rebase on upstream trunk

2025-07-09 03:04:10 -04:00 · 2010-11-24 23:27:53 +09:00 · 2010-11-24 23:27:53 +09:00 · bbf166479d
commit bbf166479d
parent 9af8b9c322 31ad3bd1bb
237 changed files with 37034 additions and 21337 deletions
--- a/Changelog.yaml
+++ b/Changelog.yaml
@ -4,6 +4,176 @@
 # for important features/bug fixes.
 # Also, each release can have new and improved recipes.

+- version: 0.7.29
+  date: 2010-11-19
+
+  new features:
+    - title: "OSX binary build is now based on Qt 4.7. Also, the build is now Intel only and requires at least OS X 10.5.2. If you are on a PowerPC machine or an older OS X version, do not upgrade"
+
+    - title: "Content server: Allow direct navigation to a set of books in the book list."
+      tickets: [7453]
+
+    - title: "OS X: When deleting books, put the files into the recycle bin instead of deleting them permanently"
+
+    - title: "Add button to easy configure Hotmail as email relay. Also improve usability of easy config buttons"
+
+    - title: "Kobo driver: Support Currently_Reading category"
+
+    - title: "Catalog generation: Thumbnail caching, wishlist, improved description layout."
+      tickets: [7376]
+
+    - title: "Support for the Cybook Orizon"
+
+  bug fixes:
+    - title: "Fix restore to defaults in preferences incorrectly setting PDF unwrap factor to 0.0"
+
+    - title: "PDF Input: Fix unwrapping of accented characters"
+
+    - title: "Do not display dialogs asking for confirmation or showing conversion errors when calibre is minimized to system tray"
+      tickets: [7549]
+
+    - title: "calibre server: Fix regression that broke digest authentication when the calibre interface language was set to non English"
+
+    - title: "EPUB Output: Do not raise an error for invalid embedded fonts in the input document."
+      tickets: [7567]
+
+    - title: "RTF Input: Improved conversion of tables, with support for border styles on table cells"
+
+    - title: "E-book viewer: Fix regression that broke hyphenation. Also add more language patterns for hyphenation"
+
+    - title: "SONY driver: Fix cover thumbnails being uploaded to wrong directory on windows"
+
+    - title: "Fix UnicodeDecodeError when displaying a failed metadata fetch message"
+      tickets: [7560]
+
+    - title: "Bulk metadata edit: Speed up remove all tags operation"
+
+    - title: "MOBI Output: Specify image sizes in pixels instead of em to accomodate Amazon's @#$%#@! MOBI renderer"
+
+    - title: "Fix bug preventing customizing of builtin recipes if they are not ascii encoded"
+
+    - title: "SONY XML cache: Handle case where XML db contains reference to a file that does not exist gracefully"
+
+  improved recipes:
+    - Al Jazeera 
+    - The Moscow Times
+    - GLobe and Mail
+    - Washington Post
+
+  new recipes:
+    - title: "Hannoversche Allgemeine Zeitung"
+      author: "Artemis"
+      
+    - title: "globes.co.il"
+      author: "marbs"
+
+    - title: "THN and RDS"
+      author: "Nexus"
+
+    - title: "pclab.pl"
+      author: "ravcio"
+
+    - title: "Now Toronto"
+      author: "Starson17"
+
+    - title: "Press releases of the German government and EU Commission"
+      author: "malfi"
+
+
+- version: 0.7.28
+  date: 2010-11-12
+
+  new features:
+    - title: "Update the version of the grahical toolkit (Qt 4.7.1) used in the calibre binary builds on windows and linux. This should result in a significant speed up for the calibre ebook viewer"
+
+    - title: "Driver for Nook Color, Eken M001"
+
+    - title: "Add a tweak to turn off double clicking to open viewer"
+
+    - title: "Catalog generation: Add indication when a book has no formats"
+      tickets: [7376]
+
+    - title: "Advanced search dialog: Add a tab to allow searching particular metadata fields easily"
+
+    - title: "Conversion pipeline: When using the Level x Table of Contents expressions, if a tag is empty but has a non-empty title attribute, use that instead of ignoring the tag"
+
+  bug fixes:
+    - title: "Comic metadata reader: Sort filenames aplhabetically when choosing an image for the cover"
+      tickets: [7488]
+
+    - title: "Bulk convert dialog: Hide useless restore defaults button."
+      tickets: [7471]
+
+    - title: "Conversion pipeline: Handle input documents that encode null bytes as HTML entities correctly"
+      tickets: [7355]
+
+    - title: "Fix some SONY readers not being detected on windows"
+      tickets: [7413]
+
+    - title: "MOBI Input: Fix images missing when converting MOBI news downloads created with Mobipocket reader"
+      tickets: [7455]
+
+    - title: "ODT Input: Handle hyperlinks to headings that have truncated destination specifiers correctly"
+      tickets: [7506]
+
+    - title: "Sony driver: Ignore invalid strings when updating XML database"
+
+    - title: "Content Server: Add day to displayed date in /mobile book listing"
+
+    - title: "MOBI Input: Do not generate filenames with only extensions if the MOBI file has no internal name"
+      tickets: [7481]
+
+    - title: "MOBI Input: Handle files that has the record sizes set incorrectly to a long integer"
+      tickets: [7472]
+
+    - title: "Fix not enough vertical space for text in the preferences dialog category listing"
+
+    - title: "Remove 'sort' from Search and replace destination fields and add it to source fields. S&R is no longer marked experimental"
+
+    - title: "Edit metadata dialog: Save dialog geometry on reject as well as on accept"
+
+    - title: "E-book viewer: Fix clicking entries in TOC that point to the currently loaded flow not scrolling view to the top of the document"
+
+    - title: "Fix bug in regex used to extract charset from <meta> tags"
+
+    - title: "MOBI Output: Add support for the <q> tag"
+
+  improved recipes:
+    - Zeit Online
+    - Gamespot Review
+    - Ploitika
+    - Pagina12
+    - Irish Times
+    - elektrolese
+
+  new recipes:
+    - title: "Handelsblatt and European Voice"
+      author: "malfi"
+      
+    - title: "Polityka and Newsweek"
+      author: "Mateusz Kielar"
+
+    - title: "MarcTV"
+      author: "Marc Toensings"
+
+    - title: "Rolling Stone"
+      author: "Darko Miletic"
+
+    - title: "Vedomosti"
+      author: "Nikolai Kotchetkov"
+
+    - title: "Hola.com"
+      author: "bmsleight"
+
+    - title: "Dnevnik, Siol.net, MMC-RTV and Avto-magazon"
+      author: "BlonG"
+
+    - title: "SC Print Magazine"
+      author: "Tony Maro"
+
+    - title: "Diario Sport"
+      author: "Jefferson Frantz"
+
 - version: 0.7.27
  date: 2010-11-05

@ -44,6 +214,7 @@
      tickets: [7356]

    - title: "News download: Workaround lack of thread safety in python mechanize, causing corrupted network packets (degrading network performance) on Ubuntu Maverick 64bit kernels"
+      tickets: [7321]

    - title: "Convert comments to HTML for book details panel in separate thread to make scrolling through the book list faster when large comments are present"

--- a/resources/catalog/stylesheet.css
+++ b/resources/catalog/stylesheet.css
@ -12,8 +12,8 @@ p.title  {
 p.author {
 	margin-top:0em;
 	margin-bottom:0em;
-	text-align: left;
-	text-indent: 1em;
+	text-align: center;
+	text-indent: 0em;
 	font-size:large;
  	}

@ -27,17 +27,28 @@ p.author_index {
 	}

 p.tags {
-	margin-top:0em;
+	margin-top:0.5em;
 	margin-bottom:0em;
 	text-align: left;
-	text-indent: 1em;
-	font-size:small;
+	text-indent: 0.0in;
 	}

-p.description {
-	text-align:left;
-	font-style:normal;
+p.formats {
+	font-size:90%;
 	margin-top:0em;
+	margin-bottom:0.5em;
+	text-align: left;
+	text-indent: 0.0in;
+	}
+
+div.description > p:first-child {
+	margin: 0 0 0 0;
+	text-indent: 0em;
+	}
+
+div.description {
+	margin: 0 0 0 0;
+	text-indent: 1em;
 	}

 p.date_index {
@ -81,6 +92,14 @@ p.unread_book {
 	text-indent:-2em;
 	}

+p.wishlist_item {
+	text-align:left;
+	margin-top:0px;
+	margin-bottom:0px;
+	margin-left:2em;
+	text-indent:-2em;
+	}
+
 p.date_read {
 	text-align:left;
 	margin-top:0px;
@ -104,3 +123,14 @@ hr.annotations_divider {
 	margin-top:0em;
 	margin-bottom:0em;
 	}
+
+td.publisher, td.date {
+	font-weight:bold;
+	text-align:center;
+	}
+td.rating {
+	text-align: center;
+	}
+td.thumbnail img {
+	-webkit-box-shadow: 4px 4px 12px #999;
+	}
--- a/resources/content_server/browse/browse.css
+++ b/resources/content_server/browse/browse.css
@ -355,6 +355,25 @@ h2.library_name {
    color: red;
 }

+#booklist > #pagelist { display: none; }
+
+#goto_page_dialog ul {
+    list-style-type: none;
+    font-size: medium;
+}
+
+#goto_page_dialog li {
+    margin-bottom: 1.5ex;
+}
+
+#goto_page_dialog a {
+    text-decoration: none;
+    color: blue;
+}
+
+#goto_page_dialog a:hover {
+    color: red;
+}

 #booklist .left .ui-button-text {
    font-size: medium;
--- a/resources/content_server/browse/browse.html
+++ b/resources/content_server/browse/browse.html
@ -4,7 +4,7 @@
 <html>
 <head>
    <meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
-    <title>..:: calibre library ::.. {title}</title>
+    <title>..:: calibre {library} ::.. {title}</title>
    <meta http-equiv="X-UA-Compatible" content="IE=100" />
    <link rel="icon" type="image/x-icon" href="http://calibre-ebook.com/favicon.ico" />

@ -41,7 +41,7 @@
            <div class="area">
              <div class="bubble">
                  <p><a href="{prefix}/browse" title="Return to top level"
-                      >&rarr;&nbsp;home&nbsp;&larr;</a></p>
+                      >&rarr;&nbsp;{home}&nbsp;&larr;</a></p>
              </div>
            </div>
            <div id="nav-container">&nbsp;
@ -80,7 +80,7 @@
                <form name="search_form"  action="{prefix}/browse/search" method="get" accept-charset="UTF-8">
                    <input value="{initial_search}" type="text" title="Search" name="query"
                                        class="search_input" />&nbsp;
-                    <input type="submit" value="Search" title="Search" alt="Search" />
+                    <input type="submit" value="{Search}" title="{Search}" alt="{Search}" />
                </form>
            </div>
            <div>&nbsp;</div>
@ -96,5 +96,6 @@
        </div>
    </div>
    <div id="book_details_dialog"></div>
+    <div id="goto_page_dialog"></div>
 </body>
 </html>
--- a/resources/content_server/browse/browse.js
+++ b/resources/content_server/browse/browse.js
@ -202,6 +202,23 @@ function previous_page() {
    else last_page();
 }

+function gp_internal(id) {
+    var gp = $('#goto_page_dialog');
+    gp.dialog('close');
+    var elem = $("#booklist #" + id);
+    load_page(elem);
+}
+
+function goto_page() {
+    var gp = $('#goto_page_dialog');
+    var pl = $('#booklist > #pagelist');
+    gp.html(pl.html());
+    gp.dialog('option', 'title', pl.attr('title'));
+    gp.dialog('option', 'height', $(window).height() - 100);
+    gp.dialog('open');
+
+}
+
 function load_page(elem) {
    if (elem.is(":visible")) return;
    var ld = elem.find('.load_data');
@ -251,6 +268,12 @@ function booklist(hide_sort) {
        modal: true,
        show: 'slide'
    });
+    $("#goto_page_dialog").dialog({
+        autoOpen: false,
+        modal: true,
+        show: 'slide'
+    });
+
    first_page(); 
 }

--- a/resources/default_tweaks.py
+++ b/resources/default_tweaks.py
@ -211,3 +211,9 @@ generate_cover_title_font = None
 # Absolute path to a TTF font file to use as the font for the footer in the
 # default cover
 generate_cover_foot_font = None
+
+
+# Behavior of doubleclick on the books list. Choices:
+# open_viewer, do_nothing, edit_cell. Default: open_viewer.
+# Example: doubleclick_on_library_view = 'do_nothing'
+doubleclick_on_library_view = 'open_viewer'
--- a/resources/images/format-text-bold.png
+++ b/resources/images/format-text-bold.png
--- a/resources/images/format-text-italic.png
+++ b/resources/images/format-text-italic.png
--- a/resources/images/format-text-strikethrough.png
+++ b/resources/images/format-text-strikethrough.png
--- a/resources/images/format-text-underline.png
+++ b/resources/images/format-text-underline.png
--- a/resources/images/hotmail.png
+++ b/resources/images/hotmail.png
--- a/resources/images/news/avto-magazin.png
+++ b/resources/images/news/avto-magazin.png
--- a/resources/images/news/dnevnik.png
+++ b/resources/images/news/dnevnik.png
--- a/resources/images/news/moscow_times.png
+++ b/resources/images/news/moscow_times.png
--- a/resources/images/news/rollingstone.png
+++ b/resources/images/news/rollingstone.png
--- a/resources/images/news/siol.png
+++ b/resources/images/news/siol.png
--- a/resources/recipes/180.recipe
+++ b/resources/recipes/180.recipe
@ -0,0 +1,50 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
+'''
+180.com.uy
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Noticias(BasicNewsRecipe):
+    title                 = '180.com.uy'
+    __author__            = 'Gustavo Azambuja'
+    description           = 'Noticias de Uruguay'
+    language       = 'es'
+    timefmt        = '[%a, %d %b, %Y]'
+    use_embedded_content  = False
+    recursion             = 5
+    encoding = 'utf-8'
+    remove_javascript = True
+    no_stylesheets = True
+
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    keep_only_tags = [dict(name='div', attrs={'class':'tef-md tef-md-seccion-sociedad'})]
+    remove_tags = [
+             dict(name=['object','link'])
+                  ]
+
+    remove_attributes = ['width','height', 'style', 'font', 'color']
+
+    extra_css = '''
+                h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
+                h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
+                h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
+                p {font-family:Arial,Helvetica,sans-serif;}
+                '''
+    feeds = [
+           (u'Titulares', u'http://www.180.com.uy/feed.php')
+        ]
+
+    def get_cover_url(self):
+		return 'http://www.180.com.uy/tplef/img/logo.gif'
+
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup
+
--- a/resources/recipes/al_jazeera.recipe
+++ b/resources/recipes/al_jazeera.recipe
@ -1,10 +1,8 @@
-#!/usr/bin/env  python
-
 __license__   = 'GPL v3'
-__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'

 '''
-aljazeera.net
+english.aljazeera.net
 '''
 from calibre.web.feeds.news import BasicNewsRecipe

@ -13,40 +11,58 @@ class AlJazeera(BasicNewsRecipe):
    __author__             = 'Darko Miletic'
    description            = 'News from Middle East'
    language               = 'en'
-
    publisher              = 'Al Jazeera'
    category               = 'news, politics, middle east'
-    simultaneous_downloads = 1
-    delay                  = 4
-    oldest_article         = 1
+    delay                  = 1
+    oldest_article         = 2
    max_articles_per_feed  = 100
    no_stylesheets         = True
    encoding               = 'iso-8859-1'
-    remove_javascript      = True
    use_embedded_content   = False
+    extra_css              = """
+                                body{font-family: Arial,sans-serif}
+                                #ctl00_cphBody_dvSummary{font-weight: bold}
+                                #dvArticleDate{font-size: small; color: #999999}
+                             """
+    conversion_options = {
+                          'comment'   : description
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
+                        }

-    html2lrf_options = [
-                          '--comment', description
-                        , '--category', category
-                        , '--publisher', publisher
-                        , '--ignore-tables'
+    keep_only_tags = [
+                         dict(attrs={'id':['DetailedTitle','ctl00_cphBody_dvSummary','dvArticleDate']})
+                        ,dict(name='td',attrs={'class':'DetailedSummary'})
                     ]

-    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_table=True'
-
-    keep_only_tags = [dict(name='div', attrs={'id':'ctl00_divContent'})]
-
    remove_tags = [
-                     dict(name=['object','link'])
+                     dict(name=['object','link','table','meta','base','iframe','embed'])
                    ,dict(name='td', attrs={'class':['MostActiveDescHeader','MostActiveDescBody']})
                  ]

    feeds = [(u'AL JAZEERA ENGLISH (AJE)', u'http://english.aljazeera.net/Services/Rss/?PostingId=2007731105943979989' )]

+    def get_article_url(self, article):
+        artlurl =  article.get('link',  None)
+        return artlurl.replace('http://english.aljazeera.net//','http://english.aljazeera.net/')
+
    def preprocess_html(self, soup):
        for item in soup.findAll(style=True):
            del item['style']
        for item in soup.findAll(face=True):
            del item['face']
+        td = soup.find('td',attrs={'class':'DetailedSummary'})
+        if td:
+           td.name = 'div'
+        spn = soup.find('span',attrs={'id':'DetailedTitle'})
+        if spn:
+           spn.name='h1'
+        for itm in soup.findAll('span', attrs={'id':['dvArticleDate','ctl00_cphBody_lblDate']}):
+            itm.name = 'div'
+        for alink in soup.findAll('a'):
+            if alink.string is not None:
+               tstr = alink.string
+               alink.replaceWith(tstr)
        return soup

--- a/resources/recipes/avto-magazin.recipe
+++ b/resources/recipes/avto-magazin.recipe
@ -0,0 +1,47 @@
+__license__ = 'GPL v3'
+__copyright__ = '2010, BlonG'
+'''
+avto-magazin.si
+'''
+from calibre.web.feeds.news import BasicNewsRecipe
+class Dnevnik(BasicNewsRecipe):
+  title = u'Avto Magazin'
+  __author__ = u'BlonG'
+  description = u'Za avtomobilisti\xc4\x8dne frike, poznavalce in nedeljske \xc5\xa1oferje.'
+  oldest_article = 7
+  max_articles_per_feed = 20
+  labguage = 'sl'
+  no_stylesheets = True
+  use_embedded_content = False
+  language = 'sl'
+
+  conversion_options = {'linearize_tables' : True}
+
+
+  cover_url = 'https://sites.google.com/site/javno2010/home/avto_magazin_cover.jpg'
+
+  extra_css = '''
+	h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
+	h2{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
+	p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+	body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
+	'''
+
+  keep_only_tags = [
+	dict(name='div', attrs={'id':'_iprom_inStream'}),
+#	dict(name='div', attrs={'class':'entry-content'}),
+	]
+
+  remove_tags = [
+	dict(name='div', attrs={'id':'voteConfirmation'}),
+	dict(name='div', attrs={'id':'InsideVote'}),
+	dict(name='div', attrs={'class':'Zone234'}),
+	dict(name='div', attrs={'class':'Comments'}),
+	dict(name='div', attrs={'class':'sorodneNovice'}),
+	dict(name='div', attrs={'id':'footer'}),
+	]
+
+
+  feeds = [
+	(u'Novice', u'http://www.avto-magazin.si/rss/')
+	]
--- a/resources/recipes/bitacora.recipe
+++ b/resources/recipes/bitacora.recipe
@ -0,0 +1,58 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
+'''
+bitacora.com.uy
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class General(BasicNewsRecipe):
+    title                 = 'bitacora.com.uy'
+    __author__            = 'Gustavo Azambuja'
+    description           = 'Noticias de Uruguay'
+    language       = 'es'
+    timefmt        = '[%a, %d %b, %Y]'
+    use_embedded_content  = False
+    recursion             = 5
+    encoding = 'iso-8859-1'
+    remove_javascript = True
+    no_stylesheets = True
+
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    keep_only_tags = [dict(id=['txt'])]
+    remove_tags = [
+             dict(name='div', attrs={'class':'tablafoot'}),
+             dict(name=['object','h4']),
+             dict(name=['object','link'])
+                  ]
+
+    remove_attributes = ['width','height', 'style', 'font', 'color']
+
+    extra_css = '''
+                h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
+                h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
+                h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
+                p {font-family:Arial,Helvetica,sans-serif;}
+                '''
+    feeds = [
+           (u'Titulares', u'http://www.bitacora.com.uy/anxml.cgi?15')
+        ]
+
+    def get_cover_url(self):
+	cover_url = None
+	index = 'http://www.bitacora.com.uy'
+	soup = self.index_to_soup(index)
+	link_item = soup.find('img',attrs={'class':'imgtapa'})
+	if link_item:
+		cover_url = "http://www.bitacora.com.uy/"+link_item['src']
+	return cover_url
+
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup
+
--- a/resources/recipes/brand_eins.recipe
+++ b/resources/recipes/brand_eins.recipe
@ -1,18 +1,22 @@
 #!/usr/bin/env  python
-# -*- coding: utf-8 -*-
+# -*- coding: utf-8 mode: python -*-
+
+# Find the newest version of this recipe here:
+# https://github.com/consti/BrandEins-Recipe/raw/master/brandeins.recipe

 __license__   = 'GPL v3'
-__copyright__ = '2010, Constantin Hofstetter <consti at consti.de>'
-__version__   = '0.95'
+__copyright__ = '2010, Constantin Hofstetter <consti at consti.de>, Steffen Siebert <calibre at steffensiebert.de>'
+__version__   = '0.96'

 ''' http://brandeins.de - Wirtschaftsmagazin '''
 import re
 import string
 from calibre.web.feeds.recipes import BasicNewsRecipe

+
 class BrandEins(BasicNewsRecipe):

-  title = u'Brand Eins'
+  title = u'brand eins'
  __author__ = 'Constantin Hofstetter'
  description = u'Wirtschaftsmagazin'
  publisher ='brandeins.de'
@ -22,11 +26,14 @@ class BrandEins(BasicNewsRecipe):
  no_stylesheets = True
  encoding = 'utf-8'
  language = 'de'
+  publication_type = 'magazine'
+  needs_subscription = True

  # 2 is the last full magazine (default)
  # 1 is the newest (but not full)
  # 3 is one before 2 etc.
-  which_ausgabe = 2
+  # This value can be set via the username field.
+  default_issue = 2

  keep_only_tags = [dict(name='div', attrs={'id':'theContent'}), dict(name='div', attrs={'id':'sidebar'}), dict(name='div', attrs={'class':'intro'}), dict(name='p', attrs={'class':'bodytext'}), dict(name='div', attrs={'class':'single_image'})]

@ -61,17 +68,31 @@ class BrandEins(BasicNewsRecipe):

    return soup

+  def get_cover(self, soup):
+    cover_url = None
+    cover_item = soup.find('div', attrs = {'class': 'cover_image'})
+    if cover_item:
+      cover_url = 'http://www.brandeins.de/' + cover_item.img['src']
+    return cover_url
+
  def parse_index(self):
    feeds = []

    archive = "http://www.brandeins.de/archiv.html"

+    issue = self.default_issue
+    if self.username:
+      try:
+        issue = int(self.username)
+      except:
+        pass
+
    soup = self.index_to_soup(archive)
    latest_jahrgang = soup.findAll('div', attrs={'class': re.compile(r'\bjahrgang-latest\b') })[0].findAll('ul')[0]
-    pre_latest_issue = latest_jahrgang.findAll('a')[len(latest_jahrgang.findAll('a'))-self.which_ausgabe]
+    pre_latest_issue = latest_jahrgang.findAll('a')[len(latest_jahrgang.findAll('a'))-issue]
    url = pre_latest_issue.get('href', False)
-    # Get the title for the magazin - build it out of the title of the cover - take the issue and year;
-    self.title = "Brand Eins "+ re.search(r"(?P<date>\d\d\/\d\d\d\d+)", pre_latest_issue.find('img').get('title', False)).group('date')
+    # Get month and year of the magazine issue - build it out of the title of the cover
+    self.timefmt = " " + re.search(r"(?P<date>\d\d\/\d\d\d\d)", pre_latest_issue.find('img').get('title', False)).group('date')
    url = 'http://brandeins.de/'+url

    # url = "http://www.brandeins.de/archiv/magazin/tierisch.html"
@ -83,6 +104,7 @@ class BrandEins(BasicNewsRecipe):

  def brand_eins_parse_latest_issue(self, url):
    soup = self.index_to_soup(url)
+    self.cover_url = self.get_cover(soup)
    article_lists = [soup.find('div', attrs={'class':'subColumnLeft articleList'}), soup.find('div', attrs={'class':'subColumnRight articleList'})]

    titles_and_articles = []
@ -123,3 +145,4 @@ class BrandEins(BasicNewsRecipe):
          current_articles.append({'title': title, 'url': url, 'description': description, 'date':''})
    titles_and_articles.append([chapter_title, current_articles])
    return titles_and_articles
+
--- a/resources/recipes/cnetjapan.recipe
+++ b/resources/recipes/cnetjapan.recipe
@ -1,9 +1,11 @@
-import re;
+import re
+from calibre.web.feeds.news import BasicNewsRecipe

 class CNetJapan(BasicNewsRecipe):
    title          = u'CNET Japan'
    oldest_article = 3
    max_articles_per_feed = 30
+    __author__  = 'Hiroshi Miura'

    feeds          = [(u'cnet rss', u'http://feeds.japan.cnet.com/cnet/rss')]
    language       = 'ja'
--- a/resources/recipes/cosmopolitan.recipe
+++ b/resources/recipes/cosmopolitan.recipe
@ -0,0 +1,69 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
+'''
+Muy Interesante
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class General(BasicNewsRecipe):
+    title                 = 'Cosmopolitan'
+    __author__            = 'Gustavo Azambuja'
+    description           = 'Revista Cosmopolitan, Edicion Espanola'
+    language       = 'es'
+    timefmt        = '[%a, %d %b, %Y]'
+    use_embedded_content  = False
+    recursion             = 1
+    encoding = 'utf8'
+    remove_javascript = True
+    no_stylesheets = True
+    conversion_options = {'linearize_tables': True}
+
+    oldest_article        = 180
+    max_articles_per_feed = 100
+    keep_only_tags = [
+             dict(id=['contenido']),
+             dict(name='td', attrs={'class':['contentheading', 'txt_articulo']})
+                     ]
+    remove_tags = [
+             dict(name='div', attrs={'class':['breadcrumb', 'bloque1', 'article', 'bajo_title', 'tags_articles', 'otrosenlaces_title', 'otrosenlaces_parent', 'compartir']}),
+             dict(name='div', attrs={'id':'comment'}),
+             dict(name='table', attrs={'class':'pagenav'}),
+             dict(name=['object','link'])
+                  ]
+    remove_attributes = ['width','height', 'style', 'font', 'color']
+
+    extra_css = '''
+                h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
+                h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
+                h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
+                img {float:left; clear:both; margin:10px}
+                p {font-family:Arial,Helvetica,sans-serif;}
+                '''
+    feeds = [
+                  (u'Articulos', u'http://feeds.feedburner.com/cosmohispano/FSSt')
+    ]
+
+    def preprocess_html(self, soup):
+        attribs = [  'style','font','valign'
+                    ,'colspan','width','height'
+                    ,'rowspan','summary','align'
+                    ,'cellspacing','cellpadding'
+                    ,'frames','rules','border'
+                  ]
+        for item in soup.body.findAll(name=['table','td','tr','th','caption','thead','tfoot','tbody','colgroup','col']):
+            item.name = 'div'
+            for attrib in attribs:
+                if item.has_key(attrib):
+                   del item[attrib]
+        return soup
+
+    def get_cover_url(self):
+		index = 'http://www.cosmohispano.com/revista'
+		soup = self.index_to_soup(index)
+		link_item = soup.find('img',attrs={'class':'img_portada'})
+		if link_item:
+			cover_url = "http://www.cosmohispano.com"+link_item['src']
+		return cover_url
--- a/resources/recipes/danas.recipe
+++ b/resources/recipes/danas.recipe
@ -25,7 +25,7 @@ class Danas(BasicNewsRecipe):
    remove_empty_feeds    = True
    extra_css             = """ @font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)}
                                @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)}
-                                .article_description,body,.lokacija{font-family: Tahoma,Arial,Helvetica,sans1,sans-serif}
+                                .article,.articledescription,body,.lokacija,.feed{font-family: Tahoma,Arial,Helvetica,sans1,sans-serif}
                                .nadNaslov,h1,.preamble{font-family: Georgia,"Times New Roman",Times,serif1,serif}
                                .antrfileText{border-left: 2px solid #999999; 
                                              margin-left: 0.8em; 
@ -66,7 +66,7 @@ class Danas(BasicNewsRecipe):

    keep_only_tags     = [dict(name='div', attrs={'id':'left'})]
    remove_tags = [
-                     dict(name='div', attrs={'class':['width_1_4','metaClanka','baner']})
+                     dict(name='div', attrs={'class':['width_1_4','metaClanka','baner','listaVesti','article_nav']})
                    ,dict(name='div', attrs={'id':'comments'})
                    ,dict(name=['object','link','iframe','meta'])
                  ]
--- a/resources/recipes/deredactie.recipe
+++ b/resources/recipes/deredactie.recipe
@ -0,0 +1,61 @@
+import re
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class deredactie(BasicNewsRecipe):
+    title          = u'Deredactie.be'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    no_stylesheets = True
+    cover_url = 'http://www.deredactie.be/polopoly_fs/1.510827!image/2710428628.gif'
+    language = 'de'
+    keep_only_tags = []
+    __author__ = 'malfi'
+    keep_only_tags.append(dict(name = 'div', attrs = {'id': 'articlehead'}))
+    keep_only_tags.append(dict(name = 'div', attrs = {'id': 'articlebody'}))
+    remove_tags = []
+    remove_tags.append(dict(name = 'div', attrs = {'id': 'story'}))
+    remove_tags.append(dict(name = 'div', attrs = {'id': 'useractions'}))
+    remove_tags.append(dict(name = 'hr'))
+
+    extra_css = '''
+     h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
+     h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
+     p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+     body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
+     '''
+    def parse_index(self):
+        categories = []
+        catnames = {}
+        soup = self.index_to_soup('http://www.deredactie.be/cm/vrtnieuws.deutsch')
+        for elem in soup.findAll('li', attrs={'id' : re.compile("^navItem[2-9]") }):
+              a = elem.find('a', href=True)
+              m = re.search('(?<=/)[^/]*$', a['href'])
+              cat = str(m.group(0))
+              categories.append(cat)
+              catnames[cat] = a['title']
+              self.log("found cat %s\n" % catnames[cat])
+
+        feeds = []
+
+        for cat in categories:
+            articles = []
+            soup = self.index_to_soup('http://www.deredactie.be/cm/vrtnieuws.deutsch/'+cat)
+            for a in soup.findAll('a',attrs={'href' : re.compile("deutsch.*/[0-9][0-9][0-9][0-9][0-9][0-9]_")}):
+                skip_this_article = False
+                url = a['href'].strip()
+                if url.startswith('/'):
+                    url = 'http://www.deredactie.be' + url
+                myarticle=({'title':self.tag_to_string(a), 'url':url, 'description':'', 'date':''})
+                for article in articles :
+                    if article['url'] == url :
+                        skip_this_article = True
+                        self.log("SKIPPING DUP %s" % url)
+                        break
+                if skip_this_article :
+                        continue;
+                articles.append(myarticle)
+                self.log("Adding URL %s\n" %url)
+            if articles:
+                feeds.append((catnames[cat], articles))
+        return feeds
+
--- a/resources/recipes/diario_sport.recipe
+++ b/resources/recipes/diario_sport.recipe
@ -0,0 +1,42 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class DiarioSport(BasicNewsRecipe):
+    title          = u'Diario Sport'
+    oldest_article = 2
+    max_articles_per_feed = 75
+    __author__  = 'Jefferson Frantz'
+    description = 'Todas las noticias del Barça y del mundo del deporte en general'
+    timefmt = ' [%d %b, %Y]'
+    language = 'es'
+    no_stylesheets = True
+
+    feeds          = [(u'Sport', u'http://feeds.feedburner.com/sport/ultimahora')]
+
+    extra_css              = '''
+                                h2{font-family: serif; font-size: small; font-weight: bold; color: #000000; text-align: justify}
+                                '''
+
+    keep_only_tags = [dict(name='div', attrs={'id':['noticiasMedio']})]
+
+    remove_tags        = [
+                             dict(name=['object','link','script','ul'])
+                            ,dict(name='div', attrs={'id':['scrAdSense','herramientas2','participacion','participacion2','bloque1resultados','bloque2resultados','cont_vinyetesAnt','tinta','noticiasSuperior','cintillopublicidad2']})
+                            ,dict(name='p', attrs={'class':['masinformacion','hora']})
+                            ,dict(name='a', attrs={'class':["'link'"]})
+                            ,dict(name='div', attrs={'class':['addthis_toolbox addthis_default_style','firma','pretitularnoticia']})
+                            ,dict(name='form', attrs={'id':['formularioDeBusquedaAvanzada']})
+                         ]
+
+    def preprocess_html(self, soup):
+            for item in soup.findAll(style=True):
+               del item['style']
+            return soup
+
+
+    def postprocess_html(self, soup, first_fetch):
+        img = soup.find('img',src='/img/videos/mascaravideo.png')
+        if not img is None:
+            img.extract()
+
+        return soup
+
--- a/resources/recipes/dnevnik.recipe
+++ b/resources/recipes/dnevnik.recipe
@ -0,0 +1,63 @@
+__license__ = 'GPL v3'
+__copyright__ = '2010, BlonG'
+'''
+dnevnik.si
+'''
+from calibre.web.feeds.news import BasicNewsRecipe
+class Dnevnik(BasicNewsRecipe):
+  title = u'Dnevnik.si'
+  __author__ = u'BlonG'
+  description = u'''Dnevnik je \u010dasnik z ve\u010d kot polstoletno zgodovino.
+  Pod sloganom \xbb\u017divljenje ima besedo\xab na svojih straneh prina\u0161a
+  bralcem bogastvo informacij, komentarjev in kolumen in raznovrstnost
+  pogledov, zaznamovanih z odgovornostjo do posameznika in \u0161ir\u0161e
+  dru\u017ebe.'''
+  oldest_article = 3
+  max_articles_per_feed = 20
+  language = 'sl'
+  no_stylesheets = True
+  use_embedded_content = False
+
+  cover_url = 'https://sites.google.com/site/javno2010/home/dnevnik_cover.jpg'
+
+  extra_css = '''
+	h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
+	h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
+	p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+	body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
+	'''
+
+  keep_only_tags = [
+	dict(name='div', attrs={'id':'_iprom_inStream'}),
+	dict(name='div', attrs={'class':'entry-content'}),
+	]
+
+  remove_tags = [
+	dict(name='div', attrs={'class':'fb_article_top'}),
+	dict(name='div', attrs={'class':'related'}),
+	dict(name='div', attrs={'class':'fb_article_foot'}),
+	dict(name='div', attrs={'class':'spreading'}),
+	dict(name='dl', attrs={'class':'ad'}),
+	dict(name='p', attrs={'class':'report'}),
+	dict(name='div', attrs={'class':'hfeed comments'}),
+	dict(name='dl', attrs={'id':'entryPanel'}),
+	dict(name='dl', attrs={'class':'infopush ip_wide'}),
+	dict(name='div', attrs={'class':'sidebar'}),
+	dict(name='dl', attrs={'class':'bottom'}),
+	dict(name='div', attrs={'id':'footer'}),
+	]
+
+
+  feeds = [
+	(u'Slovenija', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=13')
+	,(u'Svet', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=14')
+	,(u'EU', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=116')
+	,(u'Poslovni dnevnik', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=5')
+	,(u'Kronika', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=15')
+	,(u'Kultura', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=17')
+	,(u'Zdravje', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=18')
+	,(u'Znanost in IT', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=19')
+	,(u'(Ne)verjetno', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=20')
+	,(u'E-strada', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=21')
+	,(u'Svet vozil', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=22')
+	]
--- a/resources/recipes/el_pais_uy.recipe
+++ b/resources/recipes/el_pais_uy.recipe
@ -0,0 +1,67 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
+'''
+http://www.elpais.com.uy/
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class General(BasicNewsRecipe):
+    title                 = 'Diario El Pais'
+    __author__            = 'Gustavo Azambuja'
+    description           = 'Noticias | Uruguay'
+    language       = 'es'
+    timefmt        = '[%a, %d %b, %Y]'
+    use_embedded_content  = False
+    recursion             = 2
+    encoding = 'iso-8859-1'
+    remove_javascript = True
+    no_stylesheets = True
+
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    keep_only_tags = [
+                      dict(name='h1'),
+                      dict(name='div', attrs={'id':'Contenido'})
+                      ]
+    remove_tags = [
+				 dict(name='div', attrs={'class':['date_text', 'comments', 'form_section', 'share_it']}),
+				 dict(name='div', attrs={'id':['relatedPosts', 'spacer', 'banner_izquierda', 'right_container']}),
+				 dict(name='p', attrs={'class':'FacebookLikeButton'}),
+				 dict(name=['object','form']),
+				 dict(name=['object','table']) ]
+
+    extra_css = '''
+                h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
+                h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
+                h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
+                p {font-family:Arial,Helvetica,sans-serif;}
+                '''
+    feeds = [
+           (u'Ultimo Momento', u'http://www.elpais.com.uy/formatos/rss/index.asp?seccion=umomento'),
+           (u'Editorial', u'http://www.elpais.com.uy/formatos/rss/index.asp?seccion=editorial'),
+           (u'Nacional', u'http://www.elpais.com.uy/formatos/rss/index.asp?seccion=nacional'),
+           (u'Internacional', u'http://www.elpais.com.uy/formatos/rss/index.asp?seccion=internacional'),
+           (u'Espectaculos', u'http://www.elpais.com.uy/formatos/rss/index.asp?seccion=espectaculos'),
+           (u'Deportes', u'http://www.elpais.com.uy/formatos/rss/index.asp?seccion=deportes'),
+           (u'Ciudades', u'http://www.elpais.com.uy/formatos/rss/index.asp?seccion=ciudades'),
+           (u'Economia', u'http://www.elpais.com.uy/formatos/rss/index.asp?seccion=economia') 
+        ]
+
+    def get_cover_url(self):
+		cover_url = None
+		index = 'http://www.elpais.com.uy'
+		soup = self.index_to_soup(index)
+		link_item = soup.find('div',attrs={'class':'boxmedio box257'})
+		print link_item
+		if link_item:
+			cover_url = 'http://www.elpais.com.uy'+link_item.img['src']
+		return cover_url
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup
+
--- a/resources/recipes/endgadget_ja.recipe
+++ b/resources/recipes/endgadget_ja.recipe
@ -10,6 +10,8 @@ from calibre.web.feeds.news import BasicNewsRecipe

