Sync to trunk.

Changelog.yaml

@@ -19,6 +19,169 @@
 #  new recipes:
 #    - title: 
 
+- version: 0.8.19
+  date: 2011-09-16
+
+  new features:
+    - title: "Driver for Sony Ericsson Xperia Arc"
+
+    - title: "MOBI Output: Add option in Preferences->Output Options->MOBI Output to enable the share via Facebook feature for calibre produced MOBI files. Note that enabling this disables the sync last read position across multiple devices feature. Don't ask me why, ask Amazon."
+
+    - title: "Content server: Update metadata when sending MOBI as well as EPUB files"
+
+    - title: "News download: Add an auto_cleanup_keep variable that allows recipe writers to tell the auto cleanup to never remove a specified element"
+
+    - title: "Conversion: Remove paragraph spacing: If you set the indent size negative, calibre will now leave the indents specified in the input document"
+  
+  bug fixes:
+    - title: "Fix regression in 0.8.18 that broke PDF Output"
+
+    - title: "MOBI Output: Revert change in 0.8.18 that marked news downloads with a single section as blogs, as the Kindle does not auto archive them"
+
+    - title: "PDF output on OSX now generates proper non image based documents"
+
+    - title: "RTF Input: Fix handling of internal links and underlined text"
+      tickets: [845328]
+
+    - title: "Fix language sometimes not getting set when downloading metadata in the edit metadata dialog"
+
+    - title: "Fix regression that broke killing of multiple jobs"
+      tickets: [850764]
+
+    - title: "Fix bug processing author names with initials when downloading metadata from ozon.ru."
+      tickets: [845420]
+
+    - title: "Fix a memory leak in the Copy to library operation which also fixes the metadata.db being held open in the destination library"
+      tickets: [849469]
+
+    - title: "Keyboard shortcuts: Allow use of symbol keys like >,*,etc."
+      tickets: [847378]
+
+    - title: "EPUB Output: When splitting be a little cleverer about discarding 'empty' pages"
+
+
+  improved recipes:
+    - Twitch Films
+    - Japan Times
+    - People/US Magazine mashup
+    - Business World India
+    - Inquirer.net
+    - Guardian/Observer
+
+  new recipes:
+    - title: RT
+      author: Darko Miletic
+
+    - title: CIO Magazine
+      author: Julio Map
+
+    - title: India Today and Hindustan Times
+      author: Krittika Goyal
+
+    - title: Pagina 12 Print Edition
+      author: Pablo Marfil
+
+- version: 0.8.18
+  date: 2011-09-09
+
+  new features:
+    - title: "Kindle news download: On Kindle 3 and newer have the View Articles and Sections menu remember the current article."
+      tickets: [748741]
+
+    - title: "Conversion: Add option to unsmarten puctuation under Look & Feel"
+
+    - title: "Driver of Motorola Ex124G and Pandigital Nova Tablet"
+
+    - title: "Allow downloading metadata from amazon.co.jp. To use it, configure the amazon metadata source to use the Japanese amazon site."
+      tickets: [842447]
+
+    - title: "When automatically generating author sort for author name, ignore common prefixes like Mr. Dr. etc. Controllable via tweak. Also add a tweak to allow control of how a string is split up into multiple authors."
+      tickets: [795984]
+
+    - title: "TXT Output: Preserve as much formatting as possible when generating Markdown output including various CSS styles"
+  
+  bug fixes:
+
+    - title: "Fix pubdate incorrect when used in save to disk template in timezones ahead of GMT."
+      tickets: [844445]
+
+    - title: "When attempting to stop multiple device jobs at once, only show a single error message"
+      tickets: [841588]
+
+    - title: "Fix conversion of large EPUB files to PDF erroring out on systems with a limited number of available file handles"
+      tickets: [816616]
+
+    - title: "EPUB catalog generation: Fix some entries going off the left edge of the page for unread/wishlist items"
+
+    - title: "When setting language in an EPUB file always use the 2 letter language code in preference to the three letter code, when possible."
+      tickets: [841201] 
+
+    - title: "Content server: Fix --url-prefix not used for links in the book details view."
+
+    - title: "MOBI Input: When links in a MOBI file point to just before block elements, and there is a page break on the block element, the links can end up pointing to the wrong place on conversion. Adjust the location in such cases to point to the block element directly."
+
+  improved recipes:
+    - Kopalnia Wiedzy
+    - FilmWeb.pl
+    - Philadelphia Inquirer
+    - Honolulu Star Advertiser
+    - Counterpunch
+    - Philadelphia Inquirer
+
+  new recipes:
+    - title: Various Polish news sources
+      author: fenuks
+
+- version: 0.8.17
+  date: 2011-09-02
+
+  new features:
+    - title: "Basic support for Amazon AZW4 format (PDF wrapped inside a MOBI)"
+
+    - title: "When showing the cover browser in a separate window, allow the use of the V, D shortcut keys to view the current book and send it to device respectively."
+      tickets: [836402]
+
+    - title: "Add an option in Preferences->Miscellaneous to abort conversion jobs that take too long."
+      tickets: [835233]
+
+    - title: "Driver for HTC Evo and HP TouchPad (with kindle app)"
+
+    - title: "Preferences->Adding books, detect when the user specifies a test expression with no file extension and popup a warning"
+  
+  bug fixes:
+    - title: "E-book viewer: Ensure toolbars are always visible"
+
+    - title: "Content server: Fix grouping of Tags/authors not working for some non english languages with Internet Explorer"
+      tickets: [835238]
+
+    - title: "When downloading metadata from amazon, fix italics inside brackets getting lost."
+      tickets: [836857]
+
+    - title: "Get Books: Add EscapeMagazine.pl and RW2010.pl stores"
+
+    - title: "Conversion pipeline: Fix conversion of cm/mm to pts. Fixes use of cm as a length unit when converting to MOBI."
+
+    - title: "When showing the cover browser in a separate window, focus the cover browser so that keyboard shortcuts work immediately."
+      tickets: [835933]
+
+    - title: "HTMLZ Output: Fix special chars like ampersands, etc. not being converted to entities"
+
+    - title: "Keyboard shortcuts config: Fix clicking done in the shortcut editor with shortcuts set to default caused the displayed shortcut to be always set to None"
+
+    - title: "Fix bottom most entries in keyboard shortcuts not editable"
+
+  improved recipes:
+    - Hacker News
+    - Nikkei News
+
+  new recipes:
+    - title: "Haber 7 and Hira"
+      authors: thomass
+
+    - title: "NTV and NTVSpor by A Erdogan"
+      author: A Erdogan
+
+
 - version: 0.8.16
   date: 2011-08-26
 

