdapter(BaseSiteAdapter):
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','nha')

-        # 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","Buffy the Vampire Slayer")
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = " %m/%d/%y"
@@ -56,11 +56,6 @@ class OcclumencySycophantHexComAdapter(BaseSiteAdapter):
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','osph')

-        # If all stories from the site fall into the same category,
-        # the site itself isn't likely to label them as such, so we
-        # do.
-        self.story.addToList("category","Harry Potter")
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%m/%d/%Y"
@@ -55,11 +55,6 @@ class OneDirectionFanfictionComAdapter(BaseSiteAdapter):
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','odf')

-        # 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","One Direction")
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%m/%d/%y"
@@ -55,11 +55,6 @@ class PhoenixSongNetAdapter(BaseSiteAdapter):
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','phs')

-        # If all stories from the site fall into the same category,
-        # the site itself isn't likely to label them as such, so we
-        # do.
-        self.story.addToList("category","Harry Potter")
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%B %d %Y"
@@ -60,11 +60,6 @@ class PonyFictionArchiveNetAdapter(BaseSiteAdapter):
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','pffa')

-        # 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","My Little Pony")
-            
    @staticmethod # must be @staticmethod, don't remove it.
    def getSiteDomain():
        # The site domain.  Does have www here, if it uses it.
@@ -62,11 +62,6 @@ class PortkeyOrgAdapter(BaseSiteAdapter): # XXX
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','prtky') # XXX

-        # 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") # XXX
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%d/%m/%y" # XXX
@@ -37,7 +37,6 @@ class PotionsAndSnitchesNetSiteAdapter(BaseSiteAdapter):
                               # Most sites that claim to be
                               # iso-8859-1 (and some that claim to be
                               # utf8) are really windows-1252.
-        self.story.addToList("category","Harry Potter")
        
        # get storyId from url--url validation guarantees query is only sid=1234
        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
@@ -142,7 +141,7 @@ class PotionsAndSnitchesNetSiteAdapter(BaseSiteAdapter):
                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
                charstext = [char.string for char in chars]
                for char in charstext:
-                    if char == "!Snape and Harry (required)":
+                    if "Snape and Harry (required)" in char:
                        self.story.addToList('characters',"Snape")
                        self.story.addToList('characters',"Harry")
                    else:
@@ -55,11 +55,6 @@ class PretenderCenterComAdapter(BaseSiteAdapter):
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','ptdc')

-        # 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","The Pretender")
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%d/%m/%y"
@@ -55,11 +55,6 @@ class PrisonBreakFicNetAdapter(BaseSiteAdapter):
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','pbf')

-        # 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","Prison Break")
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%B %d, %Y"
@@ -157,6 +152,11 @@ class PrisonBreakFicNetAdapter(BaseSiteAdapter):
                for char in chars:
                    self.story.addToList('characters',char.string)

+            if 'Pairing' in label:
+                ships = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=3')) # XXX
+                for ship in ships:
+                    self.story.addToList('ships',ship.string.replace(" and ","/"))
+
            if 'Genre' in label:
                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1')) # XXX
                for genre in genres:
@@ -55,11 +55,6 @@ class SamDeanArchiveNuAdapter(BaseSiteAdapter):
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','sda')

-        # 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"
@@ -0,0 +1,244 @@
+# -*- 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')
+
+        # 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+((?:&amp;ageconsent=ok)?&amp;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 &amp; error in url.
+                addurl = addurl.replace("&amp;","&")
+                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)
@@ -58,7 +58,7 @@ class SG1HeliopolisComAdapter(BaseSiteAdapter):

        # 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.
+        # do.  Can't use extracategories, could be Atlantis or SG-1
        if 'atlantis' in self.story.getMetadata('section'):
            self.story.addToList("category","Stargate: Atlantis")
        else:
@@ -0,0 +1,248 @@
+# -*- 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')
+
+        # 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+((?:&amp;ageconsent=ok)?&amp;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 &amp; error in url.
+                addurl = addurl.replace("&amp;","&")
+                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)
@@ -56,11 +56,6 @@ class SiyeCoUkAdapter(BaseSiteAdapter): # XXX
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','siye') # XXX

-        # 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") # XXX
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%Y.%m.%d" # XXX
@@ -55,11 +55,6 @@ class StargateAtlantisOrgAdapter(BaseSiteAdapter):
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','stat')

-        # If all stories from the site fall into the same category,
-        # the site itself isn't likely to label them as such, so we
-        # do.
-        self.story.addToList("category","Stargate: Atlantis")
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%B %d %Y"
@@ -55,11 +55,6 @@ class StoriesOfArdaComAdapter(BaseSiteAdapter):
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','soa')

-        # If all stories from the site fall into the same category,
-        # the site itself isn't likely to label them as such, so we
-        # do.
-        self.story.addToList("category","Lord of the Rings")
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%m/%d/%Y"
@@ -73,8 +73,8 @@ class TestSiteAdapter(BaseSiteAdapter):
            self.story.setMetadata(u'title',"Test Story Title "+self.story.getMetadata('storyId'))
            self.story.setMetadata('author','Test Author aa')
        self.story.setMetadata('storyUrl',self.url)
-        self.story.setMetadata('description',u'Description '+self.crazystring+u''' Done
-
+        self.setDescription(self.url,u'Description '+self.crazystring+u''' Done
+<p>
 Some more longer description.  "I suck at summaries!"  "Better than it sounds!"  "My first fic"
 ''')
        self.story.setMetadata('datePublished',makeDate("1975-03-15","%Y-%m-%d"))
@@ -55,11 +55,6 @@ class TheAlphaGateComAdapter(BaseSiteAdapter):
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','tag')

-        # If all stories from the site fall into the same category,
-        # the site itself isn't likely to label them as such, so we
-        # do.
-        self.story.addToList("category","Stargate: SG-1")
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%d %b %Y"
@@ -55,11 +55,6 @@ class TheHexFilesNetAdapter(BaseSiteAdapter):
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','thf')

-        # If all stories from the site fall into the same category,
-        # the site itself isn't likely to label them as such, so we
-        # do.
-        self.story.addToList("category","Harry Potter")
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%Y.%m.%d"
@@ -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)
@@ -60,11 +60,6 @@ class TheQuidditchPitchOrgAdapter(BaseSiteAdapter): # XXX
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','tqdpch') # XXX

-        # 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") # XXX
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%m/%d/%Y" # XXX
@@ -55,11 +55,6 @@ class TwilightArchivesComAdapter(BaseSiteAdapter):
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','twa')

-        # 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","Twilight")
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%d %b %y"
@@ -37,7 +37,6 @@ class TwilightedNetSiteAdapter(BaseSiteAdapter):
                               # Most sites that claim to be
                               # iso-8859-1 (and some that claim to be
                               # utf8) are really windows-1252.
-        self.story.addToList("category","Twilight")
        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
        self.password = ""
        
@@ -37,7 +37,6 @@ class TwiwriteNetSiteAdapter(BaseSiteAdapter):
                               # Most sites that claim to be
                               # iso-8859-1 (and some that claim to be
                               # utf8) are really windows-1252.
-        self.story.addToList("category","Twilight")
        self.is_adult = False
        self.username = "NoneGiven" # if left empty, twiwrite.net doesn't return any message at all.
        self.password = ""
@@ -53,11 +53,6 @@ class WalkingThePlankOrgAdapter(BaseSiteAdapter):
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','wtp')

-        # If all stories from the site fall into the same category,
-        # the site itself isn't likely to label them as such, so we
-        # do.
-        self.story.addToList("category","Harry Potter")
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%b %d, %Y"
@@ -0,0 +1,216 @@
+# -*- 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')
+
+        # 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)
@@ -56,11 +56,6 @@ class WraithBaitComAdapter(BaseSiteAdapter):
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','wb')

-        # If all stories from the site fall into the same category,
-        # the site itself isn't likely to label them as such, so we
-        # do.
-        self.story.addToList("category","Stargate")
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%d  %b %Y"
@@ -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))

@@ -199,7 +199,8 @@ class BaseSiteAdapter(Configurable):
                if (self.chapterFirst!=None and index < self.chapterFirst) or \
                        (self.chapterLast!=None and index > self.chapterLast):
                    self.story.addChapter(removeEntities(title),
-                                          None)
+                                          None,
+                                          self)
                else:
                    if self.oldchapters and index < len(self.oldchapters):
                        data = self.utf8FromSoup(None,
@@ -208,7 +209,8 @@ class BaseSiteAdapter(Configurable):
                    else:
                        data = self.getChapterText(url)
                    self.story.addChapter(removeEntities(title),
-                                          removeEntities(data))
+                                          removeEntities(data),
+                                          self)
            self.storyDone = True
            