 class EndgadgetJapan(BasicNewsRecipe):
    title          = u'Endgadget\u65e5\u672c\u7248'
+    language = 'ja'
+    __author__ = 'Hiroshi Miura'
    cover_url      = 'http://skins18.wincustomize.com/1/49/149320/29/7578/preview-29-7578.jpg'
    masthead_url   = 'http://www.blogsmithmedia.com/japanese.engadget.com/media/eng-jp-logo-t.png'
    oldest_article = 7
--- a/resources/recipes/eu_commission.recipe
+++ b/resources/recipes/eu_commission.recipe
@ -0,0 +1,58 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+LANGUAGE = 'de'
+
+def feedlink(num):
+    return    u'http://europa.eu/rapid/syndication/QuickRSSAction.do?id='+\
+            str(num)+'&lang='+ LANGUAGE
+
+class EUCommissionPress(BasicNewsRecipe):
+    title          = u'Pressemitteilungen der EU Kommission pro Politikbereich'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    no_stylesheets = True
+    cover_url = 'http://ec.europa.eu/wel/template_2007/images/banners/banner-background.jpg'
+    __author__ = 'malfi'
+    language = LANGUAGE
+    keep_only_tags = []
+    keep_only_tags.append(dict(name = 'div', attrs = {'class': 'pressReleaseContentMain'}))
+    remove_tags = []
+
+
+    feeds          = [
+                      (u'Pressemitteilung des Tages',feedlink(64)),
+                      (u'Presidency',feedlink(137)),
+                      (u'Foreign affairs and security policy',feedlink(138)),
+                      (u'Agriculture and rural development',feedlink(139)),
+                      (u'Budget and financial programming ',feedlink(140)),
+                      (u'Climate action',feedlink(141)),
+                      (u'Competition',feedlink(142)),
+                      (u'Development',feedlink(143)),
+                      (u'Digital agenda',feedlink(144)),
+                      (u'Economic and monetary affairs',feedlink(145)),
+                      (u'Education, culture, multilingualism and youth ',feedlink(146)),
+                      (u'Employment, social Affairs and inclusion ',feedlink(147)),
+                      (u'Energy',feedlink(148)),
+                      (u'Enlargment and European neighbourhood policy ',feedlink(149)),
+                      (u'Environment',feedlink(150)),
+                      (u'Health and consumer policy',feedlink(151)),
+                      (u'Home affairs',feedlink(152)),
+                      (u'Industry and entrepreneurship',feedlink(153)),
+                      (u'Inter-Institutional relations and administration',feedlink(154)),
+                      (u'Internal market and services',feedlink(155)),
+                      (u'International cooperation, humanitarian aid and crisis response',feedlink(156)),
+                      (u'Justice, fundamental rights and citizenship',feedlink(157)),
+                      (u'Maritime affairs and fisheries',feedlink(158)),
+                      (u'Regional policy',feedlink(159)),
+                      (u'Research and innovation',feedlink(160)),
+                      (u'Taxation and customs union, audit and anti-fraud',feedlink(161)),
+                      (u'Trade',feedlink(162)),
+                      (u'Transport',feedlink(163))
+                      ]
+    extra_css = '''
+     h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
+     h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
+     p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+     body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
+     '''
+
--- a/resources/recipes/european_voice.recipe
+++ b/resources/recipes/european_voice.recipe
@ -0,0 +1,51 @@
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class EuropeanVoice(BasicNewsRecipe):
+    title          = u'European Voice'
+    __author__     = 'malfi'
+    oldest_article = 14
+    max_articles_per_feed = 100
+    no_stylesheets = True
+    cover_url = 'http://www.europeanvoice.com/Css/images/logo.gif'
+    language = 'en'
+    keep_only_tags    = [dict(name='div', attrs={'id':'articleLeftColumn'})]
+    remove_tags    = [dict(name='div', attrs={'id':'BreadCrump'})]
+    feeds          = [
+                        (u'Whole site ',u'http://www.europeanvoice.com/Rss/2.xml'),
+                          (u'News and analysis',u'http://www.europeanvoice.com/Rss/6.xml'),
+                          (u'Comment',u'http://www.europeanvoice.com/Rss/7.xml'),
+                          (u'Special reports',u'http://www.europeanvoice.com/Rss/5.xml'),
+                          (u'People',u'http://www.europeanvoice.com/Rss/8.xml'),
+                          (u'Career',u'http://www.europeanvoice.com/Rss/11.xml'),
+                          (u'Policies',u'http://www.europeanvoice.com/Rss/4.xml'),
+                          (u'EVents',u'http://www.europeanvoice.com/Rss/10.xml'),
+                          (u'Policies - Economics',u'http://www.europeanvoice.com/Rss/31.xml'),
+                          (u'Policies - Business',u'http://www.europeanvoice.com/Rss/19.xml'),
+                          (u'Policies - Trade',u'http://www.europeanvoice.com/Rss/25.xml'),
+                          (u'Policies - Information society',u'http://www.europeanvoice.com/Rss/20.xml'),
+                          (u'Policies - Energy',u'http://www.europeanvoice.com/Rss/15.xml'),
+                          (u'Policies - Transport',u'http://www.europeanvoice.com/Rss/18.xml'),
+                          (u'Policies - Climate change',u'http://www.europeanvoice.com/Rss/16.xml'),
+                          (u'Policies - Environment',u'http://www.europeanvoice.com/Rss/17.xml'),
+                          (u'Policies - Farming & food',u'http://www.europeanvoice.com/Rss/23.xml'),
+                          (u'Policies - Health & society',u'http://www.europeanvoice.com/Rss/24.xml'),
+                          (u'Policies - Justice',u'http://www.europeanvoice.com/Rss/29.xml'),
+                          (u'Policies - Foreign affairs',u'http://www.europeanvoice.com/Rss/27.xml')
+                     ]
+    extra_css = '''
+        h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
+        h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
+        p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+        body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
+        '''
+
+    def print_version(self, url):
+          return url + '?bPrint=1'
+
+    def preprocess_html(self, soup):
+           denied = soup.findAll(True,text='Subscribers')
+           if denied:
+                raise Exception('Article skipped, because content can only be seen with subscription')
+           return soup
+
--- a/resources/recipes/freeway.recipe
+++ b/resources/recipes/freeway.recipe
@ -0,0 +1,100 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
+'''
+http://freeway.com.uy
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class General(BasicNewsRecipe):
+    title                 = 'freeway.com.uy'
+    __author__            = 'Gustavo Azambuja'
+    description           = 'Revista Freeway, Montevideo, Uruguay'
+    language       = 'es'
+    timefmt        = '[%a, %d %b, %Y]'
+    use_embedded_content  = False
+    recursion             = 1
+    encoding = 'utf8'
+    remove_javascript = True
+    no_stylesheets = True
+    conversion_options = {'linearize_tables': True}
+
+    oldest_article        = 180
+    max_articles_per_feed = 100
+    keep_only_tags = [
+             dict(id=['contenido']),
+             dict(name='a', attrs={'class':'titulo_art_ppal'}),
+             dict(name='img', attrs={'class':'recuadro'}),
+             dict(name='td', attrs={'class':'txt_art_ppal'})
+                     ]
+    remove_tags = [
+             dict(name=['object','link'])
+                  ]
+    remove_attributes = ['width','height', 'style', 'font', 'color']
+
+    extra_css = '''
+                h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
+                h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
+                h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
+                img {float:left; clear:both; margin:10px}
+                p {font-family:Arial,Helvetica,sans-serif;}
+                '''
+
+    def parse_index(self):
+            feeds = []
+            for title, url in [('Articulos', 'http://freeway.com.uy/revista/')]:
+               articles = self.art_parse_section(url)
+               if articles:
+                   feeds.append((title, articles))
+            return feeds
+
+    def art_parse_section(self, url):
+            soup = self.index_to_soup(url)
+            div = soup.find(attrs={'id': 'tbl_1'})
+
+            current_articles = []
+            for tag in div.findAllNext(attrs = {'class': 'ancho_articulos'}):
+                if tag.get('class') == 'link-list-heading':
+                    break
+                for td in tag.findAll('td'):
+                    a = td.find('a', attrs= {'class': 'titulo_articulos'})
+                    if a is None:
+                        continue
+                    title = self.tag_to_string(a)
+                    url = a.get('href', False)
+                    if not url or not title:
+                        continue
+                    if url.startswith('/'):
+                         url = 'http://freeway.com.uy'+url
+                    p = td.find('p', attrs= {'class': 'txt_articulos'})
+                    description = self.tag_to_string(p)
+                    self.log('\t\tFound article:', title)
+                    self.log('\t\t\t', url)
+                    self.log('\t\t\t', description)
+                    current_articles.append({'title': title, 'url': url, 'description':description, 'date':''})
+
+            return current_articles
+
+    def preprocess_html(self, soup):
+        attribs = [  'style','font','valign'
+                    ,'colspan','width','height'
+                    ,'rowspan','summary','align'
+                    ,'cellspacing','cellpadding'
+                    ,'frames','rules','border'
+                  ]
+        for item in soup.body.findAll(name=['table','td','tr','th','caption','thead','tfoot','tbody','colgroup','col']):
+            item.name = 'div'
+            for attrib in attribs:
+                if item.has_key(attrib):
+                   del item[attrib]
+        return soup
+
+    def get_cover_url(self):
+		#index = 'http://www.cosmohispano.com/revista'
+		#soup = self.index_to_soup(index)
+		#link_item = soup.find('img',attrs={'class':'img_portada'})
+		#if link_item:
+		#	cover_url = "http://www.cosmohispano.com"+link_item['src']
+		return 'http://freeway.com.uy/_upload/_n_foto_grande/noticia_1792_tapanoviembre2010.jpg'
--- a/resources/recipes/gamespot.recipe
+++ b/resources/recipes/gamespot.recipe
@ -1,5 +1,5 @@
 __license__   = 'GPL v3'
-__author__ = u'Marc T\xf6nsing'
+__author__    = u'Marc Toensing'

 from calibre.web.feeds.news import BasicNewsRecipe

@ -17,6 +17,7 @@ class GamespotCom(BasicNewsRecipe):
    no_javascript = True

    feeds =  [
+               ('All Reviews', 'http://www.gamespot.com/rss/game_updates.php?type=5'),
               ('PC Reviews', 'http://www.gamespot.com/rss/game_updates.php?type=5&platform=5'),
               ('XBOX 360 Reviews', 'http://www.gamespot.com/rss/game_updates.php?type=5&platform=1029'),
               ('Wii Reviews', 'http://www.gamespot.com/rss/game_updates.php?type=5&platform=1031'),
@ -37,5 +38,3 @@ class GamespotCom(BasicNewsRecipe):

    def get_article_url(self, article):
        return article.get('link') + '?print=1'
-
-
--- a/resources/recipes/german_gov.recipe
+++ b/resources/recipes/german_gov.recipe
@ -0,0 +1,28 @@
+import re
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class GermanGovermentPress(BasicNewsRecipe):
+    title          = u'Pressemitteilungen der Bundesregierung'
+    oldest_article = 14
+    __author__ = 'malfi'
+    max_articles_per_feed = 100
+    no_stylesheets = True
+    cover_url = 'http://www.bundesregierung.de/static/images/logoBR.gif'
+    language = 'de'
+    keep_only_tags = []
+    keep_only_tags.append(dict(name = 'h2'))
+    keep_only_tags.append(dict(name = 'div', attrs = {'class': 'textblack'}))
+    keep_only_tags.append(dict(name = 'div', attrs = {'class': 'subtitle'}))
+    keep_only_tags.append(dict(name = 'div', attrs = {'class': 'text'}))
+    remove_tags = []
+    feeds          = [ (u'Pressemitteilungen',u'http://www.bundesregierung.de/Webs/Breg/DE/Service/RSS/Functions/bundesregierungPressemitteilungenRSS20,templateId=renderNewsfeed.rdf') ]
+    extra_css = '''
+     h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
+     h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
+     p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+     body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
+     '''
+    def print_version(self, url):
+         m = re.search(r'^(.*).html$', url)
+         return str(m.group(1)) + ',layoutVariant=Druckansicht.html'
--- a/resources/recipes/globe_and_mail.recipe
+++ b/resources/recipes/globe_and_mail.recipe
@ -1,7 +1,7 @@
 #!/usr/bin/env  python
 __license__   = 'GPL v3'

-__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
+__copyright__ = '2010, Szing'
 __docformat__ = 'restructuredtext en'

 '''
@ -10,49 +10,52 @@ globeandmail.com

 from calibre.web.feeds.news import BasicNewsRecipe

-class GlobeAndMail(BasicNewsRecipe):
-    title = u'Globe and Mail'
-    language = 'en_CA'
-
-    __author__ = 'Kovid Goyal'
+class AdvancedUserRecipe1287083651(BasicNewsRecipe):
+    title          = u'Globe & Mail'
+    __license__   = 'GPL v3'
+    __author__ = 'Szing'
    oldest_article = 2
-    max_articles_per_feed = 10
    no_stylesheets = True
-    extra_css = '''
-    h3 {font-size: 22pt; font-weight:bold; margin:0px; padding:0px 0px 8pt 0px;}
-    h4 {margin-top: 0px;}
-    #byline { font-family: monospace; font-weight:bold; }
-    #placeline {font-weight:bold;}
-    #credit {margin-top:0px;}
-    .tag {font-size: 22pt;}'''
-    description = 'Canada\'s national newspaper'
-    keep_only_tags = [dict(name='article')]
-    remove_tags = [dict(name='aside'),
-                   dict(name='footer'),
-                   dict(name='div', attrs={'class':(lambda x: isinstance(x, (str,unicode)) and 'articlecommentcountholder' in x.split(' '))}),
-                   dict(name='ul', attrs={'class':(lambda x: isinstance(x, (str,unicode)) and 'articletoolbar' in x.split(' '))}),
-                  ]
+    max_articles_per_feed = 100
+    encoding               = 'utf8'
+    publisher              = 'Globe & Mail'
+    language               = 'en_CA'
+    extra_css = 'p.meta {font-size:75%}\n .redtext {color: red;}\n .byline {font-size: 70%}'
+
    feeds          = [
-            (u'Latest headlines', u'http://www.theglobeandmail.com/?service=rss'),
-            (u'Top stories', u'http://www.theglobeandmail.com/?service=rss&feed=topstories'),
-            (u'National', u'http://www.theglobeandmail.com/news/national/?service=rss'),
-            (u'Politics', u'http://www.theglobeandmail.com/news/politics/?service=rss'),
-            (u'World', u'http://www.theglobeandmail.com/news/world/?service=rss'),
+      (u'Top National Stories', u'http://www.theglobeandmail.com/news/national/?service=rss'),
      (u'Business', u'http://www.theglobeandmail.com/report-on-business/?service=rss'),
-            (u'Opinions', u'http://www.theglobeandmail.com/news/opinions/?service=rss'),
-            (u'Columnists', u'http://www.theglobeandmail.com/news/opinions/columnists/?service=rss'),
-            (u'Globe Investor', u'http://www.theglobeandmail.com/globe-investor/?service=rss'),
-            (u'Sports', u'http://www.theglobeandmail.com/sports/?service=rss'),
+      (u'Commentary', u'http://www.theglobeandmail.com/report-on-business/commentary/?service=rss'),
+      (u'Blogs', u'http://www.theglobeandmail.com/blogs/?service=rss'),
+      (u'Facts & Arguments', u'http://www.theglobeandmail.com/life/facts-and-arguments/?service=rss'),
      (u'Technology', u'http://www.theglobeandmail.com/news/technology/?service=rss'),
+      (u'Investing', u'http://www.theglobeandmail.com/globe-investor/?service=rss'),
+      (u'Top Polical Stories', u'http://www.theglobeandmail.com/news/politics/?service=rss'),
      (u'Arts', u'http://www.theglobeandmail.com/news/arts/?service=rss'),
      (u'Life', u'http://www.theglobeandmail.com/life/?service=rss'),
-            (u'Blogs', u'http://www.theglobeandmail.com/blogs/?service=rss'),
      (u'Real Estate', u'http://www.theglobeandmail.com/real-estate/?service=rss'),
-            (u'Auto', u'http://www.theglobeandmail.com/auto/?service=rss')
+      (u'Auto', u'http://www.theglobeandmail.com/sports/?service=rss'),
+      (u'Sports', u'http://www.theglobeandmail.com/auto/?service=rss')
    ]

-    def get_article_url(self, article):
-        url = BasicNewsRecipe.get_article_url(self, article)
-        if '/video/' not in url:
-            return url
+    keep_only_tags = [
+      dict(name='h1'),
+      dict(name='h2', attrs={'id':'articletitle'}),
+      dict(name='p', attrs={'class':['leadText', 'meta', 'leadImage', 'redtext byline', 'bodyText']}),
+      dict(name='div', attrs={'class':['news','articlemeta','articlecopy']}),
+      dict(name='id', attrs={'class':'article'}),
+      dict(name='table', attrs={'class':'todays-market'}),
+      dict(name='header', attrs={'id':'leadheader'})
+    ]
+
+    remove_tags = [
+      dict(name='div', attrs={'id':['tabInside', 'ShareArticles', 'topStories']})
+    ]
+
+    #this has to be here or the text in the article appears twice.
+    remove_tags_after = [dict(id='article')]
+
+    #Use the mobile version rather than the web version
+    def print_version(self, url):
+        return url + '&service=mobile'

--- a/resources/recipes/globes_co_il.recipe
+++ b/resources/recipes/globes_co_il.recipe
@ -0,0 +1,47 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.ebooks.BeautifulSoup import re
+
+class AdvancedUserRecipe1283848012(BasicNewsRecipe):
+    description   = 'This is Globes.co.il.'
+    cover_url      = 'http://www.the7eye.org.il/SiteCollectionImages/BAKTANA/arye_avnery_010709_377.jpg'
+    title          = u'Globes'
+    language              = 'he'
+    __author__ = 'marbs'
+    extra_css='img {max-width:100%;} body{direction: rtl;max-width:100%;}title{direction: rtl; } article_description{direction: rtl; }, a.article{direction: rtl;max-width:100%;} calibre_feed_description{direction: rtl; }'
+    simultaneous_downloads = 5
+    remove_javascript     = True
+    timefmt        = '[%a, %d %b, %Y]'
+    oldest_article = 1
+    max_articles_per_feed = 100
+    remove_attributes = ['width','style']
+
+
+    feeds          = [(u'שוק ההון', u'http://www.globes.co.il/webservice/rss/rssfeeder.asmx/FeederNode?iID=585'),
+                           (u'נדל"ן', u'http://www.globes.co.il/webservice/rss/rssfeeder.asmx/FeederNode?iID=607'),
+                           (u'וול סטריט ושווקי העולם', u'http://www.globes.co.il/webservice/rss/rssfeeder.asmx/FeederNode?iID=1225'),
+                           (u'ניתוח טכני', u'http://www.globes.co.il/webservice/rss/rssfeeder.asmx/FeederNode?iID=1294'),
+                           (u'היי טק', u'http://www.globes.co.il/webservice/rss/rssfeeder.asmx/FeederNode?iID=594'),
+                           (u'נתח שוק וצרכנות', u'http://www.globes.co.il/webservice/rss/rssfeeder.asmx/FeederNode?iID=821'),
+                           (u'דין וחשבון', u'http://www.globes.co.il/webservice/rss/rssfeeder.asmx/FeederNode?iID=829'),
+                           (u'רכב', u'http://www.globes.co.il/webservice/rss/rssfeeder.asmx/FeederNode?iID=3220'),
+                           (u'דעות', u'http://www.globes.co.il/webservice/rss/rssfeeder.asmx/FeederNode?iID=845'),
+                           (u'קניון המניות - טור שבועי', u'http://www.globes.co.il/webservice/rss/rssfeeder.asmx/FeederNode?iID=3175'),
+                           (u'סביבה', u'http://www.globes.co.il/webservice/rss/rssfeeder.asmx/FeederNode?iID=3221')]
+
+    def print_version(self, url):
+        split1 = url.split("=")
+        print_url = 'http://www.globes.co.il/serve/globes/printwindow.asp?did=' + split1[1]
+        return print_url
+
+
+    def preprocess_html(self, soup):
+        soup.find('tr',attrs={'bgcolor':'black'}).findPrevious('tr').extract()
+        soup.find('tr',attrs={'bgcolor':'black'}).extract()
+        return soup
+
+    def fixChars(self,string):
+        # Replace lsquo (\x91)
+        fixed = re.sub("■","■",string)
+        return fixed
+
+
--- a/resources/recipes/handelsblatt.recipe
+++ b/resources/recipes/handelsblatt.recipe
@ -0,0 +1,41 @@
+import re
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Handelsblatt(BasicNewsRecipe):
+    title          = u'Handelsblatt'
+    __author__ = 'malfi'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    no_stylesheets = True
+    cover_url = 'http://www.handelsblatt.com/images/logo/logo_handelsblatt.com.png'
+    language = 'de'
+    keep_only_tags = []
+    keep_only_tags.append(dict(name = 'div', attrs = {'class': 'structOneCol'}))
+    keep_only_tags.append(dict(name = 'div', attrs = {'id': 'fullText'}))
+    remove_tags    = [dict(name='img', attrs = {'src': 'http://www.handelsblatt.com/images/icon/loading.gif'})]
+
+    feeds          = [
+                        (u'Handelsblatt Exklusiv',u'http://www.handelsblatt.com/rss/exklusiv'),
+                        (u'Handelsblatt Top-Themen',u'http://www.handelsblatt.com/rss/top-themen'),
+                        (u'Handelsblatt Schlagzeilen',u'http://www.handelsblatt.com/rss/ticker/'),
+                        (u'Handelsblatt Finanzen',u'http://www.handelsblatt.com/rss/finanzen/'),
+                        (u'Handelsblatt Unternehmen',u'http://www.handelsblatt.com/rss/unternehmen/'),
+                        (u'Handelsblatt Politik',u'http://www.handelsblatt.com/rss/politik/'),
+                        (u'Handelsblatt Technologie',u'http://www.handelsblatt.com/rss/technologie/'),
+                        (u'Handelsblatt Meinung',u'http://www.handelsblatt.com/rss/meinung'),
+                        (u'Handelsblatt Magazin',u'http://www.handelsblatt.com/rss/magazin/'),
+                        (u'Handelsblatt Weblogs',u'http://www.handelsblatt.com/rss/blogs')
+                     ]
+    extra_css = '''
+        h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
+        h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
+        p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+        body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
+        '''
+
+    def print_version(self, url):
+         m = re.search('(?<=;)[0-9]*', url)
+         return u'http://www.handelsblatt.com/_b=' + str(m.group(0)) + ',_p=21,_t=ftprint,doc_page=0;printpage'
+
+
--- a/resources/recipes/hannoversche_zeitung.recipe
+++ b/resources/recipes/hannoversche_zeitung.recipe
@ -0,0 +1,38 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class AdvancedUserRecipe1287519083(BasicNewsRecipe):
+    title          = u'Hannoversche Allgemeine Zeitung'
+    oldest_article = 1
+    __author__ = 'Artemis'
+    max_articles_per_feed = 30
+    language = 'de'
+    no_stylesheets = True
+
+    feeds = [
+	#(u'Schlagzeilen', u'http://www.haz.de/rss/feed/haz_schlagzeilen'),
+	(u'Politik', u'http://www.haz.de/rss/feed/haz_politik'),
+	(u'Wirtschaft', u'http://www.haz.de/rss/feed/haz_wirtschaft'),
+	(u'Panorama', u'http://www.haz.de/rss/feed/haz_panorama'),
+	(u'Wissen', u'http://www.haz.de/rss/feed/haz_wissen'),
+	(u'Kultur', u'http://www.haz.de/rss/feed/haz_kultur'),
+	(u'Sp\xe4tvorstellung', u'http://www.haz.de/rss/feed/haz_spaetvorstellung'),
+	(u'Hannover & Region', u'http://www.haz.de/rss/feed/haz_hannoverregion'),
+	(u'Netzgefl\xfcster', u'http://www.haz.de/rss/feed/haz_netzgefluester'),
+	(u'Meinung', u'http://www.haz.de/rss/feed/haz_meinung'),
+	(u'ZiSH', u'http://www.haz.de/rss/feed/haz_zish'),
+	(u'Medien', u'http://www.haz.de/rss/feed/haz_medien'),
+	#(u'Sport', u'http://www.haz.de/rss/feed/haz_sport'),
+	#(u'Hannover 96', u'http://www.haz.de/rss/feed/haz_hannover96')
+	]
+
+    remove_tags_before =dict(id='modul_artikel')
+    remove_tags_after =dict(id='articlecontent')
+
+    remove_tags = dict(id='articlesidebar')
+
+    remove_tags = [
+	dict(name='div', attrs={'class':['articlecomment',
+	'articlebookmark', 'teaser_anzeige', 'teaser_umfrage',
+	'navigation', 'subnavigation']})
+	]
+
--- a/resources/recipes/hola.recipe
+++ b/resources/recipes/hola.recipe
@ -0,0 +1,38 @@
+#!/usr/bin/env  python
+__license__   = 'GPL v3'
+__copyright__ = '2010, Brendan Sleight <bms.calibre at barwap.com>'
+'''
+hola.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Hackaday(BasicNewsRecipe):
+    title                 = u'Hola'
+    __author__            = 'bmsleight'
+    description           = 'diario de actualidad, moda y belleza.'
+    oldest_article        = 10
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    language              = 'es'
+
+    use_embedded_content  = False
+
+    keep_only_tags      = [
+                           dict(name='div', attrs={'id':'cuerpo'})
+                          ]
+
+    feeds               = [
+                         (u'Famosos'        , u'http://www.hola.com/famosos/rss.xml'           ),
+                         (u'Realeza'        , u'http://www.hola.com/realeza/rss.xml'           ),
+                         (u'Cine'           , u'http://www.hola.com/cine/rss.xml'              ),
+                         (u'Música'         , u'http://www.hola.com/musica/rss.xml'            ),
+                         (u'Moda y modelos' , u'http://www.hola.com/moda/portada/rss.xml'      ),
+                         (u'Belleza y salud', u'http://www.hola.com/belleza/portada/rss.xml'   ),
+                         (u'Niños'          , u'http://www.hola.com/ninos/rss.xml'             ),
+                         (u'Todas las noticias', u'http://int2.hola.com/app/feeds/rss_hola.php'),
+                         ]
+
+    def get_article_url(self, article):
+        url = article.get('guid', None)
+        return url
--- a/resources/recipes/irish_times.recipe
+++ b/resources/recipes/irish_times.recipe
@ -13,7 +13,6 @@ class IrishTimes(BasicNewsRecipe):
    language = 'en_IE'
    timefmt = ' (%A, %B %d, %Y)'

-
    oldest_article = 3
    no_stylesheets = True
    simultaneous_downloads= 1
@ -33,10 +32,10 @@ class IrishTimes(BasicNewsRecipe):
                      ('Letters', 'http://www.irishtimes.com/feeds/rss/newspaper/letters.rss'),
                    ]

-
    def print_version(self, url):
         if url.count('rss.feedsportal.com'):
-            u = url.replace('0Bhtml/story01.htm','_pf0Bhtml/story01.htm')
+            u = 'http://www.irishtimes.com' + \
+                     (((url[69:].replace('0C','/')).replace('0A','0'))).replace('0Bhtml/story01.htm','_pf.html')
         else:
             u = url.replace('.html','_pf.html')
         return u
--- a/resources/recipes/jijinews.recipe
+++ b/resources/recipes/jijinews.recipe
@ -6,6 +6,8 @@ __copyright__ = '2010, Hiroshi Miura <miurahr@linux.com>'
 www.jiji.com
 '''

+from calibre.web.feeds.news import BasicNewsRecipe
+
 class JijiDotCom(BasicNewsRecipe):
    title          = u'\u6642\u4e8b\u901a\u4fe1'
    __author__     = 'Hiroshi Miura'
--- a/resources/recipes/la_diaria.recipe
+++ b/resources/recipes/la_diaria.recipe
@ -0,0 +1,48 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
+'''
+ladiaria.com.uy
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class General(BasicNewsRecipe):
+    title                 = 'La Diaria'
+    __author__            = 'Gustavo Azambuja'
+    description           = 'Noticias de Uruguay'
+    language       = 'es'
+    timefmt        = '[%a, %d %b, %Y]'
+    use_embedded_content  = False
+    recursion             = 5
+    encoding = 'utf8'
+    remove_javascript = True
+    no_stylesheets = True
+
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    keep_only_tags = [dict(id=['article'])]
+    remove_tags = [
+             dict(name='div', attrs={'class':['byline', 'hr', 'titlebar', 'volver-arriba-right']}),
+             dict(name='div', attrs={'id':'discussion'}),
+             dict(name=['object','link'])
+                  ]
+
+    extra_css = '''
+                h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
+                h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
+                h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
+                p {font-family:Arial,Helvetica,sans-serif;}
+                '''
+    feeds = [
+           (u'Articulos', u'http://ladiaria.com/feeds/articulos')
+        ]
+
+    def get_cover_url(self):
+        return 'http://ladiaria.com/edicion/imagenportada/'
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup
--- a/resources/recipes/la_jornada.recipe
+++ b/resources/recipes/la_jornada.recipe
@ -54,10 +54,7 @@ class LaJornada_mx(BasicNewsRecipe):
    preprocess_regexps = [
                          (re.compile(  r'<div class="inicial">(.*)</div><p class="s-s">'
                                       ,re.DOTALL|re.IGNORECASE)
-                                       ,lambda match: '<p class="inicial">' + match.group(1) + '</p><p class="s-s">'),
-                          (re.compile(  r'<q>(.*?)</q>'
-                                       ,re.DOTALL|re.IGNORECASE)
-                                       ,lambda match: '"' + match.group(1) + '"')
+                                       ,lambda match: '<p class="inicial">' + match.group(1) + '</p><p class="s-s">')
                         ]
                        
    keep_only_tags = [
--- a/resources/recipes/la_razon_bo.recipe
+++ b/resources/recipes/la_razon_bo.recipe
@ -8,7 +8,7 @@ from calibre import strftime
 from calibre.web.feeds.news import BasicNewsRecipe

 class LaRazon_Bol(BasicNewsRecipe):
-    title                 = 'La Razón - Bolivia'
+    title                 = u'La Razón - Bolivia'
    __author__            = 'Darko Miletic'
    description           = 'El diario nacional de Bolivia'
    publisher             = 'Praxsis S.R.L.'
--- a/resources/recipes/mainichi.recipe
+++ b/resources/recipes/mainichi.recipe
@ -6,6 +6,8 @@ __copyright__ = '2010, Hiroshi Miura <miurahr@linux.com>'
 www.mainichi.jp
 '''

