Yet more fixes for poor parsing of numeric entities--this time, my poor parsing.

Added tag FanFictionDownLoader-4.4.8 for changeset 8fc7a6cc2d87
Bump Web/CLI version.
2026-09-15 11:36:30 +08:00 · 2012-04-25 21:52:56 -05:00 · 2012-04-22 10:10:08 -05:00 · 2012-04-22 10:09:44 -05:00 · 2012-04-22 09:55:58 -05:00 · 2012-04-22 09:55:39 -05:00
29 changed files with 1640 additions and 412 deletions
@@ -0,0 +1,78 @@
+<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01//EN">
+<html>
+  <head>
+    <link href="/css/index.css" rel="stylesheet" type="text/css">
+    <title>FanFictionDownLoader (fanfiction.net, fanficauthors, fictionalley, ficwad to epub and HTML)</title>
+    <meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
+    <script type="text/javascript">
+
+      var _gaq = _gaq || [];
+      _gaq.push(['_setAccount', 'UA-12136939-1']);
+      _gaq.push(['_trackPageview']);
+
+      (function() {
+      var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true;
+      ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js';
+      var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s);
+      })();
+
+    </script>
+  </head>
+  <body>
+    <div id='main'>
+      <h1>
+	<a href="/" style="text-decoration: none; color: black;">FanFictionDownLoader</a>
+      </h1>
+      
+      <script type="text/javascript"><!--
+                                        google_ad_client = "ca-pub-0320924304307555";
+                                        /* Standard */
+                                        google_ad_slot = "8974025478";
+                                        google_ad_width = 468;
+                                        google_ad_height = 60;
+                                        //-->
+      </script>
+      <script type="text/javascript"
+              src="http://pagead2.googlesyndication.com/pagead/show_ads.js">
+      </script>
+      <!--			<div id='yourfile'> -->
+      {{yourfile}}
+      <!--			</div> -->
+      
+      <div id='helpbox'>
+	{% for fic in fics %}
+	<p>
+  	  <a href="{{ fic.url }}" title="Link to original story"><span class="recent"><i>{{ fic.title }}</i></span></a>
+	      by <a href="{{ fic.authorUrl }}">{{ fic.author }}</a>  <b>Download Count:</b> {{ fic.count }} <br />
+	  <b>Word Count:</b> {{ fic.numWords }} <b>Chapter Count:</b> {{ fic.numChapters }}<br />
+	  {% if fic.category %} <b>Categories:</b> {{ fic.category }} <br /> {% endif %}
+	  {% if fic.genre %} <b>Genres:</b> {{ fic.genre }} <br /> {% endif %}
+	  {% if fic.language %} <b>Language:</b> {{ fic.language }} <br /> {% endif %}
+	  {% if fic.series %} <b>Series:</b> {{ fic.series }} <br /> {% endif %}
+	  {% if fic.characters %} <b>Characters:</b> {{ fic.characters }} <br /> {% endif %}
+	  {% if fic.status %} <b>Status:</b> {{ fic.status }} <br /> {% endif %}
+	  {% if fic.datePublished %} <b>Published:</b> {{ fic.datePublished }} <br /> {% endif %}
+	  {% if fic.dateUpdated %} <b>Last Updated:</b> {{ fic.dateUpdated }} <br /> {% endif %}
+	  {% if fic.dateCreated %} <b>Last Downloaded:</b> {{ fic.dateCreated }} <br /> {% endif %}
+	  {% if fic.rating %} <b>Rating:</b> {{ fic.rating }} <br /> {% endif %}
+	  {% if fic.warnings %} <b>Warnings:</b> {{ fic.warnings }} <br /> {% endif %}
+	  {% if fic.description %} <b>Summary:</b> {{ fic.description }} <br /> {% endif %}
+	</p>
+	{% endfor %}
+      </div>
+      
+      <script type="text/javascript"><!--
+                                        google_ad_client = "ca-pub-0320924304307555";
+                                        /* Standard */
+                                        google_ad_slot = "8974025478";
+                                        google_ad_width = 468;
+                                        google_ad_height = 60;
+                                        //-->
+      </script>
+      <script type="text/javascript"
+              src="http://pagead2.googlesyndication.com/pagead/show_ads.js">
+      </script>				
+      
+    </div>
+  </body>
+</html>
@@ -1,6 +1,6 @@
 # ffd-retief-hrd fanfictiondownloader
 application: fanfictiondownloader
-version: 4-4-2
+version: 4-4-8
 runtime: python27
 api_version: 1
 threadsafe: true
@@ -35,8 +35,8 @@ handlers:
 - url: /.*
  script: main.app

-builtins:
- datastore_admin: on
+#builtins:
+#- datastore_admin: on

 libraries:
 - name: django
@@ -27,7 +27,7 @@ class FanFictionDownLoaderBase(InterfaceActionBase):
    description         = 'UI plugin to download FanFiction stories from various sites.'
    supported_platforms = ['windows', 'osx', 'linux']
    author              = 'Jim Miller'
-    version             = (1, 5, 8)
+    version             = (1, 5, 16)
    minimum_calibre_version = (0, 8, 30)

    #: This field defines the GUI plugin class that contains all the code
@@ -18,3 +18,11 @@ group</a> for the downloader.  That covers the web application and CLI, too.

 The source for this plugin is available at it's 
 <a href="http://code.google.com/p/fanficdownloader">project home</a>.
+<hr />
+
+<p>
+See the <a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownloaderSupportedsites">list of supported sites</a>.
+</p>
+<p>
+Read the <a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownloaderFAQs">FAQs</a>.
+</p>
@@ -126,6 +126,10 @@ class ConfigWidget(QWidget):
        self.l = QVBoxLayout()
        self.setLayout(self.l)

+        label = QLabel('<a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownloaderSupportedsites">List of Supported Sites</a> -- <a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownloaderFAQs">FAQs</a>')
+        label.setOpenExternalLinks(True)
+        self.l.addWidget(label)
+
        tab_widget = QTabWidget(self)
        self.l.addWidget(tab_widget)

@@ -279,7 +283,7 @@ class BasicTab(QWidget):

        # this is a cheat to make it easier for users to realize there's a new include_images features.
        self.includeimages = QCheckBox("Include images in EPUBs?",self)
-        self.includeimages.setToolTip("Download and include images in EPUB stories.  This is equivalent to adding:\n\n[defaults]\ninclude_images:true\nkeep_summary_html:true\nmake_firstimage_cover:true\n\n ...to the top of personal.ini.  Your settings in personal.ini will override this.")
+        self.includeimages.setToolTip("Download and include images in EPUB stories.  This is equivalent to adding:\n\n[epub]\ninclude_images:true\nkeep_summary_html:true\nmake_firstimage_cover:true\n\n ...to the top of personal.ini.  Your settings in personal.ini will override this.")
        self.includeimages.setChecked(prefs['includeimages'])
        self.l.addWidget(self.includeimages)
        
@@ -109,6 +109,9 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
        # Assign our menu to this action
        self.menu = QMenu(self.gui)
        self.old_actions_unique_map = {}
+        # menu_actions is just to keep a live reference to the menu
+        # items to prevent GC removing it.
+        self.menu_actions = []
        self.qaction.setMenu(self.menu)
        self.menu.aboutToShow.connect(self.about_to_show_menu)

@@ -135,6 +138,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
            do_user_config = self.interface_action_base_plugin.do_user_config
            self.menu.clear()
            self.actions_unique_map = {}
+            self.menu_actions = []
            self.add_action = self.create_menu_item_ex(self.menu, '&Add New from URL(s)', image='plus.png',
                                                       unique_name='Add New FanFiction Book(s) from URL(s)',
                                                       shortcut_name='Add New FanFiction Book(s) from URL(s)',
@@ -227,6 +231,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
        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)
        return ac

    def plugin_button(self):
@@ -415,7 +420,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
        options['personal.ini'] = prefs['personal.ini']
        if prefs['includeimages']:
            # this is a cheat to make it easier for users.
-            options['personal.ini'] = '''[defaults]
+            options['personal.ini'] = '''[epub]
 include_images:true
 keep_summary_html:true
 make_firstimage_cover:true
@@ -506,8 +511,11 @@ make_firstimage_cover:true
            if len(identicalbooks) > 1:
                raise NotGoingToDownload("More than one identical book--can't tell which to update/overwrite.","minusminus.png")

+            ## changed: add new book when CALIBREONLY if none found.
            if collision == CALIBREONLY and not identicalbooks:
-                raise NotGoingToDownload("Not updating Calibre Metadata, no existing book to update.","search_delete_saved.png")
+                collision = ADDNEW
+                options['collision'] = ADDNEW
+            #     raise NotGoingToDownload("Not updating Calibre Metadata, no existing book to update.","search_delete_saved.png")

            if len(identicalbooks)>0:
                book_id = identicalbooks.pop()
@@ -515,7 +523,7 @@ make_firstimage_cover:true
                book['icon'] = 'edit-redo.png'

        if book_id != None and collision != ADDNEW:
-            if options['collision'] in (CALIBREONLY):
+            if collision in (CALIBREONLY):
                book['comment'] = 'Metadata collected.'
                # don't need temp file created below.
                return
@@ -640,12 +648,14 @@ make_firstimage_cover:true
    def _update_books_completed(self, book_list, options={}):
        
        add_list = filter(lambda x : x['good'] and x['added'], book_list)
+        add_ids = [ x['calibre_id'] for x in add_list ]
        update_list = filter(lambda x : x['good'] and not x['added'], book_list)
        update_ids = [ x['calibre_id'] for x in update_list ]
        
        if len(add_list):
            ## even shows up added to searchs.  Nice.
            self.gui.library_view.model().books_added(len(add_list))
+            self.gui.library_view.model().refresh_ids(add_ids)

        if update_ids:
            self.gui.library_view.model().refresh_ids(update_ids)
@@ -763,7 +773,13 @@ make_firstimage_cover:true
            if epubmi.cover_data[1] is not None:
                db.set_cover(book_id, epubmi.cover_data[1])
            #mi.cover = epubmi.cover_data[1]
-                
+
+        # set author link if found.  All current adapters have authorUrl.
+        if 'authorUrl' in book['all_metadata']:
+            autid=db.get_author_id(book['author'])
+            db.set_link_field_for_author(autid, unicode(book['all_metadata']['authorUrl']),
+                                         commit=False, notify=False)
+            
        db.set_metadata(book_id,mi)