            # include image, but no cover from story, add default_cover_image cover.
@@ -289,7 +291,7 @@ class BaseSiteAdapter(Configurable):
    def setDescription(self,url,svalue):
        #print("\n\nsvalue:\n%s\n"%svalue)
        if self.getConfig('keep_summary_html'):
-            if isinstance(svalue,str) or isinstance(svalue,unicode):
+            if isinstance(svalue,basestring):
                svalue = bs.BeautifulSoup(svalue)
            self.story.setMetadata('description',self.utf8FromSoup(url,svalue))
        else:
@@ -0,0 +1,325 @@
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+#
+# Author:        Pau Sanchez (contact@pausanchez.com)
+# Version:       v1.0
+# Last Modified: 2010/09/15
+# 
+# For the latest version check out:
+#   http://www.codigomanso.com/en/projects
+# 
+# My blog:
+#   http://www.codigomanso.com/en/  - English Version
+#   http://www.codigomanso.com/es/  - Spanish Version
+#
+
+import sys
+import os
+import re
+import urllib
+
+class bbcode2html:
+  '''
+  This class gets a parsed BBCode and transforms it to valid HTML
+
+  Useful functions of this class:
+    html
+    convertToHTML
+
+  Example:
+    > parser = bbcodeparser ()
+    > parser.parse ('[b]bold[/b]')
+    > bbcode2html (parser).html()
+    <b>bold</b>
+
+    # This is faster for huge strings but changes the parser object internally
+    > bbcode2html (parser).html(doDeepCopy = False)
+    <b>bold</b>
+  '''
+  def __init__ (self, parser):
+    self._parser = parser
+    return
+
+  def html (self, allowClassAttr = False, doDeepCopy = True, parser = None):
+    '''
+    Convert current parsed code to HTML
+
+    Example:
+      code = bbcodeparser ('[b]bold[/b]')
+      code.html() -> '<b>bold</b>'
+    '''
+    if parser is None:
+      parser = self._parser
+
+    tokens = parser
+    if instanceof (parser, bbcodeparser):
+      tokens = parser.getTokens()
+
+    return bbcode2html.convertToHTML (tokens, allowClassAttr = allowClassAttr, doDeepCopy = doDeepCopy)
+
+  @staticmethod
+  def htmlString (string):
+    toReplace = {
+      u'<' : '&lt;',
+      u'>' : '&gt;',
+      u'"' : "&quot;",
+      u'&' : "&amp;"
+    }
+    for entity in toReplace:
+      string = string.replace(entity, toReplace[entity])
+    return string
+
+  @staticmethod
+  def getValidTags ():
+    simpleTags = ['b', 'u', 'i', 'sup', 'sub', 'ul', 'ol', 'li', 'table', 'tr', 'th', 'td', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6']
+    validTags = {
+      'p'         : { 'color' : 'color', 'size' : 'size', 'font' : 'font' },
+      'color'     : { 'color' : 'color' },
+      'size'      : { 'size' : 'size' },
+      'font'      : { 'font' : 'font' },
+      'img'       : { 'alt' : 'alt', 'title' : 'title', 'width' : 'width' , 'height' : 'height', 'img' : 'img'},
+      'url'       : { 'href' : 'href', 'url' : 'href', 'link'  : 'href', 'title' : 'title' },
+      's'         : { },
+      'code'      : { },
+      'quote'     : { },
+      'list'      : { 'list' : 'type' },
+      'email'     : { 'email': 'href'},
+      'google'    : { 'google':  'google'},
+      'wikipedia' : { 'wikipedia' : 'wikipedia', 'language' : 'language', 'lang' : 'lang'}
+    }
+
+    for tag in simpleTags:
+      validTags[tag] = { }
+    return validTags
+
+  @staticmethod
+  def convertToHTML (tokens, allowClassAttr = False, validTags = None, doDeepCopy = True):
+    '''
+    Convert internally parsed BBCode to XHTML
+
+    @doDeepCopy 
+      True:  it does a deep copy of tokens so this list will remain unchanged
+      False: tokens will be modified internally, but the output will be produced like 5x faster
+             it's a good idea to use False only when this is the last operation
+    '''
+    # do a deep copy
+    if doDeepCopy:
+      import copy
+      tokens = copy.deepcopy (tokens)
+
+    # filter invalid tags and attributes
+    if validTags is None:
+      validTags = bbcode2html.getValidTags()    
+
+    bbcode2html._filterInvalidTagsAndAttributes (tokens, validTags, allowClassAttr)
+    
+    # Start to convert
+    index       = 0
+    tokenLength = len (tokens)
+
+    # use a list for the output (an order of magnitude faster than using string concatenation)
+    htmlList = []
+    lastListOpener = []
+
+    while index < tokenLength:
+
+      if isinstance (tokens [index], basestring):
+        htmlList.append (bbcode2html.htmlString (tokens [index]))
+        index += 1
+        continue
+
+      token     = tokens[index] 
+      tag       = token['tag']  # opening or closing simple tag. e.g: 'b', '/b', '/u', ...
+      tagName   = (tag[1:] if tag[0] == '/' else tag)
+      tagOpener = (u'/' if tag[0] == '/' else u'')
+      tokenArgs = (token['args'] if 'args' in token else {})
+
+      # opening or closing simple tag COLOR / SIZE
+      if (tagName in ['p', 'color', 'size', 'font']): 
+        style  = ''
+        style += ((u' color: ' + tokenArgs['color'] + u';') if ('color' in tokenArgs) else '')
+        style += ((u' font-size: ' + tokenArgs['size'] + u'pt;') if ('size' in tokenArgs) else '')
+        style += ((u' font-family: ' + tokenArgs['font'] + u';') if ('font' in tokenArgs) else '')
+        style  = style.strip()
+
+        pArgs = {}
+        if style != '':
+          pArgs ['style'] = style
+
+        if 'class' in tokenArgs:
+          pArgs ['class'] = tokenArgs['class']
+
+        if ('args' not in token) and (tagName != 'p'):
+          if (tagOpener == '/'): # if closing tag, close it
+            htmlList.append (u'</span>')
+          index += 1
+          continue
+
+        if tagName != 'p':
+          tag = tagOpener + u'span'
+
+        htmlList.append (bbcode2html.xml (tag, pArgs))
+
+      # IMG tag
+      elif tag == 'img' and (index+2 < tokenLength):
+        if 'img' in tokenArgs:
+          # has the form of <width>x<height> ?
+          sizeMatch = re.match (u'^\s*(\d+)[xX](\d+)\s*$', tokenArgs['img'])
+          if sizeMatch is not None:
+            tokenArgs['width']  = sizeMatch.group(1)
+            tokenArgs['height'] = sizeMatch.group(2)
+          # then assume is the alternative text
+          else:
+            tokenArgs['alt'] = tokenArgs['img']
+          del tokenArgs['img']
+
+        # add the source of the image
+        tokenArgs ['src'] = tokens[index+1]
+
+        # [img]http://www.whatever.com/pic.jpg[/img]
+        htmlList.append (
+          bbcode2html.xml ('img', tokenArgs, soloTag=True)
+        )
+        index += 2 # skip next token and closing tag
+
+      # URL tag
+      elif tag == 'url':
+        if ('args' not in token) and (index+2 < tokenLength):
+          # [url]http://www.google.com[/url]
+          htmlList.append (bbcode2html.xml ('a', { 'href' : tokens[index+1] }))
+        else:
+          # [url=http://www.google.com]Google[/url]
+          # [url link=http://www.google.com title="This is Google"]Google[/url]
+          htmlList.append (bbcode2html.xml ('a', tokenArgs))
+  
+      # URL closing tag (sometimes needed)
+      elif (tag == '/url') or (tag == '/email'):
+        htmlList.append (u'</a>')
+
+      # Email tag
+      elif tag == 'email':
+        if ('args' not in token) and (index+2 < tokenLength):
+          # [email]asdf@asdf.com]
+          htmlList.append (bbcode2html.xml ('a', { 'href' : u'mailto:' + tokens[index+1].strip() }))
+        else:
+          # [email=asdf@asfd.com]john smith[/email]
+          if 'href' in tokenArgs:
+            tokenArgs['href'] = u'mailto:' + tokenArgs['href']
+          htmlList.append (bbcode2html.xml ('a', tokenArgs))
+  
+      elif tagName == 'list':
+        if tagOpener == '/':
+          htmlList.append (bbcode2html.xml (u'/' + lastListOpener.pop()))
+        else:
+          if ('type' not in tokenArgs):
+            htmlList.append (bbcode2html.xml (tagOpener + u'ul', tokenArgs))
+            lastListOpener.append ('ul')
+          else:
+            htmlList.append (bbcode2html.xml (tagOpener + u'ol', tokenArgs))
+            lastListOpener.append ('ol')
+
+      elif tagName == '*':
+        htmlList.append (bbcode2html.xml (tagOpener + u'li', tokenArgs))
+
+      elif (tagName == 's'):
+        tokenArgs['style'] =  'text-decoration: line-through;'
+        htmlList.append (bbcode2html.xml (tagOpener + u'span', tokenArgs))
+
+      elif (tagName == 'code'):
+        htmlList.append (bbcode2html.xml (tagOpener + u'pre', tokenArgs))
+
+      elif (tagName == 'quote'):
+        htmlList.append (bbcode2html.xml (tagOpener + u'blockquote', tokenArgs))
+
+      elif (tagName == 'google'):
+        htmlList.append (
+          bbcode2html.xml (
+            tagOpener + u'a', 
+            {'href' : 'http://www.google.com/search?q=' + urllib.quote_plus (tokens[index+1])},
+            tokens[index+1]
+          )
+        )
+        index += 2
+
+      elif (tagName == 'wikipedia'):
+        subdomain = 'www'
+        for arg  in ['lang', 'language', 'wikipedia']:
+          if arg in tokenArgs:
+            subdomain = tokenArgs[arg] 
+
+        htmlList.append (
+          bbcode2html.xml (
+            tagOpener + u'a', 
+            {'href' : 'http://' + subdomain + '.wikipedia.org/wiki/' + tokens[index+1].replace (' ', '_')},
+            tokens[index+1]
+          )
+        )
+        index += 2
+
+      elif (tagName in validTags):