+from calibre.web.feeds.news import BasicNewsRecipe
+
 class MainichiDailyNews(BasicNewsRecipe):
    title          = u'\u6bce\u65e5\u65b0\u805e'
    __author__     = 'Hiroshi Miura'
--- a/resources/recipes/mainichi_it_news.recipe
+++ b/resources/recipes/mainichi_it_news.recipe
@ -1,3 +1,5 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
 class MainichiDailyITNews(BasicNewsRecipe):
    title          = u'\u6bce\u65e5\u65b0\u805e(IT&\u5bb6\u96fb)'
    __author__     = 'Hiroshi Miura'
--- a/resources/recipes/marctv.recipe
+++ b/resources/recipes/marctv.recipe
@ -0,0 +1,35 @@
+__license__   = 'GPL v3'
+__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
+
+'''
+Fetch MarcTV.
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class MarcTVde(BasicNewsRecipe):
+
+    title = 'Marc Toensings Visionen'
+
+    description = 'Marc Toensings Visionen'
+
+    language = 'de'
+
+    __author__ = 'Marc Toensing'
+
+    max_articles_per_feed = 40
+
+    oldest_article = 665
+
+    use_embedded_content = False
+
+    remove_tags = []
+
+    keep_only_tags = dict(name='div', attrs={'class':["content"]})
+
+    feeds          = [(u'Spiele', u'http://feeds.feedburner.com/marctv/spiele'), (u'Leben', u'http://feeds.feedburner.com/marctv/leben'), (u'Medien', u'http://feeds.feedburner.com/marctv/medien')]
+
+    extra_css = '.#wrapper .entry p img{width:620px; height: 270px;}'
+
+    def get_cover_url(self):
+            return 'http://marctv.de/marctv.png'
--- a/resources/recipes/ming_pao.recipe
+++ b/resources/recipes/ming_pao.recipe
@ -3,13 +3,28 @@ __copyright__ = '2010, Eddie Lau'
 '''
 modified from Singtao Toronto calibre recipe by rty
 Change Log:
+2010/11/22: add English section, remove eco-news section which is not updated daily, correct
+            ordering of articles
+2010/11/12: add news image and eco-news section
+2010/11/08: add parsing of finance section
+2010/11/06: temporary work-around for Kindle device having no capability to display unicode
+            in section/article list.
 2010/10/31: skip repeated articles in section pages
 '''

-import datetime
+import os, datetime, re
 from calibre.web.feeds.recipes import BasicNewsRecipe
+from contextlib import nested

-class AdvancedUserRecipe1278063072(BasicNewsRecipe):
+
+from calibre import __appname__, strftime
+from calibre.ebooks.BeautifulSoup import BeautifulSoup
+from calibre.ebooks.metadata.opf2 import OPFCreator
+from calibre.ebooks.metadata.toc import TOC
+from calibre.ebooks.metadata import MetaInformation
+from calibre.utils.date import now as nowf
+
+class MPHKRecipe(BasicNewsRecipe):
    title          = 'Ming Pao - Hong Kong'
    oldest_article = 1
    max_articles_per_feed = 100
@ -24,27 +39,131 @@ class AdvancedUserRecipe1278063072(BasicNewsRecipe):
    encoding = 'Big5-HKSCS'
    recursions = 0
    conversion_options = {'linearize_tables':True}
+    extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px;}'
+    #extra_css = 'img {float:right; margin:4px;}'
    masthead_url = 'http://news.mingpao.com/image/portals_top_logo_news.gif'
    keep_only_tags = [dict(name='h1'),
+                      #dict(name='font', attrs={'style':['font-size:14pt; line-height:160%;']}), # for entertainment page
+                      dict(attrs={'class':['photo']}),
+                      dict(attrs={'id':['newscontent']}),
                      dict(attrs={'id':['newscontent01','newscontent02']})]
+    remove_tags = [dict(name='style'),
+                   dict(attrs={'id':['newscontent135']})]  # for the finance page
+    remove_attributes = ['width']
+    preprocess_regexps = [
+                            (re.compile(r'<h5>', re.DOTALL|re.IGNORECASE),
+                            lambda match: '<h1>'),
+                            (re.compile(r'</h5>', re.DOTALL|re.IGNORECASE),
+                            lambda match: '</h1>'),
+                         ]
+
+    def image_url_processor(cls, baseurl, url):
+        # trick: break the url at the first occurance of digit, add an additional
+        # '_' at the front
+        # not working, may need to move this to preprocess_html() method
+        #minIdx = 10000
+        #i0 = url.find('0')
+        #if i0 >= 0 and i0 < minIdx:
+        #   minIdx = i0
+        #i1 = url.find('1')
+        #if i1 >= 0 and i1 < minIdx:
+        #   minIdx = i1
+        #i2 = url.find('2')
+        #if i2 >= 0 and i2 < minIdx:
+        #   minIdx = i2
+        #i3 = url.find('3')
+        #if i3 >= 0 and i0 < minIdx:
+        #   minIdx = i3
+        #i4 = url.find('4')
+        #if i4 >= 0 and i4 < minIdx:
+        #   minIdx = i4
+        #i5 = url.find('5')
+        #if i5 >= 0 and i5 < minIdx:
+        #   minIdx = i5
+        #i6 = url.find('6')
+        #if i6 >= 0 and i6 < minIdx:
+        #   minIdx = i6
+        #i7 = url.find('7')
+        #if i7 >= 0 and i7 < minIdx:
+        #   minIdx = i7
+        #i8 = url.find('8')
+        #if i8 >= 0 and i8 < minIdx:
+        #   minIdx = i8
+        #i9 = url.find('9')
+        #if i9 >= 0 and i9 < minIdx:
+        #   minIdx = i9
+        #return url[0:minIdx] + '_' + url[minIdx+1:]
+        return url

    def get_fetchdate(self):
        dt_utc = datetime.datetime.utcnow()
-        # convert UTC to local hk time - at around HKT 5.30am, all news are available
-        dt_local = dt_utc - datetime.timedelta(-2.5/24)
+        # convert UTC to local hk time - at around HKT 6.00am, all news are available
+        dt_local = dt_utc - datetime.timedelta(-2.0/24)
        return dt_local.strftime("%Y%m%d")

    def parse_index(self):
            feeds = []
            dateStr = self.get_fetchdate()
-        for title, url in [(u'\u8981\u805e Headline', 'http://news.mingpao.com/' + dateStr + '/gaindex.htm'), (u'\u6559\u80b2 Education', 'http://news.mingpao.com/' + dateStr + '/gfindex.htm'), (u'\u6e2f\u805e Local', 'http://news.mingpao.com/' + dateStr + '/gbindex.htm'), (u'\u793e\u8a55\u2027\u7b46\u9663 Editorial', 'http://news.mingpao.com/' + dateStr + '/mrindex.htm'), (u'\u8ad6\u58c7 Forum', 'http://news.mingpao.com/' + dateStr + '/faindex.htm'), (u'\u4e2d\u570b China', 'http://news.mingpao.com/' + dateStr + '/caindex.htm'), (u'\u570b\u969b World', 'http://news.mingpao.com/' + dateStr + '/taindex.htm'), ('Tech News', 'http://news.mingpao.com/' + dateStr + '/naindex.htm'), (u'\u9ad4\u80b2 Sport', 'http://news.mingpao.com/' + dateStr + '/spindex.htm'), (u'\u526f\u520a Supplement', 'http://news.mingpao.com/' + dateStr + '/jaindex.htm'),]:
+            for title, url in [(u'\u8981\u805e Headline', 'http://news.mingpao.com/' + dateStr + '/gaindex.htm'),
+                               (u'\u6559\u80b2 Education', 'http://news.mingpao.com/' + dateStr + '/gfindex.htm'),
+                               (u'\u6e2f\u805e Local', 'http://news.mingpao.com/' + dateStr + '/gbindex.htm'),
+                               (u'\u793e\u8a55\u2027\u7b46\u9663 Editorial', 'http://news.mingpao.com/' + dateStr + '/mrindex.htm'),
+                               (u'\u8ad6\u58c7 Forum', 'http://news.mingpao.com/' + dateStr + '/faindex.htm'),
+                               (u'\u4e2d\u570b China', 'http://news.mingpao.com/' + dateStr + '/caindex.htm'),
+                               (u'\u570b\u969b World', 'http://news.mingpao.com/' + dateStr + '/taindex.htm'),
+                               ('Tech News', 'http://news.mingpao.com/' + dateStr + '/naindex.htm'),
+                               (u'\u9ad4\u80b2 Sport', 'http://news.mingpao.com/' + dateStr + '/spindex.htm'),
+                               (u'\u526f\u520a Supplement', 'http://news.mingpao.com/' + dateStr + '/jaindex.htm'),
+                               (u'\u82f1\u6587 English', 'http://news.mingpao.com/' + dateStr + '/emindex.htm')]:
                articles = self.parse_section(url)
                if articles:
                    feeds.append((title, articles))
+            # special - finance
+            fin_articles = self.parse_fin_section('http://www.mpfinance.com/htm/Finance/' + dateStr + '/News/ea,eb,ecindex.htm')
+            if fin_articles:
+                feeds.append((u'\u7d93\u6fdf Finance', fin_articles))
+            # special - eco-friendly
+            # eco_articles = self.parse_eco_section('http://tssl.mingpao.com/htm/marketing/eco/cfm/Eco1.cfm')
+            # if eco_articles:
+            #   feeds.append((u'\u74b0\u4fdd Eco News', eco_articles))
+            # special - entertainment
+            #ent_articles = self.parse_ent_section('http://ol.mingpao.com/cfm/star1.cfm')
+            #if ent_articles:
+            #   feeds.append(('Entertainment', ent_articles))
            return feeds

    def parse_section(self, url):
            dateStr = self.get_fetchdate()
+            soup = self.index_to_soup(url)
+            divs = soup.findAll(attrs={'class': ['bullet','bullet_grey']})
+            current_articles = []
+            included_urls = []
+            divs.reverse()
+            for i in divs:
+                a = i.find('a', href = True)
+                title = self.tag_to_string(a)
+                url = a.get('href', False)
+                url = 'http://news.mingpao.com/' + dateStr + '/' +url
+                if url not in included_urls and url.rfind('Redirect') == -1:
+                    current_articles.append({'title': title, 'url': url, 'description':'', 'date':''})
+                    included_urls.append(url)
+            current_articles.reverse()
+            return current_articles
+
+    def parse_fin_section(self, url):
+        dateStr = self.get_fetchdate()
+        soup = self.index_to_soup(url)
+        a = soup.findAll('a', href= True)
+        current_articles = []
+        for i in a:
+            url = i.get('href', False)
+            if not url.rfind(dateStr) == -1 and url.rfind('index') == -1:
+                title = self.tag_to_string(i)
+                url = 'http://www.mpfinance.com/cfm/' +url
+                current_articles.append({'title': title, 'url': url, 'description':''})
+        return current_articles
+
+    def parse_eco_section(self, url):
        soup = self.index_to_soup(url)
        divs = soup.findAll(attrs={'class': ['bullet']})
        current_articles = []
@ -53,9 +172,162 @@ class AdvancedUserRecipe1278063072(BasicNewsRecipe):
            a = i.find('a', href = True)
            title = self.tag_to_string(a)
            url = a.get('href', False)
-            url = 'http://news.mingpao.com/' + dateStr + '/' +url
-            if url not in included_urls:
+            url = 'http://tssl.mingpao.com/htm/marketing/eco/cfm/' +url
+            if url not in included_urls and url.rfind('Redirect') == -1:
                current_articles.append({'title': title, 'url': url, 'description':''})
                included_urls.append(url)
        return current_articles

+    #def parse_ent_section(self, url):
+    #   dateStr = self.get_fetchdate()
+    #   soup = self.index_to_soup(url)
+    #   a = soup.findAll('a', href=True)
+    #   current_articles = []
+    #   included_urls = []
+    #   for i in a:
+    #       title = self.tag_to_string(i)
+    #       url = 'http://ol.mingpao.com/cfm/' + i.get('href', False)
+    #       if url not in included_urls and not url.rfind('.txt') == -1 and not url.rfind(dateStr) == -1 and not title == '':
+    #           current_articles.append({'title': title, 'url': url, 'description': ''})
+    #   return current_articles
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        for item in soup.findAll(style=True):
+            del item['width']
+        for item in soup.findAll(stype=True):
+            del item['absmiddle']
+        return soup
+
+    def create_opf(self, feeds, dir=None):
+        #super(MPHKRecipe,self).create_opf(feeds, dir)
+        if dir is None:
+            dir = self.output_dir
+        title = self.short_title()
+        if self.output_profile.periodical_date_in_title:
+            title += strftime(self.timefmt)
+        mi = MetaInformation(title, [__appname__])
+        mi.publisher = __appname__
+        mi.author_sort = __appname__
+        mi.publication_type = self.publication_type+':'+self.short_title()
+        mi.timestamp = nowf()
+        mi.comments = self.description
+        if not isinstance(mi.comments, unicode):
+            mi.comments = mi.comments.decode('utf-8', 'replace')
+        mi.pubdate = nowf()
+        opf_path = os.path.join(dir, 'index.opf')
+        ncx_path = os.path.join(dir, 'index.ncx')
+        opf = OPFCreator(dir, mi)
+        # Add mastheadImage entry to <guide> section
+        mp = getattr(self, 'masthead_path', None)
+        if mp is not None and os.access(mp, os.R_OK):
+            from calibre.ebooks.metadata.opf2 import Guide
+            ref = Guide.Reference(os.path.basename(self.masthead_path), os.getcwdu())
+            ref.type = 'masthead'
+            ref.title = 'Masthead Image'
+            opf.guide.append(ref)
+
+        manifest = [os.path.join(dir, 'feed_%d'%i) for i in range(len(feeds))]
+        manifest.append(os.path.join(dir, 'index.html'))
+        manifest.append(os.path.join(dir, 'index.ncx'))
+
+        # Get cover
+        cpath = getattr(self, 'cover_path', None)
+        if cpath is None:
+            pf = open(os.path.join(dir, 'cover.jpg'), 'wb')
+            if self.default_cover(pf):
+                cpath =  pf.name
+        if cpath is not None and os.access(cpath, os.R_OK):
+            opf.cover = cpath
+            manifest.append(cpath)
+
+        # Get masthead
+        mpath = getattr(self, 'masthead_path', None)
+        if mpath is not None and os.access(mpath, os.R_OK):
+            manifest.append(mpath)
+
+        opf.create_manifest_from_files_in(manifest)
+        for mani in opf.manifest:
+            if mani.path.endswith('.ncx'):
+                mani.id = 'ncx'
+            if mani.path.endswith('mastheadImage.jpg'):
+                mani.id = 'masthead-image'
+        entries = ['index.html']
+        toc = TOC(base_path=dir)
+        self.play_order_counter = 0
+        self.play_order_map = {}
+
+        def feed_index(num, parent):
+            f = feeds[num]
+            for j, a in enumerate(f):
+                if getattr(a, 'downloaded', False):
+                    adir = 'feed_%d/article_%d/'%(num, j)
+                    auth = a.author
+                    if not auth:
+                        auth = None
+                    desc = a.text_summary
+                    if not desc:
+                        desc = None
+                    else:
+                        desc = self.description_limiter(desc)
+                    entries.append('%sindex.html'%adir)
+                    po = self.play_order_map.get(entries[-1], None)
+                    if po is None:
+                        self.play_order_counter += 1
+                        po = self.play_order_counter
+                    parent.add_item('%sindex.html'%adir, None, a.title if a.title else _('Untitled Article'),
+                                    play_order=po, author=auth, description=desc)
+                    last = os.path.join(self.output_dir, ('%sindex.html'%adir).replace('/', os.sep))
+                    for sp in a.sub_pages:
+                        prefix = os.path.commonprefix([opf_path, sp])
+                        relp = sp[len(prefix):]
+                        entries.append(relp.replace(os.sep, '/'))
+                        last = sp
+
+                    if os.path.exists(last):
+                        with open(last, 'rb') as fi:
+                            src = fi.read().decode('utf-8')
+                        soup = BeautifulSoup(src)
+                        body = soup.find('body')
+                        if body is not None:
+                            prefix = '/'.join('..'for i in range(2*len(re.findall(r'link\d+', last))))
+                            templ = self.navbar.generate(True, num, j, len(f),
+                                            not self.has_single_feed,
+                                            a.orig_url, __appname__, prefix=prefix,
+                                            center=self.center_navbar)
+                            elem = BeautifulSoup(templ.render(doctype='xhtml').decode('utf-8')).find('div')
+                            body.insert(len(body.contents), elem)
+                            with open(last, 'wb') as fi:
+                                fi.write(unicode(soup).encode('utf-8'))
+        if len(feeds) == 0:
+            raise Exception('All feeds are empty, aborting.')
+
+        if len(feeds) > 1:
+            for i, f in enumerate(feeds):
+                entries.append('feed_%d/index.html'%i)
+                po = self.play_order_map.get(entries[-1], None)
+                if po is None:
+                    self.play_order_counter += 1
+                    po = self.play_order_counter
+                auth = getattr(f, 'author', None)
+                if not auth:
+                    auth = None
+                desc = getattr(f, 'description', None)
+                if not desc:
+                    desc = None
+                feed_index(i, toc.add_item('feed_%d/index.html'%i, None,
+                    f.title, play_order=po, description=desc, author=auth))
+
+        else:
+            entries.append('feed_%d/index.html'%0)
+            feed_index(0, toc)
+
+        for i, p in enumerate(entries):
+            entries[i] = os.path.join(dir, p.replace('/', os.sep))
+        opf.create_spine(entries)
+        opf.set_toc(toc)
+
+        with nested(open(opf_path, 'wb'), open(ncx_path, 'wb')) as (opf_file, ncx_file):
+            opf.render(opf_file, ncx_file)
+
--- a/resources/recipes/mmc_rtv.recipe
+++ b/resources/recipes/mmc_rtv.recipe
@ -0,0 +1,57 @@
+__license__ = 'GPL v3'
+__copyright__ = '2010, BlonG'
+'''
+www.rtvslo.si
+'''
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class MMCRTV(BasicNewsRecipe):
+    title = u'MMC RTV Slovenija'
+    __author__ = u'BlonG'
+    description = u"Prvi interaktivni multimedijski portal, MMC RTV Slovenija"
+    oldest_article = 3
+    max_articles_per_feed = 20
+    language = 'sl'
+    no_stylesheets = True
+    use_embedded_content = False
+
+    cover_url = 'https://sites.google.com/site/javno2010/home/rtv_slo_cover.jpg'
+
+    extra_css = '''
+            h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
+            h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
+            p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+            body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
+            '''
+
+    def print_version(self, url):
+            split_url = url.split("/")
+            print_url = 'http://www.rtvslo.si/index.php?c_mod=news&op=print&id=' + split_url[-1]
+            return print_url
+
+    keep_only_tags = [
+            dict(name='div', attrs={'class':'title'}),
+            dict(name='div', attrs={'id':'newsbody'}),
+            dict(name='div', attrs={'id':'newsblocks'}),
+            ]
+#    remove_tags=[
+# 40            dict(name='div', attrs={'id':'newsblocks'}),
+#            ]
+
+    feeds = [
+            (u'Slovenija', u'http://www.rtvslo.si/feeds/01.xml'),
+            (u'Svet', u'http://www.rtvslo.si/feeds/02.xml'),
+            (u'Evropska unija', u'http://www.rtvslo.si/feeds/16.xml'),
+            (u'Gospodarstvo', u'http://www.rtvslo.si/feeds/04.xml'),
+            (u'\u010crna kronika', u'http://www.rtvslo.si/feeds/08.xml'),
+            (u'Okolje', u'http://www.rtvslo.si/feeds/12.xml'),
+            (u'Znanost in tehnologija', u'http://www.rtvslo.si/feeds/09.xml'),
+            (u'Zabava', u'http://www.rtvslo.si/feeds/06.xml'),
+            (u'Ture avanture', u'http://www.rtvslo.si/feeds/28.xml'),
+            ]
+
+#    def preprocess_html(self, soup):
+#            newsblocks = soup.find('div',attrs = ['id':'newsblocks'])
+#            soup.find('div', attrs = {'id':'newsbody'}).insert(-1, newsblocks)
+#            return soup
+
--- a/resources/recipes/montevideo_com.recipe
+++ b/resources/recipes/montevideo_com.recipe
@ -0,0 +1,56 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
+'''
+http://www.montevideo.com.uy
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Noticias(BasicNewsRecipe):
+    title                 = 'Montevideo COMM'
+    __author__            = 'Gustavo Azambuja'
+    description           = 'Noticias de Uruguay'
+    language       = 'es'
+    timefmt        = '[%a, %d %b, %Y]'
+    use_embedded_content  = False
+    recursion             = 5
+    encoding = 'utf-8'
+    remove_javascript = True
+    no_stylesheets = True
+
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    keep_only_tags = [dict(id=['txt'])]
+    remove_tags = [
+             dict(name=['object','link'])
+                  ]
+
+    remove_attributes = ['width','height', 'style', 'font', 'color']
+
+    extra_css = '''
+                h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
+                h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
+                h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
+                p {font-family:Arial,Helvetica,sans-serif;}
+                '''
+    feeds = [
+           (u'Destacados', u'http://www.montevideo.com.uy/anxml.aspx?58'),
+           (u'Noticias', u'http://www.montevideo.com.uy/anxml.aspx?59'),
+           (u'Tecnologia', u'http://www.montevideo.com.uy/anxml.aspx?133'),
+           (u'Tiempo Libre', u'http://www.montevideo.com.uy/anxml.aspx?60'),
+           # (u'Deportes', u'http://www.montevideo.com.uy/anxml.aspx?968'),
+           # (u'Pantallazo', u'http://www.montevideo.com.uy/anxml.aspx?1022'),
+           (u'Gastronomia', u'http://www.montevideo.com.uy/anxml.aspx?1023')
+        ]
+
+    def get_cover_url(self):
+		return 'http://sphotos.ak.fbcdn.net/hphotos-ak-snc1/hs276.snc1/10319_147339559330_147337559330_2625816_6636564_n.jpg'
+
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup
+
--- a/resources/recipes/moscow_times.recipe
+++ b/resources/recipes/moscow_times.recipe
@ -1,30 +1,32 @@
-#!/usr/bin/env  python
-
 __license__   = 'GPL v3'
-__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
+__copyright__ = '2008-2010, Darko Miletic <darko.miletic at gmail.com>'
 '''
-moscowtimes.ru
+www.themoscowtimes.com
 '''

 from calibre.web.feeds.news import BasicNewsRecipe

 class Moscowtimes(BasicNewsRecipe):
-    title                 = u'The Moscow Times'
+    title                 = 'The Moscow Times'
    __author__            = 'Darko Miletic and Sujata Raman'
-    description           = 'News from Russia'
+    description           = 'The Moscow Times is a daily English-language newspaper featuring objective, reliable news on business, politics, sports and culture in Moscow, in Russia and the former Soviet Union (CIS).'
+    category              = 'Russia, Moscow, Russian news, Moscow news, Russian newspaper, daily news, independent news, reliable news, USSR, Soviet Union, CIS, Russian politics, Russian business, Russian culture, Russian opinion, St Petersburg, Saint Petersburg'
+    publisher             = 'The Moscow Times'
    language              = 'en'
-    lang = 'en'
-    oldest_article        = 7
+    oldest_article        = 2
    max_articles_per_feed = 100
    no_stylesheets        = True
    use_embedded_content  = False
-    #encoding = 'utf-8'
-    encoding =  'cp1252'
-    remove_javascript = True
+    remove_empty_feeds    = True
+    encoding              = 'cp1251'
+    masthead_url          = 'http://www.themoscowtimes.com/bitrix/templates/tmt/img/logo.gif'
+    publication_type      = 'newspaper'

    conversion_options = {
                          'comment'   : description
-        , 'language'         : lang
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
                        }

    extra_css      = '''
@ -35,39 +37,37 @@ class Moscowtimes(BasicNewsRecipe):
                        .text{font-family:Arial,Tahoma,Verdana,Helvetica,sans-serif ; font-size:75%; }
                        '''
    feeds          = [
-                        (u'The Moscow Times Top Stories' , u'http://www.themoscowtimes.com/rss/top'),
-                        (u'The Moscow Times Current Issue' , u'http://www.themoscowtimes.com/rss/issue'),
-                        (u'The Moscow Times News' , u'http://www.themoscowtimes.com/rss/news'),
-                        (u'The Moscow Times Business' , u'http://www.themoscowtimes.com/rss/business'),
-                        (u'The Moscow Times Art and Ideas' , u'http://www.themoscowtimes.com/rss/art'),
-                        (u'The Moscow Times Opinion' , u'http://www.themoscowtimes.com/rss/opinion')
-                     ]
-
-    keep_only_tags = [
-                        dict(name='div', attrs={'class':['newstextblock']})
+                         (u'Top Stories'   , u'http://www.themoscowtimes.com/rss/top'     )
+                        ,(u'Current Issue' , u'http://www.themoscowtimes.com/rss/issue'   )
+                        ,(u'News'          , u'http://www.themoscowtimes.com/rss/news'    )
+                        ,(u'Business'      , u'http://www.themoscowtimes.com/rss/business')
+                        ,(u'Art and Ideas' , u'http://www.themoscowtimes.com/rss/art'     )
+                        ,(u'Opinion'       , u'http://www.themoscowtimes.com/rss/opinion' )
                     ]

+    keep_only_tags = [dict(name='div', attrs={'id':'content'})]
    remove_tags    = [
-                        dict(name='div', attrs={'class':['photo_nav']})
+                       dict(name='div', attrs={'class':['photo_nav','phototext']})
+                      ,dict(name=['iframe','meta','base','link','embed','object'])
                     ]
                     
    def preprocess_html(self, soup):
-        soup.html['xml:lang'] = self.lang
-        soup.html['lang']     = self.lang
-        mtag = '<meta http-equiv="Content-Type" content="text/html; charset=' + self.encoding + '">'
-        soup.head.insert(0,mtag)
-
-        return self.adeify_images(soup)
+        for lnk in soup.findAll('a'):
+            if lnk.string is not None:
+               ind = self.tag_to_string(lnk)
+               lnk.replaceWith(ind)
+        return soup

+    def print_version(self, url):        
+        return url.replace('.themoscowtimes.com/','.themoscowtimes.com/print/')

    def get_cover_url(self):
-
+        cover_url = None
        href =  'http://www.themoscowtimes.com/pdf/'
-
        soup = self.index_to_soup(href)        
        div = soup.find('div',attrs={'class':'left'})
+        if div:
            a = div.find('a')
-        print a
            if a :
-           cover_url = a.img['src']
+               cover_url = 'http://www.themoscowtimes.com' + a.img['src']
        return cover_url
--- a/resources/recipes/msnsankei.recipe
+++ b/resources/recipes/msnsankei.recipe
@ -6,6 +6,8 @@ __copyright__ = '2010, Hiroshi Miura <miurahr@linux.com>'
 sankei.jp.msn.com
 '''

+from calibre.web.feeds.news import BasicNewsRecipe
+
 class MSNSankeiNewsProduct(BasicNewsRecipe):
    title          = u'MSN\u7523\u7d4c\u30cb\u30e5\u30fc\u30b9(\u65b0\u5546\u54c1)'
    __author__      = 'Hiroshi Miura'
--- a/resources/recipes/newsweek_polska.recipe
+++ b/resources/recipes/newsweek_polska.recipe
@ -0,0 +1,68 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2010, Mateusz Kielar, matek09@gmail.com'
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Newsweek(BasicNewsRecipe):
+	EDITION = 0
+
+	title = u'Newsweek Polska'
+	__author__ = 'Mateusz Kielar'
+	description = 'Weekly magazine'
+	encoding = 'utf-8'
+	no_stylesheets = True
+	language = 'en'
+	remove_javascript = True
+
+	keep_only_tags =[]
+	keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'article'}))
+
+	remove_tags =[]
+	remove_tags.append(dict(name = 'div', attrs = {'class' : 'copy'}))
+	remove_tags.append(dict(name = 'div', attrs = {'class' : 'url'}))
+
+	extra_css = '''
+					.body {font-size: small}
+					.author {font-size: x-small}
+					.lead {font-size: x-small}
+					.title{font-size: x-large; font-weight: bold}
+					'''
+
+	def print_version(self, url):
+		return url.replace("http://www.newsweek.pl/artykuly/wydanie/" + str(self.EDITION), "http://www.newsweek.pl/artykuly") + '/print'
+
+	def find_last_full_issue(self):
+		page = self.index_to_soup('http://www.newsweek.pl/Frames/IssueCover.aspx')
+		issue = 'http://www.newsweek.pl/Frames/' + page.find(lambda tag: tag.name == 'span' and not tag.attrs).a['href']
+		page = self.index_to_soup(issue)
+		issue = 'http://www.newsweek.pl/Frames/' + page.find(lambda tag: tag.name == 'span' and not tag.attrs).a['href']
+		page = self.index_to_soup(issue)
+		self.EDITION = page.find('a', attrs={'target' : '_parent'})['href'].replace('/wydania/','')
+
+	def parse_index(self):
+		self.find_last_full_issue()
+		soup = self.index_to_soup('http://www.newsweek.pl/wydania/' + str(self.EDITION))
+		img = soup.find('img', id="ctl00_C1_PaperIsssueView_IssueImage", src=True)
+		self.cover_url = img['src']
+		feeds = []
+		parent = soup.find(id='content-left-big')
+		for txt in parent.findAll(attrs={'class':'txt_normal_red strong'}):
+			section = self.tag_to_string(txt).capitalize()
+			articles = list(self.find_articles(txt))
+			feeds.append((section, articles))
+		return feeds
+
+	def find_articles(self, txt):
+		for a in txt.findAllNext( attrs={'class':['strong','hr']}):
+			if a.name in "div":
+				break
+			yield {
+				'title' : self.tag_to_string(a),
+				'url'   : 'http://www.newsweek.pl'+a['href'],
+				'date'  : '',
+				'description' : ''
+				}
+
+
--- a/resources/recipes/nikkei_free.recipe
+++ b/resources/recipes/nikkei_free.recipe
@ -6,6 +6,8 @@ __copyright__ = '2010, Hiroshi Miura <miurahr@linux.com>'
 www.nikkei.com
 '''

+from calibre.web.feeds.news import BasicNewsRecipe
+
 class NikkeiNet(BasicNewsRecipe):
    title          = u'\u65e5\u7d4c\u65b0\u805e\u96fb\u5b50\u7248(Free)'
    __author__     = 'Hiroshi Miura'
--- a/resources/recipes/nikkei_sub.recipe
+++ b/resources/recipes/nikkei_sub.recipe
@ -0,0 +1,125 @@
+import re
+from calibre.web.feeds.recipes import BasicNewsRecipe
+import mechanize
+from calibre.ptempfile import PersistentTemporaryFile
+
+
+class NikkeiNet_subscription(BasicNewsRecipe):
+    title           = u'\u65e5\u7d4c\u65b0\u805e\u96fb\u5b50\u7248'
+    __author__      = 'Hiroshi Miura'
+    description     = 'News and current market affairs from Japan'
+    needs_subscription = True
+    oldest_article  = 2
+    max_articles_per_feed = 20
+    language        = 'ja'
+    remove_javascript = False
+    temp_files = []
+
+    remove_tags_before = {'class':"cmn-section cmn-indent"}
+    remove_tags = [
+                       {'class':"JSID_basePageMove JSID_baseAsyncSubmit cmn-form_area JSID_optForm_utoken"},
+                       {'class':"cmn-article_keyword cmn-clearfix"},
+                       {'class':"cmn-print_headline cmn-clearfix"},
+                         ]
+    remove_tags_after = {'class':"cmn-pr_list"}
+
+
+    def get_browser(self):
+        br = BasicNewsRecipe.get_browser()
+
+        cj = mechanize.LWPCookieJar()
+        br.set_cookiejar(cj)
+
+        #br.set_debug_http(True)
+        #br.set_debug_redirects(True)
+        #br.set_debug_responses(True)
+
+        if self.username is not None and self.password is not None:
+            #print "----------------------------get login form--------------------------------------------"
+            # open login form
+            br.open('https://id.nikkei.com/lounge/nl/base/LA0010.seam')
+            response = br.response()
+            #print "----------------------------get login form---------------------------------------------"
+            #print "----------------------------set login form---------------------------------------------"
+            # remove disabled input which brings error on mechanize
+            response.set_data(response.get_data().replace("<input id=\"j_id48\"", "<!-- "))
+            response.set_data(response.get_data().replace("gm_home_on.gif\" />", " -->"))
+            br.set_response(response)
+            br.select_form(name='LA0010Form01')
+            br['LA0010Form01:LA0010Email']   = self.username
+            br['LA0010Form01:LA0010Password'] = self.password
+            br.form.find_control(id='LA0010Form01:LA0010AutoLoginOn',type="checkbox").get(nr=0).selected = True
+            br.submit()
+            br.response()
+            #print "----------------------------send login form---------------------------------------------"
+            #print "----------------------------open news main page-----------------------------------------"
+            # open news site
+            br.open('http://www.nikkei.com/')
+            br.response()
+            #print "----------------------------www.nikkei.com BODY   --------------------------------------"
+            #print response2.get_data()
+            #print "-------------------------^^-got auto redirect form----^^--------------------------------"
+            # forced redirect in default
+            br.select_form(nr=0)
+            br.submit()
+            response3 = br.response()
+            # return some cookie which should be set by Javascript
+            #print response3.geturl()
+            raw = response3.get_data()
+            #print "---------------------------response to form --------------------------------------------"
+            # grab cookie from JS and set it
+            redirectflag = re.search(r"var checkValue = '(\d+)';", raw, re.M).group(1)
+            br.select_form(nr=0)
+
+            self.temp_files.append(PersistentTemporaryFile('_fa.html'))
+            self.temp_files[-1].write("#LWP-Cookies-2.0\n")
+
+            self.temp_files[-1].write("Set-Cookie3: Cookie-dummy=Cookie-value; domain=\".nikkei.com\"; path=\"/\"; path_spec; secure; expires=\"2029-12-21 05:07:59Z\"; version=0\n")
+            self.temp_files[-1].write("Set-Cookie3: redirectFlag="+redirectflag+"; domain=\".nikkei.com\"; path=\"/\"; path_spec; secure; expires=\"2029-12-21 05:07:59Z\"; version=0\n")
+            self.temp_files[-1].close()
+            cj.load(self.temp_files[-1].name)
+
+            br.submit()
+
+            #br.set_debug_http(False)
+            #br.set_debug_redirects(False)
+            #br.set_debug_responses(False)
+        return br
+
+
+
+    feeds = [ (u'\u65e5\u7d4c\u4f01\u696d', 	u'http://www.zou3.net/php/rss/nikkei2rss.php?head=sangyo'),
+		 (u'\u65e5\u7d4c\u88fd\u54c1',	u'http://www.zou3.net/php/rss/nikkei2rss.php?head=newpro'),
+		 (u'internet',		u'http://www.zou3.net/php/rss/nikkei2rss.php?head=internet'),
+		 (u'\u653f\u6cbb', 		u'http://www.zou3.net/php/rss/nikkei2rss.php?head=seiji'),
+		 (u'\u8ca1\u52d9', 		u'http://www.zou3.net/php/rss/nikkei2rss.php?head=zaimu'),
+		 (u'\u7d4c\u6e08', 		u'http://www.zou3.net/php/rss/nikkei2rss.php?head=keizai'),
+		 (u'\u56fd\u969b', 		u'http://www.zou3.net/php/rss/nikkei2rss.php?head=kaigai'),
+		 (u'\u79d1\u5b66', 		u'http://www.zou3.net/php/rss/nikkei2rss.php?head=kagaku'),
+		 (u'\u30de\u30fc\u30b1\u30c3\u30c8', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=market'),
+		 (u'\u304f\u3089\u3057', 	u'http://www.zou3.net/php/rss/nikkei2rss.php?head=kurashi'),
+		 (u'\u30b9\u30dd\u30fc\u30c4', 	u'http://www.zou3.net/php/rss/nikkei2rss.php?head=sports'),
+		 (u'\u793e\u4f1a', 		u'http://www.zou3.net/php/rss/nikkei2rss.php?head=shakai'),
+		 (u'\u30a8\u30b3', 		u'http://www.zou3.net/php/rss/nikkei2rss.php?head=eco'),
+		 (u'\u5065\u5eb7', 		u'http://www.zou3.net/php/rss/nikkei2rss.php?head=kenkou'),
+		 (u'\u96c7\u7528', 		u'http://www.zou3.net/php/rss/nikkei2rss.php?head=koyou'),
+		 (u'\u6559\u80b2', 		u'http://www.zou3.net/php/rss/nikkei2rss.php?head=kyouiku'),
+		 (u'\u304a\u304f\u3084\u307f', 	u'http://www.zou3.net/php/rss/nikkei2rss.php?head=okuyami'),
+		 (u'\u4eba\u4e8b', 		u'http://www.zou3.net/php/rss/nikkei2rss.php?head=zinzi'),
+		 (u'\u7279\u96c6', 		u'http://www.zou3.net/php/rss/nikkei2rss.php?head=special'),
+		 (u'\u5730\u57df\u30cb\u30e5\u30fc\u30b9', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=local'),
+		 (u'\u7d71\u8a08\u30fb\u767d\u66f8', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=report'),
+		 (u'\u30e9\u30f3\u30ad\u30f3\u30b0', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=ranking'),
+		 (u'\u4f1a\u898b', 		u'http://www.zou3.net/php/rss/nikkei2rss.php?head=interview'),
+		 (u'\u793e\u8aac\u30fb\u6625\u79cb', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=shasetsu'),
+		 (u'\u30b9\u30dd\u30fc\u30c4\uff1a\u30d7\u30ed\u91ce\u7403', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=baseball'),
+		 (u'\u30b9\u30dd\u30fc\u30c4\uff1a\u5927\u30ea\u30fc\u30b0', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=mlb'),
+		 (u'\u30b9\u30dd\u30fc\u30c4\uff1a\u30b5\u30c3\u30ab\u30fc', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=soccer'),
+		 (u'\u30b9\u30dd\u30fc\u30c4\uff1a\u30b4\u30eb\u30d5', 	u'http://www.zou3.net/php/rss/nikkei2rss.php?head=golf'),
+		 (u'\u30b9\u30dd\u30fc\u30c4\uff1a\u76f8\u64b2', 	u'http://www.zou3.net/php/rss/nikkei2rss.php?head=sumou'),
+		 (u'\u30b9\u30dd\u30fc\u30c4\uff1a\u7af6\u99ac', 	u'http://www.zou3.net/php/rss/nikkei2rss.php?head=keiba'),
+ 		 (u'\u8abf\u67fb\u30fb\u30a2\u30f3\u30b1\u30fc\u30c8', 	u'http://www.zou3.net/php/rss/nikkei2rss.php?head=research')
+		]
+
+
+
--- a/resources/recipes/nikkei_sub_economy.recipe
+++ b/resources/recipes/nikkei_sub_economy.recipe
@ -6,13 +6,11 @@ __copyright__ = '2010, Hiroshi Miura <miurahr@linux.com>'
 www.nikkei.com
 '''