        # do configured column updates here.
@@ -777,7 +793,8 @@ make_firstimage_cover:true
                print("%s not an existing column, skipping."%col)
                continue
            coldef = custom_columns[col]
-            if not meta.startswith('status-') and meta not in book['all_metadata']:
+            if not meta.startswith('status-') and meta not in book['all_metadata'] or \
+                    meta.startswith('status-') and 'status' not in book['all_metadata']:
                print("No value for %s, skipping."%meta)
                continue
            if meta not in permitted_values[coldef['datatype']]:
@@ -112,9 +112,9 @@ zip_output: false
 ## Can include directories.  .zip will be added if not in name somewhere
 zip_filename: ${title}-${siteabbrev}_${storyId}${formatext}.zip

-## Normally, try to make the output file name 'safe' by removing
-## invalid filename chars.  Applies to both output_filename &
-## zip_filename.  
+## Normally, try to make the filenames 'safe' by removing invalid
+## filename chars.  Applies to default_cover_image, output_filename &
+## zip_filename.
 allow_unsafe_filename: false

 ## entries to make epub subjects and calibre tags
@@ -259,9 +259,18 @@ output_css:
 ## Note that if you enable make_firstimage_cover in [epub], but want
 ## to use default_cover_image for a specific site, use the site:format
 ## section, for example: [www.ficwad.com:epub]
+## default_cover_image is a python string Template string with
+## ${title}, ${author} etc, same as titlepage_entries. Unless
+## allow_unsafe_filename is true, invalid filename chars will be
+## removed from metadata fields
 #default_cover_image:file:///C:/Users/username/Desktop/nook/images/icon.png
+#default_cover_image:file:///C:/Users/username/Desktop/nook/images/${title}/icon.png
 #default_cover_image:http://www.somesite.com/someimage.gif

+## some sites include images that we don't ever want becoming the
+## cover image.  This lets you exclude them.
+#cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
+
 ## Resize images down to width, height, preserving aspect ratio.
 ## Nook size, with margin.
 image_max_size: 580, 725
@@ -311,9 +320,16 @@ extratags: FanFiction,Testing,HTML
 #is_adult:true

 [fanfiction.mugglenet.com]
-## Some sites do not require a login, but do require the user to
-## confirm they are adult for adult content.  In commandline version,
-## this should go in your personal.ini, not defaults.ini.
+## 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

 [fanfiction.portkey.org]
@@ -330,6 +346,12 @@ extratags: FanFiction,Testing,HTML
 #username:YourName
 #password:yourpassword

+[nfacommunity.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
 ## Some sites also require the user to confirm they are adult for
 ## adult content.  In commandline version, this should go in your
 ## personal.ini, not defaults.ini.
@@ -396,8 +418,6 @@ extratags:
 ## when a password is required rather than prompting every time.
 #fail_on_password: false

-[www.gayauthors.org]
-
 [www.harrypotterfanfiction.com]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
@@ -412,6 +432,16 @@ extratags:

 [www.mediaminer.org]

+[www.midnightwhispers.ca]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
+## some sites include images that we don't ever want becoming the
+## cover image.  This lets you exclude them.
+cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
+
 [www.potionsandsnitches.net]

 [www.siye.co.uk]
@@ -44,11 +44,14 @@ import adapter_whoficcom
 import adapter_siyecouk
 import adapter_archiveofourownorg
 import adapter_ficbooknet
-import adapter_gayauthorsorg
 import adapter_portkeyorg
 import adapter_mugglenetcom
 import adapter_hpfandomnet
 import adapter_thequidditchpitchorg
+import adapter_nfacommunitycom
+import adapter_midnightwhispersca
+import adapter_ksarchivecom
+import adapter_archiveskyehawkecom

 ## This bit of complexity allows adapters to be added by just adding
 ## importing.  It eliminates the long if/else clauses we used to need
@@ -101,7 +101,7 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
        # Now go hunting for all the meta data and the chapter list.
        
        ## Title
-        a = soup.find('a', href=re.compile(r"^/works/\w+"))
+        a = soup.find('a', href=re.compile(r"^/works/\d+$"))
        self.story.setMetadata('title',a.string)
 		
        # Find authorid and URL from... author url.
@@ -0,0 +1,190 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2011 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+
+def getClass():
+    return ArchiveSkyeHawkeComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class ArchiveSkyeHawkeComAdapter(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() + '/story.php?no='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','ash')
+
+        # 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 'archive.skyehawke.com'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/story.php?no=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/story.php?no=")+r"\d+$"
+
+
+        
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        url = self.url
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        data = self._fetchUrl(url)
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title
+        a = soup.find('div', {'class':"story border"}).find('span',{'class':'left'})
+        title=a.text.split('"')[1]
+        self.story.setMetadata('title',title)
+        
+        # Find authorid and URL from... author url.
+        author = a.find('a')
+        self.story.setMetadata('authorId',author['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+author['href'])
+        self.story.setMetadata('author',author.string)
+		
+        authorSoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
+		
+        chapter=soup.find('select',{'name':'chapter'}).findAll('option')
+	
+        for i in range(1,len(chapter)):
+            ch=chapter[i]
+            self.chapterUrls.append((stripHTML(ch),ch['value']))
+		
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+		
+        box=soup.find('div', {'class': "container borderridge"})
+        sum=box.find('span').text
+        self.setDescription(url,sum)
+
+        boxes=soup.findAll('div', {'class': "container bordersolid"})
+        for box in boxes:
+            if box.find('b') != None and box.find('b').text == "History and Story Information":
+			
+                for b in box.findAll('b'):
+                    if "words" in b.nextSibling:
+                        self.story.setMetadata('numWords', b.text)
+                    if "archived" in b.previousSibling:
+                        self.story.setMetadata('datePublished', makeDate(stripHTML(b.text), self.dateformat))
+                    if "updated" in b.previousSibling:
+                        self.story.setMetadata('dateUpdated', makeDate(stripHTML(b.text), self.dateformat))
+                    if "fandom" in b.nextSibling:
+                        self.story.addToList('category', b.text)
+						
+                for br in box.findAll('br'):
+                    br.replaceWith('split')
+                genre=box.text.split("Genre:")[1].split("split")[0]
+                if not "Unspecified" in genre:
+                    self.story.addToList('genre',genre)
+			
+			
+            if box.find('span') != None and box.find('span').text == "WARNING":
+			
+                rating=box.findAll('span')[1]
+                rating.find('br').replaceWith('split')
+                rating=rating.text.replace("This story is rated",'').split('split')[0]
+                self.story.setMetadata('rating',rating)
+                logging.debug(self.story.getMetadata('rating'))
+			
+                warnings=box.find('ol')
+                if warnings != None:
+                    warnings=warnings.text.replace(']', '').replace('[', '').split('  ')
+                    for warning in warnings:
+                        self.story.addToList('warnings',warning)
+	
+	
+        for asoup in authorSoup.findAll('div', {'class':"story bordersolid"}):
+            if asoup.find('a')['href'] == 'story.php?no='+self.story.getMetadata('storyId'):
+                if '[ Completed ]' in asoup.text:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+                chars=asoup.findNext('div').text.split('Characters')[1].split(']')[0]
+                for char in chars.split(','):
+                    if not "None" in char:
+                        self.story.addToList('characters',char)
+                break
+	
+	
+            
+    # 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':"chapter bordersolid"}).findNext('div').findNext('div')
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)
@@ -20,7 +20,8 @@ import logging
 import re
 import urllib2
 import cookielib as cl
-import datetime
+from datetime import datetime
+import json

 from .. import BeautifulSoup as bs
 from ..htmlcleanup import stripHTML
@@ -36,7 +37,7 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
    def __init__(self, config, url):
        BaseSiteAdapter.__init__(self, config, url)
        self.story.setMetadata('siteabbrev','fimficnet')
-        self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2])
+        self.story.setMetadata('storyId', self.parsedUrl.path.split('/',)[2])
        self._setURL("http://"+self.getSiteDomain()+"/story/"+self.story.getMetadata('storyId')+"/")
        self.is_adult = False
        
@@ -74,6 +75,10 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
            self.opener = urllib2.build_opener(cookieproc)
        
        try:
+            apiResponse = urllib2.urlopen("http://www.fimfiction.net/api/story.php?story=%s" % (self.story.getMetadata("storyId"))).read()
+            apiData = json.loads(apiResponse)
+            
+            # Unfortunately, we still need to load the story index page to parse the characters
            data = self._fetchUrl(self.url)
        except urllib2.HTTPError, e:
            if e.code == 404:
@@ -87,9 +92,12 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
        if "/images/missing_story.png" in data:
            raise exceptions.StoryDoesNotExist(self.url)
        
+        if "Invalid story id" in apiData.values():
+            raise exceptions.StoryDoesNotExist(self.url)
+        
        if "This story has been marked as having adult content." in data:
            raise exceptions.AdultCheckRequired(self.url)
-
+        
        if self.password:
            params = {}
            params['password'] = self.password
@@ -100,95 +108,56 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
                raise exceptions.FailedToDownload("%s requires story password and fail_on_password is true."%self.url)
            else:
                raise exceptions.FailedToLogin(self.url,"Story requires individual password",passwdonly=True)
+         
+        storyMetadata = apiData["story"]    
+            
+        self.story.setMetadata("title", storyMetadata["title"])
+        self.story.setMetadata("author", storyMetadata["author"]["name"])
+        self.story.setMetadata("authorId", storyMetadata["author"]["id"])
+        self.story.setMetadata("authorUrl", "http://%s/user/%s" % (self.getSiteDomain(), storyMetadata["author"]["name"]))
        