+        htmlList.append (
+          bbcode2html.xml (tag, tokenArgs)
+        )
+
+      else:
+        # ignore this tag
+        pass 
+
+      index += 1
+
+    return ''.join (htmlList)
+
+  @staticmethod
+  def _filterInvalidTagsAndAttributes (tokens, validTags, allowClassAttr):
+    '''
+    Helper function to filter out invalid attributes from the tokens list
+    '''
+    # add 'class' attribute as valid (mapping 'class' itself)
+    if allowClassAttr:
+      for attr in validTags:
+        validTags[attr]['class'] = 'class'
+
+    # remove invalid attributes from tokens
+    for tindex in range(0, len(tokens)):
+      if isinstance (tokens[tindex], dict) and ('args' in tokens[tindex]) and (tokens[tindex]['tag'] in validTags):
+        validList = validTags[tokens[tindex]['tag']]
+
+        filteredArgs = {}
+        for arg in tokens[tindex]['args']:
+          if arg in validList:
+            # rename the argument
+            filteredArgs[validList[arg]] = tokens[tindex]['args'][arg]
+          else:
+            pass # do not include this arg in the filteredArgs
+
+        tokens[tindex]['args'] = filteredArgs
+
+    return
+
+  @staticmethod
+  def xml (tag, attrs = {}, text = None, soloTag = False):
+    '''
+    Helper function to produce valid XML output
+    '''
+    xml = u'<' + tag.lower()
+
+    # make sure we sort attributes alphabetically (for deterministic output)
+    # Faster but non-deterministic:
+    #  for (key, value) in attrs.iteritems():
+    #    xml += u' ' + key + u'="' + value + u'"'
+    for key in sorted (attrs.keys()):
+      xml += u' ' + key + u'="' + attrs[key] + u'"'
+      
+    # close tag
+    if text is None:
+      if soloTag:
+        xml += u' />'
+      else:
+        xml += u'>'
+    else:
+      xml += u'>' + text + u'</' + tag.lower() + '>'
+
+    return xml
+
+
+
@@ -0,0 +1,77 @@
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+#
+# Author:        Pau Sanchez (contact@pausanchez.com)
+# Version:       v1.0
+# Last Modified: 2010/09/15
+# 
+# For the latest version check out:
+#   http://www.codigomanso.com/en/projects
+# 
+# My blog:
+#   http://www.codigomanso.com/en/  - English Version
+#   http://www.codigomanso.com/es/  - Spanish Version
+#
+
+import sys
+import os
+import re
+import hashlib
+
+class bbcodebuilder:
+  '''
+  This class helps to build BBCode programmatically.
+
+  The function names are used as the tag name, then the first parameter
+  is the string that goes inside the tags and any extra parameter is 
+  appended as a parameter to the tag
+
+  Examples:
+    > bbcode = bbcodebuilder()  # create a instance!
+
+    > print bbcode.b ('bold')
+    [b]bold[/b]
+
+    > print bbcode.color ('this goes in red', 'red')
+    [color=red]this goes in red[/color]
+
+    > print bbcode.url ('Google', 'http://www.google.com')
+    [url=http://www.google.com]Google[/url]
+    
+    > print bbcode.alist('item 1', 'item 2')
+    [list=a]
+      [*]item 1
+      [*]item 2
+    [/list]
+
+
+  This solution is based on the recipe found on:
+    http://code.activestate.com/recipes/576831-simple-bbcode-support/
+  '''
+
+  def __getattr__(self, name):
+    '''
+    This is a generic getter that returns a function which gets the first parameter
+    as the string that goes between the tags, and extra parameters as tag parameters.
+
+    The name of the attribute is used as the tag name
+    '''
+    class bbcodebuilder_helper:
+      def __init__(self, name):
+        self._name = name
+
+      def __call__(self, string, *args):
+        return u'[{0}{1}]{2}[/{0}]'.format(self._name, (u'=' + u','.join(map(str, args))) if args else u'', string)
+    
+    return bbcodebuilder_helper (name)
+
+  def list(self, *items):
+    return u'[list]' + u''.join(map(lambda item: u"\n  [*]" + item, items)) + u"\n[/list]"
+
+  def nlist(self, *items):
+    return u'[list=1]' + u''.join(map(lambda item: u"\n  [*]" + item, items)) + u"\n[/list]"
+
+  def alist(self, *items):
+    return u'[list=a]' + u''.join(map(lambda item: u"\n  [*]" + item, items)) + u"\n[/list]"
+
+
@@ -0,0 +1,251 @@
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+#
+# Author:        Pau Sanchez (contact@pausanchez.com)
+# Version:       v1.0
+# Last Modified: 2010/09/15
+# 
+# For the latest version check out:
+#   http://www.codigomanso.com/en/projects
+# 
+# My blog:
+#   http://www.codigomanso.com/en/  - English Version
+#   http://www.codigomanso.com/es/  - Spanish Version
+#
+
+import sys
+import os
+import re
+import hashlib
+
+class bbcodeparser:
+  '''
+  This class parses BBCode into a internal structure to allow later processing and
+  conversion to HTML.
+
+  The parser tries to fix invalid code (like unclosed tags)
+
+  Useful URLs:
+    http://en.wikipedia.org/wiki/BBCode
+    http://www.bbcode.org/reference.php
+
+  Example:
+    > bbcode = bbcodeparser ()
+    > bbcode.parse ('[b]text in bold[/b]').html()
+    <b>text in bold</b>
+
+    # dump HTML
+    > bbcode.parse ('[p][color=red]text in red').html()
+    <p><span style="color:red;">text in red</span></p>
+
+    # dump fixed BBCode
+    > bbcode.parse ('[p][color=red]text in red').bbcode()
+    [p][color=red]text in red[/color][/p]
+
+    > bbcode.parse ('This [b][i]code[/b] will be fixed[/invalid]').bbcode()
+    This [b][i]code[/i][/b] will be fixed
+
+    # dump fixed bbcode
+    > str (bbcodeparse ('This [b][i]code[/b] will be fixed[/invalid]'))
+    This [b][i]code[/i][/b] will be fixed
+  '''
+  _bbcode = ''
+  _tokens = []
+
+  def __init__ (self, bbcode = '', fixInvalidCode = True):
+    ''' Initialize and parse bbcode string (if any is given)
+    '''
+    self.parse (bbcode, fixInvalidCode)
+    return
+
+  def __str__ (self):
+    return self.bbcode()
+
+  def parse (self, bbcode = None, fixInvalidCode = True):
+    '''
+    It will parse and return the token list, trying to fix tags if
+    fixInvalidCode is True
+
+    It will return the current object to allow chaining
+
+    Example:
+      code = bbcode()
+      code.parse ('<b>bold</b>', True) -> 
+      code.parse ('<b>bold<i>italics</b>', True) -> internally will add the missing '</i>'
+    '''
+    if bbcode is not None:
+      self._bbcode = bbcode
+      self._tokens = self.tokenize (bbcode)
+      if fixInvalidCode:
+        self._tokens = self.fixWrongTags (self._tokens)
+
+    return self
+
+  # return ALL tokens
+  def getTokens (self):
+    return self._tokens
+
+  def bbcode (self):
+    '''
+    Dump BBCode again. This is useful for dumping valid BBCode
+    '''
+    bbcode = []
+    for token in self._tokens:
+      if token is None:
+        continue
+
+      if isinstance (token, basestring):
+        bbcode.append (token.replace (u'[', u'\[').replace (u']', u'\]'))
+        continue
+      
+      tag       = token['tag']  # opening or closing simple tag. e.g: 'b', '/b', '/u', ...
+      tagOpener = (u'/' if tag[0] == u'/' else u'')
+
+      if (tagOpener == '/') or ('args' not in token):
+        bbcode.append (u'[' + tag + u']')
+      else:
+        # process args
+        argstr = ''
+
+        # the arg with the same name as the tag repersents the '=whatever'
+        if tag in token['args']:
+          if re.match ('\s|"', token['args'][tag]) is None:
+            argstr = u'=' + token['args'][tag]
+          else:
+            argstr = u'="' + token['args'][tag].replace (u'"', u'\"') + u'"'
+
+        for (k,v) in token['args'].iteritems():
+          if k == tag: # already processed
+            continue
+          argstr += ' ' + k + u'="' + v.replace (u'"', u'\"') + u'"'
+          
+        bbcode.append (u'[' + tag + argstr + ']')
+
+    return u''.join (bbcode)
+
+  def html (self, allowClassAttr = False, doDeepCopy = True):
+    '''
+    Convert current parsed code to HTML
+
+    @allowClassAttr
+      Is something like [b class="asdf"] allowed?
+
+    @doDeepCopy 
+      True:  it does a deep copy of tokens so this list will remain unchanged
+      False: tokens will be modified internally, but the output will be produced like 5x faster
+             it's a good idea to use False when the string parsed is huge and this is the
+             last operation on the string
+
+    Example:
+      code = bbcode ('[b]bold[/b]')
+      code.html() -> '<b>bold</b>'
+    '''
+    from bbcode2html import bbcode2html
+    return bbcode2html.convertToHTML (self._tokens, allowClassAttr = allowClassAttr, doDeepCopy = doDeepCopy)
+
+
+  @staticmethod
+  def fixWrongTags (inTokenList):
+    ''' Add missing tokens that have not been closed properly and try to fix some scenarios
+    '''
+    opened       = []
+    outTokenList = []
+    for token in inTokenList:
+      # normal string... do nothing
+      if isinstance(token, basestring):
+        outTokenList.append (token)
+      else:
+        # if starts with '/' is closing a tag
+        if token['tag'][0] == '/':
+          while (len (opened) > 0) and (opened[-1] != token['tag'][1:]):
+            outTokenList.append ({'tag' : '/' + opened[-1] })
+            del opened[-1]
+
+          if len(opened):
+            del opened[-1]
+            outTokenList.append (token)
+
+        # opening tag
+        else:
+          # if I open the same tag I opened before, close it, and open it again