-import string, re, sys
-from calibre import strftime
+import re
 from calibre.web.feeds.recipes import BasicNewsRecipe
 import mechanize
 from calibre.ptempfile import PersistentTemporaryFile

-
 class NikkeiNet_sub_economy(BasicNewsRecipe):
    title           = u'\u65e5\u7d4c\u65b0\u805e\u96fb\u5b50\u7248(\u7d4c\u6e08)'
    __author__      = 'Hiroshi Miura'
@ -70,12 +68,12 @@ class NikkeiNet_sub_economy(BasicNewsRecipe):
            br['LA0010Form01:LA0010Password'] = self.password
            br.form.find_control(id='LA0010Form01:LA0010AutoLoginOn',type="checkbox").get(nr=0).selected = True
            br.submit()
-            response1 = br.response()
+            br.response()
            #print "----------------------------send login form---------------------------------------------"
            #print "----------------------------open news main page-----------------------------------------"
            # open news site
            br.open('http://www.nikkei.com/')
-            response2 = br.response()
+            br.response()
            #print "----------------------------www.nikkei.com BODY   --------------------------------------"
            #print response2.get_data()
            #print "-------------------------^^-got auto redirect form----^^--------------------------------"
--- a/resources/recipes/nikkei_sub_industry.recipe
+++ b/resources/recipes/nikkei_sub_industry.recipe
@ -6,8 +6,7 @@ __copyright__ = '2010, Hiroshi Miura <miurahr@linux.com>'
 www.nikkei.com
 '''

-import string, re, sys
-from calibre import strftime
+import re
 from calibre.web.feeds.recipes import BasicNewsRecipe
 import mechanize
 from calibre.ptempfile import PersistentTemporaryFile
@ -68,12 +67,12 @@ class NikkeiNet_sub_industory(BasicNewsRecipe):
            br['LA0010Form01:LA0010Password'] = self.password
            br.form.find_control(id='LA0010Form01:LA0010AutoLoginOn',type="checkbox").get(nr=0).selected = True
            br.submit()
-            response1 = br.response()
+            br.response()
            #print "----------------------------send login form---------------------------------------------"
            #print "----------------------------open news main page-----------------------------------------"
            # open news site
            br.open('http://www.nikkei.com/')
-            response2 = br.response()
+            br.response()
            #print "----------------------------www.nikkei.com BODY   --------------------------------------"
            #print response2.get_data()
            #print "-------------------------^^-got auto redirect form----^^--------------------------------"
--- a/resources/recipes/nikkei_sub_life.recipe
+++ b/resources/recipes/nikkei_sub_life.recipe
@ -6,8 +6,7 @@ __copyright__ = '2010, Hiroshi Miura <miurahr@linux.com>'
 www.nikkei.com
 '''

-import string, re, sys
-from calibre import strftime
+import re
 from calibre.web.feeds.recipes import BasicNewsRecipe
 import mechanize
 from calibre.ptempfile import PersistentTemporaryFile
@ -69,12 +68,12 @@ class NikkeiNet_sub_life(BasicNewsRecipe):
            br['LA0010Form01:LA0010Password'] = self.password
            br.form.find_control(id='LA0010Form01:LA0010AutoLoginOn',type="checkbox").get(nr=0).selected = True
            br.submit()
-            response1 = br.response()
+            br.response()
            #print "----------------------------send login form---------------------------------------------"
            #print "----------------------------open news main page-----------------------------------------"
            # open news site
            br.open('http://www.nikkei.com/')
-            response2 = br.response()
+            br.response()
            #print "----------------------------www.nikkei.com BODY   --------------------------------------"
            #print response2.get_data()
            #print "-------------------------^^-got auto redirect form----^^--------------------------------"
--- a/resources/recipes/nikkei_sub_main.recipe
+++ b/resources/recipes/nikkei_sub_main.recipe
@ -6,8 +6,7 @@ __copyright__ = '2010, Hiroshi Miura <miurahr@linux.com>'
 www.nikkei.com
 '''

-import string, re, sys
-from calibre import strftime
+import re
 from calibre.web.feeds.recipes import BasicNewsRecipe
 import mechanize
 from calibre.ptempfile import PersistentTemporaryFile
@ -62,12 +61,12 @@ class NikkeiNet_sub_main(BasicNewsRecipe):
            br['LA0010Form01:LA0010Password'] = self.password
            br.form.find_control(id='LA0010Form01:LA0010AutoLoginOn',type="checkbox").get(nr=0).selected = True
            br.submit()
-            response1 = br.response()
+            br.response()
            #print "----------------------------send login form---------------------------------------------"
            #print "----------------------------open news main page-----------------------------------------"
            # open news site
            br.open('http://www.nikkei.com/')
-            response2 = br.response()
+            br.response()
            #print "----------------------------www.nikkei.com BODY   --------------------------------------"
            #print response2.get_data()
            #print "-------------------------^^-got auto redirect form----^^--------------------------------"
--- a/resources/recipes/nikkei_sub_sports.recipe
+++ b/resources/recipes/nikkei_sub_sports.recipe
@ -6,8 +6,7 @@ __copyright__ = '2010, Hiroshi Miura <miurahr@linux.com>'
 www.nikkei.com
 '''

-import string, re, sys
-from calibre import strftime
+import re
 from calibre.web.feeds.recipes import BasicNewsRecipe
 import mechanize
 from calibre.ptempfile import PersistentTemporaryFile
@ -69,12 +68,12 @@ class NikkeiNet_sub_sports(BasicNewsRecipe):
            br['LA0010Form01:LA0010Password'] = self.password
            br.form.find_control(id='LA0010Form01:LA0010AutoLoginOn',type="checkbox").get(nr=0).selected = True
            br.submit()
-            response1 = br.response()
+            br.response()
            #print "----------------------------send login form---------------------------------------------"
            #print "----------------------------open news main page-----------------------------------------"
            # open news site
            br.open('http://www.nikkei.com/')
-            response2 = br.response()
+            br.response()
            #print "----------------------------www.nikkei.com BODY   --------------------------------------"
            #print response2.get_data()
            #print "-------------------------^^-got auto redirect form----^^--------------------------------"
--- a/resources/recipes/now_toronto.recipe
+++ b/resources/recipes/now_toronto.recipe
@ -0,0 +1,36 @@
+#!/usr/bin/env  python
+# -*- coding: utf-8 -*-
+#Based on Lars Jacob's Taz Digiabo recipe
+
+__license__   = 'GPL v3'
+__copyright__ = '2010, Starson17'
+
+import os, urllib2, zipfile
+from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.ptempfile import PersistentTemporaryFile
+
+class NowToronto(BasicNewsRecipe):
+    title = u'Now Toronto'
+    description = u'Now Toronto'
+    __author__ = 'Starson17'
+    language = 'en_CA'
+    conversion_options = {
+        'no_default_epub_cover' : True
+    }
+
+    def build_index(self):
+        epub_feed = "http://feeds.feedburner.com/NowEpubEditions"
+        soup = self.index_to_soup(epub_feed)
+        url = soup.find(name = 'feedburner:origlink').string
+        f = urllib2.urlopen(url)
+        tmp = PersistentTemporaryFile(suffix='.epub')
+        self.report_progress(0,_('downloading epub'))
+        tmp.write(f.read())
+        tmp.close()
+        zfile = zipfile.ZipFile(tmp.name, 'r')
+        self.report_progress(0,_('extracting epub'))
+        zfile.extractall(self.output_dir)
+        tmp.close()
+        index = os.path.join(self.output_dir, 'content.opf')
+        self.report_progress(1,_('epub downloaded and extracted'))
+        return index
--- a/resources/recipes/nytimes.recipe
+++ b/resources/recipes/nytimes.recipe
@ -7,14 +7,22 @@ nytimes.com
 '''
 import re, string, time
 from calibre import entity_to_unicode, strftime
+from datetime import timedelta, date
 from calibre.web.feeds.recipes import BasicNewsRecipe
 from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag, BeautifulStoneSoup

+
 class NYTimes(BasicNewsRecipe):

-    # set headlinesOnly to True for the headlines-only version
+    # set headlinesOnly to True for the headlines-only version. If True, webEdition is ignored.
    headlinesOnly = True

+    # set webEdition to True for the Web edition of the newspaper. Set oldest_article to the
+    # number of days old an article can be for inclusion. If oldest_article = 0 all articles
+    # will be included. Note: oldest_article is ignored if webEdition = False
+    webEdition = False
+    oldest_article = 7
+
    # includeSections: List of sections to include. If empty, all sections found will be included.
    # Otherwise, only the sections named will be included. For example,
    #
@ -39,20 +47,76 @@ class NYTimes(BasicNewsRecipe):
    # from an article (if one exists).  If one_picture_per_article = True, the image
    # will be moved to a location between the headline and the byline.
    # If one_picture_per_article = False, all images from the article will be included
-
    # and shown in their original location.
-    one_picture_per_article = True
+    one_picture_per_article = False

    # The maximum number of articles that will be downloaded
    max_articles_per_feed = 100

+    # Whether to omit duplicates of articles (typically arsing when articles are indexed in
+    # more than one section). If True, only the first occurance will be downloaded.
+    filterDuplicates = True
+
+    # Sections to collect for the Web edition.
+    # Delete any you don't want, or use includeSections or excludeSections
+    web_sections = [(u'World',u'world'),
+                    (u'U.S.',u'national'),
+                    (u'Politics',u'politics'),
+                    (u'New York',u'nyregion'),
+                    (u'Business','business'),
+                    (u'Technology',u'technology'),
+                    (u'Sports',u'sports'),
+                    (u'Science',u'science'),
+                    (u'Health',u'health'),
+                    (u'Opinion',u'opinion'),
+                    (u'Arts',u'arts'),
+                    (u'Books',u'books'),
+                    (u'Movies',u'movies'),
+                    (u'Music',u'arts/music'),
+                    (u'Television',u'arts/television'),
+                    (u'Style',u'style'),
+                    (u'Dining & Wine',u'dining'),
+                    (u'Fashion & Style',u'fashion'),
+                    (u'Home & Garden',u'garden'),
+                    (u'Travel',u'travel'),
+                    ('Education',u'education'),
+                    ('Multimedia',u'multimedia'),
+                    (u'Obituaries',u'obituaries'),
+                    (u'Sunday Magazine',u'magazine'),
+                    (u'Week in Review',u'weekinreview')]
+

    if headlinesOnly:
        title='New York Times Headlines'
        description = 'Headlines from the New York Times'
+        needs_subscription = False
+    elif webEdition:
+        title='New York Times (Web)'
+        description = 'New York Times on the Web'
+        needs_subscription = True
    else:
        title='New York Times'
        description = 'Today\'s New York Times'
+        needs_subscription = True
+
+
+    month_list = ['january','february','march','april','may','june','july','august','september','october','november','december']
+
+    def decode_us_date(self,datestr):
+        udate = datestr.strip().lower().split()
+        try:
+            m = self.month_list.index(udate[0])+1
+        except:
+            return date.today()
+        d = int(udate[1])
+        y = int(udate[2])
+        try:
+            d = date(y,m,d)
+        except:
+            d = date.today
+        return d
+
+    earliest_date = date.today() - timedelta(days=oldest_article)

    __author__  = 'GRiker/Kovid Goyal/Nick Redding'
    language = 'en'
@ -136,6 +200,12 @@ class NYTimes(BasicNewsRecipe):
                .image {text-align: center;}
                .source {text-align: left; }'''

+
+    articles = {}
+    key = None
+    ans = []
+    url_list = []
+
    def filter_ans(self, ans) :
        total_article_count = 0
        idx = 0
@ -164,6 +234,29 @@ class NYTimes(BasicNewsRecipe):
        self.log( "Queued %d articles" % total_article_count )
        return ans

+    def exclude_url(self,url):
+        if not url.startswith("http"):
+            return True
+        if not url.endswith(".html"):
+            return True
+        if 'nytimes.com' not in url:
+            return True
+        if 'podcast' in url:
+            return True
+        if '/video/' in url:
+            return True
+        if '/slideshow/' in url:
+            return True
+        if '/magazine/index' in url:
+            return True
+        if '/interactive/' in url:
+            return True
+        if '/reference/' in url:
+            return True
+        if '/premium/' in url:
+            return True
+        return False
+
    def fixChars(self,string):
        # Replace lsquo (\x91)
        fixed = re.sub("\x91","‘",string)
@ -249,7 +342,6 @@ class NYTimes(BasicNewsRecipe):
            return BeautifulSoup(_raw, markupMassage=massage)

        # Entry point
-        print "index_to_soup()"
        soup = get_the_soup( self.encoding, url_or_raw )
        contentType = soup.find(True,attrs={'http-equiv':'Content-Type'})
        docEncoding =  str(contentType)[str(contentType).find('charset=') + len('charset='):str(contentType).rfind('"')]
@ -273,33 +365,24 @@ class NYTimes(BasicNewsRecipe):
        else:
            return description

-    def parse_todays_index(self):
-
-        def feed_title(div):
+    def feed_title(self,div):
        return ''.join(div.findAll(text=True, recursive=True)).strip()

-        articles = {}
-        key = None
-        ans = []
-        url_list = []
-
-        def handle_article(div):
+    def handle_article(self,div):
+        thumbnail = div.find('div','thumbnail')
+        if thumbnail:
+            thumbnail.extract()
        a = div.find('a', href=True)
        if not a:
            return
        url = re.sub(r'\?.*', '', a['href'])
-            if not url.startswith("http"):
-                return
-            if not url.endswith(".html"):
-                return
-            if 'podcast' in url:
-                return
-            if '/video/' in url:
+        if self.exclude_url(url):
            return
        url += '?pagewanted=all'
-            if url in url_list:
+        if self.filterDuplicates:
+            if url in self.url_list:
                return
-            url_list.append(url)
+        self.url_list.append(url)
        title = self.tag_to_string(a, use_alt=True).strip()
        description = ''
        pubdate = strftime('%a, %d %b')
@ -314,42 +397,78 @@ class NYTimes(BasicNewsRecipe):
            authorAttribution = div.find(True, attrs={'class':'byline'})
            if authorAttribution:
                author = self.tag_to_string(authorAttribution, use_alt=False)
-            feed = key if key is not None else 'Uncategorized'
-            if not articles.has_key(feed):
-                ans.append(feed)
-                articles[feed] = []
-            articles[feed].append(
+        feed = self.key if self.key is not None else 'Uncategorized'
+        if not self.articles.has_key(feed):
+            self.ans.append(feed)
+            self.articles[feed] = []
+        self.articles[feed].append(
                        dict(title=title, url=url, date=pubdate,
                            description=description, author=author,
                            content=''))


+    def parse_web_edition(self):
+
+        for (sec_title,index_url) in self.web_sections:
+            if self.includeSections != []:
+                if sec_title not in self.includeSections:
+                    print "SECTION NOT INCLUDED: ",sec_title
+                    continue
+            if sec_title in self.excludeSections:
+                print "SECTION EXCLUDED: ",sec_title
+                continue
+            print 'Index URL: '+'http://www.nytimes.com/pages/'+index_url+'/index.html'
+            soup = self.index_to_soup('http://www.nytimes.com/pages/'+index_url+'/index.html')
+            self.key = sec_title
+            # Find each article
+            for div in soup.findAll(True,
+                attrs={'class':['section-headline', 'story', 'story headline','sectionHeader','headlinesOnly multiline flush']}):
+                if div['class'] in ['story', 'story headline'] :
+                    self.handle_article(div)
+                elif div['class'] == 'headlinesOnly multiline flush':
+                    for lidiv in div.findAll('li'):
+                        self.handle_article(lidiv)
+
+        self.ans = [(k, self.articles[k]) for k in self.ans if self.articles.has_key(k)]
+        return self.filter_ans(self.ans)
+
+
+    def parse_todays_index(self):
+
        soup = self.index_to_soup('http://www.nytimes.com/pages/todayspaper/index.html')

-
+        skipping = False
        # Find each article
        for div in soup.findAll(True,
            attrs={'class':['section-headline', 'story', 'story headline','sectionHeader','headlinesOnly multiline flush']}):

            if div['class'] in ['section-headline','sectionHeader']:
-                key = string.capwords(feed_title(div))
-                key = key.replace('Op-ed','Op-Ed')
-                key = key.replace('U.s.','U.S.')
+                self.key = string.capwords(self.feed_title(div))
+                self.key = self.key.replace('Op-ed','Op-Ed')
+                self.key = self.key.replace('U.s.','U.S.')
+                self.key = self.key.replace('N.y.','N.Y.')
+                skipping = False
+                if self.includeSections != []:
+                    if self.key not in self.includeSections:
+                        print "SECTION NOT INCLUDED: ",self.key
+                        skipping = True
+                if self.key in self.excludeSections:
+                    print "SECTION EXCLUDED: ",self.key
+                    skipping = True
+
            elif div['class'] in ['story', 'story headline'] :
-                handle_article(div)
+                if not skipping:
+                    self.handle_article(div)
            elif div['class'] == 'headlinesOnly multiline flush':
                for lidiv in div.findAll('li'):
-                    handle_article(lidiv)
+                    if not skipping:
+                        self.handle_article(lidiv)

-        ans = [(key, articles[key]) for key in ans if articles.has_key(key)]
-        return self.filter_ans(ans)
+        self.ans = [(k, self.articles[k]) for k in self.ans if self.articles.has_key(k)]
+        return self.filter_ans(self.ans)

    def parse_headline_index(self):

-        articles = {}
-        ans = []
-        url_list = []
-
        soup = self.index_to_soup('http://www.nytimes.com/pages/todaysheadlines/')

        # Fetch the content table
@ -363,15 +482,24 @@ class NYTimes(BasicNewsRecipe):
        for td_col in content_table.findAll('td', {'id' : re.compile('Column')}):
            for div_sec in td_col.findAll('div',recursive=False):
                for h6_sec_name in div_sec.findAll('h6',{'style' : re.compile('text-transform: *uppercase')}):
+
                    section_name = self.tag_to_string(h6_sec_name,use_alt=False)
                    section_name = re.sub(r'^ *$','',section_name)
+
                    if section_name == '':
                        continue
+                    if self.includeSections != []:
+                        if section_name not in self.includeSections:
+                            print "SECTION NOT INCLUDED: ",section_name
+                            continue
+                    if section_name in self.excludeSections:
+                        print "SECTION EXCLUDED: ",section_name
+                        continue
+
                    section_name=string.capwords(section_name)
-                    if section_name == 'U.s.':
-                       section_name = 'U.S.'
-                    elif section_name == 'Op-ed':
-                       section_name = 'Op-Ed'
+                    section_name = section_name.replace('Op-ed','Op-Ed')
+                    section_name = section_name.replace('U.s.','U.S.')
+                    section_name = section_name.replace('N.y.','N.Y.')
                    pubdate = strftime('%a, %d %b')

                    search_div = div_sec
@ -392,37 +520,32 @@ class NYTimes(BasicNewsRecipe):
                        if not a:
                            continue
                        url = re.sub(r'\?.*', '', a['href'])
-                        if not url.startswith("http"):
-                            continue
-                        if not url.endswith(".html"):
-                            continue
-                        if 'podcast' in url:
-                            continue
-                        if 'video' in url:
+                        if self.exclude_url(url):
                            continue
                        url += '?pagewanted=all'
-                        if url in url_list:
+                        if self.filterDuplicates:
+                            if url in self.url_list:
                                continue
-                        url_list.append(url)
-                        self.log("URL %s" % url)
+                        self.url_list.append(url)
                        title = self.tag_to_string(a, use_alt=True).strip()
                        desc = h3_item.find('p')
                        if desc is not None:
                            description = self.tag_to_string(desc,use_alt=False)
                        else:
                            description = ''
-                        if not articles.has_key(section_name):
-                            ans.append(section_name)
-                            articles[section_name] = []
-                        articles[section_name].append(dict(title=title, url=url, date=pubdate, description=description, author=author, content=''))
+                        if not self.articles.has_key(section_name):
+                            self.ans.append(section_name)
+                            self.articles[section_name] = []
+                        self.articles[section_name].append(dict(title=title, url=url, date=pubdate, description=description, author=author, content=''))

-
-        ans = [(key, articles[key]) for key in ans if articles.has_key(key)]
-        return self.filter_ans(ans)
+        self.ans = [(k, self.articles[k]) for k in self.ans if self.articles.has_key(k)]
+        return self.filter_ans(self.ans)

    def parse_index(self):
        if self.headlinesOnly:
            return self.parse_headline_index()
+        elif self.webEdition:
+            return self.parse_web_edition()
        else:
            return self.parse_todays_index()

@ -438,6 +561,21 @@ class NYTimes(BasicNewsRecipe):

    def preprocess_html(self, soup):

+        if self.webEdition & (self.oldest_article>0):
+            date_tag = soup.find(True,attrs={'class': ['dateline','date']})
+            if date_tag:
+                date_str = self.tag_to_string(date_tag,use_alt=False)
+                date_str = date_str.replace('Published:','')
+                date_items = date_str.split(',')
+                try:
+                    datestring = date_items[0]+' '+date_items[1]
+                    article_date = self.decode_us_date(datestring)
+                except:
+                    article_date = date.today()
+                if article_date < self.earliest_date:
+                    self.log("Skipping article dated %s" % date_str)
+                    return None
+
        kicker_tag = soup.find(attrs={'class':'kicker'})
        if kicker_tag: # remove Op_Ed author head shots
            tagline = self.tag_to_string(kicker_tag)
@ -462,7 +600,6 @@ class NYTimes(BasicNewsRecipe):
                    for inlineImg in inlineImgs[1:]:
                        inlineImg.extract()
                    # Move firstImg before article body
-                    #article_body = soup.find(True, {'id':'articleBody'})
                    cgFirst = soup.find(True, {'class':re.compile('columnGroup  *first')})
                    if cgFirst:
                        # Strip all sibling NavigableStrings: noise
@ -548,4 +685,3 @@ class NYTimes(BasicNewsRecipe):
            divTag.replaceWith(tag)

        return soup
-
--- a/resources/recipes/nytimes_sub.recipe
+++ b/resources/recipes/nytimes_sub.recipe
@ -7,14 +7,22 @@ nytimes.com
 '''
 import re, string, time
 from calibre import entity_to_unicode, strftime
+from datetime import timedelta, date
 from calibre.web.feeds.recipes import BasicNewsRecipe
 from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag, BeautifulStoneSoup

+
 class NYTimes(BasicNewsRecipe):

-    # set headlinesOnly to True for the headlines-only version
+    # set headlinesOnly to True for the headlines-only version. If True, webEdition is ignored.
    headlinesOnly = False

+    # set webEdition to True for the Web edition of the newspaper. Set oldest_article to the
+    # number of days old an article can be for inclusion. If oldest_article = 0 all articles
+    # will be included. Note: oldest_article is ignored if webEdition = False
+    webEdition = False
+    oldest_article = 7
+
    # includeSections: List of sections to include. If empty, all sections found will be included.
    # Otherwise, only the sections named will be included. For example,
    #
@ -39,20 +47,76 @@ class NYTimes(BasicNewsRecipe):
    # from an article (if one exists).  If one_picture_per_article = True, the image
    # will be moved to a location between the headline and the byline.
    # If one_picture_per_article = False, all images from the article will be included
-
    # and shown in their original location.
-    one_picture_per_article = True
+    one_picture_per_article = False

    # The maximum number of articles that will be downloaded
    max_articles_per_feed = 100

+    # Whether to omit duplicates of articles (typically arsing when articles are indexed in
+    # more than one section). If True, only the first occurance will be downloaded.
+    filterDuplicates = True
+
+    # Sections to collect for the Web edition.
+    # Delete any you don't want, or use includeSections or excludeSections
+    web_sections = [(u'World',u'world'),
+                    (u'U.S.',u'national'),
+                    (u'Politics',u'politics'),
+                    (u'New York',u'nyregion'),
+                    (u'Business','business'),
+                    (u'Technology',u'technology'),
+                    (u'Sports',u'sports'),
+                    (u'Science',u'science'),
+                    (u'Health',u'health'),
+                    (u'Opinion',u'opinion'),
+                    (u'Arts',u'arts'),
+                    (u'Books',u'books'),
+                    (u'Movies',u'movies'),
+                    (u'Music',u'arts/music'),
+                    (u'Television',u'arts/television'),
+                    (u'Style',u'style'),
+                    (u'Dining & Wine',u'dining'),
+                    (u'Fashion & Style',u'fashion'),
+                    (u'Home & Garden',u'garden'),
+                    (u'Travel',u'travel'),
+                    ('Education',u'education'),
+                    ('Multimedia',u'multimedia'),
+                    (u'Obituaries',u'obituaries'),
+                    (u'Sunday Magazine',u'magazine'),
+                    (u'Week in Review',u'weekinreview')]
+

    if headlinesOnly:
        title='New York Times Headlines'
        description = 'Headlines from the New York Times'
+        needs_subscription = False
+    elif webEdition:
+        title='New York Times (Web)'
+        description = 'New York Times on the Web'
+        needs_subscription = True
    else:
        title='New York Times'
        description = 'Today\'s New York Times'
+        needs_subscription = True
+
+
+    month_list = ['january','february','march','april','may','june','july','august','september','october','november','december']
+
+    def decode_us_date(self,datestr):
+        udate = datestr.strip().lower().split()
+        try:
+            m = self.month_list.index(udate[0])+1
+        except:
+            return date.today()
+        d = int(udate[1])
+        y = int(udate[2])
+        try:
+            d = date(y,m,d)
+        except:
+            d = date.today
+        return d
+
+    earliest_date = date.today() - timedelta(days=oldest_article)

    __author__  = 'GRiker/Kovid Goyal/Nick Redding'
    language = 'en'
@ -60,7 +124,6 @@ class NYTimes(BasicNewsRecipe):


    timefmt = ''
-    needs_subscription = True
    masthead_url = 'http://graphics8.nytimes.com/images/misc/nytlogo379x64.gif'
    cover_margins = (18,18,'grey99')

@ -137,6 +200,12 @@ class NYTimes(BasicNewsRecipe):
                .image {text-align: center;}
                .source {text-align: left; }'''

+
+    articles = {}
+    key = None
+    ans = []
+    url_list = []
+
    def filter_ans(self, ans) :
        total_article_count = 0
        idx = 0
@ -165,6 +234,29 @@ class NYTimes(BasicNewsRecipe):
        self.log( "Queued %d articles" % total_article_count )
        return ans

+    def exclude_url(self,url):
+        if not url.startswith("http"):
+            return True
+        if not url.endswith(".html"):
+            return True
+        if 'nytimes.com' not in url:
+            return True
+        if 'podcast' in url:
+            return True
+        if '/video/' in url:
+            return True
+        if '/slideshow/' in url:
+            return True
+        if '/magazine/index' in url:
+            return True
+        if '/interactive/' in url:
+            return True
+        if '/reference/' in url:
+            return True
+        if '/premium/' in url:
+            return True
+        return False
+
    def fixChars(self,string):
        # Replace lsquo (\x91)
        fixed = re.sub("\x91","‘",string)
@ -250,7 +342,6 @@ class NYTimes(BasicNewsRecipe):
            return BeautifulSoup(_raw, markupMassage=massage)

        # Entry point
-        print "index_to_soup()"
        soup = get_the_soup( self.encoding, url_or_raw )
        contentType = soup.find(True,attrs={'http-equiv':'Content-Type'})
        docEncoding =  str(contentType)[str(contentType).find('charset=') + len('charset='):str(contentType).rfind('"')]
@ -274,33 +365,24 @@ class NYTimes(BasicNewsRecipe):
        else:
            return description

-    def parse_todays_index(self):
-
-        def feed_title(div):
+    def feed_title(self,div):
        return ''.join(div.findAll(text=True, recursive=True)).strip()

-        articles = {}
-        key = None
-        ans = []
-        url_list = []
-
-        def handle_article(div):
+    def handle_article(self,div):
+        thumbnail = div.find('div','thumbnail')
+        if thumbnail:
+            thumbnail.extract()
        a = div.find('a', href=True)
        if not a:
            return
        url = re.sub(r'\?.*', '', a['href'])
-            if not url.startswith("http"):
-                return
-            if not url.endswith(".html"):
-                return
-            if 'podcast' in url:
-                return
-            if '/video/' in url:
+        if self.exclude_url(url):
            return
        url += '?pagewanted=all'
-            if url in url_list:
+        if self.filterDuplicates:
+            if url in self.url_list:
                return
-            url_list.append(url)
+        self.url_list.append(url)
        title = self.tag_to_string(a, use_alt=True).strip()
        description = ''
        pubdate = strftime('%a, %d %b')
@ -315,42 +397,78 @@ class NYTimes(BasicNewsRecipe):
            authorAttribution = div.find(True, attrs={'class':'byline'})
            if authorAttribution:
                author = self.tag_to_string(authorAttribution, use_alt=False)
-            feed = key if key is not None else 'Uncategorized'
-            if not articles.has_key(feed):
-                ans.append(feed)
-                articles[feed] = []
-            articles[feed].append(
+        feed = self.key if self.key is not None else 'Uncategorized'
+        if not self.articles.has_key(feed):
+            self.ans.append(feed)
+            self.articles[feed] = []
+        self.articles[feed].append(
                        dict(title=title, url=url, date=pubdate,
                            description=description, author=author,
                            content=''))


+    def parse_web_edition(self):
+
+        for (sec_title,index_url) in self.web_sections:
+            if self.includeSections != []:
+                if sec_title not in self.includeSections:
+                    print "SECTION NOT INCLUDED: ",sec_title
+                    continue
+            if sec_title in self.excludeSections:
+                print "SECTION EXCLUDED: ",sec_title
+                continue
+            print 'Index URL: '+'http://www.nytimes.com/pages/'+index_url+'/index.html'
+            soup = self.index_to_soup('http://www.nytimes.com/pages/'+index_url+'/index.html')
+            self.key = sec_title
+            # Find each article
+            for div in soup.findAll(True,
+                attrs={'class':['section-headline', 'story', 'story headline','sectionHeader','headlinesOnly multiline flush']}):
+                if div['class'] in ['story', 'story headline'] :
+                    self.handle_article(div)
+                elif div['class'] == 'headlinesOnly multiline flush':
+                    for lidiv in div.findAll('li'):
+                        self.handle_article(lidiv)
+
+        self.ans = [(k, self.articles[k]) for k in self.ans if self.articles.has_key(k)]
+        return self.filter_ans(self.ans)
+
+
+    def parse_todays_index(self):
+
        soup = self.index_to_soup('http://www.nytimes.com/pages/todayspaper/index.html')