-        soup = bs.BeautifulSoup(data).find("div", {"class":"content_box post_content_box"})
-
-        titleheader = soup.find("h2")
-        title = titleheader.find("a", href=re.compile(r'^/story/')).text
-        author = titleheader.find("a", href=re.compile(r'^/user/')).text
-        self.story.setMetadata("title", title)
-        self.story.setMetadata("author", author)
-        self.story.setMetadata("authorId", author) # The author's name will be unique
-        self.story.setMetadata("authorUrl", "http://%s/user/%s" % (self.getSiteDomain(),author))
+        chapters = [{"chapterTitle": chapter["title"], "chapterURL": chapter["link"]} for chapter in storyMetadata["chapters"]]
+        for chapter in chapters:
+            self.chapterUrls.append((chapter["chapterTitle"], chapter["chapterURL"]))
+        self.story.setMetadata("numChapters", len(self.chapterUrls))
        
-        chapterDates = []
-
-        for chapter in soup.findAll("a", {"class":"chapter_link"}):
-            chapterDates.append(chapter.span.extract().text.strip("()"))
-            self.chapterUrls.append((chapter.text.strip(), "http://"+self.getSiteDomain() + chapter['href']))
-
-        self.story.setMetadata('numChapters',len(self.chapterUrls))
-        
-        for character in [character_icon['title'] for character_icon in soup.findAll("a", {"class":"character_icon"})]:
-            self.story.addToList("characters", character)
-        for category in [category.text for category in soup.find("div", {"class":"categories"}).findAll("a")]:
-            self.story.addToList("genre", category)
-        self.story.addToList("category", "My Little Pony")
-        
-        
-        # The very last list element in the list of chapters contains the status, rating and word count e.g.:
-        #
-        #    <li>
-        #       Incomplete | Rating:
-        #       <span style="color:#c78238;">Teen</span>
-        #       <div class="word_count"><b>5,203</b>words total</div>
-        #    </li>
-        #
-
-        status_bar = soup.findAll('li')[-1]
        # In the case of fimfiction.net, possible statuses are 'Completed', 'Incomplete', 'On Hiatus' and 'Cancelled'
        # For the sake of bringing it in line with the other adapters, 'Incomplete' and 'On Hiatus' become 'In-Progress'
        # and 'Complete' beomes 'Completed'. 'Cancelled' seems an important enough (not to mention more strictly true) 
        # status to leave unchanged.
-        status = status_bar.text.split("|")[0].strip().replace("Incomplete", "In-Progress").replace("On Hiatus", "In-Progress").replace("Complete", "Completed")
-        self.story.setMetadata('status', status)
-        self.story.setMetadata('rating', status_bar.span.text)
-        # This way is less elegant, perhaps, but more robust in face of format changes.
-        numWords = status_bar.find("div",{"class":"word_count"}).b.text
-        self.story.setMetadata('numWords', numWords)
-        
-        description_soup = soup.find("div", {"class":"description"})
-        # Sometimes the description has an expanding element
-        # This removes the ellipsis and the expand button
-        try:
-            description_soup.find('span', {"id":re.compile(r"description_more_elipses_\d+")}).extract() # Web designer can't spell 'ellipsis'
-            description_soup.find('a', {"class":"more"}).extract()
-        except:
-            pass
+        status = storyMetadata["status"].replace("Incomplete", "In-Progress").replace("On Hiatus", "In-Progress").replace("Complete", "Completed")
+        self.story.setMetadata("status", status)
+        self.story.setMetadata("rating", storyMetadata["content_rating_text"])
+            
+        for category in storyMetadata["categories"]:
+            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.
-        story_img = soup.find('img',{'class':'story_image'})
-        if self.getConfig('include_images') and story_img:
-            self.story.addImgUrl(self,self.url,story_img['src'],self._fetchUrlRaw,cover=True)
-        self.setDescription(self.url,description_soup.text)
-        #self.story.setMetadata('description', description_soup.text)
+        if self.getConfig('include_images') and "image" in storyMetadata.keys():
+            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"])
        
-        # Unfortunately, nowhere on the page is the year mentioned.
-        # Best effort to deal with this:
-        # Use this year, if that's a date in the future, subtract one year.
-        # Their earliest story is Jun, so they'll probably change the date
-        # around then.
-
-        now = datetime.datetime.now()
+        # Dates are in Unix time
+        # Take the publish date from the first chapter posted
+        rawDatePublished = storyMetadata["chapters"][0]["date_modified"]
+        self.story.setMetadata("datePublished", datetime.fromtimestamp(rawDatePublished))
+        rawDateUpdated = storyMetadata["date_modified"]
+        self.story.setMetadata("dateUpdated", datetime.fromtimestamp(rawDateUpdated))
        
-        dateUpdated_soup = bs.BeautifulSoup(data).find("div", {"class":"calendar"})
-        dateUpdated_soup.find('span').extract()
-        dateUpdated = makeDate("%s%s"%(now.year,dateUpdated_soup.text), "%Y%b%d")
-        if dateUpdated > now :
-            dateUpdated = dateUpdated.replace(year=now.year-1)
-        self.story.setMetadata("dateUpdated", dateUpdated)
-        
-        # Get the date of creation from the first chapter
-        if len(chapterDates) > 0:
-            datePublished_text = chapterDates[0]
-            day, month = datePublished_text.split()
-            day = re.sub(r"[^\d.]+", '', day)
-            datePublished = makeDate("%s%s%s"%(now.year,month,day), "%Y%b%d")
-            if datePublished > now :
-                datePublished = datePublished.replace(year=now.year-1)
-            self.story.setMetadata("datePublished", datePublished)
-        else:
-            self.story.setMetadata("datePublished", dateUpdated)
+        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)
+            
            