recipes/adventure_zone_pl.recipe

@@ -0,0 +1,38 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Adventure_zone(BasicNewsRecipe):
+    title          = u'Adventure Zone'
+    __author__        = 'fenuks'
+    description   = 'Adventure zone - adventure games from A to Z'
+    category       = 'games'
+    language       = 'pl'
+    oldest_article = 15
+    max_articles_per_feed = 100
+    no_stylesheets = True
+    remove_tags_before= dict(name='td', attrs={'class':'main-bg'})
+    remove_tags_after= dict(name='td', attrs={'class':'main-body middle-border'})
+    extra_css              = '.main-bg{text-align: left;}  td.capmain{ font-size: 22px; }'
+    feeds          = [(u'Nowinki', u'http://www.adventure-zone.info/fusion/feeds/news.php')]
+
+    def get_cover_url(self):
+        soup = self.index_to_soup('http://www.adventure-zone.info/fusion/news.php')
+        cover=soup.find(id='box_OstatninumerAZ')
+        self.cover_url='http://www.adventure-zone.info/fusion/'+ cover.center.a.img['src']
+        return getattr(self, 'cover_url', self.cover_url)
+
+
+    def skip_ad_pages(self, soup):
+        skip_tag = soup.body.findAll(name='a')
+        if skip_tag is not None:
+            for r in skip_tag:
+                 if 'articles.php?' in r['href']:
+                     if r.strong is not None:
+                         word=r.strong.string
+                         if ('zapowied' or 'recenzj') in word:
+                             return self.index_to_soup('http://www.adventure-zone.info/fusion/print.php?type=A&item_id'+r['href'][r['href'].find('_id')+3:], raw=True)
+        else:
+            None
+
+    def print_version(self, url):
+        return url.replace('news.php?readmore', 'print.php?type=N&item_id')
+

recipes/astro_news_pl.recipe

@@ -0,0 +1,18 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class AstroNEWS(BasicNewsRecipe):
+    title          = u'AstroNEWS'
+    __author__        = 'fenuks'
+    description   = 'AstroNEWS- astronomy every day'
+    category       = 'astronomy, science'
+    language       = 'pl'
+    oldest_article = 8
+    max_articles_per_feed = 100
+    auto_cleanup = True
+    cover_url='http://news.astronet.pl/img/logo_news.jpg'
+   # no_stylesheets= True
+    feeds          = [(u'Wiadomości', u'http://news.astronet.pl/rss.cgi')]
+
+    def print_version(self, url):
+        return url.replace('astronet.pl/', 'astronet.pl/print.cgi?')
+

recipes/astronomia_pl.recipe

@@ -0,0 +1,15 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Astronomia_pl(BasicNewsRecipe):
+    title          = u'Astronomia.pl'
+    __author__        = 'fenuks'
+    description   = 'Astronomia - polish astronomy site'
+    cover_url      = 'http://www.astronomia.pl/grafika/logo.gif'
+    category       = 'astronomy, science'
+    language       = 'pl'
+    oldest_article = 8
+    max_articles_per_feed = 100
+    #no_stylesheets=True
+    remove_tags_before=dict(name='div', attrs={'id':'a1'})
+    keep_only_tags=[dict(name='div', attrs={'id':['a1', 'h2']})]
+    feeds          = [(u'Wiadomości z astronomii i astronautyki', u'http://www.astronomia.pl/rss/')]