-
+        skipping = False
        # Find each article
        for div in soup.findAll(True,
            attrs={'class':['section-headline', 'story', 'story headline','sectionHeader','headlinesOnly multiline flush']}):

            if div['class'] in ['section-headline','sectionHeader']:
-                key = string.capwords(feed_title(div))
-                key = key.replace('Op-ed','Op-Ed')
-                key = key.replace('U.s.','U.S.')
+                self.key = string.capwords(self.feed_title(div))
+                self.key = self.key.replace('Op-ed','Op-Ed')
+                self.key = self.key.replace('U.s.','U.S.')
+                self.key = self.key.replace('N.y.','N.Y.')
+                skipping = False
+                if self.includeSections != []:
+                    if self.key not in self.includeSections:
+                        print "SECTION NOT INCLUDED: ",self.key
+                        skipping = True
+                if self.key in self.excludeSections:
+                    print "SECTION EXCLUDED: ",self.key
+                    skipping = True
+
            elif div['class'] in ['story', 'story headline'] :
-                handle_article(div)
+                if not skipping:
+                    self.handle_article(div)
            elif div['class'] == 'headlinesOnly multiline flush':
                for lidiv in div.findAll('li'):
-                    handle_article(lidiv)
+                    if not skipping:
+                        self.handle_article(lidiv)

-        ans = [(key, articles[key]) for key in ans if articles.has_key(key)]
-        return self.filter_ans(ans)
+        self.ans = [(k, self.articles[k]) for k in self.ans if self.articles.has_key(k)]
+        return self.filter_ans(self.ans)

    def parse_headline_index(self):

-        articles = {}
-        ans = []
-        url_list = []
-
        soup = self.index_to_soup('http://www.nytimes.com/pages/todaysheadlines/')

        # Fetch the content table
@ -364,15 +482,24 @@ class NYTimes(BasicNewsRecipe):
        for td_col in content_table.findAll('td', {'id' : re.compile('Column')}):
            for div_sec in td_col.findAll('div',recursive=False):
                for h6_sec_name in div_sec.findAll('h6',{'style' : re.compile('text-transform: *uppercase')}):
+
                    section_name = self.tag_to_string(h6_sec_name,use_alt=False)
                    section_name = re.sub(r'^ *$','',section_name)
+
                    if section_name == '':
                        continue
+                    if self.includeSections != []:
+                        if section_name not in self.includeSections:
+                            print "SECTION NOT INCLUDED: ",section_name
+                            continue
+                    if section_name in self.excludeSections:
+                        print "SECTION EXCLUDED: ",section_name
+                        continue
+
                    section_name=string.capwords(section_name)
-                    if section_name == 'U.s.':
-                       section_name = 'U.S.'
-                    elif section_name == 'Op-ed':
-                       section_name = 'Op-Ed'
+                    section_name = section_name.replace('Op-ed','Op-Ed')
+                    section_name = section_name.replace('U.s.','U.S.')
+                    section_name = section_name.replace('N.y.','N.Y.')
                    pubdate = strftime('%a, %d %b')

                    search_div = div_sec
@ -393,37 +520,32 @@ class NYTimes(BasicNewsRecipe):
                        if not a:
                            continue
                        url = re.sub(r'\?.*', '', a['href'])
-                        if not url.startswith("http"):
-                            continue
-                        if not url.endswith(".html"):
-                            continue
-                        if 'podcast' in url:
-                            continue
-                        if 'video' in url:
+                        if self.exclude_url(url):
                            continue
                        url += '?pagewanted=all'
-                        if url in url_list:
+                        if self.filterDuplicates:
+                            if url in self.url_list:
                                continue
-                        url_list.append(url)
-                        self.log("URL %s" % url)
+                        self.url_list.append(url)
                        title = self.tag_to_string(a, use_alt=True).strip()
                        desc = h3_item.find('p')
                        if desc is not None:
                            description = self.tag_to_string(desc,use_alt=False)
                        else:
                            description = ''
-                        if not articles.has_key(section_name):
-                            ans.append(section_name)
-                            articles[section_name] = []
-                        articles[section_name].append(dict(title=title, url=url, date=pubdate, description=description, author=author, content=''))
+                        if not self.articles.has_key(section_name):
+                            self.ans.append(section_name)
+                            self.articles[section_name] = []
+                        self.articles[section_name].append(dict(title=title, url=url, date=pubdate, description=description, author=author, content=''))

-
-        ans = [(key, articles[key]) for key in ans if articles.has_key(key)]
-        return self.filter_ans(ans)
+        self.ans = [(k, self.articles[k]) for k in self.ans if self.articles.has_key(k)]
+        return self.filter_ans(self.ans)

    def parse_index(self):
        if self.headlinesOnly:
            return self.parse_headline_index()
+        elif self.webEdition:
+            return self.parse_web_edition()
        else:
            return self.parse_todays_index()

@ -439,6 +561,21 @@ class NYTimes(BasicNewsRecipe):

    def preprocess_html(self, soup):

+        if self.webEdition & (self.oldest_article>0):
+            date_tag = soup.find(True,attrs={'class': ['dateline','date']})
+            if date_tag:
+                date_str = self.tag_to_string(date_tag,use_alt=False)
+                date_str = date_str.replace('Published:','')
+                date_items = date_str.split(',')
+                try:
+                    datestring = date_items[0]+' '+date_items[1]
+                    article_date = self.decode_us_date(datestring)
+                except:
+                    article_date = date.today()
+                if article_date < self.earliest_date:
+                    self.log("Skipping article dated %s" % date_str)
+                    return None
+
        kicker_tag = soup.find(attrs={'class':'kicker'})
        if kicker_tag: # remove Op_Ed author head shots
            tagline = self.tag_to_string(kicker_tag)
@ -463,7 +600,6 @@ class NYTimes(BasicNewsRecipe):
                    for inlineImg in inlineImgs[1:]:
                        inlineImg.extract()
                    # Move firstImg before article body
-                    #article_body = soup.find(True, {'id':'articleBody'})
                    cgFirst = soup.find(True, {'class':re.compile('columnGroup  *first')})
                    if cgFirst:
                        # Strip all sibling NavigableStrings: noise
--- a/resources/recipes/observa_digital.recipe
+++ b/resources/recipes/observa_digital.recipe
@ -0,0 +1,63 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
+'''
+observa.com.uy
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Noticias(BasicNewsRecipe):
+    title                 = 'Observa Digital'
+    __author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
+    description           = 'Noticias desde Uruguay'
+    language       = 'es'
+    timefmt        = '[%a, %d %b, %Y]'
+    use_embedded_content  = False
+    recursion             = 5
+    encoding = 'utf8'
+    remove_javascript = True
+    no_stylesheets = True
+
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    keep_only_tags = [dict(id=['contenido'])]
+    remove_tags = [
+             dict(name='div', attrs={'id':'contenedorVinculadas'}),
+             dict(name='p', attrs={'id':'nota_firma'}),
+             dict(name=['object','link'])
+                  ]
+
+    remove_attributes = ['width','height', 'style', 'font', 'color']
+
+    extra_css = '''
+                h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
+                h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
+                h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
+                p {font-family:Arial,Helvetica,sans-serif;}
+                '''
+    feeds = [
+           (u'Actualidad', u'http://www.observa.com.uy/RSS/actualidad.xml'),
+           (u'Deportes', u'http://www.observa.com.uy/RSS/deportes.xml'),
+           (u'Vida', u'http://www.observa.com.uy/RSS/vida.xml'),
+           (u'Ciencia y Tecnologia', u'http://www.observa.com.uy/RSS/ciencia.xml')
+        ]
+
+    def get_cover_url(self):
+		cover_url = None
+		index = 'http://www.elobservador.com.uy/elobservador/nav_portada.asp?suplemento=dia'
+		soup = self.index_to_soup(index)
+		link_item = soup.find('img',attrs={'usemap':'#mapeo_imagenes'})
+		if link_item:
+			cover_url = 'http://www.elobservador.com.uy'+link_item['src'].strip()
+
+		print cover_url
+
+		return cover_url
+
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup
--- a/resources/recipes/pagina12.recipe
+++ b/resources/recipes/pagina12.recipe
@ -21,8 +21,16 @@ class Pagina12(BasicNewsRecipe):
    use_embedded_content  = False
    language              = 'es'
    remove_empty_feeds    = True
+    publication_type      = 'newspaper'
    masthead_url          = 'http://www.pagina12.com.ar/commons/imgs/logo-home.gif'
-    extra_css             = ' body{font-family: Arial,Helvetica,sans-serif } img{margin-bottom: 0.4em} #autor{font-weight: bold} #fecha,#epigrafe{font-size: 0.9em; margin: 5px} #imagen{border: 1px solid black; margin: 0 0 1.25em 1.25em; width: 232px }  '
+    extra_css             = """ 
+                               body{font-family: Arial,Helvetica,sans-serif } 
+                               img{margin-bottom: 0.4em; display:block}
+                               #autor{font-weight: bold} 
+                               #fecha,#epigrafe{font-size: 0.9em; margin: 5px} 
+                               #imagen{border: 1px solid black; margin: 0 0 1.25em 1.25em; width: 232px }
+                               .fgprincipal{font-size: large; font-weight: bold}
+                            """

    conversion_options = {
                          'comment'   : description
@ -31,7 +39,11 @@ class Pagina12(BasicNewsRecipe):
                        , 'language'  : language
                        }

-    remove_tags = [dict(name='div', attrs={'id':['volver','logo','logo_suple','fin','permalink']})]
+    remove_tags = [
+                     dict(name=['meta','link'])
+                    ,dict(name='div', attrs={'id':['volver','logo','logo_suple','fin','permalink']})
+                  ]
+    remove_attributes=['lang']


    feeds = [
@ -65,4 +77,13 @@ class Pagina12(BasicNewsRecipe):
    def preprocess_html(self, soup):
        for item in soup.findAll(style=True):
            del item['style']
+        for item in soup.findAll('span', attrs={'id':'seccion'}):
+            it = item.a
+            it.name='span'
+            del it['href']
+            del it['title']
+        for item in soup.findAll('p'):
+            it = item.find('h3')            
+            if it:
+               it.name='span'
        return soup
--- a/resources/recipes/pc_lab.recipe
+++ b/resources/recipes/pc_lab.recipe
@ -0,0 +1,70 @@
+#!/usr/bin/env  python
+
+from calibre.web.feeds.recipes import BasicNewsRecipe
+
+class PCLab(BasicNewsRecipe):
+    cover_url             = 'http://pclab.pl/img/logo.png'
+    title                 = u"PC Lab"
+    __author__            = 'ravcio - rlelusz[at]gmail.com'
+    description           = u"Articles from PC Lab website"
+    language              = 'pl'
+    oldest_article        = 30.0
+    max_articles_per_feed = 100
+    recursions            = 0
+    encoding              = 'iso-8859-2'
+    no_stylesheets        = True
+    remove_javascript     = True
+    use_embedded_content  = False
+
+    keep_only_tags = [
+            dict(name='div', attrs={'class':['substance']})
+                     ]
+
+    remove_tags = [
+            dict(name='div', attrs={'class':['chapters']})
+            ,dict(name='div', attrs={'id':['script_bxad_slot_display_list_bxad_slot']})
+                  ]
+
+    remove_tags_after = [
+            dict(name='div', attrs={'class':['navigation']})
+                ]
+
+    #links to RSS feeds
+    feeds = [ ('PCLab', u'http://pclab.pl/xml/artykuly.xml') ]
+
+    #load second and subsequent page content
+    # in: soup - full page with 'next' button
+    # out: appendtag - tag to which new page is to be added
+    def append_page(self, soup, appendtag):
+        # find the 'Next' button
+        pager = soup.find('div', attrs={'class':'next'})
+
+        if pager:
+            #search for 'a' element with link to next page (exit if not found)
+            a = pager.find('a')
+            if a:
+                nexturl = a['href']
+
+                soup2 = self.index_to_soup('http://pclab.pl/' + nexturl)
+
+                pagetext_substance = soup2.find('div', attrs={'class':'substance'})
+                pagetext = pagetext_substance.find('div', attrs={'class':'data'})
+                pagetext.extract()
+
+                pos = len(appendtag.contents)
+                appendtag.insert(pos, pagetext)
+                pos = len(appendtag.contents)
+
+                self.append_page(soup2, appendtag)
+
+
+    def preprocess_html(self, soup):
+
+        # soup.body contains no title and no navigator, they are in soup
+        self.append_page(soup, soup.body)
+
+        # finally remove some tags
+        tags = soup.findAll('div',attrs={'class':['tags', 'index', 'script_bxad_slot_display_list_bxad_slot', 'index first', 'zumi', 'navigation']})
+        [tag.extract() for tag in tags]
+
+        return soup
--- a/resources/recipes/politika.recipe
+++ b/resources/recipes/politika.recipe
@ -1,13 +1,10 @@
-#!/usr/bin/env  python
-
 __license__   = 'GPL v3'
-__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
+__copyright__ = '2008-2010, Darko Miletic <darko.miletic at gmail.com>'
 '''
 politika.rs
 '''
 import re
 from calibre.web.feeds.news import BasicNewsRecipe
-from calibre.ebooks.BeautifulSoup import Tag

 class Politika(BasicNewsRecipe):
    title                 = 'Politika Online'
@ -19,53 +16,51 @@ class Politika(BasicNewsRecipe):
    max_articles_per_feed = 100
    no_stylesheets        = True
    use_embedded_content  = False
-    remove_javascript     = True
    encoding              = 'utf8'
+    delay                 = 1
    language              = 'sr'
-
-    lang                 = 'sr-Latn-RS'
-    direction            = 'ltr'
-    extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{font-family: serif1, serif} .article_description{font-family: sans1, sans-serif}'
+    publication_type      = 'newspaper'    
+    masthead_url          = 'http://static.politika.co.rs/images_new/politika.gif'    
+    extra_css             = """ 
+                               @font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} 
+                               @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} 
+                               body{font-family: Arial,Helvetica,sans1,sans-serif}
+                               h1{font-family: "Times New Roman",Times,serif1,serif}
+                               .articledescription{font-family: sans1, sans-serif}
+                            """

    conversion_options = {
                          'comment'   : description
                        , 'tags'      : category
                        , 'publisher' : publisher
-                        , 'language'         : lang
-                        , 'pretty_print'     : True
+                        , 'language'  : language
                        }


    preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]

-    keep_only_tags     = [dict(name='div', attrs={'class':'content_center_border'})]
-
-    remove_tags = [
-                    dict(name='div', attrs={'class':['send_print','txt-komentar']})
-                   ,dict(name=['object','link','a'])
-                   ,dict(name='h1', attrs={'class':'box_header-tags'})
-                  ]
-
+    keep_only_tags     = [dict(name='div', attrs={'class':'big_article_home item_details'})]
+    remove_tags_after  = dict(attrs={'class':'online_date'})
+    remove_tags        = [dict(name=['link','meta','iframe','embed','object'])]
    
    feeds          = [
                         (u'Politika'         , u'http://www.politika.rs/rubrike/Politika/index.1.lt.xml'         )
                        ,(u'Svet'             , u'http://www.politika.rs/rubrike/Svet/index.1.lt.xml'             )
-                        ,(u'Redakcijski komentari', u'http://www.politika.rs/rubrike/redakcijski-komentari/index.1.lt.xml')
+                        ,(u'Ostali komentari' , u'http://www.politika.rs/rubrike/ostali-komentari/index.1.lt.xml' )
                        ,(u'Pogledi'          , u'http://www.politika.rs/pogledi/index.lt.xml'                    )
                        ,(u'Pogledi sa strane', u'http://www.politika.rs/rubrike/Pogledi-sa-strane/index.1.lt.xml')
                        ,(u'Tema dana'        , u'http://www.politika.rs/rubrike/tema-dana/index.1.lt.xml'        )
                        ,(u'Kultura'          , u'http://www.politika.rs/rubrike/Kultura/index.1.lt.xml'          )
-                        ,(u'Zivot i stil'         , u'http://www.politika.rs/rubrike/zivot-i-stil/index.1.lt.xml'         )
+                        ,(u'Spektar'          , u'http://www.politika.rs/rubrike/zivot-i-stil/index.1.lt.xml'     )
                     ]

    def preprocess_html(self, soup):
-        soup.html['lang'] = self.lang
-        soup.html['dir' ] = self.direction
-        mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)])
-        soup.head.insert(0,mlang)
        for item in soup.findAll(style=True):
            del item['style']
-        ftag = soup.find('div',attrs={'class':'content_center_border'})
-        if ftag.has_key('align'):
-           del ftag['align']
-        return self.adeify_images(soup)
+        for item in soup.findAll('a', attrs={'class':'category'}):
+            item.name='span'
+            if item.has_key('href'):            
+               del item['href']
+            if item.has_key('title'):            
+               del item['title']
+        return soup
--- a/resources/recipes/polityka.recipe
+++ b/resources/recipes/polityka.recipe
@ -0,0 +1,68 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2010, Mateusz Kielar, matek09@gmail.com'
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Polityka(BasicNewsRecipe):
+
+	title = u'Polityka'
+	__author__ = 'Mateusz Kielar'
+	description = 'Weekly magazine. Last archive issue'
+	encoding = 'utf-8'
+	no_stylesheets = True
+	language = 'en'
+	remove_javascript = True
+
+	remove_tags_before = dict(dict(name = 'h2', attrs = {'class' : 'box_nag'}))
+	remove_tags_after = dict(dict(name = 'div', attrs = {'class' : 'box_footer'}))
+
+	remove_tags =[]
+	remove_tags.append(dict(name = 'h2', attrs = {'class' : 'box_nag'}))
+	remove_tags.append(dict(name = 'div', attrs = {'class' : 'box_footer'}))
+
+
+	extra_css = '''
+					h1 {font-size: x-large; font-weight: bold}
+					'''
+
+	def parse_index(self):
+		soup = self.index_to_soup('http://archiwum.polityka.pl/')
+		box_img3 = soup.findAll(attrs={'class' : 'box_img3'})
+		feeds = []
+		last = 0
+		self.cover_url = 'http://archiwum.polityka.pl' + box_img3[-1].find('img')['src']
+		last_edition = 'http://archiwum.polityka.pl' + box_img3[-1].find('a')['href']
+
+		while True:
+			index = self.index_to_soup(last_edition)
+
+
+			box_list = index.findAll('div', attrs={'class' : 'box_list'})
+			if len(box_list) == 0:
+				break
+
+			articles = {}
+			for box in box_list:
+				for div in box.findAll('div', attrs={'class': 'list_tresc'}):
+					article_page = self.index_to_soup('http://archiwum.polityka.pl' + div.a['href'],)
+					section = self.tag_to_string(article_page.find('h2', attrs = {'class' : 'box_nag'})).split('/')[0].lstrip().rstrip()
+					print section
+					if not articles.has_key(section):
+						articles[section] = []
+					articles[section].append( {
+						'title' : self.tag_to_string(div.a),
+						'url'   : 'http://archiwum.polityka.pl' + div.a['href'],
+						'date'  : '',
+						'description' : ''
+						})
+
+			for section in articles:
+				feeds.append((section, articles[section]))
+
+			last_edition = last_edition.replace('http://archiwum.polityka.pl/wydanie/' + str(last), 'http://archiwum.polityka.pl/wydanie/' + str(last + 1))
+			last = last + 1
+
+		return feeds
+
--- a/resources/recipes/rds.recipe
+++ b/resources/recipes/rds.recipe
@ -0,0 +1,18 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class AdvancedUserRecipe1290013720(BasicNewsRecipe):
+    title          = u'RDS'
+    __author__ = 'Nexus'
+    language = 'en_CA'
+    description = 'Hockey News'
+    oldest_article = 7
+    max_articles_per_feed = 25
+    no_stylesheets = True
+    remove_tags = [dict(name='div', attrs={'id':'rdsWrap'}),
+		            dict(name='table', attrs={'id':'aVoir'}),
+		            dict(name='div', attrs={'id':'imageChronique'})]
+    keep_only_tags = [dict(name='div', attrs={'id':['enteteChronique']}),
+		                dict(name='div', attrs={'id':['contenuChronique']})]
+
+
+    feeds          = [(u'RDS', u'http://www.rds.ca/hockey/fildepresse_rds.xml')]
--- a/resources/recipes/revista_bla.recipe
+++ b/resources/recipes/revista_bla.recipe
@ -0,0 +1,54 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
+'''
+http://www.revistabla.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Noticias(BasicNewsRecipe):
+    title                 = 'Revista Bla'
+    __author__            = 'Gustavo Azambuja'
+    description           = 'Moda | Uruguay'
+    language       = 'es'
+    timefmt        = '[%a, %d %b, %Y]'
+    use_embedded_content  = False
+    recursion             = 5
+    encoding = 'utf8'
+    remove_javascript = True
+    no_stylesheets = True
+
+    oldest_article        = 20
+    max_articles_per_feed = 100
+    keep_only_tags = [dict(id=['body_container'])]
+    remove_tags = [
+				 dict(name='div', attrs={'class':['date_text', 'comments', 'form_section', 'share_it']}),
+				 dict(name='div', attrs={'id':['relatedPosts', 'spacer', 'banner_izquierda', 'right_container']}),
+				 dict(name='p', attrs={'class':'FacebookLikeButton'}),
+				 dict(name=['object','link']) ]
+
+    extra_css = '''
+                h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
+                h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
+                h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
+                p {font-family:Arial,Helvetica,sans-serif;}
+                '''
+    feeds = [
+           (u'Articulos', u'http://www.revistabla.com/feed/')
+        ]
+
+    def get_cover_url(self):
+	cover_url = None
+	index = 'http://www.revistabla.com'
+	soup = self.index_to_soup(index)
+	link_item = soup.find('div',attrs={'class':'header_right'})
+	if link_item:
+		cover_url = link_item.img['src']
+	return cover_url
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup
--- a/resources/recipes/revista_muy.recipe
+++ b/resources/recipes/revista_muy.recipe
@ -108,3 +108,10 @@ class RevistaMuyInteresante(BasicNewsRecipe):
                   feeds.append((title, articles))
            return feeds

+    def get_cover_url(self):
+        index = 'http://www.muyinteresante.es/revista'
+        soup = self.index_to_soup(index)
+        link_item = soup.find('img',attrs={'class':'img_portada'})
+        if link_item:
+            cover_url = "http://www.muyinteresante.es"+link_item['src']
+        return cover_url
--- a/resources/recipes/rollingstone.recipe
+++ b/resources/recipes/rollingstone.recipe
@ -0,0 +1,69 @@
+__license__   = 'GPL v3'
+__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
+'''
+rollingstone.com
+'''
+
+import re
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class RollingStone(BasicNewsRecipe):
+    title                 = 'Rolling Stone Magazine - free content'
+    __author__            = 'Darko Miletic'
+    description           = 'Rolling Stone Magazine features music, album and artist news, movie reviews, political, economic and pop culture commentary, videos, photos, and more.'
+    publisher             = 'Werner Media inc.'
+    category              = 'news, music, USA, world'
+    oldest_article        = 15
+    max_articles_per_feed = 200
+    no_stylesheets        = True
+    encoding              = 'utf8'
+    use_embedded_content  = False
+    language              = 'en'
+    remove_empty_feeds    = True
+    publication_type      = 'magazine'
+    masthead_url          = 'http://www.rollingstone.com/templates/rolling-stone-templates/theme/rstheme/images/rsLogo.png'
+    extra_css             = """
+                               body{font-family: Georgia,Times,serif }
+                               img{margin-bottom: 0.4em; display:block}
+                            """
+
+    conversion_options = {
+                          'comment'   : description
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
+                        }
+
+    preprocess_regexps = [
+                          (re.compile(r'xml:lang="en">.*?<head>', re.DOTALL|re.IGNORECASE),lambda match: 'xml:lang="en">\n<head>\n')
+                         ,(re.compile(r'</title>.*?</head>'     , re.DOTALL|re.IGNORECASE),lambda match: '</title>\n</head>\n'     )
+                         ]
+
+    keep_only_tags=[
+                     dict(attrs={'class':['headerImgHolder','headerContent']})
+                    ,dict(name='div',attrs={'id':['teaser','storyTextContainer']})
+                    ,dict(name='div',attrs={'class':'blogDetailModule clearfix'})
+                   ]
+
+    remove_tags = [
+                      dict(name=['meta','iframe','object','embed'])
+                     ,dict(attrs={'id':'mpStoryHeader'})
+                     ,dict(attrs={'class':'relatedTopics'})
+                  ]
+    remove_attributes=['lang','onclick','width','height','name']
+    remove_tags_before=dict(attrs={'class':'bloggerInfo'})
+    remove_tags_after=dict(attrs={'class':'relatedTopics'})
+
+
+    feeds = [
+              (u'All News'      , u'http://www.rollingstone.com/siteServices/rss/allNews'      )
+             ,(u'All Blogs'     , u'http://www.rollingstone.com/siteServices/rss/allBlogs'     )
+             ,(u'Movie Reviews' , u'http://www.rollingstone.com/siteServices/rss/movieReviews' )
+             ,(u'Album Reviews' , u'http://www.rollingstone.com/siteServices/rss/albumReviews' )
+             ,(u'Song Reviews'  , u'http://www.rollingstone.com/siteServices/rss/songReviews'  )
+            ]
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup
--- a/resources/recipes/scprint.recipe
+++ b/resources/recipes/scprint.recipe
@ -0,0 +1,73 @@
+from calibre.web.feeds.news import BasicNewsRecipe, LoginFailed
+
+class SCPrintMagazine(BasicNewsRecipe):
+    title          = u'SC Print Magazine'
+    __author__ = u'Tony Maro'
+    description = u'Last print version of the data security magazine'
+    INDEX = "http://www.scmagazineus.com/issuearchive/"
+    no_stylesheets = True
+    language = 'en'
+    keep_only_tags = [dict(id=['article','review'])]
+    remove_tags = [dict(id=['articlePrintTools','reviewBodyColumn'])]
+    LOG_IN = 'http://www.scmagazineus.com/login/'
+    tags = 'News,SC Magazine'
+    needs_subscription = True
+
+    def parse_index(self):
+        articles = []
+        issuelink = printsections = None
+
+        soup = self.index_to_soup(self.INDEX)
+        sectit = soup.find('div', attrs={'class':'issueArchiveItem'})
+        if sectit is not None:
+            linkt = sectit.find('a')
+            issuelink = linkt['href']
+            imgt = sectit.find('img')
+            self.cover_url = imgt['src']
+
+        if issuelink is not None:
+            issue = self.index_to_soup(issuelink)
+            if issue is not None:
+                printsections = issue.findAll('div',attrs={'class':'PrintSection'})
+        if printsections is not None:
+            for printsection in printsections:
+                onesection = []
+                sectiontitle = printsection.find('h3').contents[0]
+                articlesec = printsection.findAll('div',attrs={'class':'IssueArchiveFormat'})
+                if articlesec is not None:
+                    ''' got articles '''
+                    for onearticle in articlesec:
+                        ''' process one article '''
+                        arttitlet = onearticle.find('h3')
+                        if arttitlet is not None:
+                            mylink = arttitlet.find('a')
+                            if mylink is not None:
+                                if mylink.has_key('title'):
+                                    arttitle = mylink['title']
+                                else:
+                                    arttitle = 'unknown'
+                                if mylink.has_key('href'):
+                                    artlink = mylink['href']
+                                    artlink = artlink.replace("/article","/printarticle")
+                                    artlink = artlink.replace("/review","/printreview")
+                                    deck = onearticle.find('div',attrs={'class':'deck'})
+                                    if deck is not None:
+                                        deck = deck.contents[0]
+                                        onesection.append({'title':arttitle, 'url':artlink, 'description':deck,'date':''})
+                    articles.append((sectiontitle, onesection))
+
+        return articles
+
+    def get_browser(self):
+        br = BasicNewsRecipe.get_browser(self)
+        br.open(self.LOG_IN)
+        br.select_form(name='aspnetForm')
+        br['ctl00$ctl00$cphAllPageContent$cphMainContent$SubscriberEasyLoginView1$txtEmail'] = self.username
+        br['ctl00$ctl00$cphAllPageContent$cphMainContent$SubscriberEasyLoginView1$txtPassword'] = self.password
+        raw = br.submit("ctl00$ctl00$cphAllPageContent$cphMainContent$SubscriberEasyLoginView1$btnLogin").read()
+        if 'Logout</a>' not in raw:
+            raise LoginFailed(
+                    _('Failed to log in, check your username and password for'
+                    ' the calibre Periodicals service.'))
+        return br
+
--- a/resources/recipes/siol.recipe
+++ b/resources/recipes/siol.recipe
@ -0,0 +1,55 @@
+# coding: utf-8
+__license__   = 'GPL v3'
+__copyright__ = '2010, BlonG'
+'''
+www.siol.si
+'''
+from calibre.web.feeds.news import BasicNewsRecipe
+class Siol(BasicNewsRecipe):
+    title = u'Siol.net'
+    __author__ = u'BlonG'
+    description = "Multimedijski portal z aktualnimi vsebinami, intervjuji, komentarji iz Slovenije in sveta, sportal, trendi, avtomoto, blogos"
+    oldest_article = 3
+    language = 'sl'
+    max_articles_per_feed = 20
+    no_stylesheets = True
+    use_embedded_content = False
+
+    cover_url = 'https://sites.google.com/site/javno2010/home/siol_cover.jpg'
+
+    extra_css = '''
+                    h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
+                    h2{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
+                    p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
+	'''
+
+    html2lrf_options = ['--base-font-size', '10']
+
+    keep_only_tags = [
+	dict(name='div', attrs={'id':'idContent'}),
+	]
+
+    remove_tags  = [
+	dict(name='span', attrs={'class':'com1'}),
+	dict(name='div', attrs={'class':'relation'}),
+	dict(name='p', attrs={'class':'path'}),
+	dict(name='div', attrs={'class':'clear_r'}),
+	dict(name='div', attrs={'id':'appendix'}),
+	dict(name='div', attrs={'id':'rail'}),
+	dict(name='div', attrs={'id':'div_comments'}),
+	dict(name='div', attrs={'class':'thumbs'}),
+	]
+
+    feeds          = [
+	(u'Slovenija', u'http://www.siol.net/rss.aspx?path=Slovenija')
+	,(u'Lokalne novice', u'http://www.siol.net/rss.aspx?path=Slovenija/Lokalne_novice')
+	,(u'EU', u'http://www.siol.net/rss.aspx?path=EU')
+	,(u'Svet', u'http://www.siol.net/rss.aspx?path=Svet')
+	,(u'Gospodarstvo', u'http://www.siol.net/rss.aspx?path=Gospodarstvo')
+	,(u'Sportal', u'http://www.siol.net/rss.aspx?path=Sportal')
+	,(u'Trendi', u'http://www.siol.net/rss.aspx?path=Trendi')
+	,(u'Avtomoto', u'http://www.siol.net/rss.aspx?path=Avtomoto')
+	,(u'Tehnologija', u'http://www.siol.net/rss.aspx?path=Tehnologija')
+	,(u'TV / Film', u'http://www.siol.net/rss.aspx?path=TV')
+	]
--- a/resources/recipes/spiegelde.recipe
+++ b/resources/recipes/spiegelde.recipe
@ -6,6 +6,7 @@ __copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
 spiegel.de
 '''

+from time import strftime
 from calibre.web.feeds.news import BasicNewsRecipe

 class Spiegel_ger(BasicNewsRecipe):
@ -44,3 +45,6 @@ class Spiegel_ger(BasicNewsRecipe):
        rmain, rsep, rrest = main.rpartition(',')
        purl = rmain + ',druck-' + rrest + ',' + rest
        return purl
+
+    def get_cover_url(self):
+        return 'http://wissen.spiegel.de/wissen/titel/SP/' + strftime("%Y/%W/%j/titel.jpg")
--- a/resources/recipes/tagesan.recipe
+++ b/resources/recipes/tagesan.recipe
@ -7,7 +7,7 @@ class AdvancedUserRecipe1284927619(BasicNewsRecipe):
    __author__ = 'noxxx'
    max_articles_per_feed = 100
    description = 'tagesanzeiger.ch: Nichts verpassen'
-    category = 'News, Politik, Nachrichten, Schweiz, Zürich'
+    category = 'News, Politik, Nachrichten, Schweiz, Zuerich'
    language = 'de'

    conversion_options = {
--- a/resources/recipes/telepolis.recipe
+++ b/resources/recipes/telepolis.recipe
@ -3,12 +3,12 @@
 __license__   = 'GPL v3'
 __copyright__ = '2009, Gerhard Aigner <gerhard.aigner at gmail.com>'

-''' http://www.derstandard.at - Austrian Newspaper '''
+
 import re
 from calibre.web.feeds.news import BasicNewsRecipe

 class TelepolisNews(BasicNewsRecipe):
-    title          = u'Telepolis (News)'
+    title          = u'Telepolis (News+Artikel)'
    __author__ = 'Gerhard Aigner'
    publisher = 'Heise Zeitschriften Verlag GmbH & Co KG'
    description = 'News from telepolis'
@ -26,10 +26,10 @@ class TelepolisNews(BasicNewsRecipe):
    preprocess_regexps = [(re.compile(r'<a[^>]*>', re.DOTALL|re.IGNORECASE), lambda match: ''),
        (re.compile(r'</a>', re.DOTALL|re.IGNORECASE), lambda match: ''),]

-    keep_only_tags = [dict(name = 'table',attrs={'class':'blogtable'})]
-    remove_tags = [dict(name='img'), dict(name='td',attrs={'class':'blogbottom'})]
+    keep_only_tags = [dict(name = 'td',attrs={'class':'bloghead'}),dict(name = 'td',attrs={'class':'blogfliess'})]
+    remove_tags = [dict(name='img'), dict(name='td',attrs={'class':'blogbottom'}), dict(name='td',attrs={'class':'forum'})]

-    feeds          = [(u'News', u'http://www.heise.de/tp/news.rdf')]
+    feeds          = [(u'News', u'http://www.heise.de/tp/news-atom.xml')]

    html2lrf_options = [
        '--comment'  , description
@ -41,7 +41,7 @@ class TelepolisNews(BasicNewsRecipe):

    def get_article_url(self, article):
        '''if the linked article is of kind artikel don't take it'''
-        if (article.link.count('artikel') > 0) :
+        if (article.link.count('artikel') > 1) :
            return None
        return article.link

@ -49,3 +49,5 @@ class TelepolisNews(BasicNewsRecipe):
        mtag = '<meta http-equiv="Content-Type" content="text/html; charset=' + self.encoding + '">'
        soup.head.insert(0,mtag)
        return soup
+
+
--- a/resources/recipes/the_h.recipe
+++ b/resources/recipes/the_h.recipe
@ -6,6 +6,8 @@ __copyright__ = '2010, Hiroshi Miura <miurahr@linux.com>'
 www.h-online.com
 '''