    def getChapterText(self, url):
        logging.debug('Getting chapter text from: %s' % url)
@@ -1,205 +0,0 @@
-# -*- coding: utf-8 -*-
-
-# Copyright 2011 Fanficdownloader team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-#
-
-import datetime
-import logging
-import re
-import urllib2
-from urllib import unquote
-
-from .. import BeautifulSoup as bs
-from ..htmlcleanup import stripHTML
-from .. import exceptions as exceptions
-
-from base_adapter import BaseSiteAdapter, makeDate
-
-def getClass():
-    return GayAuthorsAdapter
-
-# Class name has to be unique.  Our convention is camel case the
-# sitename with Adapter at the end.  www is skipped.
-class GayAuthorsAdapter(BaseSiteAdapter):
-
-    def __init__(self, config, url):
-        BaseSiteAdapter.__init__(self, config, url)
-
-        self.decode = ["utf8",
-                       "Windows-1252"] # 1252 is a superset of iso-8859-1.
-                               # Most sites that claim to be
-                               # iso-8859-1 (and some that claim to be
-                               # utf8) are really windows-1252.
-        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
-        self.password = ""
-        self.is_adult=False
-       
-		
-        # get storyId from url--url validation guarantees query is only sid=1234
-        self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[3])
-        logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
-
-        # unqoute, change '_' and ' ' to '-', downcase, and remove non-[a-z0-9-]
-        authid = unquote(self.parsedUrl.path.split('/',)[2])
-        authid = authid.lower().replace('_','-').replace(' ','-')
-        authid = re.sub(r"[^a-z0-9-]","",authid)
-        
-        self.story.setMetadata('authorId',authid)
-        logging.debug("authorId: (%s)"%self.story.getMetadata('authorId'))
-        
-        # normalized story URL.
-        self._setURL('http://' + self.getSiteDomain() + '/story/'+self.story.getMetadata('authorId') + '/' + self.story.getMetadata('storyId'))
-        
-        # Each adapter needs to have a unique site abbreviation.
-        self.story.setMetadata('siteabbrev','ga')
-
-        # The date format will vary from site to site.
-        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = "%d %b %Y"
-            
-    @staticmethod # must be @staticmethod, don't remove it.
-    def getSiteDomain():
-        # The site domain.  Does have www here, if it uses it.
-        return 'www.gayauthors.org'
-
-    def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/story/author/storytitle"
-
-    def getSiteURLPattern(self):
-        return re.escape("http://"+self.getSiteDomain()+"/story/")+r".*?/\w+.*?$"
-
-    
-
-    ## Getting the chapter list and the meta data, plus 'is adult' checking.
-    def extractChapterUrlsAndMetadata(self):
-
-
-        url = self.url
-        logging.debug("URL: "+url)
-
-        try:
-            data = self._fetchUrl(url)
-        except urllib2.HTTPError, e:
-            if e.code == 404:
-                raise exceptions.StoryDoesNotExist(self.url)
-            else:
-                raise e
-
-
-            
-        # 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.
-        msoup = soup.find('div', {'class' : 'story'})
-        if msoup == None:
-            msoup = soup.find('div', {'class' : 'story ispinned'})
-        csoup = soup.find('div', {'id' : 'story_chapters'})
-        
-        ## Title
-        a = msoup.find('span', {'class' : 'title'})
-        title=a.find('span', {'itemprop' : 'name'})
-        self.story.setMetadata('title',title.text)
-        try:
-            # Find Series name from series URL.
-            series = a.find('span',{'class':"description"})
-            series_name = series.find('a')
-            series_name.extract()
-            series_index = int(series.text.split(' ')[1])
-            self.setSeries(series_name.text, series_index)
-            
-        except:
-            # I find it hard to care if the series parsing fails
-            pass
-        
-        # Find authorid and URL from... author url.
-        a = msoup.find('a', href=re.compile(r'/author/'+self.story.getMetadata('authorId')))
-        self.story.setMetadata('authorUrl',a['href'])
-        self.story.setMetadata('author',a.text)
-		
-
-        # Find the chapters:
-        spans=csoup.findAll('span', {'class' : 'desc chapter-info'})
-        for span in spans:
-            span.extract()
-        for chapter in csoup.findAll('a'):
-            # just in case there's tags, like <i> in chapter titles.
-            a=chapter['href'].split(self.story.getMetadata('author'))
-            a=a[0]+self.story.getMetadata('authorId')+a[1]
-            self.chapterUrls.append((stripHTML(chapter),a))
-
-
-        self.story.setMetadata('numChapters',len(self.chapterUrls))
-		
-        cats = msoup.findAll('a', href=re.compile(r'/browse/list/page__filtertype_0__category\w+$'))
-        for cat in cats:
-            self.story.addToList('category',cat.text)
-		
-        genres = msoup.findAll('a', href=re.compile(r'/browse/list/page__filtertype_1__genre\w+$'))
-        for genre in genres:
-            self.story.addToList('genre',genre.text)
-        genres = msoup.findAll('a', href=re.compile(r'/browse/list/page__filtertype_2__tag\w+$'))
-        for genre in genres:
-            self.story.addToList('genre',genre.text)
-			
-        status = msoup.find('a', href=re.compile(r'/browse/list/page__filtertype_3__status\w+$'))
-        self.story.setMetadata('status',status.text)
-		
-        rating = msoup.find('a', href=re.compile(r'/browse/list/page__filtertype_4__rating\w+$'))
-        self.story.setMetadata('rating',rating.text)
-		
-        summary = msoup.find('span', {'itemprop' : 'description'})
-        self.setDescription(self.url,summary.text)
-        #self.story.setMetadata('description',summary.text)
-	
-
-        stats = msoup.find('dl',{'class':'info'})
-        dt = stats.findAll('dt')
-        dd = stats.findAll('dd')
-        for x in range(0,len(dt)):
-            label = dt[x].text
-            value = dd[x].text
-
-            if 'Words:' in label:
-                self.story.setMetadata('numWords', value)
-
-            if 'Published:' in label:
-                date=stripHTML(value.split(' - ')[0])
-                if ',' in date:
-                    date=datetime.date.today().strftime(self.dateformat)
-                self.story.setMetadata('datePublished', makeDate(date, self.dateformat))
-				
-            if 'Updated:' in label:
-                date=stripHTML(value.split(' - ')[0])
-                if ',' in date:
-                    date=datetime.date.today().strftime(self.dateformat)
-                self.story.setMetadata('dateUpdated', makeDate(date, self.dateformat))
-            
-    # grab the text for an individual chapter.
-    def getChapterText(self, url):
-
-        logging.debug('Getting chapter text from: %s' % url)
-
-        data = self._fetchUrl(url)
-        data = data[data.index("<div id='chapter-content'>"):]
-        soup = bs.BeautifulSoup(data) # this one's happier with Soup, not StoneSoup for some reason.
-        
-        div = soup.find('div', {'id' : 'chapter-content'})
-
-        if None == div:
-            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
-        return self.utf8FromSoup(url,div)
@@ -0,0 +1,306 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2011 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+# Search for XXX comments--that's where things are most likely to need changing.
+
+# This function is called by the downloader in all adapter_*.py files
+# in this dir to register the adapter class.  So it needs to be
+# updated to reflect the class below it.  That, plus getSiteDomain()
+# take care of 'Registering'.
+def getClass():
+    return KSArchiveComAdapter # XXX
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class KSArchiveComAdapter(BaseSiteAdapter): # XXX
+
+    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.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.
+        # XXX Most sites don't have the /fanfic part.  Replace all to remove it usually.
+        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','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
+            
+    @classmethod
+    def getAcceptDomains(cls):
+        return ['www.ksarchive.com','ksarchive.com']
+
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'ksarchive.com' # XXX
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return "http://(www.)?"+re.escape(self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        if self.is_adult or self.getConfig("is_adult"):
+            # Weirdly, different sites use different warning numbers.
+            # If the title search below fails, there's a good chance
+            # you need a different number.  print data at that point
+            # and see what the 'click here to continue' url says.
+
+            # Furthermore, there's a couple sites now with more than
+            # one warning level for different ratings.  And they're
+            # fussy about it.  midnightwhispers has three: 10, 3 & 5.
+            # we'll try 5 first.
+            addurl = "&ageconsent=ok&warning=2" # XXX
+        else:
+            addurl=""
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'+addurl
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        # The actual text that is used to announce you need to be an
+        # adult varies from site to site.  Again, print data before
+        # the title search to troubleshoot.
+            
+        # Since the warning text can change by warning level, let's
+        # look for the warning pass url.  ksarchive uses
+        # &amp;warning= -- actually, so do other sites.  Must be an
+        # eFiction book.
+            
+        # viewstory.php?sid=1882&amp;warning=4
+        # viewstory.php?sid=1654&amp;ageconsent=ok&amp;warning=5
+        #print data
+        #m = re.search(r"'viewstory.php\?sid=1882(&amp;warning=4)'",data)
+        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',stripHTML(a)) # title's inside a <b> tag.
+
+        # 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'))
+                catstext = [cat.string for cat in cats]
+                for cat in catstext:
+                    if cat.string.strip() in ('Poetry','Essays'):
+                        self.story.addToList('category',cat.string)
+
+            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]
+                for char in charstext:
+                    self.story.addToList('characters',char.string)
+
+            ## Not all sites use Genre, but there's no harm to
+            ## leaving it in.  Check to make sure the type_id number
+            ## is correct, though--it's site specific.
+            if 'Genre' in label:
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1')) # XXX
+                genrestext = [genre.string for genre in genres]
+                self.genre = ', '.join(genrestext)
+                for genre in genrestext:
+                    self.story.addToList('genre',genre.string)
+
+            ## 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]
+                self.genre = ', '.join(genrestext)
+                for genre in genrestext:
+                    self.story.addToList('genre',genre.string)
+
+            ## Not all sites use Warnings, but there's no harm to
+            ## leaving it in.  Check to make sure the type_id number
+            ## is correct, though--it's site specific.
+            if 'Warnings' in label:
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')) # XXX
+                warningstext = [warning.string for warning in warnings]
+                self.warning = ', '.join(warningstext)
+                for warning in warningstext:
+                    self.story.addToList('warnings',warning.string)
+
+            if 'Completed' in label:
+                if 'Yes' in value:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+
+            if 'Published' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            
+            if 'Updated' in label:
+                # there's a stray [ at the end.
+                #value = value[0:-1]
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+
+        try:
+            # Find Series name from series URL.
+            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
+            i=1
+            for a in storyas:
+                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                    self.setSeries(series_name, i)
+                    break
+                i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        data = self._fetchUrl(url)
+        soup = bs.BeautifulStoneSoup(data,
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('div', {'id' : 'story'})
+
+        if None == div:
+            if "A fatal MySQL error was encountered" in data:
+                raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Database error on the site reported!" % url)
+            else:
+                raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)
@@ -0,0 +1,289 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2011 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+# Search for XXX comments--that's where things are most likely to need changing.
+
+# This function is called by the downloader in all adapter_*.py files
+# in this dir to register the adapter class.  So it needs to be
+# updated to reflect the class below it.  That, plus getSiteDomain()
+# take care of 'Registering'.
+def getClass():
+    return MidnightwhispersCaAdapter # XXX
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class MidnightwhispersCaAdapter(BaseSiteAdapter): # XXX
+
+    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.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.
+        # XXX Most sites don't have the /fanfic part.  Replace all to remove it usually.
+        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','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
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'www.midnightwhispers.ca' # XXX
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        if self.is_adult or self.getConfig("is_adult"):
+            # Weirdly, different sites use different warning numbers.
+            # If the title search below fails, there's a good chance
+            # you need a different number.  print data at that point
+            # and see what the 'click here to continue' url says.
+
+            # Furthermore, there's a couple sites now with more than
+            # one warning level for different ratings.  And they're
+            # fussy about it.  midnightwhispers has three: 10, 3 & 5.
+            # we'll try 5 first.
+            addurl = "&ageconsent=ok&warning=5" # XXX
+        else:
+            addurl=""
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'+addurl
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        # The actual text that is used to announce you need to be an
+        # adult varies from site to site.  Again, print data before
+        # the title search to troubleshoot.
+            
+        # Since the warning text can change by warning level, let's
+        # look for the warning pass url.  nfacommunity uses
+        # &amp;warning= -- actually, so do other sites.  Must be an
+        # eFiction book.
+            
+        # viewstory.php?sid=1882&amp;warning=4
+        # viewstory.php?sid=1654&amp;ageconsent=ok&amp;warning=5
+        #print data
+        #m = re.search(r"'viewstory.php\?sid=1882(&amp;warning=4)'",data)
+        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',stripHTML(a)) # title's inside a <b> tag.
+
+        # 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'))
+                catstext = [cat.string for cat in cats]
+                for cat in catstext:
+                    self.story.addToList('category',cat.string)
+
+            if 'Characters' in label:
+                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+                charstext = [char.string for char in chars]
+                for char in charstext:
+                    self.story.addToList('characters',char.string)
+
+            ## Not all sites use Genre, but there's no harm to
+            ## leaving it in.  Check to make sure the type_id number
+            ## is correct, though--it's site specific.
+            if 'Genre' in label:
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')) # XXX
+                genrestext = [genre.string for genre in genres]
+                self.genre = ', '.join(genrestext)
+                for genre in genrestext:
+                    self.story.addToList('genre',genre.string)
+
+            ## Not all sites use Warnings, but there's no harm to
+            ## leaving it in.  Check to make sure the type_id number
+            ## is correct, though--it's site specific.
+            if 'Warnings' in label:
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')) # XXX
+                warningstext = [warning.string for warning in warnings]
+                self.warning = ', '.join(warningstext)
+                for warning in warningstext:
+                    self.story.addToList('warnings',warning.string)
+
+            if 'Completed' in label:
+                if 'Yes' in value:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+
+            if 'Published' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            
+            if 'Updated' in label:
+                # there's a stray [ at the end.
+                #value = value[0:-1]
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+
+        try:
+            # Find Series name from series URL.
+            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
+            i=1
+            for a in storyas:
+                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                    self.setSeries(series_name, i)
+                    break
+                i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        data = self._fetchUrl(url)
+        soup = bs.BeautifulStoneSoup(data,
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('div', {'id' : 'story'})
+
+        if None == div:
+            if "A fatal MySQL error was encountered" in data:
+                raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Database error on the site reported!" % url)
+            else:
+                raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)
@@ -79,6 +79,41 @@ class MuggleNetComAdapter(BaseSiteAdapter): # XXX
    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 "class='errortext'>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&sid='+self.story.getMetadata('storyId')
+        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):