recipes/bash_org_pl.recipe

@@ -1,15 +1,52 @@
 from calibre.web.feeds.news import BasicNewsRecipe
 
-
 class Bash_org_pl(BasicNewsRecipe):
     title          = u'Bash.org.pl'
     __author__        = 'fenuks'
     description   = 'Bash.org.pl - funny quotations from IRC discussions'
     category       = 'funny quotations, humour'
     language       = 'pl'
-    oldest_article = 15
     cover_url = u'http://userlogos.org/files/logos/dzikiosiol/none_0.png'
-    max_articles_per_feed = 100
+    max_articles_per_feed = 50
     no_stylesheets= True
-    keep_only_tags= [dict(name='div', attrs={'class':'quote post-content post-body'})]
+    keep_only_tags= [dict(name='a', attrs={'class':'qid click'}), 
-    feeds          = [(u'Cytaty', u'http://bash.org.pl/rss')]
+	          dict(name='div', attrs={'class':'quote post-content post-body'})]
+
+
+    def latest_articles(self):
+        articles = []
+        soup=self.index_to_soup(u'http://bash.org.pl/latest/')
+        #date=soup.find('div', attrs={'class':'right'}).string
+        tags=soup.findAll('a', attrs={'class':'qid click'})
+        for a in tags:
+             title=a.string
+             url='http://bash.org.pl' +a['href']
+             articles.append({'title' : title,
+	               'url'   : url,
+	               'date'  : '',
+	               'description' : ''
+	                })
+        return articles
+
+
+    def random_articles(self):
+         articles = []
+         for i in range(self.max_articles_per_feed):
+             soup=self.index_to_soup(u'http://bash.org.pl/random/')
+             #date=soup.find('div', attrs={'class':'right'}).string
+             url=soup.find('a', attrs={'class':'qid click'})
+             title=url.string
+             url='http://bash.org.pl' +url['href']
+             articles.append({'title' : title,
+	               'url'   : url,
+	               'date'  : '',
+	               'description' : ''
+	                })
+         return articles
+
+
+    def parse_index(self):
+         feeds          = []
+         feeds.append((u"Najnowsze", self.latest_articles()))
+         feeds.append((u"Losowe", self.random_articles()))
+         return feeds

recipes/benchmark_pl.recipe

@@ -0,0 +1,70 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+import re
+class Benchmark_pl(BasicNewsRecipe):
+    title          = u'Benchmark.pl'
+    __author__        = 'fenuks'
+    description   = u'benchmark.pl -IT site'
+    cover_url      = 'http://www.ieaddons.pl/benchmark/logo_benchmark_new.gif'
+    category       = 'IT'
+    language       = 'pl'
+    oldest_article = 8
+    max_articles_per_feed = 100
+    no_stylesheets=True
+    preprocess_regexps = [(re.compile(ur'\bWięcej o .*</body>', re.DOTALL|re.IGNORECASE), lambda match: '</body>')]
+    keep_only_tags=[dict(name='div', attrs={'class':['m_zwykly', 'gallery']})]
+    remove_tags_after=dict(name='div', attrs={'class':'body'})
+    remove_tags=[dict(name='div', attrs={'class':['kategoria', 'socialize', 'thumb', 'panelOcenaObserwowane', 'categoryNextToSocializeGallery']})]
+    INDEX= 'http://www.benchmark.pl'
+    feeds          = [(u'Aktualności', u'http://www.benchmark.pl/rss/aktualnosci-pliki.xml'), 
+                          (u'Testy i recenzje', u'http://www.benchmark.pl/rss/testy-recenzje-minirecenzje.xml')]
+
+
+    def append_page(self, soup, appendtag):
+        nexturl = soup.find('span', attrs={'class':'next'})
+        while nexturl is not None:
+            nexturl= self.INDEX + nexturl.parent['href']
+            soup2 = self.index_to_soup(nexturl)
+            nexturl=soup2.find('span', attrs={'class':'next'})
+            pagetext = soup2.find(name='div', attrs={'class':'body'})
+            appendtag.find('div', attrs={'class':'k_ster'}).extract()
+            pos = len(appendtag.contents)
+            appendtag.insert(pos, pagetext)
+        if appendtag.find('div', attrs={'class':'k_ster'}) is not None:
+            appendtag.find('div', attrs={'class':'k_ster'}).extract()
+
+
+    def image_article(self, soup, appendtag):
+        nexturl=soup.find('div', attrs={'class':'preview'})
+        if nexturl is not None:
+            nexturl=nexturl.find('a', attrs={'class':'move_next'})
+            image=appendtag.find('div', attrs={'class':'preview'}).div['style'][16:]
+            image=self.INDEX + image[:image.find("')")]
+            appendtag.find(attrs={'class':'preview'}).name='img'
+            appendtag.find(attrs={'class':'preview'})['src']=image
+            appendtag.find('a', attrs={'class':'move_next'}).extract()
+        while nexturl is not None:
+            nexturl= self.INDEX + nexturl['href']
+            soup2 = self.index_to_soup(nexturl)
+            nexturl=soup2.find('a', attrs={'class':'move_next'})
+            image=soup2.find('div', attrs={'class':'preview'}).div['style'][16:]
+            image=self.INDEX + image[:image.find("')")]
+            soup2.find(attrs={'class':'preview'}).name='img'
+            soup2.find(attrs={'class':'preview'})['src']=image
+            pagetext=soup2.find('div', attrs={'class':'gallery'})
+            pagetext.find('div', attrs={'class':'title'}).extract()
+            pagetext.find('div', attrs={'class':'thumb'}).extract()
+            pagetext.find('div', attrs={'class':'panelOcenaObserwowane'}).extract()       
+            if nexturl is not None:
+                pagetext.find('a', attrs={'class':'move_next'}).extract()
+            pagetext.find('a', attrs={'class':'move_back'}).extract()
+            pos = len(appendtag.contents)
+            appendtag.insert(pos, pagetext)
+            
+
+
+    def preprocess_html(self, soup):
+        if soup.find('div', attrs={'class':'preview'}) is not None:
+            self.image_article(soup, soup.body)
+        else:
+            self.append_page(soup, soup.body)
+        return soup