+          if (len(opened) > 0) and (token['tag'] == opened[-1]):
+            outTokenList.append ({'tag' : '/' + opened[-1] })
+          else:
+            opened.append (token['tag'])
+          outTokenList.append (token)
+
+    # close all elements that have not been closed
+    while len(opened):
+      outTokenList.append ({'tag' : '/' + opened[-1] })
+      del opened[-1]
+
+    return outTokenList
+
+  @staticmethod
+  def tokenize(code):
+    '''
+    Tokenize BBCode tags and parameters
+
+    Return the token list using a internal format. See the example:
+      [
+        { 'tag' : 'p', 'args' : { 'font' : 'arial' } },
+        'This is ',
+        { 'tag' : 'url', 'args' : {'url' : 'http://www.google.com'} },
+        'a link to google',
+        { 'tag' : '/url' },
+        { 'tag' : '/p' }
+      ]
+    '''
+    re_tags    = re.compile (r'(\[[^]]+\])', re.DOTALL | re.UNICODE)
+    re_tagName = re.compile (r'\[([^]=\s]+)([^]]*)\]',  re.DOTALL | re.UNICODE)
+    #re_tagArgs = re.compile (r'\s*([^=]*)=(("([^"]+)")|([^\s]+))',  re.DOTALL | re.UNICODE)
+    re_tagArgs = re.compile (r'\s*([\w]*)=(("([^"]+)")|([^\s]+))',  re.DOTALL | re.UNICODE)
+
+    # get a unique name and replace escaped braces 
+    unique = hashlib.md5(code).hexdigest()
+    code   = code.replace ('\[', unique+'_OPEN_BRACE')
+    code   = code.replace ('\]', unique+'_CLOSE_BRACE')
+
+    splitted = re_tags.split(code)
+
+    outTokenList = []
+    for token in splitted:
+      if len(token) == 0:
+        continue
+      
+      if token[0] == '[':
+        match   = re_tagName.match (token)
+        tagName = match.group(1)
+        tagArgs = match.group(2)
+        
+        tagToken = { 'tag' : tagName.lower() }
+
+        # parse arguments (if any)
+        if len(tagArgs) > 0:
+          allArgs = re_tagArgs.findall(tagArgs)
+
+          tagArgs = {}
+          for arg in allArgs:
+            # if the argument has no name, use the tagName itself
+            argName  = (arg[0] if arg[0] != '' else tagName)
+            argValue = (arg[3] if (arg[1][0] == '"') else arg[4])
+
+            tagArgs[argName.lower()] = argValue.replace ('\"', '"')
+
+          tagToken['args'] = tagArgs
+
+        outTokenList.append (tagToken)
+
+      # append the text as it is
+      else:
+        outTokenList.append (token)
+
+    # restore escaped braces back (once code is parsed)
+    restoredTokenList = []
+    for token in outTokenList:
+      if isinstance (token, basestring):
+        token = token.replace (unique+'_OPEN_BRACE', '[').replace (unique+'_CLOSE_BRACE', ']')
+      restoredTokenList.append (token)
+
+    return restoredTokenList
+
@@ -0,0 +1,81 @@
+AUTHOR
+  Pau Sanchez
+  http://www.codigomanso.com/
+
+VERSION:
+  bbcodeutils v1.0
+  
+LICENSE
+  This code is licensed under Creative Commons Attribution 3.0
+  http://creativecommons.org/licenses/by/3.0/
+
+  You can use this python module or any part of the code you want as long as you add
+  my name as a contributor to your project.
+  
+DESCRIPTION
+  This module can be used to produce HTML from BBCode, to generate BBCode or to fix invalid BBCode.
+
+  The classes are:
+    - bbcodeparser
+    - bbcodebuilder
+    - bbcode2html
+  
+  You can use bbcodeparser to parse BBCode and to produce output in any format you want.
+
+  Open the python file to find more information and examples of use of each class. It can
+  be a good idea to check the test.py for examples
+
+  To run the unit tests:
+    > python test.py
+  
+  To run the performance test:
+    > python test.py BBCodeTests.performanceTest  
+
+
+EXAMPLES OF BBCode:
+
+  [b] -> bold
+  [u] -> underline
+  [i] -> italic
+
+  [center] -> center the text inside
+  [color=XXX] -> change color of text
+  [size=XXX] -> change size of text
+
+  Lists:
+  [ul] -> unordered list
+  [ol] -> ordered list
+  [li] -> list item
+
+  [list] -> start unordered list
+  [*]    -> list item
+  [list=1] -> start a list of numbers
+  [list=a] -> start a list of alphabetic characters
+
+  Advanced:
+  [url] -> link to url
+  [url=http://link/url/]text[/url]  
+  [url link=http://link/url/ title="This is the title"]text[/url]  
+
+  [img]http://to/image[/img]
+  [img=230x330]http://to/image[/img]
+  [img="Alt text here"]http://to/image[/img]
+  [img="Alt text here" width=320 height=240]http://to/image[/img]
+
+  [email]asdf@asdf.com[/email]
+  [email=john@asdf.com]John Smith[/email]
+
+  [google]search this[/google]
+  [wikipedia]Tom Hanks[/wikipedia]
+  [wikipedia lang=es]Tom Hanks[/wikipedia]
+
+  Tables:
+  [table]
+  [tr]
+  [th]
+  [td]
+
+  Advanced:
+  [google]
+  [wikipedia]
+
@@ -0,0 +1,420 @@
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+#
+# Author:        Pau Sanchez (contact@pausanchez.com)
+# Version:       v1.0
+# Last Modified: 2010/09/15
+# 
+# For the latest version check out:
+#   http://www.codigomanso.com/en/projects
+# 
+# My blog:
+#   http://www.codigomanso.com/en/  - English Version
+#   http://www.codigomanso.com/es/  - Spanish Version
+#
+
+from bbcodeparser import bbcodeparser
+from bbcodebuilder import bbcodebuilder
+
+import random
+import unittest
+
+class BBCodeTests(unittest.TestCase):
+  def setUp (self):
+    self.bbcode = bbcodeparser()
+    return
+
+  def testConstructor (self):
+    self.assertEqual (bbcodeparser ('whatever').html(), 'whatever')
+    self.assertEqual (bbcodeparser ('[b]bold[/b]').html(), '<b>bold</b>')
+    self.assertEqual (str (bbcodeparser ('[b]bold[/b]')), '[b]bold[/b]')
+    return
+
+  def testBold (self):
+    self.assertEqual (self.bbcode.parse ('whatever').html(), 'whatever')
+    self.assertEqual (self.bbcode.parse ('[b]bold[/b]').html(), '<b>bold</b>')
+    self.assertEqual (self.bbcode.parse ('[B]bold[/b]').html(), '<b>bold</b>')
+    self.assertEqual (self.bbcode.parse ('this is [B]bold[/B]').html(), 'this is <b>bold</b>')
+    return
+
+  def testItalic (self):
+    self.assertEqual (self.bbcode.parse ('[i]italic[/i]').html(), '<i>italic</i>')
+    return
+
+  def testUnderline (self):
+    self.assertEqual (self.bbcode.parse ('[u]italic[/u]').html(), '<u>italic</u>')
+    return
+
+  def testURLs (self):
+    self.assertEqual (
+      self.bbcode.parse ('[url]http://www.google.com[/url]').html(),
+      '<a href="http://www.google.com">http://www.google.com</a>'
+    )
+    self.assertEqual (
+      self.bbcode.parse ('[url=http://www.google.com]Google[/url]').html(),
+      '<a href="http://www.google.com">Google</a>'
+    )
+    self.assertEqual (
+      self.bbcode.parse ('[url="http://www.google.com"]Google[/url]').html(),
+      '<a href="http://www.google.com">Google</a>'
+    )
+    self.assertEqual (
+      self.bbcode.parse ('[url="http://www.google.com" title="Search Engine"]Google[/url]').html(),
+      '<a href="http://www.google.com" title="Search Engine">Google</a>'
+    )
+    self.assertEqual (
+      self.bbcode.parse ('[url link="http://www.google.com"]Google[/url]').html(),
+      '<a href="http://www.google.com">Google</a>'
+    )
+    return
+
+  def testPTag (self):
+    self.assertEqual (
+      self.bbcode.parse ('[p color=#0000ff]blue[/p]').html(),
+      u'<p style="color: #0000ff;">blue</p>'
+    )
+    self.assertEqual (
+      self.bbcode.parse ('[p size=12]12pt font[/p]').html(),
+      u'<p style="font-size: 12pt;">12pt font</p>'
+    )
+
+    self.assertEqual (
+      self.bbcode.parse ('[p font=arial]arial[/p]').html(),
+      u'<p style="font-family: arial;">arial</p>'
+    )
+
+    self.assertEqual (
+      self.bbcode.parse ('[p font=arial color=blue size=14]blue 14pt arial').html(),
+      u'<p style="color: blue; font-size: 14pt; font-family: arial;">blue 14pt arial</p>' 
+    )
+
+    self.assertEqual (
+      self.bbcode.parse ('[p class=whatever]text[/p]').html(),
+      u'<p>text</p>' 
+    )
+    return
+
+  def testColorTag (self):
+    self.assertEqual (
+      self.bbcode.parse ('[color=#0000ff]blue[/color]').html(),
+      u'<span style="color: #0000ff;">blue</span>'
+    )
+    return
+
+  def testSizeTag (self):
+    self.assertEqual (
+      self.bbcode.parse ('[size=12]12pt font[/size]').html(),
+      u'<span style="font-size: 12pt;">12pt font</span>'
+    )
+    return
+
+  def testEmail(self):
+    self.assertEqual (
+      self.bbcode.parse ('[email]asdf@asdf.com[/email]').html(),
+      u'<a href="mailto:asdf@asdf.com">asdf@asdf.com</a>'
+    )
+
+    self.assertEqual (
+      self.bbcode.parse ('[email=john@smith.com]John Smith[/email]').html(),
+      u'<a href="mailto:john@smith.com">John Smith</a>'
+    )
+    return
+
+  def testImgTag (self):
+    self.assertEqual (
+      self.bbcode.parse ('[img]http://www.codigomanso.com/image.jpg[/img]').html(),
+      u'<img src="http://www.codigomanso.com/image.jpg" />'
+    )
+
+    self.assertEqual (
+      self.bbcode.parse ('[img="This is the ALT of the image"]http://www.codigomanso.com/image.jpg[/img]').html(),
+      u'<img alt="This is the ALT of the image" src="http://www.codigomanso.com/image.jpg" />'
+    )
+
+    self.assertEqual (
+      self.bbcode.parse ('[img=320x200]http://www.codigomanso.com/image.jpg[/img]').html(),
+      u'<img height="200" src="http://www.codigomanso.com/image.jpg" width="320" />'
+    )
+
+    self.assertEqual (
+      self.bbcode.parse ('[img=320x200 title="Image Test"]http://www.codigomanso.com/image.jpg[/img]').html(),