@@ -87,7 +122,8 @@ class MuggleNetComAdapter(BaseSiteAdapter): # XXX
            # 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" # XXX
+            # http://fanfiction.mugglenet.com/viewstory.php?sid=91079&ageconsent=ok&warning=3
+            addurl = "&ageconsent=ok&warning=3" # XXX  &warning=5
        else:
            addurl=""

@@ -104,13 +140,47 @@ class MuggleNetComAdapter(BaseSiteAdapter): # XXX
            else:
                raise e

+        if self.needToLoginCheck(data):
+            # need to log in for this one.
+            self.performLogin(url)
+            data = self._fetchUrl(url)
+            #print("\nurl:%s\ndata:\n%s\n"%(url,data))
+
        # 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 "This story may contain some sexuality, violence and or profanity not suitable for younger readers." in data: # XXX 
-            raise exceptions.AdultCheckRequired(self.url)
+            
+        # Since the warning text can change by warning level, let's
+        # look for the warning pass url.  nfacommunity uses
+        # &amp;warning= -- actually, so do other sites.  Must be an
+        # eFiction book.
+            
+        # viewstory.php?sid=1882&amp;warning=4
+        # viewstory.php?sid=1654&amp;ageconsent=ok&amp;warning=5
+        #print data
+        #m = re.search(r"'viewstory.php\?sid=1882(&amp;warning=4)'",data)
+        m = re.search(r"'viewstory.php\?sid=%s((?:&amp;ageconsent=ok)?&amp;warning=\d+)'"%self.story.getMetadata('storyId'),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)

-        # Dunno if this site uses this or not.
+                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.")
            
@@ -137,6 +207,16 @@ class MuggleNetComAdapter(BaseSiteAdapter): # XXX

        self.story.setMetadata('numChapters',len(self.chapterUrls))

+
+        # Not good enough-- content can contain a ('), which ends the content prematurely.
+        # metadesc = soup.find('meta',{'name':'description'})
+        # print("removeAllEntities(metadesc['content']):\n%s\n"%removeAllEntities(metadesc['content']))
+        start='<span class="label">Summary: </span>'
+        end='<span class="label">Rated:</span>'
+        summarydata = data[data.index(start)+len(start):data.index(end)]
+        #print("summarydata:\n%s\n"%summarydata)
+        self.setDescription(url,bs.BeautifulSoup(summarydata))
+        
        # eFiction sites don't help us out a lot with their meta data
        # formating, so it's a little ugly.

@@ -153,13 +233,14 @@ class MuggleNetComAdapter(BaseSiteAdapter): # XXX
            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)
+            # not good enough--poorly formated summary html will break it.
+            # 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:
@@ -0,0 +1,289 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2011 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+# Search for XXX comments--that's where things are most likely to need changing.
+
+# This function is called by the downloader in all adapter_*.py files
+# in this dir to register the adapter class.  So it needs to be
+# updated to reflect the class below it.  That, plus getSiteDomain()
+# take care of 'Registering'.
+def getClass():
+    return NfaCommunityComAdapter # XXX
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class NfaCommunityComAdapter(BaseSiteAdapter): # XXX
+
+    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.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.
+        # XXX Most sites don't have the /fanfic part.  Replace all to remove it usually.
+        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','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
+            
+    @classmethod
+    def getAcceptDomains(cls):
+        return ['www.nfacommunity.com','nfacommunity.com']
+
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'nfacommunity.com' # XXX
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return "http://(www.)?"+re.escape(self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        if self.is_adult or self.getConfig("is_adult"):
+            # Weirdly, different sites use different warning numbers.
+            # If the title search below fails, there's a good chance
+            # you need a different number.  print data at that point
+            # and see what the 'click here to continue' url says.
+
+            # Furthermore, there's a couple sites now with more than
+            # one warning level for different ratings.  And they're
+            # fussy about it.  nfacommunity has two: 4 & 5.
+            # we'll try 5 first.
+            addurl = "&ageconsent=ok&warning=5" # XXX
+        else:
+            addurl=""
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'+addurl
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        # The actual text that is used to announce you need to be an
+        # adult varies from site to site.  Again, print data before
+        # the title search to troubleshoot.
+            
+        # Since the warning text can change by warning level, let's
+        # look for the warning pass url.  nfacommunity uses
+        # &amp;warning= -- actually, so do other sites.  Must be an
+        # eFiction book.
+            
+        # viewstory.php?sid=1882&amp;warning=4
+        # viewstory.php?sid=1654&amp;ageconsent=ok&amp;warning=5
+        #print data
+        #m = re.search(r"'viewstory.php\?sid=1882(&amp;warning=4)'",data)
+        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)
+
+        # 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'))
+                catstext = [cat.string for cat in cats]
+                for cat in catstext:
+                    self.story.addToList('category',cat.string)
+
+            if 'Characters' in label:
+                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+                charstext = [char.string for char in chars]
+                for char in charstext:
+                    self.story.addToList('characters',char.string)
+
+            ## Not all sites use Genre, but there's no harm to
+            ## leaving it in.  Check to make sure the type_id number
+            ## is correct, though--it's site specific.
+            if 'Genre' in label:
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')) # XXX
+                genrestext = [genre.string for genre in genres]
+                self.genre = ', '.join(genrestext)
+                for genre in genrestext:
+                    self.story.addToList('genre',genre.string)
+
+            ## Not all sites use Warnings, but there's no harm to
+            ## leaving it in.  Check to make sure the type_id number
+            ## is correct, though--it's site specific.
+            if 'Warnings' in label:
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')) # XXX
+                warningstext = [warning.string for warning in warnings]
+                self.warning = ', '.join(warningstext)
+                for warning in warningstext:
+                    self.story.addToList('warnings',warning.string)
+
+            if 'Completed' in label:
+                if 'Yes' in value:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+
+            if 'Published' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            
+            if 'Updated' in label:
+                # there's a stray [ at the end.
+                #value = value[0:-1]
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+
+        try:
+            # Find Series name from series URL.
+            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
+            i=1
+            for a in storyas:
+                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                    self.setSeries(series_name, i)
+                    break
+                i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('div', {'id' : 'story'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)
@@ -253,14 +253,18 @@ class PortkeyOrgAdapter(BaseSiteAdapter): # XXX
    def getChapterText(self, url):

        logging.debug('Getting chapter text from: %s' % url)
-
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
+        data = self._fetchUrl(url)
+        soup = bs.BeautifulStoneSoup(data,
                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.

        #print("soup:%s"%soup)
-        td = soup.find('td', {'class' : 'story'})
+        tag = soup.find('td', {'class' : 'story'})
+        if tag == None and "<center><b>Chapter does not exist!</b></center>" in data:
+            print("Chapter is missing at: %s"%url)
+            return  self.utf8FromSoup(url,bs.BeautifulStoneSoup("<div><p><center><b>Chapter does not exist!</b></center></p><p>Chapter is missing at: <a href='%s'>%s</a></p></div>"%(url,url)))
+        tag.name='div' # force to be a div to avoid problems with nook.

-        centers = td.findAll('center')
+        centers = tag.findAll('center')
        # first two and last two center tags are some script, 'report
        # story', 'report story' and an ad.
        centers[0].extract()
@@ -268,7 +272,7 @@ class PortkeyOrgAdapter(BaseSiteAdapter): # XXX
        centers[-1].extract()
        centers[-2].extract()

-        if None == td:
+        if None == tag:
            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
    
-        return self.utf8FromSoup(url,td)
+        return self.utf8FromSoup(url,tag)
@@ -179,11 +179,12 @@ Some more longer description.  "I suck at summaries!"  "Better than it sounds!"
 <div>
 <h3>Chapter title from site</h3>
 <p><center>Centered text</center></p>
-<p>Lorem '''+self.crazystring+''' <i>italics</i>, <b>bold</b>, <u>underline</u> consectetur adipisicing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.</p>
+<p>Lorem '''+self.crazystring+u''' <i>italics</i>, <b>bold</b>, <u>underline</u> consectetur adipisicing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.</p>
 br breaks<br><br>
-
+Puella Magi Madoka Magica/魔法少女まどか★マギカ
 <a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownLoaderPluginWithReadingList" title="Tilt-a-Whirl by Jim &amp; Sarah, on Flickr"><img src="http://i.imgur.com/bo8eD.png"></a><br/>
 br breaks<br><br>
+Don't&#8212e;ver&#8212d;o&#8212;that&#8212a;gain, &#27861; &#xE9;
 <hr>
 horizontal rules
 <hr size=1 noshade>
@@ -38,6 +38,7 @@ class TwiwriteNetSiteAdapter(BaseSiteAdapter):
                               # 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 = ""
        
@@ -99,7 +100,16 @@ class TwiwriteNetSiteAdapter(BaseSiteAdapter):

    def extractChapterUrlsAndMetadata(self):

-        url = self.url+'&index=1'
+        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=1" # XXX
+        else:
+            addurl=""
+            
+        url = self.url+'&index=1'+addurl
        logging.debug("URL: "+url)

        try:
@@ -118,6 +128,9 @@ class TwiwriteNetSiteAdapter(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.")