+from calibre.web.feeds.news import BasicNewsRecipe
+
 class TheHeiseOnline(BasicNewsRecipe):
    title          = u'The H'
    __author__     = 'Hiroshi Miura'
--- a/resources/recipes/thn.recipe
+++ b/resources/recipes/thn.recipe
@ -0,0 +1,19 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class AdvancedUserRecipe1289990851(BasicNewsRecipe):
+    title          = u'The Hockey News'
+    language = 'en_CA'
+    __author__ = 'Nexus'
+    oldest_article = 7
+    max_articles_per_feed = 25
+    no_stylesheets = True
+    remove_tags = [dict(name='div', attrs={'class':'article_info'}),
+                          dict(name='div', attrs={'class':'photo_details'}),
+                          dict(name='div', attrs={'class':'tool_menu'}),
+	                  dict(name='div', attrs={'id':'comments_container'}),
+                          dict(name='div', attrs={'id':'wrapper'})]
+    keep_only_tags = [dict(name='h1', attrs={'class':['headline']}),
+		                dict(name='div', attrs={'class':['box_container']})]
+
+    feeds          = [(u'THN', u'http://www.thehockeynews.com/rss/all_categories.xml')]
+
--- a/resources/recipes/tsn.recipe
+++ b/resources/recipes/tsn.recipe
@ -0,0 +1,34 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class AdvancedUserRecipe1289990851(BasicNewsRecipe):
+    title          = u'TSN'
+    oldest_article = 7
+    max_articles_per_feed = 50
+    language = 'en_CA'
+    __author__ = 'Nexus'
+    no_stylesheets = True
+    INDEX = 'http://tsn.ca/nhl/story/?id=nhl'
+    keep_only_tags = [dict(name='div', attrs={'id':['tsnColWrap']}),
+                             dict(name='div', attrs={'id':['tsnStory']})]
+    remove_tags = [dict(name='div', attrs={'id':'tsnRelated'}),
+                          dict(name='div', attrs={'class':'textSize'})]
+
+    def parse_index(self):
+        feeds = []
+        soup = self.index_to_soup(self.INDEX)
+        feed_parts = soup.findAll('div', attrs={'class': 'feature'})
+        for feed_part  in feed_parts:
+            articles = []
+            if not feed_part.h2:
+                continue
+            feed_title = feed_part.h2.string
+            article_parts = feed_part.findAll('a')
+            for article_part in article_parts:
+                article_title = article_part.string
+                article_date = ''
+                article_url = 'http://tsn.ca/' + article_part['href']
+                articles.append({'title': article_title, 'url': article_url, 'description':'', 'date':article_date})
+            if articles:
+                feeds.append((feed_title, articles))
+        return feeds
+
--- a/resources/recipes/vedomosti.recipe
+++ b/resources/recipes/vedomosti.recipe
@ -0,0 +1,195 @@
+#!/usr/bin/env  python
+
+u'''
+Ведомости
+'''
+
+from calibre.web.feeds.feedparser import parse
+from calibre.ebooks.BeautifulSoup import Tag
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class VedomostiRecipe(BasicNewsRecipe):
+    title = u'Ведомости'
+    __author__ = 'Nikolai Kotchetkov'
+    publisher = 'vedomosti.ru'
+    category = 'press, Russia'
+    description = u'Ежедневная деловая газета'
+    oldest_article = 3
+    max_articles_per_feed = 100
+
+    masthead_url = u'http://motorro.com/imgdir/logos/ved_logo_black2_cropped.gif'
+    cover_url = u'http://motorro.com/imgdir/logos/ved_logo_black2_cropped.gif'
+
+    #Add feed names if you want them to be sorted (feeds of this list appear first)
+    sortOrder = [u'_default', u'Первая полоса', u'Власть и деньги']
+
+    encoding = 'cp1251'
+    language = 'ru'
+    no_stylesheets = True
+    remove_javascript = True
+    recursions = 0
+
+    conversion_options = {
+                          'comment'   : description
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
+                        }
+
+
+    keep_only_tags = [dict(name='td', attrs={'class' : ['second_content']})]
+
+    remove_tags_after = [dict(name='div', attrs={'class' : 'article_text'})]
+
+    remove_tags = [dict(name='div', attrs={'class' : ['sep', 'choice', 'articleRightTbl']})]
+
+    feeds = [u'http://www.vedomosti.ru/newspaper/out/rss.xml']
+
+    #base URL for relative links
+    base_url = u'http://www.vedomosti.ru'
+
+    extra_css = 'h1 {font-size: 1.5em; margin: 0em 0em 0em 0em; text-align: center;}'\
+                'h2 {font-size: 1.0em; margin: 0em 0em 0em 0em;}'\
+                'h3 {font-size: 0.8em; margin: 0em 0em 0em 0em;}'\
+                '.article_date {font-size: 0.5em; color: gray; font-family: monospace; text-align:right;}'\
+                '.article_authors {font-size: 0.5em; color: gray; font-family: monospace; text-align:right;}'\
+                '.article_img {width:100%; text-align: center; padding: 3px 3px 3px 3px;}'\
+                '.article_img_desc {width:100%; text-align: center; font-size: 0.5em; color: gray; font-family: monospace;}'\
+                '.article_desc {font-size: 1em; font-style:italic;}'
+
+    def parse_index(self):
+        try:
+            feedData = parse(self.feeds[0])
+            if not feedData:
+                raise NotImplementedError
+            self.log("parse_index: Feed loaded successfully.")
+            if feedData.feed.has_key('title'):
+                self.title = feedData.feed.title
+                self.log("parse_index: Title updated to: ", self.title)
+            if feedData.feed.has_key('description'):
+                self.description = feedData.feed.description
+                self.log("parse_index: Description updated to: ", self.description)
+
+            def get_virtual_feed_articles(feed):
+                if feeds.has_key(feed):
+                    return feeds[feed][1]
+                self.log("Adding new feed: ", feed)
+                articles = []
+                feeds[feed] = (feed, articles)
+                return articles
+
+            feeds = {}
+
+            #Iterate feed items and distribute articles using tags
+            for item in feedData.entries:
+                link = item.get('link', '');
+                title = item.get('title', '');
+                if '' == link or '' == title:
+                    continue
+                article = {'title':title, 'url':link, 'description':item.get('description', ''), 'date':item.get('date', ''), 'content':''};
+                if not item.has_key('tags'):
+                    get_virtual_feed_articles('_default').append(article)
+                    continue
+                for tag in item.tags:
+                    addedToDefault = False
+                    term = tag.get('term', '')
+                    if '' == term:
+                        if (not addedToDefault):
+                            get_virtual_feed_articles('_default').append(article)
+                        continue
+                    get_virtual_feed_articles(term).append(article)
+
+            #Get feed list
+            #Select sorted feeds first of all
+            result = []
+            for feedName in self.sortOrder:
+                if (not feeds.has_key(feedName)): continue
+                result.append(feeds[feedName])
+                del feeds[feedName]
+            result = result + feeds.values()
+
+            return result
+
+        except Exception, err:
+            self.log(err)
+            raise NotImplementedError
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)
+
+    def postprocess_html(self, soup, first_fetch):
+        #self.log('Original: ', soup.prettify())
+
+        #Find article
+        contents = soup.find('div', {'class':['article_text']})
+        if not contents:
+            self.log('postprocess_html: article div not found!')
+            return soup
+        contents.extract()
+
+        #Find title
+        title = soup.find('h1')
+        if title:
+            contents.insert(0, title)
+
+        #Find article image
+        newstop = soup.find('div', {'class':['newstop']})
+        if newstop:
+            img = newstop.find('img')
+            if img:
+                imgDiv = Tag(soup, 'div')
+                imgDiv['class'] = 'article_img'
+
+                if img.has_key('width'):
+                    del(img['width'])
+                if img.has_key('height'):
+                    del(img['height'])
+
+                #find description
+                element = img.parent.nextSibling
+
+                img.extract()
+                imgDiv.insert(0, img)
+
+                while element:
+                    if not isinstance(element, Tag):
+                        continue
+                    nextElement = element.nextSibling
+                    if 'p' == element.name:
+                        element.extract()
+                        element['class'] = 'article_img_desc'
+                        imgDiv.insert(len(imgDiv.contents), element)
+                    element = nextElement
+
+                contents.insert(1, imgDiv)
+
+        #find article abstract
+        abstract = soup.find('p', {'class':['subhead']})
+        if abstract:
+            abstract['class'] = 'article_desc'
+            contents.insert(2, abstract)
+
+        #Find article authors
+        authorsDiv = soup.find('div', {'class':['autors']})
+        if authorsDiv:
+            authorsP = authorsDiv.find('p')
+            if authorsP:
+                authorsP['class'] = 'article_authors'
+                contents.insert(len(contents.contents), authorsP)
+
+        #Fix urls that use relative path
+        urls = contents.findAll('a');
+        if urls:
+            for url in urls:
+                if not url.has_key('href'):
+                    continue
+                if '/' == url['href'][0]:
+                    url['href'] = self.base_url + url['href']
+
+        body = soup.find('td', {'class':['second_content']})
+        if body:
+            body.replaceWith(contents)
+
+        self.log('Result: ', soup.prettify())
+        return soup
+
--- a/resources/recipes/wash_post.recipe
+++ b/resources/recipes/wash_post.recipe
@ -31,8 +31,9 @@ class WashingtonPost(BasicNewsRecipe):
                ('Education', 'http://www.washingtonpost.com/wp-dyn/rss/education/index.xml'),
                ('Style',
                     'http://www.washingtonpost.com/wp-dyn/rss/print/style/index.xml'),
-                ('Sports',
-                     'http://feeds.washingtonpost.com/wp-dyn/rss/linkset/2010/08/19/LI2010081904067_xml'),
+                ('NFL Sports',
+                     'http://www.washingtonpost.com/wp-dyn/rss/sports/index/nfl/index.xml'),
+                ('Redskins', 'http://www.washingtonpost.com/wp-dyn/rss/sports/redskins/index.xml'),
                ('Editorials', 'http://www.washingtonpost.com/wp-dyn/rss/linkset/2005/05/30/LI2005053000331.xml'),
    ]

--- a/resources/recipes/zeitde.recipe
+++ b/resources/recipes/zeitde.recipe
@ -12,6 +12,7 @@ class ZeitDe(BasicNewsRecipe):
    title = 'Zeit Online'
    description = 'Zeit Online'
    language = 'de'
+    encoding = 'UTF-8'

    __author__ = 'Martin Pitt, Sujata Raman, Ingo Paschke and Marc Toensing'

@ -43,7 +44,7 @@ class ZeitDe(BasicNewsRecipe):
               ('Sport', 'http://newsfeed.zeit.de/sport/index'),
             ]

-    extra_css = '.reaktion,.taglist,.comments,.reponse,.responsetitle,.responsebody,.reponse,.inline,.date{display:none;}li.date{display:block}'
+    extra_css = '.excerpt{font-size:1em}.reaktion,.taglist,.comments,.reponse,.responsetitle,.responsebody,.reponse,.inline,.date{display:none;}li.date{display:block}'

    #filter_regexps = [r'ad.de.doubleclick.net/']

@ -55,6 +56,16 @@ class ZeitDe(BasicNewsRecipe):
              ans = None
        return ans

+    def preprocess_html(self, soup):
+        for tag in soup.findAll(name=['ul','li']):
+            tag.name = 'div'
+
+        soup.html['xml:lang'] = self.lang
+        soup.html['lang']     = self.lang
+        mtag = '<meta http-equiv="Content-Type" content="text/html; charset=' + self.encoding + '">'
+        soup.head.insert(0,mtag)
+        return soup
+
    def get_cover_url(self):
        try:
            inhalt = self.index_to_soup('http://www.zeit.de/inhalt')
--- a/resources/recipes/zeitde_sub.recipe
+++ b/resources/recipes/zeitde_sub.recipe
@ -0,0 +1,63 @@
+#!/usr/bin/env  python
+# -*- coding: utf-8 mode: python -*-
+
+__license__   = 'GPL v3'
+__copyright__ = '2010, Steffen Siebert <calibre at steffensiebert.de>'
+__docformat__ = 'restructuredtext de'
+__version__   = '1.1'
+
+"""
+Die Zeit EPUB
+"""
+
+import os, urllib2, zipfile, re
+from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.ptempfile import PersistentTemporaryFile
+
+class ZeitEPUBAbo(BasicNewsRecipe):
+
+    title = u'Zeit Online Premium'
+    description = u'Das EPUB Abo der Zeit (needs subscription)'
+    language = 'de'
+    lang = 'de-DE'
+
+    __author__ = 'Steffen Siebert'
+    needs_subscription = True
+
+    conversion_options = {
+        'no_default_epub_cover' : True
+    }
+
+    def build_index(self):
+        domain = "http://premium.zeit.de"
+        url = domain + "/abovorteile/cgi-bin/_er_member/p4z.fpl?ER_Do=getUserData&ER_NextTemplate=login_ok"
+
+        browser = self.get_browser()
+        browser.add_password("http://premium.zeit.de", self.username, self.password)
+
+        try:
+            browser.open(url)
+        except urllib2.HTTPError:
+            self.report_progress(0,_("Can't login to download issue"))
+            raise ValueError('Failed to login, check your username and password')
+
+        response = browser.follow_link(text="DIE ZEIT als E-Paper")
+        response = browser.follow_link(url_regex=re.compile('^http://contentserver.hgv-online.de/nodrm/fulfillment\\?distributor=zeit-online&orderid=zeit_online.*'))
+
+        tmp = PersistentTemporaryFile(suffix='.epub')
+        self.report_progress(0,_('downloading epub'))
+        tmp.write(response.read())
+        tmp.close()
+
+        zfile = zipfile.ZipFile(tmp.name, 'r')
+        self.report_progress(0,_('extracting epub'))
+
+        zfile.extractall(self.output_dir)
+
+        tmp.close()
+        index = os.path.join(self.output_dir, 'content.opf')
+
+        self.report_progress(1,_('epub downloaded and extracted'))
+
+        return index
+
--- a/resources/templates/rtf.xsl
+++ b/resources/templates/rtf.xsl
@ -363,13 +363,16 @@
    </xsl:template>

    <xsl:template match="rtf:row">
-        <xsl:element name="row">
+        <xsl:element name="tr">
            <xsl:apply-templates/>
        </xsl:element>
    </xsl:template>