recipes/berliner_zeitung.recipe

@@ -0,0 +1,61 @@
+from calibre.web.feeds.recipes import BasicNewsRecipe
+import re
+
+class SportsIllustratedRecipe(BasicNewsRecipe) :
+    __author__    = 'ape'
+    __copyright__ = 'ape'
+    __license__   = 'GPL v3'
+    language      = 'de'
+    description   = 'Berliner Zeitung'
+    version       = 2
+    title         = u'Berliner Zeitung'
+    timefmt       = ' [%d.%m.%Y]'
+
+    no_stylesheets = True
+    remove_javascript = True
+    use_embedded_content = False
+    publication_type = 'newspaper'
+
+    keep_only_tags = [dict(name='div', attrs={'class':'teaser t_split t_artikel'})]
+
+    INDEX = 'http://www.berlinonline.de/berliner-zeitung/'
+
+    def parse_index(self):
+        base = 'http://www.berlinonline.de'
+        answer = []
+        articles = {}
+        more = 1
+
+        soup = self.index_to_soup(self.INDEX)
+
+        # Get list of links to ressorts from index page
+        ressort_list = soup.findAll('ul', attrs={'class': re.compile('ressortlist')})
+        for ressort in ressort_list[0].findAll('a'):
+            feed_title = ressort.string
+            print 'Analyzing', feed_title
+            if not articles.has_key(feed_title):
+                articles[feed_title] = []
+                answer.append(feed_title)
+            # Load ressort page.
+            feed = self.index_to_soup('http://www.berlinonline.de' + ressort['href'])
+            # find mainbar div which contains the list of all articles
+            for article_container in feed.findAll('div', attrs={'class': re.compile('mainbar')}):
+                # iterate over all articles
+                for article_teaser in article_container.findAll('div', attrs={'class': re.compile('teaser')}):
+                    # extract title of article
+                    if article_teaser.h3 != None:
+                        article = {'title' : article_teaser.h3.a.string, 'date' : u'', 'url'  : base + article_teaser.h3.a['href'], 'description' : u''}
+                        articles[feed_title].append(article)
+                    else:
+                        # Skip teasers for missing photos
+                        if article_teaser.div.p.contents[0].find('Foto:') > -1:
+                            continue
+                        article = {'title': 'Weitere Artikel ' + str(more), 'date': u'', 'url': base + article_teaser.div.p.a['href'], 'description': u''}
+                        articles[feed_title].append(article)
+                        more += 1
+        answer = [[key, articles[key]] for key in answer if articles.has_key(key)]
+        return answer
+
+    def get_masthead_url(self):
+        return 'http://www.berlinonline.de/.img/berliner-zeitung/blz_logo.gif'
+

recipes/business_week.recipe

@@ -1,93 +1,105 @@
-#!/usr/bin/env  python
 __license__   = 'GPL v3'
-__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
+__copyright__ = '2008 Kovid Goyal kovid@kovidgoyal.net, 2010 Darko Miletic <darko.miletic at gmail.com>'
-__docformat__ = 'restructuredtext en'
-
 '''
-businessweek.com
+www.businessweek.com
 '''
 
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class BusinessWeek(BasicNewsRecipe):
-    title          = 'Business Week'
+    title                 = 'Business Week'
-    description    = 'Business News, Stock Market and Financial Advice'
+    __author__            = 'Kovid Goyal and Darko Miletic'
-    __author__     = 'ChuckEggDotCom and Sujata Raman'
+    description           = 'Read the latest international business news & stock market news. Get updated company profiles, financial advice, global economy and technology news.'
-    language = 'en'
+    publisher             = 'Bloomberg L.P.'
+    category              = 'Business, business news, stock market, stock market news, financial advice, company profiles, financial advice, global economy, technology news'
+    oldest_article        = 7
+    max_articles_per_feed = 200
+    no_stylesheets        = True
+    encoding              = 'utf8'
+    use_embedded_content  = False
+    language              = 'en'
+    remove_empty_feeds    = True
+    publication_type      = 'magazine'
+    cover_url             = 'http://images.businessweek.com/mz/covers/current_120x160.jpg'
+    masthead_url          = 'http://assets.businessweek.com/images/bw-logo.png'
+    extra_css             = """
+                               body{font-family: Helvetica,Arial,sans-serif }
+                               img{margin-bottom: 0.4em; display:block}
+                               .tagline{color: gray; font-style: italic}
+                               .photoCredit{font-size: small; color: gray}
+                            """
 
-    oldest_article = 7
+    conversion_options = {
-    max_articles_per_feed = 10
+                          'comment'   : description
-    no_stylesheets = True
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
+                        }
 