+        if "Contains Explicit Content for mature adults only! May contain graphic violence, mature sexual situations, and explicit language. Read with caution." in data:
+            raise exceptions.AdultCheckRequired(self.url)
+        
        # problems with some stories, but only in calibre.  I suspect
        # issues with different SGML parsers in python.  This is a
        # nasty hack, but it works.
@@ -139,7 +152,7 @@ class TwiwriteNetSiteAdapter(BaseSiteAdapter):
        # 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']))
+            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']+addurl))

        self.story.setMetadata('numChapters',len(self.chapterUrls))

@@ -215,7 +215,9 @@ class BaseSiteAdapter(Configurable):
                    self.getConfig('default_cover_image'):
                self.story.addImgUrl(self,
                                     None,
-                                     self.getConfig('default_cover_image'),
+                                     #self.getConfig('default_cover_image'),
+                                     self.story.formatFileName(self.getConfig('default_cover_image'),
+                                                               self.getConfig('allow_unsafe_filename')),
                                     self._fetchUrlRaw,
                                     cover=True)
        return self.story
@@ -287,7 +289,8 @@ class BaseSiteAdapter(Configurable):
                # some pre-existing epubs have img tags that had src stripped off.
                if img.has_key('src'):
                    img['longdesc']=img['src']
-                    img['src']=self.story.addImgUrl(self,url,img['src'],fetch)
+                    img['src']=self.story.addImgUrl(self,url,img['src'],fetch,
+                                                    coverexclusion=self.getConfig('cover_exclusion_regexp'))

        for attr in soup._getAttrMap().keys():
            if attr not in acceptable_attributes:
@@ -328,10 +331,6 @@ class BaseSiteAdapter(Configurable):
        # This is primarily for epub updates.
        return re.sub(r"</?body>\r?\n?","",retval)

-fullmon = {"January":"01", "February":"02", "March":"03", "April":"04", "May":"05",
-           "June":"06","July":"07", "August":"08", "September":"09", "October":"10",
-           "November":"11", "December":"12" }
-
 def cachedfetch(realfetch,cache,url):
    if url in cache:
        print("cache hit")
@@ -339,6 +338,9 @@ def cachedfetch(realfetch,cache,url):
    else:
        return realfetch(url)
    
+fullmon = {"January":"01", "February":"02", "March":"03", "April":"04", "May":"05",
+           "June":"06","July":"07", "August":"08", "September":"09", "October":"10",
+           "November":"11", "December":"12" }

 def makeDate(string,format):
    # Surprise!  Abstracting this turned out to be more useful than
@@ -19,15 +19,31 @@ import re

 def _unirepl(match):
    "Return the unicode string for a decimal number"
-    if match.group(1)=='x':
+    if match.group(1).startswith('x'):
        radix=16
+        s = match.group(1)[1:]
    else:
        radix=10
-    value = int(match.group(2), radix )
-    return unichr(value)
+        s = match.group(1)
+    try:
+        value = int(s, radix)
+        retval = "%s%s"%(unichr(value),match.group(2))
+    except:
+        # This way, at least if there's more of entities out there
+        # that fail, it doesn't blow the entire download.
+        print "Numeric entity translation failed, skipping: &#x%s%s"%(match.group(1),match.group(2))
+        retval = ""
+    return retval

 def _replaceNumberEntities(data):
-    p = re.compile(r'&#(x?)([0-9a-fA-F]+);')
+    # The same brokenish entity parsing in SGMLParser that inserts ';'
+    # after non-entities will also insert ';' incorrectly after number
+    # entities, including part of the next word if it's a-z.
+    # "Don't&#8212ever&#8212do&#8212that&#8212again," becomes
+    # "Don't&#8212e;ver&#8212d;o&#8212;that&#8212a;gain,"
+    # Also need to allow for 5 digit decimal entities &#27861;
+    # Last expression didn't allow for 2 digit hex correctly: &#xE9;
+    p = re.compile(r'&#(x[0-9a-fA-F]{,4}|[0-9]{,5})([0-9a-fA-F]*?);')
    return p.sub(_unirepl, data)

 def _replaceNotEntities(data):
@@ -50,9 +66,6 @@ def removeAllEntities(text):
    return removeEntities(text).replace('&lt;', '<').replace('&gt;', '>').replace('&amp;', '&')

 def removeEntities(text):
-
-    # replace numeric versions of [&<>] with named versions,
-    # then replace named versions with actual characters,
    
    if text is None:
        return ""
@@ -67,6 +80,8 @@ def removeEntities(text):
        except UnicodeEncodeError, e:
            t = text
    text = t 
+    # replace numeric versions of [&<>] with named versions,
+    # then replace named versions with actual characters,
    text = re.sub(r'&#0*38;','&amp;',text)
    text = re.sub(r'&#0*60;','&lt;',text)
    text = re.sub(r'&#0*62;','&gt;',text)
@@ -17,6 +17,7 @@

 import os, re
 import urlparse
+import string
 from math import floor

 from htmlcleanup import conditionalRemoveEntities, removeAllEntities
@@ -74,6 +75,9 @@ except:
                export = True

            if normalize_format_name(img.format) != "jpg":
+                if img.mode == "P":
+                    # convert pallete gifs to RGB so jpg save doesn't fail.
+                    img = img.convert("RGB")
                export = True

            if export:
@@ -212,9 +216,9 @@ class Story:
        for (p,v) in self.replacements:
            if (isinstance(value,str) or isinstance(value,unicode)) and re.match(p,value):
                value = re.sub(p,v,value)                
-        return value;
+        return value
        
-    def getMetadata(self, key, removeallentities=False):
+    def getMetadata(self, key, removeallentities=False, doreplacements=True):
        value = None
        if self.getLists().has_key(key):
            value = ', '.join(self.getList(key))
@@ -228,21 +232,22 @@ class Story:
                if key == "datePublished" or key == "dateUpdated":
                 value = value.strftime("%Y-%m-%d")

-        value=self.doReplacments(value)
+        if doreplacements:
+            value=self.doReplacments(value)
        if removeallentities and value != None:
            return removeAllEntities(value)
        else:
            return value

-    def getAllMetadata(self, removeallentities=False):
+    def getAllMetadata(self, removeallentities=False, doreplacements=True):
        '''
        All single value *and* list value metadata as strings.
        '''
        allmetadata = {}
        for k in self.metadata.keys():
-            allmetadata[k] = self.getMetadata(k, removeallentities)
+            allmetadata[k] = self.getMetadata(k, removeallentities, doreplacements)
        for l in self.listables.keys():
-            allmetadata[l] = self.getMetadata(l, removeallentities)
+            allmetadata[l] = self.getMetadata(l, removeallentities, doreplacements)

        return allmetadata
        
@@ -275,9 +280,23 @@ class Story:
        "Chapters will be tuples of (title,html)"
        return self.chapters

+    def formatFileName(self,template,allowunsafefilename=True):
+        values = origvalues = self.getAllMetadata()
+        # fall back default:
+        if not template:
+            template="${title}-${siteabbrev}_${storyId}${formatext}"
+
+        if not allowunsafefilename:
+            values={}
+            pattern = re.compile(r"[^a-zA-Z0-9_\. \[\]\(\)&'-]+")
+            for k in origvalues.keys():
+                values[k]=re.sub(pattern,'_', removeAllEntities(self.getMetadata(k)))
+
+        return string.Template(template).substitute(values).encode('utf8')
+
    # pass fetch in from adapter in case we need the cookies collected
    # as well as it's a base_story class method.
-    def addImgUrl(self,configurable,parenturl,url,fetch,cover=False):
+    def addImgUrl(self,configurable,parenturl,url,fetch,cover=False,coverexclusion=None):
        
        url = url.strip() # ran across an image with a space in the
                          # src. Browser handled it, so we'd better, too.
@@ -298,11 +317,17 @@ class Story:
                     url,
                     '','',''))
            else:
+                toppath=""
+                if parsedUrl.path.endswith("/"):
+                    toppath = parsedUrl.path
+                else:
+                    toppath = parsedUrl.path[:parsedUrl.path.rindex('/')]
                imgurl = urlparse.urlunparse(
                    (parsedUrl.scheme,
                     parsedUrl.netloc,
-                     parsedUrl.path + url,
+                     toppath + '/' + url,
                     '','',''))
+                #print("\n===========\nparsedUrl.path:%s\ntoppath:%s\nimgurl:%s\n\n"%(parsedUrl.path,toppath,imgurl))

        prefix='ffdl'
        if imgurl not in self.imgurls:
@@ -330,9 +355,14 @@ class Story:
            else:
                self.imgurls.append(imgurl)
                # First image, copy not link because calibre will replace with it's cover.
-                if len(self.imgurls)==1 and \
+                # Only if: No cover already AND
+                #          make_firstimage_cover AND
+                #          NOT never_make_cover AND
+                #          either no coverexclusion OR coverexclusion doesn't match
+                if self.cover == None and \
                        configurable.getConfig('make_firstimage_cover') and \
-                        not configurable.getConfig('never_make_cover'):
+                        not configurable.getConfig('never_make_cover') and \
+                        (not coverexclusion or not re.search(coverexclusion,imgurl)):
                    newsrc = "images/cover.%s"%ext
                    self.cover=newsrc
                    self.imgtuples.append({'newsrc':newsrc,'mime':mime,'data':data})
@@ -18,7 +18,6 @@
 import re
 import os.path
 import datetime
-import string
 import StringIO
 import zipfile
 from zipfile import ZipFile, ZIP_DEFLATED
@@ -123,24 +122,10 @@ class BaseStoryWriter(Configurable):
            return self.getBaseFileName()

    def getBaseFileName(self):
-        return self.formatFileName(self.getConfig('output_filename'))
+        return self.story.formatFileName(self.getConfig('output_filename'),self.getConfig('allow_unsafe_filename'))
    
    def getZipFileName(self):
-        return self.formatFileName(self.getConfig('zip_filename'))
-
-    def formatFileName(self,template):
-        values = origvalues = self.story.getAllMetadata()
-        # fall back default:
-        if not template:
-            template="${title}-${siteabbrev}_${storyId}${formatext}"
-
-        if not self.getConfig('allow_unsafe_filename'):
-            values={}
-            pattern = re.compile(r"[^a-zA-Z0-9_\. \[\]\(\)&'-]+")
-            for k in origvalues.keys():
-                values[k]=re.sub(pattern,'_', removeAllEntities(self.story.getMetadata(k)))
-
-        return string.Template(template).substitute(values).encode('utf8')
+        return self.story.formatFileName(self.getConfig('zip_filename'),self.getConfig('allow_unsafe_filename'))

    def _write(self, out, text):
        out.write(text.encode('utf8'))
@@ -13,8 +13,23 @@
 # limitations under the License.
 #