+      u'<img height="200" src="http://www.codigomanso.com/image.jpg" title="Image Test" width="320" />'
+    )
+
+    self.assertEqual (
+      self.bbcode.parse ('[img="whatever" width=320 height="212" title="Image Test"]http://www.codigomanso.com/image.jpg[/img]').html(),
+      u'<img alt="whatever" height="212" src="http://www.codigomanso.com/image.jpg" title="Image Test" width="320" />'
+    )
+    return
+
+  def testGoogleURL (self):
+    self.assertEqual (
+      self.bbcode.parse ('[google]asdf[/google]').html(),
+      u'<a href="http://www.google.com/search?q=asdf">asdf</a>'
+    )
+    self.assertEqual (
+      self.bbcode.parse ('[google]Tom Hanks[/google]').html(),
+      u'<a href="http://www.google.com/search?q=Tom+Hanks">Tom Hanks</a>'
+    )
+    return
+    
+  def testWikipediaURL (self):
+    self.assertEqual (
+      self.bbcode.parse ('[wikipedia]Tom Hanks[/wikipedia]').html(),
+      u'<a href="http://www.wikipedia.org/wiki/Tom_Hanks">Tom Hanks</a>'
+    )
+
+    self.assertEqual (
+      self.bbcode.parse ('[wikipedia language=en]Tom Hanks[/wikipedia]').html(),
+      u'<a href="http://en.wikipedia.org/wiki/Tom_Hanks">Tom Hanks</a>'
+    )
+    
+    self.assertEqual (
+      self.bbcode.parse ('[wikipedia lang=es]Tom Hanks[/wikipedia]').html(),
+      u'<a href="http://es.wikipedia.org/wiki/Tom_Hanks">Tom Hanks</a>'
+    )
+    
+    self.assertEqual (
+      self.bbcode.parse ('[wikipedia=es]Tom Hanks[/wikipedia]').html(),
+      u'<a href="http://es.wikipedia.org/wiki/Tom_Hanks">Tom Hanks</a>'
+    )
+    return
+    
+  def testListTags (self):
+    self.assertEqual (
+      self.bbcode.parse ('[ul][li]item 1[/li][li]item 2[/li][/ul]').html(),
+      u'<ul><li>item 1</li><li>item 2</li></ul>'
+    )
+    
+    self.assertEqual (
+      self.bbcode.parse ('[ol][li]item 1[/li][li]item 2[/li][/ol]').html(),
+      u'<ol><li>item 1</li><li>item 2</li></ol>'
+    )
+
+    self.assertEqual (
+      self.bbcode.parse ('[list][li]item 1[/li][li]item 2[/li][/list]').html(),
+      u'<ul><li>item 1</li><li>item 2</li></ul>'
+    )
+
+    self.assertEqual (
+      self.bbcode.parse ('[list][*]item 1[*]item 2[/list]').html(),
+      u'<ul><li>item 1</li><li>item 2</li></ul>'
+    )
+
+    self.assertEqual (
+      self.bbcode.parse ('[list=1][li]item 1[/li][li]item 2[/li][/list]').html(),
+      u'<ol type="1"><li>item 1</li><li>item 2</li></ol>'
+    )
+    return
+
+  def testInvalidCode (self):
+    self.assertEqual (self.bbcode.parse ('[invalid]valid text[/invalid]').html(), 'valid text')
+    self.assertEqual (
+      self.bbcode.parse ('[b]bold and [i]italics[/b]').html(),
+      '<b>bold and <i>italics</i></b>'
+    )
+    self.assertEqual (
+      self.bbcode.parse ('[/b]invalid[/b][/p]').html(),
+      'invalid'
+    )
+    self.assertEqual (
+      self.bbcode.parse ('[p][b]bold').html(),
+      '<p><b>bold</b></p>'
+    )
+    self.assertEqual (
+      self.bbcode.parse ('[p][b]a <b>').html(),
+      '<p><b>a &lt;b&gt;</b></p>'
+    )
+
+    self.assertEqual (
+      self.bbcode.parse ('[ol][li]item 1[li]item 2[/li][/ol]').html(),
+      u'<ol><li>item 1</li><li>item 2</li></ol>'
+    )
+
+    self.assertEqual (
+      self.bbcode.parse ('[b]\[b\] stands for [b]bold[/b]').html(),
+      u'<b>[b] stands for </b><b>bold</b>'
+    )
+    return
+
+  def testEscapedBrackets (self):
+    self.assertEqual (
+      self.bbcode.parse ('\[b\]not bold\[/b\]').html(),
+      u'[b]not bold[/b]'
+    )
+
+    self.assertEqual (
+      self.bbcode.parse ('[b]\[b\] stands for bold[/b]').html(),
+      u'<b>[b] stands for bold</b>'
+    )
+
+    self.assertEqual (
+      self.bbcode.parse ('\[b\][b]stands for bold[/b]').html(),
+      u'[b]<b>stands for bold</b>'
+    )
+
+    self.assertEqual (
+      self.bbcode.parse ('\[b\][b]stands for bold[/b] just like <b> in HTML').html(),
+      u'[b]<b>stands for bold</b> just like &lt;b&gt; in HTML'
+    )
+
+  def testBigExample (self):
+    inputText = """check this out
+
+    [h1 class=circle]heading[/h1]
+
+    [p size=14 color=blue font="verdana, Times New Roman"]This is [b] bold [/b] and this [i]italic[/i] and this is [color=red]red[/color] and this is [color="red"]also red[/color].
+    [/p]
+
+    fix [b][i]bold [font=verdana][size=12]and[/size][/font] italic[/b]
+    [img]http://www.codigomanso.com/b.jpg[/img]
+    [url]http://www.codigomanso.com/[/url]
+    [url=http://www.codigomanso.com/]Codigo Manso[/url]
+    [uRl link=http://www.codigomanso.com title="Codigo Manso Blog"]Codigo Manso[/url]
+
+    [ul]
+     [Li]item 1[/Li]
+     [li]item 2[/LI]
+    [/UL]
+
+    [list=1 ]
+     [*]item 1
+     [*]item 2
+    [/list]
+
+    [table class="big"]
+      [tr]
+        [th]big[/th]
+      [/tr]
+    [/table]
+    [invalid class="extra"]whatever[/invalid]"""
+
+    out = self.bbcode.parse (inputText).html(allowClassAttr = True)
+    self.assertEquals (out, '''check this out
+
+    <h1 class="circle">heading</h1>
+
+    <p style="color: blue; font-size: 14pt; font-family: verdana, Times New Roman;">This is <b> bold </b> and this <i>italic</i> and this is <span style="color: red;">red</span> and this is <span style="color: red;">also red</span>.
+    </p>
+
+    fix <b><i>bold <span style="font-family: verdana;"><span style="font-size: 12pt;">and</span></span> italic</i></b>
+    <img src="http://www.codigomanso.com/b.jpg" />
+    <a href="http://www.codigomanso.com/">http://www.codigomanso.com/</a>
+    <a href="http://www.codigomanso.com/">Codigo Manso</a>
+    <a href="http://www.codigomanso.com" title="Codigo Manso Blog">Codigo Manso</a>
+
+    <ul>
+     <li>item 1</li>
+     <li>item 2</li>
+    </ul>
+
+    <ol type="1">
+     <li>item 1
+     </li><li>item 2
+    </li></ol>
+
+    <table class="big">
+      <tr>
+        <th>big</th>
+      </tr>
+    </table>
+    whatever''')
+
+
+  def testBBCodeDumper (self):
+    self.assertEquals (
+      self.bbcode.parse ('[b]bold[/b]').bbcode(),
+      '[b]bold[/b]'
+    )
+
+    self.assertEquals (
+      self.bbcode.parse ('[color=red]text in red[/color]').bbcode(),
+      '[color=red]text in red[/color]'
+    )
+    self.assertEquals (
+      self.bbcode.parse ('[p][color=red]text in red').bbcode(),
+      '[p][color=red]text in red[/color][/p]'
+    )
+
+    self.assertEquals (
+      self.bbcode.parse ('This [b][i]code[/b] will be fixed[/invalid]').bbcode(),
+      'This [b][i]code[/i][/b] will be fixed'
+    )
+
+    self.assertEquals (
+      self.bbcode.parse ('\[[url]http://www.codigomanso.com/en[/url]\]').bbcode(),
+      "\[[url]http://www.codigomanso.com/en[/url]\]"
+    )
+
+  def performanceTest(self):
+    '''
+    This test checks the performance of parse and html operations
+
+    To run this test type:
+      > python test.py BBCodeTests.performanceTest
+    '''
+    inputText = """check this out
+
+    [h1 class=circle]heading[/h1]
+
+    [p size=14 color=blue font="verdana, Times New Roman"]This is [b] bold [/b] and this [i]italic[/i] and this is [color=red]red[/color] and this is [color="red"]also red[/color].
+    [/p]
+
+    fix [b][i]bold [font=verdana][size=12]and[/size][/font] italic[/b]
+    [img]http://www.codigomanso.com/b.jpg[/img]
+    [url]http://www.codigomanso.com/[/url]
+    [url=http://www.codigomanso.com/]Codigo Manso[/url]
+    [uRl link=http://www.codigomanso.com title="Codigo Manso Blog"]Codigo Manso[/url]
+
+    [ul]
+     [Li]item 1[/Li]
+     [li]item 2[/LI]
+    [/UL]
+
+    [list=1 ]
+     [*]item 1
+     [*]item 2
+    [/list]
+
+    [table class="big"]
+      [tr]
+        [th]big[/th]
+      [/tr]
+    [/table]
+    [invalid class="extra"]whatever[/invalid]"""
+
+    import time
+    start = time.time()
+
+    for i in range(0, 12):
+      inputText += inputText
+
+    print "len(inputText) = %.2f MB  (took %.2f seconds)" % (len(inputText)/(1024.0*1024.0), time.time() - start)
+    
+    bbcode = bbcodeparser()
+    start = time.time()
+    bbcode.parse (inputText)
+    total = (time.time() - start)
+    print "time (bbcode.parse()) = %f" % total
+    print "  >> %.2f chars/second" % (len(inputText) / total)
+
+    start = time.time()
+    bbcode.html(doDeepCopy = False)
+    total = (time.time() - start)
+    print "time (bbcode.html()) = %f" % total
+    print "  >> %.2f chars/second" % (len(inputText) / total)
+    return
+    
+  def testCodeBuilder (self):
+    bbcode = bbcodebuilder ()
+    self.assertEquals (bbcode.b ('bold'), u'[b]bold[/b]')
+    self.assertEquals (bbcode.color ('this goes in red', 'red'), u'[color=red]this goes in red[/color]')
+    self.assertEquals (bbcode.url ('Google', 'http://www.google.com'), u'[url=http://www.google.com]Google[/url]')
+    self.assertEquals (bbcode.alist('item 1', 'item 2'), u"[list=a]\n  [*]item 1\n  [*]item 2\n[/list]")
+    return
+
+if __name__ == '__main__':
+    unittest.main()
+
+
+
@@ -225,7 +225,7 @@ class Story:
    def getMetadata(self, key, removeallentities=False, doreplacements=True):
        value = None
        if self.isList(key):
-            value = ', '.join(self.getList(key))
+            value = ', '.join(self.getList(key, removeallentities))
        elif self.metadata.has_key(key):
            value = self.metadata[key]
            if value:
@@ -310,21 +310,34 @@ class Story:

        return retlist

-    def getLists(self):
+    def getLists(self, removeallentities=False):
        lsts = {}
        for ln in self.listables.keys():
-            lsts[ln] = self.getList(ln)
+            lsts[ln] = self.getList(ln, removeallentities)
        return lsts

    def isList(self,listname):
        return self.listables.has_key(listname)
    
-    def addChapter(self, title, html):
+    def addChapter(self, title, html, configurable=None):
+        if configurable and \
+                configurable.getConfig('strip_chapter_numbers') and \
+                configurable.getConfig('chapter_title_strip_pattern'):
+            title = re.sub(configurable.getConfig('chapter_title_strip_pattern'),"",title)
        self.chapters.append( (title,html) )

-    def getChapters(self):
+    def getChapters(self, configurable=None):
        "Chapters will be tuples of (title,html)"
-        return self.chapters
+        retval = []
+        if configurable and \
+                configurable.getConfig('add_chapter_numbers') and \
+                configurable.getConfig('chapter_title_add_pattern'):
+            for index, (title,html) in enumerate(self.chapters):
+                retval.append( (string.Template(configurable.getConfig('chapter_title_add_pattern')).substitute({'index':index+1,'title':title}),html) ) 
+        else:
+            retval = self.chapters
+            
+        return retval

    def formatFileName(self,template,allowunsafefilename=True):
        values = origvalues = self.getAllMetadata()
@@ -50,6 +50,7 @@ class BaseStoryWriter(Configurable):
            'genre',
            'language',
            'characters',
+            'ships',
            'series',
            'status',
            'datePublished',
@@ -81,6 +82,7 @@ class BaseStoryWriter(Configurable):
            'status':'Status',
            'series':'Series',
            'characters':'Characters',
+            'ships':'Relationships',
            'datePublished':'Published',
            'dateUpdated':'Updated',
            'dateCreated':'Packaged',
@@ -104,12 +106,19 @@ class BaseStoryWriter(Configurable):
            }
        self.story.setMetadata('formatname',self.getFormatName())
        self.story.setMetadata('formatext',self.getFormatExt())
-        
-        for tag in self.getConfigList("extratags"):
-            self.story.addToList("extratags",tag)

-    def getMetadata(self,key):
-        return stripHTML(self.story.getMetadata(key))
+        ## Look for config parameter, split and add each to metadata field.
+        for (config,metadata) in [("extratags","extratags"),
+                                  ("extracategories","category"),
+                                  ("extragenres","genre"),
+                                  ("extracharacters","characters"),
+                                  ("extraships","ships"),
+                                  ("extrawarnings","warnings")]:
+            for val in self.getConfigList(config):
+                self.story.addToList(metadata,val)
+
+    def getMetadata(self,key, removeallentities=False):
+        return stripHTML(self.story.getMetadata(key, removeallentities))

    def getOutputFileName(self):
        if self.getConfig('zip_output'):
@@ -175,10 +184,10 @@ class BaseStoryWriter(Configurable):
        names as Story.metadata, but ENTRY should use index and chapter.
        """
        # Only do TOC if there's more than one chapter and it's configured.
-        if len(self.story.getChapters()) > 1 and self.getConfig("include_tocpage") and not self.metaonly :
+        if len(self.story.getChapters(self)) > 1 and self.getConfig("include_tocpage") and not self.metaonly :
            self._write(out,START.substitute(self.story.getAllMetadata()))

-            for index, (title,html) in enumerate(self.story.getChapters()):
+            for index, (title,html) in enumerate(self.story.getChapters(self)):
                if html:
                    self._write(out,ENTRY.substitute({'chapter':title, 'index':"%04d"%(index+1)}))

@@ -252,7 +261,7 @@ class BaseStoryWriter(Configurable):
        if close:
            outstream.close()

-    def getTags(self):
+    def getTags(self, removeallentities=False):
        # set to avoid duplicates subject tags.
        subjectset = set()
        
@@ -265,10 +274,10 @@ class BaseStoryWriter(Configurable):
            if entry in self.getConfigList("include_subject_tags") and \
                    entry not in self.story.getLists() and \
                    self.story.getMetadata(entry):
-                subjectset.add(self.getMetadata(entry))
+                subjectset.add(self.getMetadata(entry, removeallentities))
                
        # listables all go into dc:subject tags, but only if they are configured.
-        for (name,lst) in self.story.getLists().iteritems():
+        for (name,lst) in self.story.getLists(removeallentities).iteritems():
            if name in self.getConfigList("include_subject_tags"):
                for tag in lst:
                    subjectset.add(tag)
@@ -441,7 +441,7 @@ div { margin: 0pt; padding: 0pt; }
        if self.getConfig("include_titlepage"):
            items.append(("title_page","OEBPS/title_page.xhtml","application/xhtml+xml","Title Page"))
            itemrefs.append("title_page")
-        if len(self.story.getChapters()) > 1 and self.getConfig("include_tocpage") and not self.metaonly :
+        if len(self.story.getChapters(self)) > 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")

@@ -449,7 +449,7 @@ div { margin: 0pt; padding: 0pt; }
            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()):
+        for index, (title,html) in enumerate(self.story.getChapters(self)):
            if html:
                i=index+1
                items.append(("file%04d"%i,
@@ -587,7 +587,7 @@ div { margin: 0pt; padding: 0pt; }
            outputepub.writestr("OEBPS/log_page.xhtml",logpageIO.getvalue())
        logpageIO.close()
        
-        for index, (title,html) in enumerate(self.story.getChapters()):
+        for index, (title,html) in enumerate(self.story.getChapters(self)):
            if html:
                logging.debug('Writing chapter text for: %s' % title)
                fullhtml = self.EPUB_CHAPTER_START.substitute({'chapter':title, 'index':index+1}) + html + self.EPUB_CHAPTER_END.substitute({'chapter':title, 'index':index+1})
@@ -94,7 +94,7 @@ ${output_css}
                          self.HTML_TOC_ENTRY,
                          self.HTML_TOC_PAGE_END)

-        for index, (title,html) in enumerate(self.story.getChapters()):
+        for index, (title,html) in enumerate(self.story.getChapters(self)):
            if html:
                logging.debug('Writing chapter text for: %s' % title)
                self._write(out,self.HTML_CHAPTER_START.substitute({'chapter':title, 'index':"%04d"%(index+1)}))
@@ -169,7 +169,7 @@ ${value}<br />
        #     files.append(tocpageIO.getvalue())
        # tocpageIO.close()

-        for index, (title,html) in enumerate(self.story.getChapters()):
+        for index, (title,html) in enumerate(self.story.getChapters(self)):
            if html:
                logging.debug('Writing chapter text for: %s' % title)
                fullhtml = self.MOBI_CHAPTER_START.substitute({'chapter':title, 'index':index+1}) + html + self.MOBI_CHAPTER_END.substitute({'chapter':title, 'index':index+1})
@@ -133,7 +133,7 @@ End file.
        
        self._write(out,self.lineends(self.wraplines(towrap)))

-        for index, (title,html) in enumerate(self.story.getChapters()):
+        for index, (title,html) in enumerate(self.story.getChapters(self)):
            if html:
                logging.debug('Writing chapter text for: %s' % title)
                self._write(out,self.lineends(self.wraplines(removeAllEntities(self.TEXT_CHAPTER_START.substitute({'chapter':title, 'index':index+1})))))
@@ -54,6 +54,18 @@
 	      much easier. </p>
 	  </div>
 	  <!-- put announcements here, h3 is a good title size. -->
+	  <h3>New Site / Features / Fixes</h3>
+	  <p>
+	    New site merlinfic.dtwins.co.uk, thanks Ida.
+	  </p>
+	  <p>
+	    New feature options strip_chapter_numbers and add_chapter_numbers can be turned on to
+	    normalize numbers in front of chapter titles.
+	  </p>
+	  <p>
+	    Fixed BBCode in fimfiction.net story summaries.  Also improved handling of html
+	    in story summaries.
+	  </p>
 	  <p>
 	    Questions?  Check out our 
 	    <a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownloaderFAQs">FAQs</a>.
@@ -62,7 +74,7 @@
 	    If you have any problems with this application, please
 	    report them in
 	    the <a href="http://groups.google.com/group/fanfic-downloader">FanFictionDownLoader Google Group</a>.  The
-	    <a href="http://4-4-21.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
+	    <a href="http://4-4-24.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
 	  </p>
 	  <div id='error'>
 	    {{ error_message }}
@@ -499,6 +511,36 @@
 	    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>
+	  <dt>merlinfic.dtwins.co.uk</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://merlinfic.dtwins.co.uk/viewstory.php?sid=1234">http://merlinfic.dtwins.co.uk/viewstory.php?sid=1234</a>
+	  </dd>
 	</dl>
 	<p>
 	  A few additional things to know, which will make your life substantially easier:
@@ -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:
@@ -43,6 +42,7 @@ category_label:Category
 genre_label:Genre
 language_label:Language
 characters_label:Characters
+ships_label:Relationships
 series_label:Series
 ## Completed/In-Progress
 status_label:Status
@@ -75,7 +75,7 @@ version_label:FFDL Version
 ## You can include extra text or HTML that will be included as-is in
 ## the title page. Eg: titlepage_entries: ...,<br />,summary,<br />,...
 ## All current formats already include title and author.
-titlepage_entries: series,category,genre,language,characters,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,numWords,site,description
+titlepage_entries: series,category,genre,language,characters,ships,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,numWords,site,description