-    recursions = 1
+    remove_tags       = [
-    match_regexps = [r'http://www.businessweek.com/.*_page_[1-9].*']
+                           dict(attrs={'class':'inStory'})
-    extra_css = '''
+                          ,dict(name=['meta','link','iframe','base','embed','object','table','th','tr','td'])
-                h1{font-family :Arial,Helvetica,sans-serif; font-size:large;}
+                          ,dict(attrs={'id':['inset','videoDisplay']})
-                .news_story_title{font-family :Arial,Helvetica,sans-serif; font-size:large;font-weight:bold;}
+                        ]
-                h2{font-family :Arial,Helvetica,sans-serif; font-size:medium;color:#666666;}
+    keep_only_tags    = [dict(name='div', attrs={'id':['story-body','storyBody','article_body','articleBody']})]
-                h3{text-transform:uppercase;font-family :Arial,Helvetica,sans-serif; font-size:large;font-weight:bold;}
+    remove_attributes = ['lang']
-                h4{font-family :Arial,Helvetica,sans-serif; font-size:small;font-weight:bold;}
+    match_regexps     = [r'http://www.businessweek.com/.*_page_[1-9].*']
-                p{font-family :Arial,Helvetica,sans-serif; }
-                #lede600{font-size:x-small;}
-                #storybody{font-size:x-small;}
-                p{font-family :Arial,Helvetica,sans-serif;}
-                .strap{font-family :Arial,Helvetica,sans-serif; font-size:x-small; color:#064599;}
-                .byline{font-family :Arial,Helvetica,sans-serif; font-size:x-small;}
-                .postedBy{font-family :Arial,Helvetica,sans-serif; font-size:x-small;color:#666666;}
-                .trackback{font-family :Arial,Helvetica,sans-serif; font-size:x-small;color:#666666;}
-                .date{font-family :Arial,Helvetica,sans-serif; font-size:x-small;color:#666666;}
-                .wrapper{font-family :Arial,Helvetica,sans-serif; font-size:x-small;}
-                .photoCredit{font-family :Arial,Helvetica,sans-serif; font-size:x-small;color:#666666;}
-                .tagline{font-family :Arial,Helvetica,sans-serif; font-size:x-small;color:#666666;}
-                .pageCount{color:#666666;font-family :Arial,Helvetica,sans-serif; font-size:x-small;}
-                .note{font-family :Arial,Helvetica,sans-serif; font-size:small;color:#666666;font-style:italic;}
-                .highlight{font-family :Arial,Helvetica,sans-serif; font-size:small;background-color:#FFF200;}
-                .annotation{font-family :Arial,Helvetica,sans-serif; font-size:x-small;color:#666666;}                
-                '''
-   
-    remove_tags = [  dict(name='div', attrs={'id':["log","feedback","footer","secondarynav","secondnavbar","header","email","bw2-header","column2","wrapper-bw2-footer","wrapper-mgh-footer","inset","commentForm","commentDisplay","bwExtras","bw2-umbrella","readerComments","leg","rightcol"]}),
-                    dict(name='div', attrs={'class':["menu",'sponsorbox smallertext',"TopNavTile","graybottom leaderboard"]}),
-                    dict(name='img', alt ="News"),
-                     dict(name='td', width ="1"),
-                    ]
 
-    feeds          = [
+
-                      (u'Top Stories', u'http://www.businessweek.com/topStories/rss/topStories.rss'),
+    feeds = [
-                      (u'Top News', u'http://www.businessweek.com/rss/bwdaily.rss'),
+              (u'Top Stories', u'http://www.businessweek.com/topStories/rss/topStories.rss'),
-                      (u'Asia', u'http://www.businessweek.com/rss/asia.rss'),
+              (u'Top News'   , u'http://www.businessweek.com/rss/bwdaily.rss'              ),
-                      (u'Autos', u'http://www.businessweek.com/rss/autos/index.rss'),
+              (u'Asia', u'http://www.businessweek.com/rss/asia.rss'),
-                      (u'Classic Cars', u'http://rss.businessweek.com/bw_rss/classiccars'),
+              (u'Autos', u'http://www.businessweek.com/rss/autos/index.rss'),
-                      (u'Hybrids', u'http://rss.businessweek.com/bw_rss/hybrids'),
+              (u'Classic Cars', u'http://rss.businessweek.com/bw_rss/classiccars'),
-                      (u'Europe', u'http://www.businessweek.com/rss/europe.rss'),
+              (u'Hybrids', u'http://rss.businessweek.com/bw_rss/hybrids'),
-                      (u'Auto Reviews', u'http://rss.businessweek.com/bw_rss/autoreviews'),
+              (u'Europe', u'http://www.businessweek.com/rss/europe.rss'),
-                      (u'Innovation & Design', u'http://www.businessweek.com/rss/innovate.rss'),
+              (u'Auto Reviews', u'http://rss.businessweek.com/bw_rss/autoreviews'),
-                      (u'Architecture', u'http://www.businessweek.com/rss/architecture.rss'),
+              (u'Innovation & Design', u'http://www.businessweek.com/rss/innovate.rss'),
-                      (u'Brand Equity', u'http://www.businessweek.com/rss/brandequity.rss'),
+              (u'Architecture', u'http://www.businessweek.com/rss/architecture.rss'),
-                      (u'Auto Design', u'http://www.businessweek.com/rss/carbuff.rss'),
+              (u'Brand Equity', u'http://www.businessweek.com/rss/brandequity.rss'),
-                      (u'Game Room', u'http://rss.businessweek.com/bw_rss/gameroom'),
+              (u'Auto Design', u'http://www.businessweek.com/rss/carbuff.rss'),
-                      (u'Technology', u'http://www.businessweek.com/rss/technology.rss'),
+              (u'Game Room', u'http://rss.businessweek.com/bw_rss/gameroom'),
-                      (u'Investing', u'http://rss.businessweek.com/bw_rss/investor'),
+              (u'Technology', u'http://www.businessweek.com/rss/technology.rss'),
-                      (u'Small Business', u'http://www.businessweek.com/rss/smallbiz.rss'),
+              (u'Investing', u'http://rss.businessweek.com/bw_rss/investor'),
-                      (u'Careers', u'http://rss.businessweek.com/bw_rss/careers'),
+              (u'Small Business', u'http://www.businessweek.com/rss/smallbiz.rss'),
-                      (u'B-Schools', u'http://www.businessweek.com/rss/bschools.rss'),
+              (u'Careers', u'http://rss.businessweek.com/bw_rss/careers'),
-                      (u'Magazine Selections', u'http://www.businessweek.com/rss/magazine.rss'),
+              (u'B-Schools', u'http://www.businessweek.com/rss/bschools.rss'),
-                      (u'CEO Guide to Tech', u'http://www.businessweek.com/rss/ceo_guide_tech.rss'),
+              (u'Magazine Selections', u'http://www.businessweek.com/rss/magazine.rss'),
-                      ]
+              (u'CEO Guide to Tech', u'http://www.businessweek.com/rss/ceo_guide_tech.rss'),
+            ]
 