+import pickle, copy
 from google.appengine.ext import db

+class ObjectProperty(db.Property):
+	data_type = db.Blob
+
+	def get_value_for_datastore(self, model_instance):
+		value = self.__get__(model_instance, model_instance.__class__)
+		pickled_val = pickle.dumps(value,protocol=pickle.HIGHEST_PROTOCOL)
+		if value is not None: return db.Blob(pickled_val)
+
+	def make_value_from_datastore(self, value):
+		if value is not None: return pickle.loads(value)
+
+	def default_value(self):
+		return copy.copy(self.default)
+
 class DownloadMeta(db.Model):
 	user = db.UserProperty()
 	url = db.StringProperty()
@@ -37,3 +52,12 @@ class DownloadData(db.Model):
 class UserConfig(db.Model):
 	user = db.UserProperty()
 	config = db.BlobProperty()
+
+class SavedMeta(db.Model):
+	url = db.StringProperty()
+	title = db.StringProperty()
+	author = db.StringProperty()
+	date = db.DateTimeProperty(auto_now_add=True)
+	count = db.IntegerProperty()
+	meta = ObjectProperty()
+	
@@ -54,35 +54,24 @@
 	      much easier. </p>
 	  </div>
 	  <!-- put announcements here, h3 is a good title size. -->
-	  <h3>Outages</h3>
+	  <h3>Latest Changes</h3>
 	  <p>
-	    This web service has been having almost daily outages
-	    recently due to problems with running out of quota for the
-	    application.  We are working to improve the situation.
-	  </p>
-	  <h3>Update - New Sites</h3>
-	  <p>
-	    Four new sites have been added:
-	    <ul>
-	      <li>fanfiction.mugglenet.com</li>
-	      <li>fanfiction.portkey.org</li>
-	      <li>thequidditchpitch.org</li>
-	      <li>www.hpfandom.net</li>
-	    </ul>
-	    These are the four largest/most active of the sites that have been requested lately.
+	    Fix for 'Hide this banner' title issue on Archive of Our
+	    Own.
 	  </p>
 	  <p>
-	    Another site that's been requested a few times is
-	    adultfanfiction.net.  None of the current developers are
-	    interested in writing code to support it because of the
-	    ominous legal warnings and requirements to access the
-	    site.
+	    Changed implementation of fimfiction to use provided API,
+	    thanks to Althaine.
 	  </p>
+	  <p>
+	    Questions?  Check out our 
+	    <a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownloaderFAQs">FAQs</a>.
+	    </p>
 	  <p>
 	    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://4-4-0.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
+	    <a href="http://4-4-7.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
 	  </p>
 	  <div id='error'>
 	    {{ error_message }}
@@ -112,6 +101,9 @@
 	  <p>
 	    Or see your personal list of <a href="/recent">previously downloaded fanfics</a>.
 	  </p>
+	  <p>
+	    See a list of downloaded fanfics by all users by <a href="/allrecent">most popular</a> or <a href="/allrecent?bydate=1">most recent</a>.
+	  </p>
 	</div>	
      </form>
      {% else %}
@@ -146,6 +138,13 @@
 	  </p>
      </div>
      <div id='helpbox'>
+	<h3>Supported sites:</h3>
+	<p>
+	  There's a 
+ 	  <a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownloaderSupportedsites">Supported
+ 	  Sites</a> page in our wiki.  If you have a site you'd like
+ 	  to see supported, please check there first.
+	</p>
 	<dl>
 	  <dt>fictionalley.org</dt>
 	  <dd>
@@ -257,12 +256,6 @@
 	    <br /><a href="http://ficbook.net/readfic/93626">http://ficbook.net/readfic/93626</a>.
 	    <br /><a href="http://ficbook.net/readfic/93626/246417#part_content">http://ficbook.net/readfic/93626/246417#part_content</a>.
 	  </dd>
-	  <dt>gayauthors.org</dt>
-	  <dd>
-	    Use the URL of the story, or one of it's chapters, such as
-	    <br /><a href="http://www.gayauthors.org/story/mark-arbour/stvincent">http://www.gayauthors.org/story/mark-arbour/stvincent</a>.
-	    <br /><a href="http://www.gayauthors.org/story/Mark%20Arbour/stvincent/7">http://www.gayauthors.org/story/Mark Arbour/stvincent/7</a>.
-	  </dd>
 	  <dt>fanfiction.mugglenet.com</dt>
 	  <dd>
 	    Use the URL of the story's chapter list, such as
@@ -283,17 +276,38 @@
 	    Use the URL of the story's chapter list, such as
 	    <br /><a href="http://fanfiction.portkey.org/story/123">http://fanfiction.portkey.org/story/123</a>.
 	  </dd>
+	  <dt>nfacommunity.com</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://nfacommunity.com/viewstory.php?sid=1654">http://nfacommunity.com/viewstory.php?sid=1654</a>.
+	  </dd>
+	  <dt>www.midnightwhispers.ca</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://www.midnightwhispers.ca/viewstory.php?sid=1124">http://www.midnightwhispers.ca/viewstory.php?sid=1124</a>.
+	  </dd>
+	  <dt>ksarchive.com</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://ksarchive.com/viewstory.php?sid=1124">http://ksarchive.com/viewstory.php?sid=1124</a>.
+	  </dd>
+	  <dt>archive.skyehawke.com</dt>
+	  <dd>
+	    Use the URL of the story's summary, such as
+	    <br /><a href="http://archive.skyehawke.com/story.php?no=17466">http://archive.skyehawke.com/story.php?no=17466</a>.
+	  </dd>
 	</dl>
 	<p>
 	  A few additional things to know, which will make your life substantially easier:
 	</p>
 	<ol>
 	  <li>
-	    First thing to know: I do not use your Google login and password. In fact, all I know about it is your ID &ndash; password
+	    First thing to know: We do not use your Google login and password. In fact, all we know about it is your ID &ndash; password
 	    is being verified by Google and is absolutely, totally unknown to anyone but you.
 	  </li>
 	  <li>
-	    Small <a href="http://www.sigizmund.com/reading-fanfiction-off-line-in-stanza-and-oth">post written by me</a>
+	    
+	    Small <a href="http://www.sigizmund.com/reading-fanfiction-off-line-in-stanza-and-oth">post written by Roman</a>
 	    &mdash; how to read fiction in Stanza or any other ebook reader.
 	  </li>
 	  <li>
@@ -309,7 +323,7 @@
 	  </li>
 	  <li>
 	    If you think that something that should work in fact doesn't, post a message to
-	    our <a href="http://groups.google.com/group/fanfic-downloader">Google Group</a>. I also encourage you to join it so
+	    our <a href="http://groups.google.com/group/fanfic-downloader">Google Group</a>. we also encourage you to join it so
 	    you will find out about latest updates and fixes as soon as possible
 	  </li>
 	</ol>
@@ -1,6 +1,6 @@
 indexes:

-# AUTOGENERATED
+# notAUTOGENERATED

 # This index.yaml is automatically updated whenever the dev_appserver
 # detects that a new type of query is run.  If you want to manage the
@@ -21,13 +21,8 @@ indexes:
  - name: date
    direction: desc

- kind: DownloadedFanfic
+- kind: SavedMeta
  properties:
-  - name: cleared
-  - name: date
-
- kind: DownloadedFanfic
-  properties:
-  - name: user
+  - name: count
  - name: date
    direction: desc
@@ -303,6 +303,39 @@ class RecentFilesServer(webapp2.RequestHandler):
        path = os.path.join(os.path.dirname(__file__), 'recent.html')
        self.response.out.write(template.render(path, template_values))

+class AllRecentFilesServer(webapp2.RequestHandler):
+    def get(self):
+        user = users.get_current_user()
+        if not user:
+            self.redirect(users.create_login_url(self.request.uri))
+            return
+
+        q = SavedMeta.all()
+        if self.request.get('bydate'):
+            q.order('-date')
+        else:
+            q.order('-count')
+            
+        fics = q.fetch(200)
+        logging.info("Recent fetched %d downloads for user %s."%(len(fics),user.nickname()))
+
+        sendslugs = []
+
+        for fic in fics:
+            ficslug = FicSlug(fic)
+            sendslugs.append(ficslug)
+                
+        template_values = dict(fics = sendslugs, nickname = user.nickname())
+        path = os.path.join(os.path.dirname(__file__), 'allrecent.html')
+        self.response.out.write(template.render(path, template_values))
+
+class FicSlug():
+    def __init__(self,savedmeta):
+        self.url = savedmeta.url
+        self.count = savedmeta.count
+        for k, v in savedmeta.meta.iteritems():
+            setattr(self,k,v)
+        
 class FanfictionDownloader(UserConfigServer):
    def get(self):
        self.post()
@@ -464,6 +497,8 @@ class FanfictionDownloaderTask(UserConfigServer):
            download.url = adapter.getStory().getMetadata('storyUrl')
            download.put()

+            allmeta = adapter.getStory().getAllMetadata(removeallentities=True,doreplacements=False)
+
            outbuffer = StringIO()
            writer.writeStory(outbuffer)
            data = outbuffer.getvalue()
@@ -495,6 +530,21 @@ class FanfictionDownloaderTask(UserConfigServer):
            download.completed=True
            download.put()

+            smetal = SavedMeta.all().filter('url =', allmeta['storyUrl'] ).fetch(1)
+            if smetal and smetal[0]:
+                smeta = smetal[0]
+                smeta.count += 1
+            else:
+                smeta=SavedMeta()
+                smeta.count = 1
+
+            smeta.url = allmeta['storyUrl']
+            smeta.title = allmeta['title']
+            smeta.author = allmeta['author']
+            smeta.meta = allmeta
+            smeta.date = datetime.datetime.now()
+            smeta.put()
+            
            logging.info("Download finished OK")
            del data