    <xsl:template match="rtf:cell">
-        <xsl:element name="cell">
+        <xsl:element name="td">
+            <xsl:if test="@class">
+                <xsl:attribute name="class"><xsl:value-of select="@class"/></xsl:attribute>
+            </xsl:if>
            <xsl:apply-templates/>
        </xsl:element>
    </xsl:template>
--- a/resources/viewer/hyphenate/Hyphenator.js
+++ b/resources/viewer/hyphenate/Hyphenator.js
--- a/resources/viewer/hyphenate/patterns/be.js
+++ b/resources/viewer/hyphenate/patterns/be.js
--- a/resources/viewer/hyphenate/patterns/bn.js
+++ b/resources/viewer/hyphenate/patterns/bn.js
@ -1,13 +1,13 @@
-// For questions about the Bengali hyphenation patterns
+// For questions about the Bengali hyphenation patterns
 // ask Santhosh Thottingal (santhosh dot thottingal at gmail dot com)
-Hyphenator.languages.bn = {
+Hyphenator.languages['bn'] = {
 	leftmin : 2,
 	rightmin : 2,
 	shortestPattern : 1,
 	longestPattern : 1,
-	specialChars : unescape('আঅইঈউঊঋএঐঔকগখঘঙচছজঝঞটঠডঢণতথদধনপফবভমযরলশষসহিীাুূৃোোৈৌৗ্ঃং%u200D'),
+	specialChars : unescape("আঅইঈউঊঋএঐঔকগখঘঙচছজঝঞটঠডঢণতথদধনপফবভমযরলশষসহিীাুূৃোোৈৌৗ্ঃং%u200D"),
 	patterns : {
-		2 : 'অ1আ1ই1ঈ1উ1ঊ1ঋ1এ1ঐ1ঔ1ি1া1ী1ু1ৃ1ে1ো1ৌ1ৗ1্2ঃ1ং11ক1গ1খ1ঘ1ঙ1চ1ছ1জ1ঝ1ঞ1ট1ঠ1ড1ঢ1ণ1ত1থ1দ1ধ1ন1প1ফ1ব1ভ1ম1য1র1ল1শ1ষ1স1হ',
-		3 : '2ঃ12ং1'	
+		2 : "অ1আ1ই1ঈ1উ1ঊ1ঋ1এ1ঐ1ঔ1ি1া1ী1ু1ৃ1ে1ো1ৌ1ৗ1্2ঃ1ং11ক1গ1খ1ঘ1ঙ1চ1ছ1জ1ঝ1ঞ1ট1ঠ1ড1ঢ1ণ1ত1থ1দ1ধ1ন1প1ফ1ব1ভ1ম1য1র1ল1শ1ষ1স1হ",
+		3 : "2ঃ12ং1"
 	}
 };
--- a/resources/viewer/hyphenate/patterns/cs.js
+++ b/resources/viewer/hyphenate/patterns/cs.js
@ -1,11 +1,11 @@
-// For questions about the Czech hyphenation patterns
+// For questions about the Czech hyphenation patterns
 // ask Martin Hasoň (martin dot hason at gmail dot com)
-Hyphenator.languages.cs = {
+Hyphenator.languages['cs'] = {
 	leftmin : 2,
 	rightmin : 2,
 	shortestPattern : 1,
 	longestPattern : 6,
-	specialChars : 'ěščřžýáíéúůťď',
+	specialChars : "ěščřžýáíéúůťď",
 	patterns : {
    	2 : "a11f1g1k1n1pu11vy11zé11ňó11š1ť1ú1ž",
    	3 : "_a2_b2_c2_d2_e2_g2_h2_i2_j2_k2_l2_m2_o2_p2_r2_s2_t2_u2_v2_z2_č2_é2_í2_ó2_š2_ú2_ž22a_a2da2ga2ia2ka2ra2sa2ta2u2av2aya2ča2ňa2ť2b_b1db1h1bib1j2bkb1m2bn1bob2z1bá1bí2bň2c_1ca2cc1ce1ci2cl2cn1coc2p2ctcy21cá1cí2cň1ců2d_1dad1bd1d1de1did1j2dkd1m2dn1dod1t1dud2v1dy1dá1dé1dě1dí2dň1dů1dý2e_e1ae1be1ee1ie2ke1o2ere1se1te1ue1áe2ňe1ře2šeú12f_f2l2fn2fr2fs2ft2féf2ú2g_2gngo12h_h2bh2c2hd2hkh2mh2rh1č2hňhř2h2ž2i_i1ai1bi1di1hi1ji1li1mi2ni1oi1ri1ti1xi1ái2ďi1éi1ói1ři2ši2ž2j_j2d1jij1j2jkj2m2jn2jp2jz2jď1jí2jž2k_k2dk2e2kf2kkk2l2kn2ks2kčk2ň2l_2lf2lg2lh1li2lj2lk2ll2ln2lp2lv2lz2lň1lů1lý2m_1ma1me2mf1mim2l2mn1mo2mp1mu2mv2mz2mčm2ž2n_2nb2nf2ngn1j2nk2nn2nz2nď2nónů22nž2o_o1ao1cog2o1ho1io1jo1lo1mo2no1oo1to2uo1xo2zo1čo2ňo1ř2p_2pkp2l2pn2pp2ptpá12pč2pš2pťqu22r_r1br1cr1d2rkr1l2rn2rrr1x2rzr1č2ró2rš2s_s2cs2d1se2sf1sis2js2k2sn1sos2p1sr2ss1sus2v1sé1sí2sň2sť1sůs2ž2t_1te2tf2tg1ti2tl2tm2tn1to2tpt2vt2č1té1tě2tř2tš1tů2u_u2b2ufu2ku2mu2nu2pu2ru2su2vu2zu2ču2ďu2ňu2šu2ž2v_2vkv2l2vm2vnv2p2vňwe22x_2xf2xnx1ty2ay2ey2sy2ňy2šyž22z_2zbz2ez2j2zl2ztz2v2zzzá12zč2zňz2řá1bá1dá1já1sá2ňá1řá2š2č_1ča2čb1če1či2čk2čn1čoč2p2čs1ču1čá1čí1čů2ď_1ďa1ďoé2dé2fé2lé2mé2sé2té2šé2žě1cě1lě2vě2zě1řě2šě2ťě2ží1bí1hí1jí1lí1rí1tí2ňí1ří2š2ň_2ňa2ňk2ňmň1só2z2ř_2řc2řdři12řk2řn1řoř2v2řz2řš2š_2šl2šnš2p2štš2vš2ň2ť_2ťk2ťm2ťtú2dú2kú2lú2nú2pú2tú2vú2zú2čú2žů1bů1cůt2ů2vů2zů2žý1bý1dý1hý1jý1lý2ný1rý1tý1uý1ř2ž_2žk2žl2žnž2v2žď2žň2žš",
--- a/resources/viewer/hyphenate/patterns/da.js
+++ b/resources/viewer/hyphenate/patterns/da.js
@ -1,10 +1,10 @@
-Hyphenator.languages.da = {
-	'leftmin' : 2,
-	'rightmin' : 2,
-	'shortestPattern' : 2,
-	'longestPattern' : 8,
-	'specialChars' : 'æøå',
-	'patterns' : {
+Hyphenator.languages['da'] = {
+	leftmin : 2,
+	rightmin : 2,
+	shortestPattern : 2,
+	longestPattern : 8,
+	specialChars : "æøå",
+	patterns : {
 		3 : "a3ca1ea3ha3ja5oa5z1ba4bd1be1bib1j1bo4bsb5t3bub5w1by1ce3chck35cy3dad1b1ded1fd1gd3h1did3jd1kd1ld1m3dod1p1dud1v3dye3ee1he5x1faf1bf1d1fef1ff1gf1h1fif1k3fl1fof1p4ft1fuf1v3fy1gag1bg1d1geg3fg1gg1h1gi5gjg3kg1lg1m3gog3p1grg3v1gyi1ai3bi1ci3hi5ii5ji1uj5kj3rk5bk3hk1kk1tl1bl1fl3hl3jl1ll3r4ls1mam1bm3d1mem3fm1gm3h1mim3km1lm1mm1n3mom1r3my3nan1bn1c4nd1nen1f1nin1mn1n1non5pn3r4ns3nyn3zo3ao1co1eo5ho1jo3t3pap3dp3fp3mp3np1t1pup5vqu4r1br1fr1hr1lr1nr3pr1rs1d1ses1fs1msp44tbt1ht1mt1n4tsu1au1eu3iu5qv5hv5jv5kvl41vov5pv5t3vuy3ay3ey5o5bæ3dæ3døe3æe5å3fæ3fø3gæ3gåi3ø3kø3kå1mæ3mø3må3næ5nøo5åpå31sæ1sø5våæ3cæ3eæ5iæ5oø3eå1då1eå5hå3lå3t",
 		4 : "_ae3_om1_po15adg5afgaf3r5afsa4gia4gya5kaa3kea5kraku5a3laa1lea1lial3ka1loa3lua1lya3nu3anva5pea3pia5poa1ra1arba1re5arga1ria3roa3saa3sca1sia3ska3soa1tea1tia1toa5tra1tua5vaa1vebe1k4b1n1br4bs5kb3sob1stby5s4c1c4ch_ci4oda4sd1d4de5ddi1edi5l4d1n4dopd5ovd5rud4smd4sud3tad1tedt5od5trdt5udub5e5ade3afe5age3ake1ale3ane5ape3ate3blebs3e1cie4do3effe3fr3efte3gue3inei5se3jee1kae3kee3kle5kre3kue1kve5kye3lee1lie3loe5lue3lyem1s4enne4noe5nue5ole3ope1ore3ovepi3e1pre3rae1ree1rier1ker3se5rye1tae1tee1tie3tje1toe3tre3tue1tye3ume3un3eure1vae3vee1vifej4f1s4f3taf1tef1tif5toge3sgi4bg5ovgs1ag4segs1pgs1vg3tag1teg1tig5tog3trgt4sg3udgun5g5yd4ha_he5s4hethi4ehi3s4h3thun4hvo4i3dri1eli1eni3erif3ri3gui1kai1keik1li5koi3kuik3vi3liil3ki1loil5ui3mu5infin3si3nui3odi3ogi5oki3olion4i3oti5pii5pri3rei3riir5ti3sci3sii4smis3pi1tai1tei1tii3toi3tri1tui3tyi1vai1vei1vij3agjds1j3lej3lijre5ju3s5kapk5au5kavki3ek1le3kluk4ny5kod1konko3v1kra5kryk1siks3kks1pks5vkt5s3kur1kus3kutk4vok4vu5lab5lam1latl3dr1le_5led3len1ler1les4leuli5ol1kel1kol3kyl5mul3op3lov4l3pl4psl5sjl1tal1tel3tilt3ol3trl3tulu5ll3vel3vimi3kmi4o4mopm1pem3pim3plm1pom3prm5skms3pms5vm3tam3tem3tim3trm1ud1mul4nak1naln3drne5aneo4n4go4n1h4nimni5on1ken1kon3krn3kun5kv4n1ln3sin1tan1ten1tin3ton1trn3tun3ty4n1vo4asod5sof5ro5ino3kao1keo3kuo3lao3leo1lio1loo3luo5ly1omron3kook5o3oro5ovo3piop3lop3rop3s4or_o3rior3kor5oo3sio3soo1teo5unov4s4pec3pen1perpe5spe3u4p5h1pla5pok3potp4rop3skp5sops4pp3stpu5b5py34rafr3dr1relr1guri1er3kar1ker1kir3kurmo4r5muro1bro3pr3orr1sar1sirs4nr3spr5sur3svr1ter1tir3tort3sr5tyr3ud5rutr3var1ver3viry4ss3af1sams3aps1ar1sat4s1bsdy4s4ed4s3h1sig5sis5sit5sius5ju4sk_1skes3kl5skys1les1lislo35slus5lys4myso5k5sol3sons1pls5r4s1s44st_5stj3sto1strs1ud3suls3un3surs3ve3s4y5ta_1tag3tegteo14t1f6t3g3tid4t3k4t1l4t3pt4ra1tryt3sit3st4t1t5turt5ve1typ5udlud5rud3s3udvugs3u5guu5klu1lau1leu5lyu5peup5lu3rau3reu3rous5au3siu5sous5vu1teu1tiu1tout5r5u5vva5d1vedve3s5vet1visv3lev5livls1v5rev3stv5suy5dry3key5kiy3koy3kvy5liy5loy5muyns5y1pey3piy3rey3riy3siy3tiy5vezi5o_så3a3tøa5væe3læe3løe3røe5tæe5tøe1vægiø4g4søg5så3gø1i5tæl3væ5løsm5tån3kæn5tæo5læor3ø5præ5pædr5kær5tær5tør3vær5æl4røn5rør3rådr5års4kå3slås4næ5stø1stås5økti4øt4søt5såt3væu3læy5vææb3læg5aægs5æ5kvæ1reæ3riær5sæ5siæ3soæ3veøde5ø1jeø3keø3leøms5ø1reø3riør5oø1veå3reå5sk",
 		5 : "_an3k_an1s_be1t_her3_ove4_til3_yd5rab5le3abstaf4ria4gefag5inag5si3agtiais5t4alkval5siam4paar5af3a3spa3stea3stia1ta1ato5vba4tibe3robe5rube1s4be1trbi5skbo4grbo3rabo5rece5ro4d3afde5sk3drif3drivd5rosds5ands5ind1skidsu5lds5viea4laed5aredde4ed5raed3re4e1koek5sa3ekspe3ladel3akel3are1lase4lek3elem5elimel5sae4maden5ake4nanen3soer3afe4rage4rake4ref5erhve4ribero5der5over5tre3rumer5unfa4cefags3fejl1fo4rif5tvig3artgi3st4g5omgsha4g5slags3org4strheds3hi4n5ho5koho5vehund3i4bleids5ki3et_ik3reik5riiks5tik4tui3lagil3egil5ejil5elind3tings1in4svions1i5o5ri3plii3stii5suakel5ske3skke5stki3stk5lakko3ra3kortks3ank3stek5stuk4tarkti4ekt5relad3r5lagdld3st4lelele4molfin4l1go1li4galo4du4l5orlses1ls5inl4taf4m5ejm5ingmmen5mo4da4m5ovmse5sms5inm3stemu1lind5sind5sknd5spne4dan3erkn5erlne5slne5stni3stn3ordn1skuns3pon1stan5stint4suob3lio4dinod5riod5uno4geko4gelo4g5oog5reog5sk3optaor1an3ordnord5so3re_o3rego3reko3rero3retor5imor3slor3stpa5ghp5anlpe1rap4lan4ple_4pler4ples4p5p41procp5ulera5is4rarbrd4s34reksre5la5rese4ressre3st5rettri5la4rimor4ing4rinp4rintrk3sorre5sr5skrr5stur5talrt3rer5trir5trosa4ma5s4erse4se4s1g4si4bls5int1skabsk5s44snins4nit5som_3somms5oms5somt4s1op3spec4sper3s4pi1stanst5as3stat1stav1ste_1sted3stel1sten5step3stes5stetst5om1sy1s4tanvteds55tekn5termte5roti4enti3stto5rato1reto1ritor4m4trestro5vts4pats5prts5ult5udsue4t5uk4tauk4tru1reru5skaut5s43varm4v5omyk3liyk4s5yr3eky5t3r_ær5i_øv3rbrød35drøvdstå4er5øn4n5æb4s5ænså4r53værd1værkæ4gekæ4g5rælle4æn1drær4maær4moæ3steøn3støn4t3ørne3års5t",
--- a/resources/viewer/hyphenate/patterns/de.js
+++ b/resources/viewer/hyphenate/patterns/de.js
--- a/resources/viewer/hyphenate/patterns/el-monoton.js
+++ b/resources/viewer/hyphenate/patterns/el-monoton.js
@ -0,0 +1,20 @@
+// Hyphenation patterns for Modern Monotonic Greek.
+// Created by Dimitrios Filippou with some ideas borrowed from 
+// Yannis Haralambous, Kostis Dryllerakis and Claudio Beccari.
+// From http://tug.org/svn/texhyphen/branches/ptex/hyph-utf8/tex/generic/hyph-utf8/patterns/tex/hyph-el-monoton.tex
+// Converted by Pablo Rodríguez (hyphenator at pragmata dot tk)
+Hyphenator.languages['el-monoton'] = Hyphenator.languages['el'] = {
+	leftmin : 2,
+	rightmin : 2,
+	shortestPattern : 1,
+	longestPattern : 7,
+	specialChars : "αεηιουωϊϋάέήίόύώΐΰίάύέήόώβγκδζθλμπντξρσϲςφχψ'ʼ᾿’᾽",
+	patterns : {
+		2 : "α1ε1η1ι1ο1υ1ω1ϊ1ϋ1ά1έ1ή1ί1ό1ύ1ώ1ΐ1ΰ14'4ʼ4᾿",
+		3 : "α2ια2ία2ίά2ιά2ιά2ϊά2ϊα2υα2ύα2ύά3υά3υε2ιε2ίε2ίέ2ιέ2ιέ2ϊέ2ϊε2υε2ύε2ύέ3υέ3υη2υη2ύη2ύή3υή3υο2ιο2ίο2ίό2ιό2ιό2ϊό2ϊο2υο2ύο2ύό3υό3υυ2ιυ2ίυ2ίύ3ιύ3ια2ηα2ϊα2ϋε2ϊε2ϋο2ηο2ϊι2αι2άι2άι2ει2έι2έι2οι2όι2όι2ωι2ώι2ώ_ι3_ί3_ί3η2αη2άη2άη2εη2έη2έη2οη2όη2όη2ωη2ώη2ώ_η3_ή3_ή3υ2αυ2άυ2άυ2ου2όυ2όυ2ωυ2ώυ2ώ_υ3_ύ3_ύ34β_4γ_4δ_4ζ_4θ_4κ_4λ_4μ_4ν_4ξ_4π_4ρ_4σ_4ϲ_4ς_4τ_4φ_4χ_4ψ_4β'4βʼ4β᾿4γ'4γʼ4γ᾿4δ'4δʼ4δ᾿4ζ'4ζʼ4ζ᾿4θ'4θʼ4θ᾿4κ'4κʼ4κ᾿4λ'4λʼ4λ᾿4μ'4μʼ4μ᾿4ν'4νʼ4ν᾿4ξ'4ξʼ4ξ᾿4π'4πʼ4π᾿4ρ'4ρʼ4ρ᾿4σ'4σʼ4σ᾿4ϲ'4ϲʼ4ϲ᾿4τ'4τʼ4τ᾿4φ'4φʼ4φ᾿4χ'4χʼ4χ᾿4ψ'4ψʼ4ψ᾿_β4_γ4_δ4_ζ4_θ4_κ4_λ4_μ4_ν4_ξ4_π4_ρ4_σ4_ϲ4_τ4_φ4_χ4_ψ4",
+		4 : "ά3η_ά3η_ά3ι_ά3ι_ο2ειό3η_ό3η_ό3ι_ό3ι_4γκ_4μπ_4ντ_4τζ_4τσ_4τϲ_4τς_4μπ'4μπʼ4μπ᾿4ντ'4ντ’4ντ᾿4τζ'4τζʼ4τζ᾿4τσ'4τσʼ4τσ᾽4τϲ'4τϲʼ4τϲ᾿4β1β4γ1γ4δ1δ4ζ1ζ4θ1θ4κ1κ4λ1λ4μ1μ4ν1ν4π1π4ρ1ρ4σ1σ4ϲ1ϲ4τ1τ4φ1φ4χ1χ4ψ1ψ4β1ζ4β1θ4β1κ4β1μ4β1ν4β1ξ4β1π4β1σ4β1ϲ4β1τ4β1φ4β1χ4β1ψ4γ1β4γ1ζ4γ1θ4γ1μ4γ1ξ4γ1π4γ1σ4γ1ϲ4γ1τ4γ1φ4γ1χ4γ1ψ4δ1β4δ1γ4δ1ζ4δ1θ4δ1κ4δ1λ4δ1ξ4δ1π4δ1σ4δ1ϲ4δ1τ4δ1φ4δ1χ4δ1ψ4ζ1β4ζ1γ4ζ1δ4ζ1θ4ζ1κ4ζ1λ4ζ1μτζ2μ4ζ1ν4ζ1ξ4ζ1π4ζ1ρ4ζ1σ4ζ1ϲ4ζ1τ4ζ1φ4ζ1χ4ζ1ψ4θ1β4θ1γ4θ1δ4θ1ζ4θ1κ4θ1μσθ2μϲθ2μ4θ1ξ4θ1π4θ1σ4θ1ϲ4θ1τ4θ1φ4θ1χ4θ1ψ4κ1β4κ1γ4κ1δ4κ1ζ4κ1θ4κ1μ4κ1ξ4κ1π4κ1σ4κ1ϲ4κ1φ4κ1χ4κ1ψ4λ1β4λ1γ4λ1δ4λ1ζ4λ1θ4λ1κ4λ1μ4λ1ν4λ1ξ4λ1π4λ1ρ4λ1σ4λ1ϲ4λ1τ4λ1φ4λ1χ4λ1ψ4μ1β4μ1γ4μ1δ4μ1ζ4μ1θ4μ1κ4μ1λ4μ1ξ4μ1ρ4μ1σ4μ1ϲ4μ1τ4μ1φ4μ1χ4μ1ψ4ν1β4ν1γ4ν1δ4ν1ζ4ν1θ4ν1κ4ν1λ4ν1μ4ν1ξ4ν1π4ν1ρ4ν1σ4ν1ϲ4ν1φ4ν1χ4ν1ψ4ξ1β4ξ1γ4ξ1δ4ξ1ζ4ξ1θ4ξ1κ4ξ1λ4ξ1μ4ξ1ν4ξ1π4ξ1ρ4ξ1σ4ξ1ϲ4ξ1τ4ξ1φ4ξ1χ4ξ1ψ4π1β4π1γ4π1δ4π1ζ4π1θ4π1κ4π1μ4π1ξ4π1σ4π1ϲ4π1φ4π1χ4π1ψ4ρ1β4ρ1γ4ρ1δ4ρ1ζ4ρ1θ4ρ1κ4ρ1λ4ρ1μ4ρ1ν4ρ1ξ4ρ1π4ρ1σ4ρ1ϲ4ρ1τ4ρ1φ4ρ1χ4ρ1ψ4σ1δ4ϲ1δ4σ1ζ4ϲ1ζ4σ1ν4ϲ1ν4σ1ξ4ϲ1ξ4σ1ρ4ϲ1ρ4σ1ψ4ϲ1ψ4τ1β4τ1γ4τ1δ4τ1θ4τ1κ4τ1ν4τ1ξ4τ1π4τ1φστ2φϲτ2φ4τ1χ4τ1ψ4φ1β4φ1γ4φ1δ4φ1ζ4φ1κ4φ1μ4φ1ν4φ1ξ4φ1π4φ1σ4φ1ϲ4φ1χ4φ1ψ4χ1β4χ1γ4χ1δ4χ1ζ4χ1κ4χ1μ4χ1ξ4χ1π4χ1σ4χ1ϲ4χ1φ4χ1ψ4ψ1β4ψ1γ4ψ1δ4ψ1ζ4ψ1θ4ψ1κ4ψ1λ4ψ1μ4ψ1ν4ψ1ξ4ψ1π4ψ1ρ4ψ1σ4ψ1ϲ4ψ1τ4ψ1φ4ψ1χ4βρ_4γλ_4κλ_4κτ_6κς_6κϲ_4κσ_4λς_4λϲ_4λσ_4μς_4μϲ_4μσ_4νς_4νϲ_4νσ_4ρς_4ρϲ_4ρσ_4σκ_4ϲκ_4στ_4ϲτ_4τλ_4τρ_4φτ_",
+		5 : "ο3ϊ3όο3ϊ3ό4γ1κτ4μ1πτ4ν1τζ4ν1τσ4ν1τϲ4γκς_4γκϲ_4γκσ_4μπλ_4μπν_4μπρ_4ντς_4ντϲ_4ντσ_",
+		6 : "4ρ5γ2μ4ρ5θ2μ4λ5κ2μ4ρ5κ2μ4ν5κ2φ4γ5ξ2τ4ρ5ξ2τ4ρ5φ2ν4ρ5χ2μ4μ5ψ2τ4γ5κ2φ4γκ1ντ4γκ1τζ4γκ1τσ4γκ1τϲ4μπ1ντ4μπ1τζ4μπ1τσ4μπ1τϲ4ντ1μπ4τσ1γκ4τϲ1γκ4τσ1μπ4τϲ1μπ4τσ1ντ4τϲ1ντ",
+		10 : "4χτ_4γκ1μπ"
+	}
+};
--- a/resources/viewer/hyphenate/patterns/el-polyton.js
+++ b/resources/viewer/hyphenate/patterns/el-polyton.js
@ -0,0 +1,26 @@
+// Hyphenation patterns for Modern Polytonic Greek.
+// Created by Dimitrios Filippou with some ideas borrowed from 
+// Yannis Haralambous, Kostis Dryllerakis and Claudio Beccari.
+// From http://tug.org/svn/texhyphen/branches/ptex/hyph-utf8/tex/generic/hyph-utf8/patterns/tex/hyph-el-polyton.tex
+// Converted by Pablo Rodríguez (hyphenator at pragmata dot tk)
+Hyphenator.languages['el-polyton'] = {
+	leftmin : 2,
+	rightmin : 2,
+	shortestPattern : 1,
+	longestPattern : 11,
+	specialChars : "αεηιουωϊϋἀἁἂἃἄἅἆἇἐἑἒἓἔἕἠἡἢἣἤἥἦἧἰἱἲἳἴἵἶἷὀὁὂὃὄὅὐὑὒὓὔὕὖὗὠὡὢὣὤὥὦὧὰὲὴὶὸὺὼᾀᾁᾂᾃᾄᾅᾆᾇᾐᾑᾒᾓᾔᾕᾖᾗᾠᾡᾢᾣᾤᾥᾦᾧᾲᾳᾴᾶᾷῂῃῄῆῇῒῖῗῢῦῧῲῳῴῶῷάέήίόύώΐΰάέήίόύώΐΰβγκδζθλμπντξρσϲςφχψ'ʼ᾿’᾽ῤῥ",
+	patterns : {
+		2 : "α1ε1η1ι1ο1υ1ω1ϊ1ϋ1ἀ1ἁ1ἂ1ἃ1ἄ1ἅ1ἆ1ἇ1ἐ1ἑ1ἒ1ἓ1ἔ1ἕ1ἠ1ἡ1ἢ1ἣ1ἤ1ἥ1ἦ1ἧ1ἰ1ἱ1ἲ1ἳ1ἴ1ἵ1ἶ1ἷ1ὀ1ὁ1ὂ1ὃ1ὄ1ὅ1ὐ1ὑ1ὒ1ὓ1ὔ1ὕ1ὖ1ὗ1ὠ1ὡ1ὢ1ὣ1ὤ1ὥ1ὦ1ὧ1ὰ1ὲ1ὴ1ὶ1ὸ1ὺ1ὼ1ᾀ1ᾁ1ᾂ1ᾃ1ᾄ1ᾅ1ᾆ1ᾇ1ᾐ1ᾑ1ᾒ1ᾓ1ᾔ1ᾕ1ᾖ1ᾗ1ᾠ1ᾡ1ᾢ1ᾣ1ᾤ1ᾥ1ᾦ1ᾧ1ᾲ1ᾳ1ᾴ1ᾶ1ᾷ1ῂ1ῃ1ῄ1ῆ1ῇ1ῒ1ῖ1ῗ1ῢ1ῦ1ῧ1ῲ1ῳ1ῴ1ῶ1ῷ1ά1έ1ή1ί1ό1ύ1ώ1ΐ1ΰ1ά1έ1ή1ί1ό1ύ1ώ1ΐ1ΰ16'6ʼ6᾿",
+		3 : "α2ια2ία2ία2ὶα2ῖα2ἰα2ἴα2ἲα2ἶα2ἱα2ἵα2ἳα2ἷά2ιά2ιά2ϊά2ϊα2υα2ύα2ύα2ὺα2ῦα2ὐα2ὔα2ὒα2ὖα2ὑα2ὕα2ὓα2ὗά3υά3υε2ιε2ίε2ίε2ὶε2ῖε2ἰε2ἴε2ἲε2ἶε2ἱε2ἵε2ἳε2ἷέ2ιέ2ιέ2ϊέ2ϊε2υε2ύε2ύε2ὺε2ῦε2ὐε2ὔε2ὒε2ὖε2ὑε2ὕε2ὓε2ὗέ3υέ3υη2υη2ύη2ύη2ὺη2ῦη2ὐη2ὔη2ὒη2ὖη2ὑη2ὕη2ὓη2ὗο2ιο2ίο2ίο2ὶο2ῖο2ἰο2ἴο2ἲο2ἶο2ἱο2ἵο2ἳο2ἷό2ιό2ιό2ϊό2ϊο2υο2ύο2ύο2ὺο2ῦο2ὐο2ὔο2ὒο2ὖο2ὑο2ὕο2ὓο2ὗό3υό3υυ2ιυ2ίυ2ίυ2ὶυ2ῖυ2ἰυ2ἴυ2ἲυ2ἶυ2ἱυ2ἵυ2ἳυ2ἷα2ηα2ϊα2ϋά3ϋά3ϋε2ηέ2ηέ2ηε2ϊε2ϋό2ηό2ηο2ϊω2ιὠ2ιι2αι2άι2άι2ὰι2ᾶι2ει2έι2έι2ὲι2οι2όι2όι2ὸι2ωι2ώι2ώι2ὼι2ῶ_ί3_ί3_ῖ3_ἰ3_ἱ3η2αῃ2αη2άη2άη2ὰη2ᾶῃ2άῃ2άῃ2ὰῃ2ᾶη2εῃ2εη2έη2έη2ὲῃ2έῃ2έῃ2ὲη2οῃ2οη2όη2όη2ὸῃ2όῃ2όῃ2ὸη2ωῃ2ωη2ώη2ώη2ὼη2ῶῃ2ώῃ2ώῃ2ὼῃ2ῶ_ή3_ή3_ῆ3_ἠ3_ἡ3υ2αυ2άυ2άυ2ὰυ2ᾶυ2ευ2έυ2έυ2ὲυ2ου2όυ2όυ2ὸυ2ωυ2ώυ2ώυ2ὼυ2ῶ_ύ3_ύ3_ῦ3_ὑ36β_6γ_6δ_6ζ_6θ_6κ_6λ_6μ_6ν_6ξ_6π_6ρ_6σ_6ϲ_6ς_6τ_6φ_6χ_6ψ_6β'6βʼ6β᾿6γ'6γʼ6γ᾿6δ'6δʼ6δ᾿6ζ'6ζʼ6ζ᾿6θ'6θʼ6θ᾿6κ'6κʼ6κ᾿6λ'6λʼ6λ᾿6μ'6μʼ6μ᾿6ν'6νʼ6ν᾿6ξ'6ξʼ6ξ᾿6π'6πʼ6π᾿6ρ'6ρʼ6ρ᾿6σ'6σʼ6σ᾿6ϲ'6ϲʼ6ϲ᾿6τ'6τʼ6τ᾿6φ'6φʼ6φ᾿6χ'6χʼ6χ᾿6ψ'6ψʼ6ψ᾿_β6_γ6_δ6_ζ6_θ6_κ6_λ6_μ6_ν6_ξ6_π6_ρ6_σ6_ϲ6_τ6_φ6_χ6_ψ6",
+		4 : "ά3η_ά3η_ά3ι_ά3ι_ά3ϊ_ά3ϊ_ό2ειό2ειό3η_ό3η_ό3ι_ό3ι_ό3ϊ_ό3ϊ_6γκ_6μπ_6ντ_6τζ_6τσ_6τϲ_6τς_6μπ'6μπʼ6μπ᾿6ντ'6ντ’6ντ᾿6τζ'6τζʼ6τζ᾿6τσ'6τσʼ6τσ᾽6τϲ'6τϲʼ6τϲ᾿4β1β4γ1γ4δ1δ4ζ1ζ4θ1θ4κ1κ4λ1λ4μ1μ4ν1ν4π1π4ρ1ρ4ῤ1ῥ4σ1σ4ϲ1ϲ4τ1τ4φ1φ4χ1χ4ψ1ψ4β1ζ4β1θ4β1κ4β1μ4β1ν4β1ξ4β1π4β1σ4β1ϲ4β1τ4β1φ4β1χ4β1ψ4γ1β4γ1ζ4γ1θ4γ1κ4γ1μ4γ1ξ4γ1π4γ1σ4γ1ϲ4γ1τ4γ1φ4γ1χ4γ1ψ4δ1β4δ1γ4δ1ζ4δ1θ4δ1κ4δ1λ4δ1ξ4δ1π4δ1σ4δ1ϲ4δ1τ4δ1φ4δ1χ4δ1ψ4ζ1β4ζ1γ4ζ1δ4ζ1θ4ζ1κ4ζ1λ4ζ1μτζ2μ4ζ1ν4ζ1ξ4ζ1π4ζ1ρ4ζ1σ4ζ1ϲ4ζ1τ4ζ1φ4ζ1χ4ζ1ψ4θ1β4θ1γ4θ1δ4θ1ζ4θ1κ4θ1μσθ2μϲθ2μ4θ1ξ4θ1π4θ1σ4θ1ϲ4θ1τ4θ1φ4θ1χ4θ1ψ4κ1β4κ1γ4κ1δ4κ1ζ4κ1θ4κ1ξ4κ1π4κ1σ4κ1ϲ4κ1φ4κ1χ4κ1ψ4λ1β4λ1γ4λ1δ4λ1ζ4λ1θ4λ1κ4λ1μ4λ1ν4λ1ξ4λ1π4λ1ρ4λ1σ4λ1ϲ4λ1τ4λ1φ4λ1χ4λ1ψ4μ1β4μ1γ4μ1δ4μ1ζ4μ1θ4μ1κ4μ1λ4μ1ξ4μ1π4μ1ρ4μ1σ4μ1ϲ4μ1τ4μ1φ4μ1χ4μ1ψ4ν1β4ν1γ4ν1δ4ν1ζ4ν1θ4ν1κ4ν1λ4ν1μ4ν1ξ4ν1π4ν1ρ4ν1σ4ν1ϲ4ν1τ4ν1φ4ν1χ4ν1ψ4ξ1β4ξ1γ4ξ1δ4ξ1ζ4ξ1θ4ξ1κ4ξ1λ4ξ1μ4ξ1ν4ξ1π4ξ1ρ4ξ1σ4ξ1ϲ4ξ1τ4ξ1φ4ξ1χ4ξ1ψ4π1β4π1γ4π1δ4π1ζ4π1θ4π1κ4π1μ4π1ξ4π1σ4π1ϲ4π1φ4π1χ4π1ψ4ρ1β4ρ1γ4ρ1δ4ρ1ζ4ρ1θ4ρ1κ4ρ1λ4ρ1μ4ρ1ν4ρ1ξ4ρ1π4ρ1σ4ρ1ϲ4ρ1τ4ρ1φ4ρ1χ4ρ1ψ4σ1δ4ϲ1δ4σ1ζ4ϲ1ζ4σ1ν4ϲ1ν4σ1ξ4ϲ1ξ4σ1ρ4ϲ1ρ4σ1ψ4ϲ1ψ4τ1β4τ1γ4τ1δ4τ1θ4τ1ν4τ1ξ4τ1π4τ1φστ2φϲτ2φ4τ1χ4τ1ψ4φ1β4φ1γ4φ1δ4φ1ζ4φ1κ4φ1ν4φ1ξ4φ1π4φ1σ4φ1ϲ4φ1χ4φ1ψ4χ1β4χ1γ4χ1δ4χ1ζ4χ1κ4χ1μ4χ1ξ4χ1π4χ1σ4χ1ϲ4χ1φ4χ1ψ4ψ1β4ψ1γ4ψ1δ4ψ1ζ4ψ1θ4ψ1κ4ψ1λ4ψ1μ4ψ1ν4ψ1ξ4ψ1π4ψ1ρ4ψ1σ4ψ1ϲ4ψ1τ4ψ1φ4ψ1χβγ2κσγ2κϲγ2κσμ2πϲμ2πμν2τσν2τϲν2τ6βρ_6γλ_6κλ_6κτ_6κς_6κϲ_6κσ_6λς_6λϲ_6λσ_6μς_6μϲ_6μσ_6νς_6νϲ_6νσ_6ρς_6ρϲ_6ρσ_6σκ_6ϲκ_6στ_6ϲτ_6τλ_6τρ_6φτ_6χτ_",
+		5 : "ο3ϊ3όο3ϊ3όο3ϊ3ὸβ5ν2τζ5ν2τλ5ν2τρ5ν2τ",
+		6 : "4ρ5γ2μ4ρ5θ2μ4λ5κ2μ4ρ5κ2μ4γ5κ2φ4ν5κ2φ4γ5ξ2τ4ρ5ξ2τ4ρ5φ2ν4ρ5χ2μ4μ5ψ2τ4λ5γ2κ4ν5γ2κ4ρ5γ2κ4τ5γ2κ4ζ5μ2π4λ5μ2π4ν5μ2π4ρ5μ2πἄ5μ2ακἀ5μ2πρὄ5μ2ποὀ5μ2ποὀ5ν2τάὀ5ν2τάὀ5ν2τὰὀ5ν2τᾶ6μ2πλ_6μ2πν_6μ2πρ_",
+		7 : "ἰ5γ2κου_ξε5γ2κ_ξέ5γ2κ_ξέ5γ2κ_σι5γ2κ_ϲι5γ2κἀ5μ2πάκἀ5μ2πάκἀ5μ2πανἀ5μ2πάρἀ5μ2πάρἀ5μ2πᾶρἀ5μ2παρἀρα5μ2πἰ5μ2πρα_κε5μ2π_λό5μ2π_λό5μ2π5μ2πέη_5μ2πέη_5μ2πεη_5μ2πογι_ξε5μ2π_ξέ5μ2π_ξέ5μ2π_ρε5μ2π_ρέ5μ2π_ρέ5μ2π_ρο5μ2πρό5μ2παρό5μ2παρό5μ2περό5μ2περό5μ2πωρό5μ2πωρο5μ2πῶρο5μ2παρο5μ2περο5μ2πωσό5μ2πασό5μ2παϲό5μ2παϲό5μ2πασό5μ2πεσό5μ2πεϲό5μ2πεϲό5μ2πεσο5μ2πῶϲο5μ2πῶσό5μ2πωσό5μ2πωϲό5μ2πωϲό5μ2πωσο5μ2παϲο5μ2πασο5μ2πεϲο5μ2πεσο5μ2πωϲο5μ2πω_τα5μ2π_χα5μ2π_χό5μ2π_χό5μ2π_ξε5ν2τ_ξέ5ν2τ_ξέ5ν2τ6γ2κ1τζ6γ2κ1τσ6γ2κ1τϲ6μ2π1τζ6μ2π1τσ6μ2π1τϲ6τσ5γ2κ6τϲ5γ2κ6τσ5μ2π6τϲ5μ2π6τσ5ν2τ6τϲ5ν2τ",
+		8 : "ἐμι5γ2κρ_μπα5γ2κ_μπι5γ2κ_σπά5γ2κ_σπά5γ2κ_ϲπά5γ2κ_ϲπά5γ2κ_σπα5γ2κ_ϲπα5γ2κ_φιό5γ2κ_φιό5γ2κ_φιο5γ2κἀ6μ3πάριἀ6μ3πάριἀ6μ3παρι_γά5μ2πι_γά5μ2πι_γα5μ2πι_ζεϊ5μ2π_κό5μ2πρ_κό5μ2πρ_κο5μ2πρ_λι5μ2πρ5μ2πέης_5μ2πέης_5μ2πέηϲ_5μ2πέηϲ_5μ2πεης_5μ2πεηϲ_5μ2πέησ_5μ2πέησ_5μ2πεησ__μπι5μ2π_τρο6μ3π_τρό6μ3π_τρό6μ3π_ρου5μ2π_σέ5μ2πρ_σέ5μ2πρ_ϲέ5μ2πρ_ϲέ5μ2πρ_σνο5μ2π_ϲνο5μ2π_σού5μ2π_σού5μ2π_ϲού5μ2π_ϲού5μ2π_σου5μ2π_ϲου5μ2π_τζά5μ2π_τζά5μ2π_τζα5μ2π_τζι5μ2π_τό5μ2πρ_τό5μ2πρ_το5μ2πρ_φρα5μ2πἀ5ν2τάτζἀ5ν2τάτζ_βί5ν2τε_βί5ν2τε_βι5ν2τε_κα5ν2τρ_μαϊ5ν2τ_μπε5ν2τ_μπι5ν2τ_ντα5ν2τ5ν2τίβαν5ν2τίβαν_ρε5ν2τί_ρε5ν2τί_ρε5ν2τι_ροῦ5ν2τ_ρού5ν2τ_ρού5ν2τ_χα5ν2το_χα5ν2τρ_χά5ν2τρ_χά5ν2τρ6γ2κ5μ2π6γ2κ5ν2τ6μ2π5ν2τ6ν2τ5μ2π",
+		9 : "5γ2κραντ_ἴντρι5γ2κἰντρι5γ2κ_μα5γ2κιό_μα5γ2κιό_ντά5γ2κλ_ντά5γ2κλ_ντα5γ2κλἀλα5μ2πουἀρλού5μ2πἀρλού5μ2πἀρλοῦ5μ2πἀρλου5μ2π_βό5μ2πιρ_βό5μ2πιρ_βο5μ2πιρ_κα5μ2πάδ_κα5μ2πάδ_κα5μ2πίν_κα5μ2πίν_κα5μ2πῖν_κα5μ2πιν_κά5μ2ποτ_κά5μ2ποτ_κα5μ2πότ_κα5μ2πότ_κα5μ2ποτ_καου5μ2π_καρα5μ2π5μ2πα5μ2π5μ2πά5μ2π5μ2πά5μ2π5μ2πέ5μ2π5μ2πέ5μ2π5μ2πε5μ2π_νό5μ2πελ_νό5μ2πελ_νο5μ2πελ_ντό5μ2πρ_ντό5μ2πρ_ντο5μ2πρ_σα2μ5ποτ_ϲα2μ5ποτ_τε5μ2πεσ_τε5μ2πεϲ_τζου5μ2π_τσά5μ2πα_τσά5μ2πα_τϲά5μ2πα_τϲά5μ2πα_τσα5μ2πα_τϲα5μ2παἀτρα5ν2τέἀτρα5ν2τέἀτρα5ν2τὲ_γιβε5ν2τ_γκάι5ν2τ_γκάι5ν2τ_γκάϊ5ν2τ_γκάϊ5ν2τ_γκαϊ5ν2τ_κα5ν2ταΐ_κα5ν2ταΐ_κα5ν2ταϊ_μα5ν2τάμ_μα5ν2τάμ_μα5ν2τὰμ_μα5ν2ταμ_μα5ν2τέμ_μα5ν2τέμ_μα5ν2τεμ_μεϊ5ν2τά_μεϊ5ν2τά_μεϊ5ν2τα_μο5ν2τέλ_μο5ν2τέλ_μο5ν2τελμο5ν2τέρνμο5ν2τέρνμο5ν2τερν_νισα5ν2τ_νιϲα5ν2τ_ρεζε5ν2τ_σε5ν2τέφ_σε5ν2τέφ_ϲε5ν2τέφ_ϲε5ν2τέφ_σε5ν2τεφ_ϲε5ν2τεφ_σε5ν2τοῦ_ϲε5ν2τοῦ_σε5ν2τού_σε5ν2τού_ϲε5ν2τού_ϲε5ν2τού_σε5ν2του_ϲε5ν2του_τσα5ν2τί_τσα5ν2τί_τϲα5ν2τί_τϲα5ν2τί_τσα5ν2τι_τϲα5ν2τι",
+		10 : "_γιου5γ2κο_καρα5γ2κι_χούλι5γ2κ_χούλι5γ2κ_χουλι5γ2κ_γιαρα5μ2π_καλα5μ2πα_καλί5μ2πρ_καλί5μ2πρ_καλι5μ2πρ_κα5μ2παρέ_κα5μ2παρέ_κα5μ2παρὲ_κα5μ2παρε_καρνα5μ2π_κολι5μ2πρ_κου5μ2πού_κου5μ2πού_κου5μ2ποῦ_κου5μ2που5μ2πέηδες_5μ2πέηδες_5μ2πέηδεϲ_5μ2πέηδεϲ_5μ2πέηδεσ_5μ2πέηδεσ_5μ2πέηδων_5μ2πέηδων__μπό5μ2πιρ_μπό5μ2πιρ_μπο5μ2πιρ_μπο5μ2πότ_μπο5μ2πότ_μπο5μ2ποτ_σκα5μ2παβ_ϲκα5μ2παβ_ταβλα5μ2π_τζανα5μ2π_τρα5μ2πάλ_τρα5μ2πάλ_τρα5μ2παλ_φά5μ2πρικ_φά5μ2πρικ_φα5μ2πρικ_μπαλά5ν2τ_μπαλά5ν2τ_μπαλα5ν2τ_μπα5ν2ταν_μπου5ν2τα_μπου5ν2τρ",
+		11 : "_καρα6μ3πόλ_καρα6μ3πόλ_καρα6μ3πολ_κολού5μ2πρ_κολού5μ2πρ_κολοῦ5μ2πρ_κολου5μ2πρ_κο6μ3πρέσσ_κο6μ3πρέσσ_κο6μ3πρέϲϲ_κο6μ3πρέϲϲ_κο6μ3πρεσσ_κο6μ3πρεϲϲ_κοντρα5μ2π_κωλού5μ2πρ_κωλού5μ2πρ_κωλοῦ5μ2πρ_κωλου5μ2πρ_μανιτό5μ2π_μανιτό5μ2π_μπα6μ3πάκι_μπα6μ3πάκι_μπα6μ3πακι_ρεπού5μ2πλ_ρεπού5μ2πλ_ρεπου5μ2πλ_τα6μ3περαμ_τα6μ3ποῦρλ_τα6μ3πούρλ_τα6μ3πούρλ_τρα5μ2ποῦκ_τρα5μ2πούκ_τρα5μ2πούκ_τρα5μ2πουκ_τσι5μ2πούκ_τσι5μ2πούκ_τϲι5μ2πούκ_τϲι5μ2πούκ_τσι5μ2πουκ_τϲι5μ2πουκ_τσι5μ2πούσ_τσι5μ2πούσ_τϲι5μ2πούϲ_τϲι5μ2πούϲ_τσι5μ2πουσ_τϲι5μ2πουϲ_γιαχου5ν2τ",
+		12 : "_σαλτιπά5γ2κ_σαλτιπά5γ2κ_ϲαλτιπά5γ2κ_ϲαλτιπά5γ2κ_κουλού5μ2πρ_κουλού5μ2πρ_κουλοῦ5μ2πρ_κουλου5μ2πρ_μπου5μ2πούν_μπου5μ2πούν_μπου5μ2ποῦν_μπου5μ2πουν_χοντρο5μ2πα_λικβι5ν2ταρ_ντερμπε5ν2τ_ντου5ν2τούκ_ντου5ν2τούκ_ντου5ν2τοῦκ_ντου5ν2τουκ_φαστφου5ν2τ_φαϲτφου5ν2τ",
+		13 : "_μπασκε2τ5μ2π_μπαϲκε2τ5μ2π_μπασι5μ2πουζ_μπαϲι5μ2πουζ"
+	}
+};
--- a/resources/viewer/hyphenate/patterns/en-gb.js
+++ b/resources/viewer/hyphenate/patterns/en-gb.js
--- a/resources/viewer/hyphenate/patterns/en-us.js
+++ b/resources/viewer/hyphenate/patterns/en-us.js
--- a/resources/viewer/hyphenate/patterns/en.js
+++ b/resources/viewer/hyphenate/patterns/en.js
--- a/resources/viewer/hyphenate/patterns/es.js
+++ b/resources/viewer/hyphenate/patterns/es.js
--- a/resources/viewer/hyphenate/patterns/fi.js
+++ b/resources/viewer/hyphenate/patterns/fi.js
@ -1,17 +1,17 @@
-Hyphenator.languages.fi = {
+Hyphenator.languages['fi'] = {
 	leftmin : 2,
 	rightmin : 2,
 	shortestPattern : 2,
 	longestPattern : 7,
-	specialChars : 'öäå',
+	specialChars : "öäå",
 	patterns : {
-		3 : '1ba1be1bi1bo1bu1by1da1de1di1do1du1dy1dä1dö1fa1fe1fi1fo1fu1fy1ga1ge1gi1go1gu1gy1gä1gö1ha1he1hi1ho1hu1hy1hä1hö1ja1je1ji1jo1ju1jy1jä1jö1ka1ke1ki1ko1ku1ky1kä1kö1la1le1li1lo1lu1ly1lä1lö1ma1me1mi1mo1mu1my1mä1mö1na1ne1ni1no1nu1ny1nä1nö1pa1pe1pi1po1pu1py1pä1pö1ra1re1ri1ro1ru1ry1rä1rö1sa1se1si1so1su1sy1sä1sö1ta1te1ti1to1tu1ty1tä1tö1va1ve1vi1vo1vu1vy1vä1vöä2yo1yö2ya1äa1öo1äo1öä2äö2öä2öö2ä_ä2u2sb2lb2rd2rf2lf2rg2lg2rk2lp2lp2rc2lq2v',
-		4 : 'y1a2y1o2u1y2y1u2ö3a2ö3o2ä3a2ä3o2ä1u2ö1u2u1ä2u1ö2e1aai1aao1aau1aau1eea1uui1uue1uuo1uuää1iää1eää3yi1ääe1ääy1ääi1ööa1eia1oie1aii1auy1eiai1aai1eai1oai1uau1aau1eeu1aie1aie1oie1yiu1aiu1eiu1ooi1aoi1eoi1ooi1uo1uiou1eou1oue1aui1euo1auo1ue1ö2ö1e2r2asl2as1k2vsc2hts2h',
-		5 : '1st2raa1i2aa1e2aa1o2aa1u2ee1a2ee1i2ee1u2ee1y2ii1a2ii1e2ii1o2uu1a2uu1e2uu1o2uu1i2io1a2io1e2keus11b2lo1b2ri1b2ro1b2ru1d2ra1f2la1f2ra1f2re1g2lo1g2ra1k2ra1k2re1k2ri1k2va1p2ro1q2vich2r',
-		6 : '1sp2lialous1rtaus1perus12s1ase2s1apuulo2s1bib3li',
-		7 : 'yli1o2pali1a2v2s1ohje1a2sian1a2siat1a2sioi2s1o2sa2n1o2sa_ydi2n12n1otto2n1oton2n1anto2n1anno2n1aika2n1a2jo2s1a2jo',
-		8 : '2s1a2sia2n1o2pet2s1a2loialkei2s12n1e2dus2s1ajatu2s1y2rit2s1y2hti2n1a2jan2n1o2mai2n1y2lit2s1a2len2n1a2len',
-		9 : '2s1o2pisk2n1o2pist2s1o2pist2s1i2dea_2s1i2dean2s1e2sity_suu2r1a2',
-		11 : '1a2siaka2s1'
+		3 : "1ba1be1bi1bo1bu1by1da1de1di1do1du1dy1dä1dö1fa1fe1fi1fo1fu1fy1ga1ge1gi1go1gu1gy1gä1gö1ha1he1hi1ho1hu1hy1hä1hö1ja1je1ji1jo1ju1jy1jä1jö1ka1ke1ki1ko1ku1ky1kä1kö1la1le1li1lo1lu1ly1lä1lö1ma1me1mi1mo1mu1my1mä1mö1na1ne1ni1no1nu1ny1nä1nö1pa1pe1pi1po1pu1py1pä1pö1ra1re1ri1ro1ru1ry1rä1rö1sa1se1si1so1su1sy1sä1sö1ta1te1ti1to1tu1ty1tä1tö1va1ve1vi1vo1vu1vy1vä1vöä2yo1yö2ya1äa1öo1äo1öä2äö2öä2öö2ä_ä2u2sb2lb2rd2rf2lf2rg2lg2rk2lp2lp2rc2lq2v",