     def get_article_url(self, article):
-
         url = article.get('guid', None)
+        if 'podcasts' in url:
+            return None
+        if 'surveys' in url:
+            return None
+        if 'images' in url:
+            return None
+        if 'feedroom' in url:
+            return None
+        if '/magazine/toc/' in url:
+            return None
+        rurl, sep, rest = url.rpartition('?')
+        if rurl:
+           return rurl
+        return rest
 
-        if 'podcasts' in url or 'surveys' in url:
+    def print_version(self, url):
-            url = None
+        if '/news/' in url or '/blog/' in url:
-
+           return url
-        return url
+        if '/magazine' in url:
-
+          rurl = url.replace('http://www.businessweek.com/','http://www.businessweek.com/printer/')
-    def postprocess_html(self, soup, first):
+        else:
-
+          rurl = url.replace('http://www.businessweek.com/','http://www.businessweek.com/print/')
-            for tag in soup.findAll(name=['ul','li','table','td','tr','span']):
+        return rurl.replace('/investing/','/investor/')
-                tag.name = 'div'
-            for tag in soup.findAll(name= 'div',attrs={ 'id':'pageNav'}):                
-                tag.extract()
-            return soup
 
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        for alink in soup.findAll('a'):
+            if alink.string is not None:
+               tstr = alink.string
+               alink.replaceWith(tstr)
+        return soup

recipes/businessworldin.recipe

@@ -4,95 +4,73 @@ __copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
 www.businessworld.in
 '''
 
-from calibre import strftime
+import re
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class BusinessWorldMagazine(BasicNewsRecipe):
     title                = 'Business World Magazine'
-    __author__           = 'Darko Miletic'
+    __author__           = 'Kovid Goyal'
     description          = 'News from India'
     publisher            = 'ABP Pvt Ltd Publication'
     category             = 'news, politics, finances, India, Asia'
     delay                = 1
     no_stylesheets       = True
-    INDEX                = 'http://www.businessworld.in/bw/Magazine_Current_Issue'
+    INDEX                = 'http://www.businessworld.in/businessworld/magazine_latest_issue.php'
     ROOT                 = 'http://www.businessworld.in'
-    use_embedded_content = False
     encoding             = 'utf-8'
     language             = 'en_IN'
-    extra_css            = """
+    auto_cleanup = True
-                              img{display: block; margin-bottom: 0.5em}
-                              body{font-family: Arial,Helvetica,sans-serif}
-                              h2{color: gray; display: block}
-                           """
 