@@ -563,6 +613,7 @@ app = webapp2.WSGIApplication([('/', MainHandler),
                               ('/fdown', FanfictionDownloader),
                               (r'/file.*', FileServer),
                               ('/status', FileStatusServer),
+                               ('/allrecent', AllRecentFilesServer),
                               ('/recent', RecentFilesServer),
                               ('/editconfig', EditConfigServer),
                               ('/clearrecent', ClearRecentServer),
@@ -231,9 +231,18 @@ output_css:
 ## Note that if you enable make_firstimage_cover in [epub], but want
 ## to use default_cover_image for a specific site, use the site:format
 ## section, for example: [www.ficwad.com:epub]
+## default_cover_image is a python string Template string with
+## ${title}, ${author} etc, same as titlepage_entries. Unless
+## allow_unsafe_filename is true, invalid filename chars will be
+## removed from metadata fields
 #default_cover_image:file:///C:/Users/username/Desktop/nook/images/icon.png
+#default_cover_image:file:///C:/Users/username/Desktop/nook/images/${title}/icon.png
 #default_cover_image:http://www.somesite.com/someimage.gif

+## some sites include images that we don't ever want becoming the
+## cover image.  This lets you exclude them.
+#cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
+
 ## Resize images down to width, height, preserving aspect ratio.
 ## Nook size, with margin.
 image_max_size: 580, 725
@@ -283,9 +292,16 @@ extratags: FanFiction,Testing,HTML
 #is_adult:true

 [fanfiction.mugglenet.com]
-## Some sites do not require a login, but do require the user to
-## confirm they are adult for adult content.  In commandline version,
-## this should go in your personal.ini, not defaults.ini.
+## 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

 [fanfiction.portkey.org]
@@ -302,6 +318,12 @@ extratags: FanFiction,Testing,HTML
 #username:YourName
 #password:yourpassword

+[nfacommunity.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
 ## Some sites also require the user to confirm they are adult for
 ## adult content.  In commandline version, this should go in your
 ## personal.ini, not defaults.ini.
@@ -365,8 +387,6 @@ extratags:
 ## when a password is required rather than prompting every time.
 #fail_on_password: false

-[www.gayauthors.org]
-
 [www.harrypotterfanfiction.com]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
@@ -381,6 +401,16 @@ extratags:

 [www.mediaminer.org]

+[www.midnightwhispers.ca]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
+## some sites include images that we don't ever want becoming the
+## cover image.  This lets you exclude them.
+cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
+
 [www.potionsandsnitches.net]

 [www.siye.co.uk]
@@ -10,5 +10,10 @@ python downloader.py http://www.fanfiction.net/s/5192986/1/A_Fox_in_Tokyo

 Do 'python downloader.py -h' for more options.

-This tool uses Python 2.5.2, but should work with newer versions of Python.
+This tool uses Python 2.7, but should work with newer versions of Python.

+For more information, see:
+
+http://code.google.com/p/fanficdownloader/wiki/FanFictionDownloaderSupportedsites
+
+http://code.google.com/p/fanficdownloader/wiki/FanFictionDownloaderFAQs
Author	SHA1	Message	Date
Jim Miller	0a2cff3469	Yet more fixes for poor parsing of numeric entities--this time, my poor parsing.	2012-04-25 21:52:56 -05:00
Jim Miller	3cb92f48cc	Added tag FanFictionDownLoader-4.4.8 for changeset 8fc7a6cc2d87	2012-04-22 10:10:08 -05:00
Jim Miller	e5cc4ebbd5	Bump Web/CLI version.	2012-04-22 10:09:44 -05:00
Jim Miller	c6c67f99ca	Moved tag calibre-plugin-1.5.15 to changeset a1a840bcd4c9 (from changeset bac4028b803d)	2012-04-22 09:55:58 -05:00
Jim Miller	c75e62d07e	Merge fimfiction changes to trunk.	2012-04-22 09:55:39 -05:00
Jim Miller	e9b203eb57	Added tag calibre-plugin-1.5.15 for changeset bac4028b803d	2012-04-21 21:37:27 -05:00
Jim Miller	a2eaa9fb22	Fix for ArchiveOfOurOwn site change.	2012-04-21 21:37:16 -05:00
althaine	0cf5ec9880	Updated fimfic.net adapter to use provided API	2012-04-20 20:36:20 +10:00
Jim Miller	465e25d3e6	Added tag FanFictionDownLoader-4.4.7 for changeset c8ab1f6bbd57	2012-04-19 12:19:06 -05:00
Jim Miller	0c85cf1d10	Web- Add list of all downloads feature to web service.	2012-04-19 12:18:40 -05:00
Jim Miller	7f7a1a983c	Plugin-Fix setting status column with no status available(fictionalley).	2012-04-19 12:14:51 -05:00
Jim Miller	6f4be261ef	Fix Japanese in CLI & web version. Broke it in 443 and didn't notice.	2012-04-18 17:54:42 -05:00
Jim Miller	04eb551d48	Added tag CLI-4.4.6 for changeset b69d6004ae25	2012-04-17 14:07:50 -05:00
Jim Miller	6299fc7582	Added tag calibre-plugin-1.5.14 for changeset b69d6004ae25	2012-04-17 14:07:29 -05:00
Jim Miller	c2d7b4ecce	Change plugin 'images' checkbox to add to [epubs], kludge for fimfiction images	2012-04-17 14:07:19 -05:00
Jim Miller	01b14701a0	Moved tag calibre-plugin-1.5.13 to changeset b55fabb0b8c9 (from changeset b0720fc31c10)	2012-04-11 11:11:43 -05:00
Jim Miller	08aa677855	Fix for Python GC'ing menu objects with no explicit Python references.	2012-04-11 11:11:25 -05:00
Jim Miller	bd477d2696	Added tag FanFictionDownLoader-4.4.5 for changeset b0720fc31c10	2012-04-10 09:43:20 -05:00
Jim Miller	1f3220a221	Added tag calibre-plugin-1.5.13 for changeset b0720fc31c10	2012-04-10 09:42:32 -05:00
Jim Miller	b4a8361df9	Package Ida's new archive.skyehawke.com adapter for release.	2012-04-10 09:42:01 -05:00
Ida	e647b0e69b	First version adapter for archive.skyehawke.com	2012-04-10 01:59:34 -04:00
Jim Miller	a5fd8646b7	Added tag calibre-plugin-1.5.12 for changeset 6145294332cd	2012-04-09 11:35:25 -05:00
Jim Miller	ce8cf44101	Set calibre's author link field to authorUrl.	2012-04-09 11:34:52 -05:00
Jim Miller	d5f1484cb7	Added tag calibre-plugin-1.5.11 for changeset 5ad254071cc4	2012-03-24 12:09:31 -05:00
Jim Miller	ad092e2d5f	Another work around for SGMLParser's entity handling. &#8212again v &#8212a;gain	2012-03-24 12:09:18 -05:00
Jim Miller	a9e873490d	Added tag FanFictionDownLoader-4.4.4 for changeset 4a7cf5c4919c	2012-03-19 21:06:20 -05:00
Jim Miller	53c80e3c71	Added tag calibre-plugin-1.5.10 for changeset 4a7cf5c4919c	2012-03-19 21:06:10 -05:00
Jim Miller	f32667ea04	Update index.html, plugin-defaults.ini, bump versions.	2012-03-19 21:06:00 -05:00
Jim Miller	7c43ecb56d	Make default_cover_image use ${title}, etc; add cover_exclusion_regexp feature.	2012-03-19 16:22:51 -05:00
Jim Miller	3a8d045e7a	Add ksarchive.com adapter from Jade Aislin.	2012-03-19 16:16:18 -05:00
Jim Miller	55b9f90c66	Fixes for mugglenet.com--add user/pass, better warning & summary handling.	2012-03-19 16:15:09 -05:00
Jim Miller	22be02369f	Added tag FanFictionDownLoader-4.4.3 for changeset 361de9f22e6e	2012-03-16 17:23:29 -05:00
Jim Miller	392a5e834c	Added tag calibre-plugin-1.5.9 for changeset 361de9f22e6e	2012-03-16 17:23:18 -05:00
Jim Miller	f2794b1e64	Bump web/cli version, update index.html.	2012-03-16 17:23:08 -05:00
Jim Miller	0f68c6ec29	Bump plugin version, add links to FAQ & Supported list to About & Config. Add DB error to mw.	2012-03-16 17:02:58 -05:00
Jim Miller	8c5f784afb	Remove gayauthors.org at the site admin's request.	2012-03-16 12:27:06 -05:00
Jim Miller	f207ba01fe	Adding Sam's code for nfacommunity.com & midnightwhispers.ca.	2012-03-16 12:26:45 -05:00
Jim Miller	59d0040e64	Make 'Update Calibre Only' add a new book if no matching book found.	2012-03-14 16:51:41 -05:00
Jim Miller	949de85150	Turn off gayauthors.org. Wyndham reports complaints from site admin.	2012-03-13 17:21:20 -05:00
Jim Miller	1d1494d11c	Turn off gayauthors.org. Wyndham reports complaints from site admin.	2012-03-13 17:12:43 -05:00
Jim Miller	1d474f6493	Improve image support for a couple of obscure cases.	2012-03-13 14:08:40 -05:00
Jim Miller	b31b497698	portkeyorg- Write 'Chapter does not exist' chapter when chapter does not exist.	2012-03-12 21:43:29 -05:00
Jim Miller	eac6304e98	Add is_adult check to twiwrite for when user on site is not set to adult.	2012-03-12 21:42:39 -05:00
Jim Miller	df3655a57c	Change td in portkey chapter text to div for nook.	2012-03-07 15:22:21 -06:00
Jim Miller	b7a3f327b0	Minor improvement to column updates for new stories.	2012-03-07 10:48:38 -06:00
Jim Miller	42fa7cfc3e	Moved tag FanFictionDownLoader-4.4.2 to changeset 3f66d81535fa (from changeset 5df1a1ed38c9)	2012-03-06 21:12:10 -06:00
Jim Miller	9fb319f42f	Moved tag calibre-plugin-1.5.8 to changeset 3f66d81535fa (from changeset 01d1a20329b9)	2012-03-06 21:11:42 -06:00