 ## Try to collect series name and number of this story in series.
 ## Some sites (ab)use 'series' for reading lists and personal
@@ -101,11 +101,20 @@ include_tocpage: true

 ## entries to make epub subjects and calibre tags
 ## lastupdate creates two tags: "Last Update Year/Month: %Y/%m" and "Last Update: %Y/%m/%d"
-include_subject_tags: extratags, genre, category, characters, status
+include_subject_tags: extratags, genre, category, characters, ships, status

 ## extra tags (comma separated) to include, primarily for epub.
 extratags: FanFiction

+## extra categories, genres, characters, ships and warnings can be
+## configured.  Used primarily for sites that are dedicated to a genre
+## or 'ship and so don't included it for every story.
+#extracategories:
+#extragenres:
+#extracharacters:
+#extraships:
+#extrawarnings:
+
 ## number of seconds to sleep between calls to the story site.  May by
 ## useful if pulling large numbers of stories or if the site is slow.
 #slow_down_sleep_time:0.5
@@ -143,6 +152,45 @@ extratags: FanFiction
 # ${category} => Buffy:? [tT]he Vampire Slayer => BuffyCover
 # ${category} => Star Trek => StarTrekCover

+## If set false, the summary will have all html stripped.
+## Both this and include_images must be true to get images in the
+## summary.
+keep_summary_html:true
+
+## Don't like the numbers at the start of chapter titles on some
+## sites?  You can use strip_chapter_numbers to strip them off.  Just
+## want to make them all look the same?  Strip them off, then add them
+## back on with add_chapter_numbers.  Don't like the way it strips
+## numbers or adds them back?  See chapter_title_strip_pattern and
+## chapter_title_add_pattern.
+strip_chapter_numbers:false
+add_chapter_numbers:false
+
+## (Two versions of chapter_title_strip_pattern are shown below.  You
+## should only have one uncommented.)
+## This version will remove the leading number from:
+## "1." => ""
+## "1. The Beginning" => "The Beginning"
+## "1: Start" => "Start"
+## "2, Chapter the second" => "Chapter the second"
+## etc
+chapter_title_strip_pattern:^[0-9]+[\.: -]+
+
+## This version will strip all of the above *plus* remove 'Chapter 1':
+## "Chapter 1" => ""
+## "1. Chapter 1" => ""
+## "1. Chapter 1, Bob's First Clue" => "Bob's First Clue"
+## "Chapter 2 - Pirates Place" => "Pirates Place"
+## etc
+#chapter_title_strip_pattern:^([0-9]+[\.: -]+)?(Chapter *[0-9]+[\.:, -]*)?
+
+## Uses a python template substitution.  The ${index} is the 'chapter'
+## number and ${title} is the chapter title, after applying
+## chapter_title_strip_pattern.  Those are the only variables available.
+## "The Beginning" => "1. The Beginning" 
+chapter_title_add_pattern:${index}. ${title}
+
+
 ## Each output format has a section that overrides [defaults]
 [html]

@@ -215,10 +263,12 @@ 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; }
@@ -245,11 +295,6 @@ output_css:
 ## stories.  Images will be converted to jpg for size if possible.
 #include_images:false

-## If not set, the summary will have all html stripped for safety.
-## Both this and include_images must be true to get images in the
-## summary.
-#keep_summary_html:false
-
 ## If set, the first image found will be made the cover image.  If
 ## keep_summary_html is true, any images in summary will be before any
 ## in chapters.
@@ -302,6 +347,11 @@ nook_img_fix:true
 ## URLs like: http://test1.com?sid=12345
 [test1.com]
 extratags: FanFiction,Testing
+extracategories:Fafner
+extragenres:Romance,Fluff
+extracharacters:Reginald Smythe-Smythe,Mokona
+extraships:Smythe-Smythe/Mokona
+extrawarnings:Extreme Bogosity

 ## If necessary, you can define [<site>:<format>] sections to
 ## customize the formats differently for the same site.  Overrides
@@ -328,6 +378,11 @@ extratags: FanFiction,Testing,HTML
 #is_adult:true

 [ashwinder.sycophanthex.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+extracharacters:Severus Snape,Hermione Granger
+extraships:Severus Snape/Hermione Granger
+
 ## 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
@@ -336,6 +391,9 @@ extratags: FanFiction,Testing,HTML
 #password:yourpassword

 [castlefans.org]
+## Site dedicated to these categories/characters/ships
+extracategories:Castle
+
 ## 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
@@ -359,6 +417,11 @@ extratags: FanFiction,Testing,HTML
 cover_exclusion_regexp:/images/.*?ribbon.gif

 [dark-solace.org]
+## Site dedicated to these categories/characters/ships
+extracategories:Buffy: The Vampire Slayer
+extracharacters:Buffy, Spike
+extraships:Spike/Buffy
+
 ## 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
@@ -367,6 +430,11 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 #password:yourpassword

 [dramione.org]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+extracharacters:Draco Malfoy,Hermione Granger
+extraships:Draco Malfoy/Hermione Granger
+
 ## 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
@@ -380,6 +448,9 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 #is_adult:true

 [erosnsappho.sycophanthex.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 ## 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.
@@ -390,6 +461,9 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 cover_exclusion_regexp:/images/.*?ribbon.gif

 [fanfiction.mugglenet.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 ## 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
@@ -403,6 +477,10 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 #is_adult:true

 [fanfiction.portkey.org]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+extraships:Harry Potter/Hermione Granger
+
 ## 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.
@@ -425,6 +503,10 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 #password:yourpassword

 [grangerenchanted.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+extracharacters:Hermione Granger
+
 ## 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
@@ -438,26 +520,67 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 #is_adult:true

 [hlfiction.net]
+## Site dedicated to these categories/characters/ships
+extracategories:Highlander
+
+[ksarchive.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Star Trek
+extracharacters:Kirk,Spock
+extraships:Kirk/Spock

 [lumos.sycophanthex.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 ## 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

+[merlinfic.dtwins.co.uk]
+## Site dedicated to these categories/characters/ships
+extracategories:Merlin
+
+## 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
+
 [national-library.net]
+## Site dedicated to these categories/characters/ships
+extracategories:West Wing

 [ncisfic.com]
+## Site dedicated to these categories/characters/ships
+extracategories:NCIS

 [nfacommunity.com]
+## Site dedicated to these categories/characters/ships
+extracategories:NCIS
+
 ## 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

 [nha.magical-worlds.us]
+## Site dedicated to these categories/characters/ships
+extracategories:Buffy: The Vampire Slayer
+extracharacters:Willow

 [occlumency.sycophanthex.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+extracharacters:Severus Snape
+
 ## 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
@@ -466,6 +589,9 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 #password:yourpassword

 [onedirectionfanfiction.com]
+## Site dedicated to these categories/characters/ships
+extracategories:One Direction
+
 ## 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
@@ -479,18 +605,28 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 #is_adult:true

 [ponyfictionarchive.net]
+## Site dedicated to these categories/characters/ships
+extracategories:My Little Pony: Friendship is Magic
+
 ## 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

 [pretendercentre.com]
+## Site dedicated to these categories/characters/ships
+extracategories:The Pretender
+
 ## 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

 [samdean.archive.nu]
+## Site dedicated to these categories/characters/ships
+extracategories:Supernatural
+extracharacters:Sam,Dean
+extraships:Sam/Dean

 [sg1-heliopolis.com]
 ## Some sites do not require a login, but do require the user to
@@ -499,6 +635,8 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 #is_adult:true

 [stargate-atlantis.org]
+## Site dedicated to these categories/characters/ships
+extracategories:Stargate: Atlantis

 [svufiction.com]
 ## Some sites require login (or login for some rated stories) The
@@ -514,6 +652,10 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 #is_adult:true

 [thehexfiles.net]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+extracharacters:Draco Malfoy,Harry Potter
+extraships:Harry Potter/Draco Malfoy

 [themasque.net]
 ## Some sites require login (or login for some rated stories) The
@@ -529,6 +671,9 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 #is_adult:true

 [thequidditchpitch.org]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 ## 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
@@ -542,14 +687,40 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 #is_adult:true

 [www.adastrafanfic.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Star Trek
+
 ## 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.dracoandginny.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+extracharacters:Draco Malfoy,Ginny Weasley
+extraships:Draco Malfoy/Ginny Weasley
+
+## 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]
+## Site dedicated to these categories/characters/ships
+extracategories:Stargate: SG-1

 [www.checkmated.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 ## 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
@@ -564,6 +735,10 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 #is_adult:true

 [www.dokuga.com]
+## Site dedicated to these categories/characters/ships
+extracategories:InuYasha
+extracharacters:Sesshoumaru,Kagome
+extraships:Sesshoumaru/Kagome