-    conversion_options = {
-                          'comment'          : description
-                        , 'tags'             : category
-                        , 'publisher'        : publisher
-                        , 'language'         : language
-                        }
-
-    def is_in_list(self,linklist,url):
-        for litem in linklist:
-            if litem == url:
-               return True
-        return False
-    
-    
     def parse_index(self):
+        br = self.browser
+        br.open(self.ROOT)
+        raw = br.open(br.click_link(text_regex=re.compile('Current.*Issue',
+            re.I))).read()
+        soup = self.index_to_soup(raw)
+        mc = soup.find(attrs={'class':'mag_cover'})
+        if mc is not None:
+            img = mc.find('img', src=True)
+            if img is not None:
+                self.cover_url = img['src']
+
+        feeds = []
+        current_section = None
         articles = []
-        linklist = []
+        for tag in soup.findAll(['h3', 'h2']):
-        soup = self.index_to_soup(self.INDEX)
+            inner_a = tag.find('a')
-        
+            if tag.name == 'h3' and inner_a is not None:
-        tough = soup.find('div', attrs={'id':'tough'})
+                continue
-        if tough:
+            if tag.name == 'h2' and (inner_a is None or current_section is
-           for item in tough.findAll('h1'):
+                    None):
-                description = ''
+                continue
-                title_prefix = ''
+
-                feed_link = item.find('a')
+            if tag.name == 'h3':
-                if feed_link and feed_link.has_key('href'):
+                if current_section is not None and articles:
-                    url   = self.ROOT + feed_link['href']
+                    feeds.append((current_section, articles))
-                    if not self.is_in_list(linklist,url):
+                current_section = self.tag_to_string(tag)
-                        title = title_prefix + self.tag_to_string(feed_link)
+                self.log('Found section:', current_section)
-                        date  = strftime(self.timefmt)
+                articles = []
-                        articles.append({
+            elif tag.name == 'h2':
-                                          'title'      :title
+                url = inner_a.get('href', None)
-                                         ,'date'       :date
+                if url is None: continue
-                                         ,'url'        :url
+                if url.startswith('/'): url = self.ROOT + url
-                                         ,'description':description
+                title = self.tag_to_string(inner_a)
-                                        })
+                h1 = tag.findPreviousSibling('h1')
-                        linklist.append(url)
+                if h1 is not None:
-        
+                    title = self.tag_to_string(h1) + title
-        for item in soup.findAll('div', attrs={'class':'nametitle'}):
+                self.log('\tFound article:', title)
-            description = ''
+                articles.append({'title':title, 'url':url, 'date':'',
-            title_prefix = ''
+                    'description':''})
-            feed_link = item.find('a')
+
-            if feed_link and feed_link.has_key('href'):
+        if current_section and articles:
-                url   = self.ROOT + feed_link['href']
+            feeds.append((current_section, articles))
-                if not self.is_in_list(linklist,url):
+
-                    title = title_prefix + self.tag_to_string(feed_link)
+        return feeds
-                    date  = strftime(self.timefmt)
+
-                    articles.append({
+
-                                      'title'      :title
+
-                                     ,'date'       :date
+
-                                     ,'url'        :url
+
-                                     ,'description':description
-                                    })
-                    linklist.append(url)
-        return [(soup.head.title.string, articles)]
 
-    
-    keep_only_tags = [dict(name='div', attrs={'id':'printwrapper'})]
-    remove_tags = [dict(name=['object','link','meta','base','iframe','link','table'])]
 
-    def print_version(self, url):
-        return url.replace('/bw/','/bw/storyContent/')
 
-    def get_cover_url(self):
-        cover_url = None
-        soup = self.index_to_soup(self.INDEX)
-        cover_item = soup.find('img',attrs={'class':'toughbor'})
-        if cover_item:
-           cover_url = self.ROOT + cover_item['src']
-        return cover_url

recipes/cgm_pl.recipe

@@ -0,0 +1,40 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class CGM(BasicNewsRecipe):
+    title          = u'CGM'
+    oldest_article = 7
+    __author__        = 'fenuks'
+    description   = u'Codzienna Gazeta Muzyczna'
+    cover_url      = 'http://www.krafcy.com/foto/tinymce/Image/cgm%281%29.jpg'
+    category       = 'music'
+    language       = 'pl'
+    use_embedded_content   = False
+    max_articles_per_feed = 100
+    no_stylesheers=True
+    extra_css      = 'div {color:black;} strong {color:black;} span {color:black;} p {color:black;}'
+    remove_tags_before=dict(id='mainContent')
+    remove_tags_after=dict(name='div', attrs={'class':'fbContainer'})
+    remove_tags=[dict(name='div', attrs={'class':'fbContainer'}),
+ 	      dict(name='p', attrs={'class':['tagCloud', 'galleryAuthor']}), 
+	      dict(id=['movieShare', 'container'])]
+    feeds          = [(u'Informacje', u'http://www.cgm.pl/rss.xml'), (u'Polecamy', u'http://www.cgm.pl/rss,4,news.xml'), 
+                          (u'Recenzje', u'http://www.cgm.pl/rss,1,news.xml')]
+
+
+    def preprocess_html(self, soup):
+        ad=soup.findAll('img')
+        for r in ad:
+            if '/_vault/_article_photos/5841.jpg' in r['src'] or '_vault/_article_photos/5807.jpg' in r['src'] or 'article_photos/5841.jpg' in r['src'] or 'article_photos/5825.jpg' in r['src'] or '_article_photos/5920.jpg' in r['src']  or '_article_photos/5919.jpg' in r['src'] or '_article_photos/5918.jpg' in r['src'] or '_article_photos/5914.jpg' in r['src'] or '_article_photos/5911.jpg' in r['src'] or '_article_photos/5923.jpg' in r['src'] or '_article_photos/5921.jpg' in r['src']:                
+                 ad[ad.index(r)].extract()
+        gallery=soup.find('div', attrs={'class':'galleryFlash'})
+        if gallery:
+            img=gallery.find('embed')
+            if img:
+                img=img['src'][35:]
+                img='http://www.cgm.pl/_vault/_gallery/_photo/'+img
+                param=gallery.findAll(name='param')
+                for i in param:
+                    i.extract()
+                gallery.contents[1].name='img'
+                gallery.contents[1]['src']=img
+        return soup