+		4 : "y1a2y1o2u1y2y1u2ö3a2ö3o2ä3a2ä3o2ä1u2ö1u2u1ä2u1ö2e1aai1aao1aau1aau1eea1uui1uue1uuo1uuää1iää1eää3yi1ääe1ääy1ääi1ööa1eia1oie1aii1auy1eiai1aai1eai1oai1uau1aau1eeu1aie1aie1oie1yiu1aiu1eiu1ooi1aoi1eoi1ooi1uo1uiou1eou1oue1aui1euo1auo1ue1ö2ö1e2r2asl2as1k2vsc2hts2h",
+		5 : "1st2raa1i2aa1e2aa1o2aa1u2ee1a2ee1i2ee1u2ee1y2ii1a2ii1e2ii1o2uu1a2uu1e2uu1o2uu1i2io1a2io1e2keus11b2lo1b2ri1b2ro1b2ru1d2ra1f2la1f2ra1f2re1g2lo1g2ra1k2ra1k2re1k2ri1k2va1p2ro1q2vich2r",
+		6 : "1sp2lialous1rtaus1perus12s1ase2s1apuulo2s1bib3li",
+		7 : "yli1o2pali1a2v2s1ohje1a2sian1a2siat1a2sioi2s1o2sa2n1o2sa_ydi2n12n1otto2n1oton2n1anto2n1anno2n1aika2n1a2jo2s1a2jo",
+		8 : "2s1a2sia2n1o2pet2s1a2loialkei2s12n1e2dus2s1ajatu2s1y2rit2s1y2hti2n1a2jan2n1o2mai2n1y2lit2s1a2len2n1a2len",
+		9 : "2s1o2pisk2n1o2pist2s1o2pist2s1i2dea_2s1i2dean2s1e2sity_suu2r1a2",
+		11 : "1a2siaka2s1"
 	}
 };
--- a/resources/viewer/hyphenate/patterns/fr.js
+++ b/resources/viewer/hyphenate/patterns/fr.js
@ -1,27 +1,26 @@
-Hyphenator.languages.fr = {
+// The french hyphenation patterns are retrieved from
+// http://tug_org/svn/texhyphen/trunk/collaboration/repository/hyphenator/
+Hyphenator.languages['fr'] = {
 	leftmin : 2,
-	rightmin : 2,
+	rightmin : 3,
 	shortestPattern : 1,
 	longestPattern : 14,
-	specialChars : 'âêîôûçœéèàî',
-	//The french hyphenation patterns are retrieved from http://extensions.services.openoffice.org/project/french-dictionary-reform1990
-	//They are under LGPL
+	specialChars : "àâçèéêîïôûœ’'",
 	patterns : {
-		2 : "1j1q1ç",
-		3 : "'a4'e4'i4'o4'u4'y4'â4'è4'é4'ê4'î4'ô4'û4_a4_e4_i4_o4_u4_y4_â4_è4_é4_ê4_î4_ô4_û41ba1be1bi1bo1bu1by1bâ1bè1bé1bê1bî1bô1bû1ca1ce1ci1co1cu1cy1câ1cè1cé1cê1cî1cô1cû1da1de1di1do1du1dy1dâ1dè1dé1dê1dî1dô1dû1fa1fe1fi1fo1fu1fy1fâ1fè1fé1fê1fî1fô1fû1ga1ge1gi1go1gu1gy1gâ1gè1gé1gê1gî1gô1gû1ha1he1hi1ho1hu1hy1hâ1hè1hé1hê1hî1hô1hû1ka1ke1ki1ko1ku1ky1kâ1kè1ké1kê1kî1kô1kû1la1le1li1lo1lu1ly1là1lâ1lè1lé1lê1lî1lô1lû1ma1me1mi1mo1mu1my1mâ1mè1mé1mê1mî1mô1mû1na1ne1ni1no1nu1ny1nâ1nè1né1nê1nî1nô1nû1pa1pe1pi1po1pu1py1pâ1pè1pé1pê1pî1pô1pû1ra1re1ri1ro1ru1ry1râ1rè1ré1rê1rî1rô1rû1sa1se1si1so1su1sy1sâ1sè1sé1sê1sî1sô1sû1ta1te1ti1to1tu1ty1tà1tâ1tè1té1tê1tî1tô1tû1va1ve1vi1vo1vu1vy1vâ1vè1vé1vê1vî1vô1vû1wa1we1wi1wo1wu1za1ze1zi1zo1zu1zy1zè1zé2'22jkn1xé1q",
-		4 : "_1ba_1bi_1ci_1co_1cu_1da_1di_1do_1dy_1dé_1ge_1la_1ma_1mi_1mo_1mé_1no_1pa_1pe_1po_1pu_1pé_1re_1ré_1sa_1se_1so_1su_1sy_1ta1b2l1b2r1c2h1c2k1c2l1c2r1c½01d2r1f2l1f2r1g2l1g2n1g2r1k2h1k2r1m½01n½01p2h1p2l1p2r1r2h1s2h1s½01t2h1t2r1v2r1w2r2chb2chg2chm2chn2chp2chs2cht2chw2ckb2ckf2ckg2ckp2cks2ckt2phn2phs2pht2shm2shr2shs2thl2thm2thn2ths4be_4ce_4ch_4ck_4de_4fe_4ge_4he_4je_4ke_4kh_4le_4me_4ne_4pe_4ph_4re_4se_4sh_4te_4th_4ve_4we_4ze_a1bîa1laa1maa1nea1nia1poa1viab2hac1qad2har1cb1leb1reb1ruc1cic1kec1lac1lec1rec2hac2hec2hic2hoc2huc2hyc2hâc2hèc2héc2hêc2hîc2hôc2hûch2lch2rd1had1hod1led1red1s2e1nif1laf1lef1ref1rif1s2g1leg1neg1rag1reg1s2i1vail2ll1lil1lul1mem1nèm1ném1s2n1sao1pup1hep1hop1lep1lup1nep1rep1rip1rop1rup1rép1syp1tèp1téph2lph2rr1cir1her1hyr1mis1cas1cos1hes1hos1las1los1pas1pes1pis1pos1tas1tes1tis1tos1tys1tét1het1rat1ret1rit1ruth2ru1ciu1niu1viv1reâ1meè1meé1ceé1cié1cué1deé1leé1lié1loé1léé1mié1neé1nié1pié1reô1me",
-		5 : "'a1mi'a1na'a1po'o1vi_1p2l_1p2r_1t2r_a1mi_a1na_a1po_c2hè_con4_cul4_dé2s_o1vi_p1ha_p1lu_p1ro_p1ré_p1sy_pe4r_réu2_s1ta_s1ti_t1ri_é1mi1d2'21g2ha1g2he1g2hi1g2ho1g2hy1p2né4bes_4ces_4des_4fes_4ges_4gue_4hes_4jes_4kes_4les_4mes_4nes_4pes_4que_4res_4ses_4tes_4ves_4wes_4zes_ab1seac1ceai1meal1coan1tiap1paar1mear1mias1meau1meca1pica1rêch1lech1loch1rech1rocil3lco1apco1arco1auco1axco1efco1enco1exco1nuco1é2cy1rid1d2hda1medi1lidé1caer1mees1cees1coes1tifa1mefu1mefé1cugil3lhil3lhu1mehy1pehy1pohé1mihé1moi1b2ri1oxyib1riim1maim1miim1poim1puin1ciin1diin1doin1duin1foin1noin1soin1tein1tiis1ceis1taja1cel1s2tlil3lmi1memil3lmo1nomu1nimé1coo1b2lo1d2lo1g2nob1looc1teog1noom1buom1meom1nior1meos1taos1tios1toos1tépa1lépa1piph1leph1reph1taph1tipi1ripo1lypu1pipu1sipé1nupé1réra1dira1mere1lere1lire1peri1meru1leré1geré1maré1suré1tis1c2ls1p2hs1t2rsc1lésc2hese1mises1qsp1hèsp1hést1rost1rusu1mesu1pesu1rasu1rét1c2ht1t2lta1metc2hith1reth1rito1metu1meté1léue1viva1civa1nive1nivi1divil3lvé1loxil3lys1toé1d2réd1riéd2hiélo1q",
-		6 : "'a1b2r'a1g2n'ab1ré'ag1na'an1ti'ar1ge'ar1pe'as2ta'i1g2n'in1te'in2er'on1gu_1c2h4_1k2h4_1p2h4_1s2h4_1t2h4_a1b2r_a1g2n_ab1ré_ag1na_an1ti_ar1de_ar1ge_ar1pe_as2ta_bi1au_bi1u2_ci1sa_co1o2_cons4_do1le_dy2s3_dé1a2_dé1io_dé1o2_dé1sa_dé1se_dé1so_dé1su_i1g2n_in1te_in2er_la1te_ma1la_ma1le_ma1li_ma1lo_mil3l_mo1no_mé1go_mé1se_mé1su_mé1ta_mé2sa_no1no_on1gu_pa1na_pa1ni_pa1no_pa1ra_pa1re_pa1te_pé1ri_re1s2_res1q_ré1a2_ré1e2_ré1i2_ré1o2_ré1é2_ré2el_ré2er_ré2èr_su1bi_su1bu_su1ri_su1ro_ta1le1m2nès1octet1p2neu1p2tèr1p2tér1s2c2h1s2cop1s2lav1s2lov1s2por2bent_2c1k3h2cent_2dent_2fent_2gent_2jent_2kent_2lent_2nent_2pent_2rent_2s2chs2s3hom2sent_2tent_2vent_2went_2xent_2zent_3d2hal4b4le_4b4re_4c4he_4c4ke_4c4le_4c4re_4d4re_4f4le_4f4re_4g4le_4g4ne_4g4re_4gues_4p4he_4p4le_4p4re_4ques_4r4he_4s4ch_4s4he_4t4he_4t4re_4v4re_abs1tiabî1meani1mear1c2harc2hias1t2ravil4laè1d2rbou1mebou1tibru1mecci1deche1vicla1meco1a2dco1accco1g2ncog1nicom1pécon1ficon1nicon1ticor1pucur1redis1codis1sidis1tidé1t2rdét1rien1t2rent1reeus1taex1t2rfi1c2hfic2hufir1mefri1tihémi1éins1tiisc2hiiva1leiè1d2rl3lionla1w2rllu1memil1lemit1tenu1t2rnut1riopu1leos1t2rost1raost1rioxy1a2oè1d2rpe1r3hper1maper1tipho1toplu1mepri1vapru1depré1sepu1g2npug1napé2nulqua1merai1mercil4lrin1germil4lry1t2hry2thmser1geser1pesla1lospa1tispi1rospo1rusto1mosté1résu1b2lsub1lisub1s2suc1cuta1c2htac2hytan1getem1péter1getes1tator1retri1detru1cutur1buucil4luvil4lvol1tawa2g3néci1meécu1meédri1qéli1meélé1meémil4léni1te",
-		7 : "'ab3réa'ami1no'e1n1a2'e1n1o2'i1n1a2'i1n1e2'i1n1i2'i1n1o2'i1n1u2'i1n1é2'i2g3ni'i2g3né'i2g4no'in2ept'in2i3q'in2i3t'in2ond'in2u3l'in2uit'ina1ni'ini1mi'ino1cu'ins1ta'iné1lu'iné1na'oua1ou_ab3réa_ami1no_bai1se_bi1a2c_bi1a2t_bio1a2_com1me_coo1li_da1c2r_dac1ry_di1ald_di1e2n_di2s3h_dia1ci_dia1to_dé2s1½_dé3s2c_dé3s2p_dé3s2t_e1n1a2_e1n1o2_gem1me_i1n1a2_i1n1e2_i1n1i2_i1n1o2_i1n1u2_i1n1é2_i2g3ni_i2g3né_i2g4no_in2ept_in2i3q_in2i3t_in2ond_in2u3l_in2uit_ina1ni_ini1mi_ino1cu_ins1ta_iné1lu_iné1na_ma1c2r_ma1g2n_ma2c3k_ma2r1x_mac1ro_mag1ni_mag1nu_mil1li_mé2s1i_mé3san_oua1ou_pa1r2h_pen2ta_pha1la_plu1ri_pon1te_pos1ti_pro1é2_pré1a2_pré1e2_pré1i2_pré1o2_pré1s2_pré1u2_pré1é2_pré2au_re2s3s_re2s3t_res1ca_res1ci_res1co_res1pe_res1pi_res1po_res1se_res1ta_res1ti_res1to_res1té_ré1t2r_ré2aux_ré2uss_réa1li_rét1ro_sar1me_ser1me_seu2le_sou1ve_stil3l_su1b2l_su2r3h_sub1li_émi1ne1alcool1s2clér1s2perm1s2phèr1s2phér1s2piel1s2tein1s2tigm1é2drie1é2nerg2chent_2guent_2phent_2quent_2r3heur2shent_2t3heur3d2houd3ph2tis4b4les_4b4res_4c4hes_4c4kes_4c4les_4c4res_4ch4le_4ch4re_4d4res_4f4les_4f4res_4g4les_4g4nes_4g4res_4p4hes_4p4les_4p4res_4ph4le_4ph4re_4r4hes_4s4hes_4t4hes_4t4res_4th4re_4v4res_amal1gaanti1feappa1rearmil5lcapil3lcarê1mechlo1rachlo1réchro1meco1ac1qco2nurbcoas1socoas1sucyril3ldia1p2hdiaph2rdili1gedéca1dee2s3c2he2s3copesti1meext1ra1extra2cextra2iflam1mefécu1legram1megran1dihype4r1hypers2hypo1a2hypo1e2hypo1i2hypo1o2hypo1s2hypo1u2hypo1é2i1al1gii1s2c2hi1s2tatiar1t2hibril3limma1neimmi1neimpo1teimpu1deinci1deindi1geindo1leinno1ceinso1leinti1meio1a2ctl2ment_la2w3remil4letmon1t2rmono1vamont1rémoye1nâmuni1fin3s2at_o1io1nio1s2taso1s2tato1s2timo1s2tomogno1moomni1poomni1s2papil2lpiril3lpoly1a2poly1e2poly1i2poly1o2poly1s2poly1u2poly1vapoly1è2poly1é2pros1taproé1mipréé1mipupil3lpusil3lreli1meryth1meréma1neréti1cesemil4lstan1dasu3r2ahsupe4r1supers2suré1mither1mothril3ltung2s3télé1e2télé1i2télé1s2u2s3t2ruevil4luni1a2xuni1o2vvacil4lvanil2lven1t2rveni1mevent1rividi1mey1al1giy1s2tomâ2ment_è2ment_é3cent_é3dent_é3rent_épis1coéqui1poéqui1vaô2ment_",
-		8 : "'a2g3nat'anti1a2'anti1e2'anti1s2'anti1é2'eu2r1a2'inau1gu'inef1fa'inte4r3'inters2'ovi1s2c_1s2c2h4_a2g3nat_anti1a2_anti1e2_anti1s2_anti1é2_bi2s1a2_chè1v2r_chèv1re_con1t2r_cont1re_di1a2cé_di1a2mi_dy2s1a2_dy2s1i2_dy2s1o2_dy2s1u2_dé2s1i2_dé2s1é2_dés2a3m_désa1te_dési1ne_déso1pi_eu2r1a2_inau1gu_inef1fa_inte4r3_inters2_ma2l1ap_ma2l1en_ma2l1oc_mono1a2_mono1e2_mono1i2_mono1o2_mono1s2_mono1u2_mono1é2_mé2g1oh_mé2s1es_ovi1s2c_pa2n1is_pa2r3hé_para1s2_pe1r1a2_pe1r1e2_pe1r1i2_pe1r1o2_pe1r1u2_pe1r1é2_pluri1a_pon2tet_pos2t3h_pos2t3r_post1s2_pro1g2n_prog1na_psyc2ho_pud1d2l_péri1os_péri1s2_péri1u2_re3s4tu_re3s4ty_res1c2r_res1p2l_resp1le_rest1re_rest1ri_ré2a3le_ré2i3fi_sta2g3n_su2b1a2_su2b1in_su2b1ur_su2b1é2_su2b3lu_su2r1a2_su2r1e2_su2r1of_su2r1ox_su2r1é2_su3r2et_syn1g2n_syng1na_tri1a2c_tri1a2n_tri1a2t_tri1o2n1m2né1mo1m2né1si1s2patia1s2piros1s2tomos1s2ty1le2b2lent_2b2rent_2c2kent_2c2lent_2c2rent_2d2lent_2d2rent_2f2lent_2f2rent_2g2lent_2g2nent_2g2rent_2p2lent_2p2rent_2t2rent_2v2rent_4ch4les_4ch4res_4ph4les_4ph4res_4s4c4he_4th4res_a1è2d1rea2s3t1roab3sent_absti1neac3cent_ai2ment_anes1t2hanest1héar2ment_as2ment_au2ment_boutil3lca3ou3t2chevil4lchien1deco1assocco1assurcompé1teconfi1deconni1veconti1necorpu1leda2ment_di2s3copdiaph1radissi1dedistil3ldétri1meentre1geer2ment_es3cent_eu1s2tatfa2ment_fichu1mefritil3lfu2ment_hu2ment_hype1ra2hype1re2hype1ri2hype1ro2hype1ru2hype1ré2hémo1p2ti1arth2ri1è2d1rei2s3c2héi2s3chiai2s3chioimmis1ceindul1geinfor1mainstil3lintel1liis3cent_ja3cent_mi2ment_mécon1ten3s2ats_nutri1meo1s2trado1è2d1reo2b3longom2ment_ombud2s3or2ment_paléo1é2papil1lopapil3lapapil3lepapil3liperma1neperti1nephoto1s2poas1t2rpu2g3nacpé1r2é2qra2ment_radio1a2re3lent_re3pent_ri2ment_ru3lent_ré3gent_résur1geslalo1mesporu1lesu2ment_subli1mesuccu1lesupe1ro2ta2ment_tachy1a2tchin3t2tempé1ratesta1meto2ment_tran2s3htran2s3ptrans1patrucu1letu2ment_turbu1letélé1o2btélé1o2pvanil1liy1as1t2hé3quent_",
-		9 : "'ae3s4c2h'apo2s3ta'ar3gent_'ar3pent_'in1s2tab'in2a3nit'in2augur'in2effab'in2o3cul'inte1ra2'inte1re2'inte1ri2'inte1ro2'inte1ru2'inte1ré2_ae3s4c2h_apo2s3ta_ar3dent__ar3gent__ar3pent__baise1ma_ci2s1alp_co2o3lie_di1a2cid_di1a2tom_do3lent__dé2s1u2n_dé3s2ert_dé3s2exu_dé3s2i3d_dé3s2i3r_dé3s2ist_dé3s2o3l_dé3s2orm_dé3s2orp_désen1si_in1s2tab_in2a3nit_in2augur_in2effab_in2o3cul_inte1ra2_inte1re2_inte1ri2_inte1ro2_inte1ru2_inte1ré2_la3tent__ma2g3num_ma2l1a2v_ma2l1int_ma2l1o2d_magni1ci_magni1fi_mala1d2r_malad1re_milli1am_mé2s1u2s_no2n1obs_pa2n1a2f_pa2n1opt_pa3rent__pa3tent__para1c2h_pos2t1in_pos2t1o2_pro1s2cé_prou3d2h_pré2a3la_péri2s3s_re2s3cap_re2s3cou_re2s3pir_re3s4t2r_re3s4tab_re3s4tag_re3s4tat_re3s4tim_re3s4tip_re3s4toc_re3s4top_re3s4tén_re3s4tér_ré2a3lis_ré2a3lit_rétro1a2_su2b3lin_su2r1i2m_su2r1inf_su2r1int_su3b2alt_su3b2é3r_su3r2a3t_su3r2eau_su3r2ell_subli1mi_ta3lent_1informat1p2sy1c2h1s2ca1p2h1s2to1c2k1é2drique1é2lément2r3hy1d2r3ph2ta1lé4s4c4hes_a2l1al1giabî2ment_amalga1meani2ment_apo2s3t2rarchié1pibou2ment_bru2ment_cci3dent_cla2ment_contin1gecur3rent_e2n1i2v2rfir2ment_grandi1loiva3lent_llu2ment_mit3tent_monova1lemunifi1ceo1s2té1roo2g3no1siomnipo1teopu3lent_ostric1tipapil3lomplu2ment_po1ast1repolyva1leprivat1dopro2s3tatproémi1nepru3dent_pré3sent_préémi1nepugna1b2lqua2ment_rai3ment_rin3gent_ser3gent_ser3pent_sesqui1a2stéréo1s2surémi1netan3gent_ter3gent_thermo1s2tor3rent_tran2s1a2tran2s1o2tran2s1u2tri3dent_vanil3linvanil3lisventri1povol2t1ampvélo1s2kiéci2ment_écu2ment_éli2ment_éni3tent_épi2s3copéquipo1teéquiva1le",
-		10 : "'amino1a2c'ana3s4t2r'in2exo1ra'on3guent__1p2sy1c2h_amino1a2c_ana3s4t2r_chèvre1fe_com3ment__contre1ma_dacryo1a2_dé3s2i3li_gem2ment__in2exo1ra_macro1s2c_mono1ï2dé_on3guent__pa2n1a2mé_pa2n1a2ra_péri2s3ta_re2s3c1ri_re2s3pect_re2s3pons_re2s3quil_re3s4tand_re4s5trin_res3sent__sar3ment__ser3ment__sou3vent__émi3nent_1s2tandard1s2tro1p2h1s2truc1tu1é2lec1t2racquies1ceantifer1meappa3rent_carê2ment_chlo2r3a2cchlo2r3é2tchro2ment_co2g3ni1tidili3gent_déca3dent_esti2ment_flam2ment_fécu3lent_gram2ment_grandilo1qimma3nent_immi3nent_impo3tent_impu3dent_inci3dent_indi3gent_indo3lent_inno3cent_inso3lent_intelli1geinti2ment_mon2t3réalmoye2n1â2go1s2tra1tureli2ment_ryth2ment_réma3nent_réti3cent_tempéra1metran3s2acttran3s2atstranspa1reveni2ment_vidi2ment_élo3quent_",
-		11 : "'anti2en1ne'in2i3mi1ti_1dé3s2o3dé_anti2en1ne_contre1s2c_dé3s2a3c2r_dé3s2ensib_dé3s2i3g2n_dé3s2i3nen_dé3s2in1vo_dé3s2o3pil_dé3s2é3g2r_in2i3mi1ti_ma2l1ai1sé_magnifi1ca_mé1ta1s2ta_pa2n1o2p2h_phalan3s2t_psycho1a2n_re2s3ci1si_re2s3ci1so_re2s3plend_re4s5trein_re4s5trict_su2b3liminabsti3nent_archi1é2pischien3dent_compé3tent_confi3dent_conni3vent_conti3nent_corpu3lent_diaphrag1medissi3dent_détri3ment_entre3gent_fichu3ment_immis4cent_indul3gent_mécon3tent_nutri3ment_o2g3nomo1niperma3nent_perti3nent_privatdo1ceprivatdo1zepu2g3nab1lerésur3gent_slalo2ment_sporu4lent_subli2ment_succu3lent_testa3ment_trucu3lent_turbu3lent_ventripo1teépi3s4co1pe",
-		12 : "'in2é3luc1ta'in2é3nar1ra_bai2se3main_dé3s2a3tell_dé3s2as1t2r_dé3s2ou1f2r_in2é3luc1ta_in2é3nar1ra_ma2l1a2d1ro_ma2l1a2dres_pa2r1a2c2he_pa2r1a2c2hè1a2nesthé1siamalga2ment_contin3gent_monova3lent_munifi3cent_o1s2trictionomnipo3tent_polyva3lent_proémi3nent_préémi3nent_surémi3nent_équipo3tent_équiva4lent_",
-		13 : "_ma2g3nici1de_ma2g3nificat_pro2g3na1t2h_syn2g3na1t2hacquies4cent_antifer3ment_intelli3gent_tempéra3ment_transpa3rent_",
-		14 : "_chèvrefeuil2l_contremaî1t2rdiaphrag2ment_privatdo3cent_privatdo3zent_ventripo3tent_",
+		2 : "1ç1j1q",
+		3 : "1gè’â41zu1zo1zi1zè1zé1ze1za’y4_y41wu1wo1wi1we1wa1vy1vû1vu1vô1vo1vî1vi1vê1vè1vé1ve1vâ1va’û4_û4’u4_u41ba1bâ1ty1be1bé1bè1bê1tû1tu1tô1bi1bî1to1tî1ti1tê1tè1té1te1tà1tâ1ta1bo1bô1sy1sû1su1sœ1bu1bû1by2’21ca1câ1sô1ce1cé1cè1cê1so1sî1si1sê1sè1sé1se1sâ1sa1ry1rû1ru1rô1ro1rî1ri1rê1rè1ré1re1râ1ra’a41py1pû1pu1pô1po1pî1pi1pê1pè1pé1pe1pâ1pa_ô41ci1cî’ô4’o4_o41nyn1x1nû1nu1nœ1nô1no1nî1ni1nê1nè1né1ne1nâ1co1cô1na1my1mû1mu1mœ1mô1mo1mî1mi1cœ1mê1mè1mé1me1mâ1ma1ly1lû1lu1lô1lo1lî1li1lê1lè1cu1cû1cy1lé1d’1da1dâ1le1là1de1dé1dè1dê1lâ1la1ky1kû1ku1kô1ko1kî1ki1kê1kè1ké1ke1kâ1ka2jk_a4’î4_î4’i4_i41hy1hû1hu1hô1ho1hî1hi1hê1hè1hé1he1hâ1ha1gy1gû1gu1gô1go1gî1gi1gê_â41gé1ge1gâ1ga1fy1di1dî1fû1fu1fô1fo’e41fî1fi1fê1fè1do1dô1fé1fe1fâ1fa’è41du1dû1dy_è4’é4_é4’ê4_ê4_e41zy",
+		4 : "1f2lab2h2ckg2ckp2cksd1s22ckb4ck_1c2k2chw4ze_4ne_2ckt1c2lad2hm1s22cht2chsch2r2chp4pe_1t2r1p2h_ph44ph_ph2l2phnph2r2phs1d2r2pht2chn4fe_2chm1p2l1p2r4me_1w2rch2l2chg1c2r2chb4ch_1f2r4le_4re_4de_f1s21k2r4we_1r2h_kh44kh_1k2h4ke_1c2h_ch44ge_4je_4se_1v2r_sh41s2h4ve_4sh_2shm2shr2shs4ce_il2l1b2r4be_1b2l4he_4te__th41t2h4th_g1s21g2r2thl1g2l2thm2thnth2r1g2n2ths2ckf",
+		5 : "2ck3h4rhe_4kes_4wes_4res_4cke_éd2hi4vre_4jes_4tre_4zes_4ges_4des_i1oxy4gle_d1d2h_cul44gne_4fre_o1d2l_sch44nes_4les_4gre_1s2ch_réu24sch_4the_1g2hy4gue_2schs4cle_1g2ho1g2hi1g2he4ses_4tes_1g2ha4ves_4she_4che_4cre_4ces_t1t2l4hes_l1s2t4bes_4ble__con4xil3lco1ap4que_vil3l4fle_co1arco1exco1enco1auco1axco1ef4pes_co1é2per3h4mes__pe4r4bre_4pre_4phe_1p2né4ple__dé2smil3llil3lhil3l4dre_cil3lgil3l4fes_",
+		6 : "’in1o2rcil4l4phre_4dres_l3lioni1algi2fent_émil4l4phle_rmil4l4ples_4phes_1p2neuextra14pres_y1asthpé2nul2xent__mé2sa2pent_y1algi4chre_1m2nès4bres_1p2tèr1p2tér4chle_’en1o24fles_oxy1a2avil4l_en1o24ques_uvil4lco1a2d4bles__in1a2’in1a21s2por_cons4_bi1u2’as2ta_in1e2’in1e2_in1é2’in1é21s2lov1s2lavco1acq2cent__as2ta_co1o24ches_hémi1é_in2er’in2er2s3homo1ioni_in1i2’in1i22went_4shes__ré1a2_ré1é2_ré1e2_ré2el_in1o2ucil4lco1accu2s3tr_ré2er_ré2èr4cles_2vent__ré1i22sent_2tent_2gent__ré1o24gues__re1s24sche_4thes_’en1a2e2s3ch4gres_1s2cop2lent__en1a22nent__in1u2’in1u24gnes_4cres_wa2g3n4fres_4tres_4gles_1octet_dé1o2_dé1io4thre__bi1au2jent__dé1a22zent_4vres_2dent_4ckes_4rhes__dy2s3sub1s22kent_2rent_2bent_3d2hal",
+		7 : "a2g3nos3d2houdé3rent__dé3s2t_dé3s2pé3dent_2r3heur2r3hydri1s2tat2frent_io1a2ctla2w3re’in2u3l_in2u3l2crent_’in2uit_in2uit1s2caph1s2clér_ré2ussi2s3ché_re2s3t_re2s3s4sches_é3cent__seu2le’in2ond_in2ond’in2i3t_in2i3t’in2i3q_ré2aux_in2i3q2shent__di1alduni1a2x’in2ept2flent__in2eptuni1o2v2brent_co2nurb2chent_2quent_1s2perm1s2phèr_ma2c3kuevil4l1s2phér1s2piel1s2tein1s2tigm4chles_1s2tock1s2tyle1p2sych_pro1é2_ma2r1x_stil3lpusil3libril3lcyril3l_pré1s2thril3l_mé3san_pré1u2_mé2s1i_pré1o2_pré1i2piril3lpupil3lâ2ment__pré1e2_pré1é2_pré2au_pré1a22prent_2vrent_supero2_di1e2npoly1u2è2ment_poly1s2poly1o2poly1i2poly1è2poly1é2poly1e2poly1a2supe4r1capil3l2plent_armil5lsemil4lmil4letvacil4l_di2s3h3ph2tis2dlent_a2s3tro4phres_l2ment_i1è2drei1arthr2drent_4phles_supers2ô2ment_extra2i2phent_su3r2ah_su2r3hextra2chypo1u21alcool_per1u2_per1o2_per1i2_per1é2hypo1s2_per1a2hypo1o2hypo1i2hypo1é2_pen2tahypo1e2hypo1a2y1s2tome2s3cophyperu2hype4r1hypers2hypero21m2némohyperi21m2nési4chres_a1è2drehyperé2hypere2hypera2’oua1ou_oua1ouo1s2tomo1s2timo1s2tato1s2tasomni1s2tung2s3_dé3s2c2blent__bio1a2télé1e2télé1i22clent_télé1s22guent_1é2nerg2grent_2trent__dé2s1œ2t3heuro1è2dre2gnent_2glent_4thres__bi1a2t1é2drie_bi1a2c_i2g3nin3s2at_’i2g3ni2ckent__i2g3né’ab3réa’i2g3né_ab3réa_per1e2",
+		8 : "_ma2l1ap_dy2s1u2_dy2s1o2_dy2s1i2n3s2ats__dy2s1a2distil3l1é2lectrinstil3l1s2trophe2n1i2vro2b3long1s2tomos_ae3s4ch’ae3s4ch_eu2r1a2ombud2s3’eu2r1a2_mono1s2_mono1u2o1s2téro_mono1o2eu1s2tato1s2tradfritil3la2l1algi_mono1i2_mono1é2_ovi1s2c’ovi1s2c_mono1e2_mono1a2co1assocpaléo1é2boutil3l1s2piros_ré2i3fi_pa2n1ischevil4l1s2patiaca3ou3t2_di1a2cé_para1s2_pa2r3héco1assur_su2b1é2tu2ment_su2ment__su2b1in_su2b3lupapil3lire3pent_’inte4r3_su2b1urab3sent__su2b1a2di2s3cophu2ment_fu2ment__intera2au2ment_as2ment_or2ment_’intera2_intere2pé1r2é2q_péri1os_péri1s2ja3cent__anti1a2_péri1u2’anti1a2er2ment__anti1e2ac3cent_ar2ment_to2ment_’intere2ré3gent_papil3leom2ment_’anti1e2photo1s2_anti1é2_interé2’anti1é2_anti1s2’anti1s23ph2talé’interé2ri2ment__interi2’interi2mi2ment_apo2s3tri2s3chio_pluri1ai2s3chia_intero2’intero2_inte4r3po1astre_interu2’interu2_inters2ai2ment_’inters2papil3la_tri1o2n_su2r1a2_pon2tet_pos2t3h_dés2a3mes3cent__pos2t3r_post1s2_tri1a2tta2ment__tri1a2nra2ment_is3cent__su2r1e2_tri1a2cfa2ment_da2ment__su3r2et_su2r1é2_mé2s1es_mé2g1oh_su2r1of_su2r1ox_re3s4ty_re3s4tu_ma2l1oc’a2g3nat_dé2s1é2_ma2l1entachy1a2_pud1d2ltchin3t2_re3s4trtran2s3p_bi2s1a2tran2s3hhémo1p2té3quent__a2g3nat_dé2s1i2télé1o2bo2g3nosiradio1a2télé1o2ppu2g3nacru3lent__sta2g3nre3lent__ré2a3le_di1a2mi",
+		9 : "_ré2a3lit_dé3s2o3lthermo1s2_dé3s2ist_dé3s2i3rmit3tent_éni3tent__do3lent__ré2a3lisopu3lent__pa3tent__re2s3cap_la3tent__co2o3lie_re2s3cou_re2s3cri_ma2g3num_re2s3pir_dé3s2i3dco2g3nititran2s1a2tran2s1o2_dé3s2exu_re3s4tab_re3s4tag_dé3s2ert_re3s4tat_re3s4tén_re3s4tér_re3s4tim_re3s4tip_re3s4toc_re3s4toptran2s1u2_no2n1obs_ma2l1a2v_ma2l1int_prou3d2hpro2s3tativa3lent__ta3lent__rétro1a2_pro1s2cé_ma2l1o2dcci3dent__pa3rent__su2r1int_su2r1inf_su2r1i2mtor3rent_cur3rent__mé2s1u2stri3dent__dé3s2orm_su3r2ell_ar3dent__su3r2eaupru3dent__pré2a3lacla2ment__su3r2a3t_pos2t1o2_pos2t1inqua2ment_ter3gent_ser3gent_rai3ment_abî2ment_éci2ment_’ar3gent__ar3gent_rin3gent_tan3gent_éli2ment_ani2ment_’apo2s3ta_apo2s3tavélo1s2kivol2t1amp_dé3s2orp_dé2s1u2n_péri2s3ssesqui1a2’ana3s4trfir2ment_écu2ment_ser3pent_pré3sent_’ar3pent__ar3pent_’in1s2tab_in1s2tab’in2o3cul_in2o3culplu2ment_bou2ment_’in2exora_in2exora_su2b3linbru2ment__su3b2é3r_milli1am’in2effab_in2effab’in2augur_di1a2cid_in2augur_pa2n1opt’in2a3nit_in2a3nit1informat_ana3s4trvanil3lis_di1a2tom_su3b2altvanil3linstéréo1s2_pa2n1a2fo1s2tratuépi2s3cop_ci2s1alp1s2tructu1é2lément1é2driquepapil3lomllu2ment_",
+		10 : "1s2tandardimmi3nent__émi3nent_imma3nent_réma3nent_épi3s4cope_in2i3miti’in2i3miti_res3sent_moye2n1â2gréti3cent__dé3s2a3crmon2t3réalinno3cent__mono1ï2dé_pa2n1a2méimpu3dent__pa2n1a2ra_amino1a2c’amino1a2c_pa2n1o2phinci3dent__ser3ment_appa3rent_déca3dent__dacryo1a2_dé3s2astr_re4s5trin_dé3s2é3gr_péri2s3ta_sar3ment__dé3s2oufr_re3s4tandchro2ment__com3ment__re2s3quil_re2s3pons_gem2ment__re2s3pect_re2s3ciso_dé3s2i3gn_dé3s2i3ligram2ment__dé3s2invo_re2s3cisitran3s2act’anti2enneindo3lent__sou3vent_indi3gent_dili3gent_flam2ment_impo3tent_inso3lent_esti2ment_’on3guent__on3guent_inti2ment__dé3s2o3défécu3lent_veni2ment_reli2ment_vidi2ment_chlo2r3é2tpu2g3nablechlo2r3a2cryth2ment_o2g3nomonicarê2ment__méta1s2ta_ma2l1aisé_macro1s2célo3quent_tran3s2ats_anti2enne",
+		11 : "_contre1s2cperti3nent_conti3nent__ma2l1a2dro_in2é3lucta_psycho1a2n_dé3s2o3pil’in2é3luctaperma3nent__in2é3narratesta3ment__su2b3liminrésur3gent_’in2é3narraimmis4cent__pro2g3nathchien3dent_sporu4lent_dissi3dent_corpu3lent_archi1é2pissubli2ment_indul3gent_confi3dent__syn2g3nathtrucu3lent_détri3ment_nutri3ment_succu3lent_turbu3lent__pa2r1a2che_pa2r1a2chèfichu3ment_entre3gent_conni3vent_mécon3tent_compé3tent__re4s5trict_dé3s2i3nen_re2s3plend1a2nesthésislalo2ment__dé3s2ensib_re4s5trein_phalan3s2tabsti3nent_",
+		12 : "polyva3lent_équiva4lent_monova3lent_amalga2ment_omnipo3tent__ma2l1a2dreséquipo3tent__dé3s2a3tellproémi3nent_contin3gent_munifi3cent__ma2g3nicideo1s2trictionsurémi3nent_préémi3nent__bai2se3main",
+		13 : "acquies4cent_intelli3gent_tempéra3ment_transpa3rent__ma2g3nificatantifer3ment_",
+		14 : "privatdo3cent_diaphrag2ment_privatdo3zent_ventripo3tent__contre3maître",
 		15 : "grandilo3quent_",
-		16 : "_cont1re3maît1re",
-		17 : "_chè2vre3feuil1le"
+		16 : "_chè2vre3feuille"
 	}
 };
--- a/resources/viewer/hyphenate/patterns/grc.js
+++ b/resources/viewer/hyphenate/patterns/grc.js
--- a/Show More
+++ b/Show More