 [www.fanfiction.net]
 ## fanfiction.net's 'cover' images are really just tiny thumbnails.
@@ -581,6 +756,9 @@ never_make_cover: true
 [www.ficbook.net]

 [www.fictionalley.org]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 ## 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.
@@ -599,6 +777,9 @@ extratags:
 #password:yourpassword

 [www.fimfiction.net]
+## Site dedicated to these categories/characters/ships
+extracategories:My Little Pony: Friendship is Magic
+
 ## 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.
@@ -610,20 +791,33 @@ extratags:
 #fail_on_password: false

 [www.harrypotterfanfiction.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 ## 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.hpfandom.net]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 ## 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.hpfanficarchive.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter

 [www.ik-eternal.net]
+## Site dedicated to these categories/characters/ships
+extracategories:InuYasha
+extracharacters:InuYasha,Kagome
+extraships:InuYasha/Kagome
+
 ## 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
@@ -637,6 +831,9 @@ extratags:
 #is_adult:true

 [www.libraryofmoria.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Lord of the Rings
+
 ## 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.
@@ -645,6 +842,9 @@ extratags:
 [www.mediaminer.org]

 [www.midnightwhispers.ca]
+## Site dedicated to these categories/characters/ships
+extracategories:Queer as Folk
+
 ## 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.
@@ -655,8 +855,14 @@ extratags:
 cover_exclusion_regexp:/stories/999/images/.*?_trophy.png

 [www.ncisfiction.com]
+## Site dedicated to these categories/characters/ships
+extracategories:NCIS

 [www.phoenixsong.net]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+extraships:Harry Potter/Ginny Weasley
+
 ## 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
@@ -665,16 +871,43 @@ cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
 #password:yourpassword

 [www.potionsandsnitches.net]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter

 [www.prisonbreakfic.net]
+## Site dedicated to these categories/characters/ships
+extracategories:Prison Break
+
+[www.scarvesandcoffee.net]
+## Site dedicated to these categories/characters/ships
+extracategories:Glee
+extracharacters:Kurt Hummel,Blaine Anderson
+
+## 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]
+## Site dedicated to these categories/characters/ships
+extracategories:Supernatural
+
+## 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]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+extracharacters:Harry Potter,Ginny Weasley
+extraships:Harry Potter/Ginny Weasley

 [www.squidge.org/peja]
 # www.squidge.org/peja calls it Fandom <shrug>
 category_label:Fandom
 # Remove numWords -- www.squidge.org/peja word counts are inaccurate
-titlepage_entries: series,category,genre,language,characters,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,description
+titlepage_entries: series,category,genre,language,characters,ships,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,description

 [www.squidge.org/peja:txt]
 ## Add URLs since there aren't links.
@@ -682,6 +915,16 @@ titlepage_entries: series,category,genre,language,characters,status,datePublishe
 titlepage_entries: series,category,genre,language,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,storyUrl, authorUrl, description

 [www.storiesofarda.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Lord of the Rings
+
+[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
@@ -713,8 +956,13 @@ collect_series: false
 #password:yourpassword

 [www.twilightarchives.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Twilight

 [www.twilighted.net]
+## Site dedicated to these categories/characters/ships
+extracategories:Twilight
+
 ## 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
@@ -726,6 +974,9 @@ collect_series: false
 collect_series: false

 [www.twiwrite.net]
+## Site dedicated to these categories/characters/ships
+extracategories:Twilight
+
 ## 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
@@ -737,6 +988,11 @@ collect_series: false
 collect_series: false

 [www.walkingtheplank.org]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+extracharacters:Severus Snape,Harry Potter
+extraships:Severus Snape/Harry Potter
+
 ## 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.
@@ -757,7 +1013,15 @@ collect_series: false
 ## personal.ini, not defaults.ini.
 #is_adult:true

+[www.wolverineandrogue.com]
+## Site dedicated to these categories/characters/ships
+extracategories:X-Men Movie
+extracharacters:Wolverine,Rogue
+
 [www.wraithbait.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Stargate: Atlantis
+
 ## 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.
@@ -1,14 +1,25 @@
 ## This is an example of what your personal configuration might look
-## like.
+## like.  Uncomment options by removing the '#' in front of them.

 [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.  Uncomment by removing '#' in front of is_adult.
 #is_adult:true

-## include images from img tags in the body and summary of
-## stories.  Images will be converted to jpg for size if possible.
+## Don't like the numbers at the start of chapter titles on some
+## sites?  You can use strip_chapter_numbers to strip them off.  Just
+## want to make them all look the same?  Strip them off, then add them
+## back on with add_chapter_numbers.  Don't like the way it strips
+## numbers or adds them back?  See chapter_title_strip_pattern and
+## chapter_title_add_pattern.
+#strip_chapter_numbers:true
+#add_chapter_numbers:true
+
+[epub]
+## include images from img tags in the body and summary of stories.
+## Images will be converted to jpg for size if possible.  Images work
+## in epub format only.  To get mobi or other format with images,
+## download as epub and use Calibre to convert.
 #include_images:true

 ## If not set, the summary will have all html stripped for safety.
@@ -29,18 +40,10 @@
 ## space.
 #grayscale_images: false

-## Try to collect series name and number of this story in series.
-## Some sites (ab)use 'series' for reading lists and personal
-## collections.  This lets us turn it on and off by site without
-## keeping a lengthy titlepage_entries per site and prevents it
-## updating in the plugin.
-## Turn off in [defaults] or [overrides] to prevent all sites from
-## updating series column.
-## default is true
-#collect_series: false

 ## Most common, I expect will be using this to save username/passwords
-## for different sites.
+## for different sites.  Here are a few examples.
+
 [www.twilighted.net]
 #username:YourPenname
 #password:YourPassword
@@ -1,3 +1,21 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2011 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+# Other code contributed by Pau Sanchez(bbcodeutils).
+
 To use, do:

 python downloader.py [-f (epub|html|txt)] <url>
Author	SHA1	Message	Date
Jim Miller	c06a4ee9de	Integrate merlinfic.dtwins.co.uk, bump versions.	2012-09-14 12:11:41 -05:00
Ida	b66af0ef73	New adapter for merlinfic.dtwins.co.uk	2012-09-13 00:11:12 -04:00
Jim Miller	0ca71a6455	Add a BBCode lib for summaries on fimfic(needed to mod for unicode), Default keep_summary_html:true to now, Changes to the AO3, ficbook.net, ficwad.com adapters for summary HTML. Add options to strip and add chapter numbers to chapter titles.	2012-09-12 18:03:30 -05:00
Jim Miller	ab521ac093	No images for non-epub forms, show that clearly in example.ini.	2012-09-10 22:53:30 -05:00
Jim Miller	a85266e908	Added tag FanFictionDownLoader-4.4.24 for changeset e651eeeb1715	2012-09-06 17:24:02 -05:00
Jim Miller	2b3826d69b	Added tag calibre-plugin-1.6.08 for changeset e651eeeb1715	2012-09-06 17:23:41 -05:00
Jim Miller	079a0f5906	Scroll custom columns config, bump versions.	2012-09-06 17:23:25 -05:00
Jim Miller	f31fcc3341	Add extracategories, etc, Relationships, another Mac fix, fix for & in tags.	2012-09-05 12:20:35 -05:00
Ida	7eb1685be1	Allows different skins for stories that require login	2012-08-28 19:46:50 -04:00
Jim Miller	30997053ef	Added tag calibre-plugin-1.6.07 for changeset 9bad71f4988c	2012-08-27 12:14:01 -05:00
Jim Miller	347eb69044	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.	2012-08-27 12:13:31 -05:00
Jim Miller	86329a1fe3	Added tag FanFictionDownLoader-4.4.23a for changeset d9c3c28e545c	2012-08-25 21:50:32 -05:00
Jim Miller	3bcc31a404	Added tag calibre-plugin-1.6.06 for changeset d9c3c28e545c	2012-08-25 21:50:12 -05:00
Jim Miller	5e7c28d2dc	Integrate new site, add adobe-text-layout to epub CSS for no nook hyphenation.	2012-08-25 21:49:36 -05:00
Ida	574981931f	New adapter for www.sinful-desire.org	2012-08-24 13:29:30 -04:00
Jim Miller	a54765cf86	Added tag FanFictionDownLoader-4.4.23 for changeset 4437edd5f6fc	2012-08-23 11:57:46 -05:00
Jim Miller	7cd77c64d1	Added tag calibre-plugin-1.6.05 for changeset 4437edd5f6fc	2012-08-23 11:57:17 -05:00
Jim Miller	fd68b32111	Fix web site.	2012-08-23 11:57:07 -05:00
Jim Miller	eb969cfe2f	Integrate new sites.	2012-08-23 11:56:33 -05:00
Ida	337da79dbc	New adapters for www.wolverineandrogue.com/wrfa/ www.thepetulantpoetess.com www.scarvesandcoffee.net http://www.dracoandginny.com	2012-08-22 22:23:05 -04:00
Jim Miller	3176b4944b	Added tag FanFictionDownLoader-4.4.22a for changeset 7a2fb1721cc5	2012-08-18 11:18:35 -05:00
Jim Miller	a18c52e5a3	Added tag calibre-plugin-1.6.04 for changeset 7a2fb1721cc5	2012-08-18 11:18:19 -05:00
Jim Miller	1cfaff9d42	Workaround for poor HTML in summary(yourfanfictioncom), minor tweaks.	2012-08-18 11:18:04 -05:00
Jim Miller	793c65495f	Fix checkbox for Flesch-Kincaid Grade Level.	2012-08-07 12:45:53 -05:00
Jim Miller	efb908d438	Added tag FanFictionDownLoader-4.4.22 for changeset 09000ad9e797	2012-08-06 21:24:09 -05:00
Jim Miller	6ea015b111	Added tag calibre-plugin-1.6.03 for changeset 09000ad9e797	2012-08-06 21:23:54 -05:00