recipes/china_post.recipe

@@ -0,0 +1,29 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class CP(BasicNewsRecipe):
+    title          = u'China Post'
+    language       = 'en_CN'
+    __author__     = 'Krittika Goyal'
+    oldest_article = 1 #days
+    max_articles_per_feed = 25
+    use_embedded_content = False
+
+    no_stylesheets = True
+    auto_cleanup = True
+
+    feeds          = [
+('Top Stories',
+ 'http://www.chinapost.com.tw/rss/front.xml'),
+('Taiwan',
+ 'http://www.chinapost.com.tw/rss/taiwan.xml'),
+('China',
+ 'http://www.chinapost.com.tw/rss/china.xml'),
+('Business',
+ 'http://www.chinapost.com.tw/rss/business.xml'),
+('World',
+ 'http://www.chinapost.com.tw/rss/international.xml'),
+('Sports',
+ 'http://www.chinapost.com.tw/rss/sports.xml'),
+]
+
+

recipes/cicero.recipe

@@ -1,35 +1,47 @@
 from calibre.web.feeds.news import BasicNewsRecipe
 
-class Cicero(BasicNewsRecipe):
+class BasicUserRecipe1316245412(BasicNewsRecipe):
-    timefmt               = ' [%Y-%m-%d]'
+    title = u'Cicero Online'
-    title                 = u'Cicero'
+    description = u'Magazin f\xfcr politische Kultur'
-    __author__            = 'mad@sharktooth.de'
+    publisher = 'Ringier Publishing GmbH'
-    description           = u'Magazin f\xfcr politische Kultur'
+    category = 'news, politics, Germany'
+    language = 'de'
+    encoding = 'UTF-8'
+    __author__ = 'Armin Geller' # Upd. 2011-09-19
+
     oldest_article        = 7
-    language              = 'de'
     max_articles_per_feed = 100
-    no_stylesheets        = True
+    no_stylesheets = True
-    use_embedded_content  = False
+    auto_cleanup = False
-    publisher             = 'Ringier Publishing'
+
-    category              = 'news, politics, Germany'
+#    remove_javascript = True
-    encoding              = 'iso-8859-1'
+
-    publication_type      = 'magazine'
+    remove_tags = [
-    masthead_url          = 'http://www.cicero.de/img2/cicero_logo_rss.gif'
+                    dict(name='div', attrs={'id':["header", "navigation", "skip-link", "header-print", "header-print-url", "meta-toolbar", "footer"]}),
-    feeds                 = [
+                    dict(name='div', attrs={'class':["region region-sidebar-first column sidebar", "breadcrumb", "breadcrumb-title", "meta", "comment-wrapper",
-(u'Das gesamte Portfolio', u'http://www.cicero.de/rss/rss.php?ress_id='),
+                                                        "field field-name-field-show-teaser-right field-type-list-boolean field-label-above"]}),
-#(u'Alle Heft-Inhalte', u'http://www.cicero.de/rss/rss.php?ress_id=heft'),
+                    dict(name='div', attrs={'title':["Dossier Auswahl"]}),
-#(u'Alle Online-Inhalte', u'http://www.cicero.de/rss/rss.php?ress_id=online'),
+                    dict(name='h2', attrs={'class':["title comment-form"]}),
-#(u'Berliner Republik', u'http://www.cicero.de/rss/rss.php?ress_id=4'),
+                    dict(name='form', attrs={'class':["comment-form user-info-from-cookie"]}),
-#(u'Weltb\xfchne', u'http://www.cicero.de/rss/rss.php?ress_id=1'),
+                    # 2011-09-19 clean-up on first feed historical caricature- and video preview pictures and social icons
-#(u'Salon', u'http://www.cicero.de/rss/rss.php?ress_id=7'),
+                    dict(name='table', attrs={'class':["mcx-social-horizontal", "page-header"]}),   # 2011-09-19
-#(u'Kapital', u'http://www.cicero.de/rss/rss.php?ress_id=6'),
+                    dict(name='div', attrs={'class':["page-header", "view view-alle-karikaturen view-id-alle_karikaturen view-display-id-default view-dom-id-1",
-#(u'Netzst\xfccke', u'http://www.cicero.de/rss/rss.php?ress_id=9'),
+                                                      "pagination",
-#(u'Leinwand', u'http://www.cicero.de/rss/rss.php?ress_id=12'),
+                                                      "view view-letzte-videos view-id-letzte_videos view-display-id-default view-dom-id-1"]}), # 2011-09-19
-#(u'Bibliothek', u'http://www.cicero.de/rss/rss.php?ress_id=15'),
+                   ]
-(u'Kolumne - Alle Kolulmnen', u'http://www.cicero.de/rss/rss2.php?ress_id='),
+
-#(u'Kolumne - Schreiber, Berlin', u'http://www.cicero.de/rss/rss2.php?ress_id=35'),
+    feeds = [
-#(u'Kolumne - TV Kritik', u'http://www.cicero.de/rss/rss2.php?ress_id=34')
+              (u'Das gesamte Portfolio', u'http://www.cicero.de/rss.xml'),
-]
+              (u'Berliner Republik', u'http://www.cicero.de/berliner-republik.xml'),
+              (u'Weltb\xfchne', u'http://www.cicero.de/weltbuehne.xml'),
+              (u'Kapital', u'http://www.cicero.de/kapital.xml'),
+              (u'Salon', u'http://www.cicero.de/salon.xml'),
+              (u'Blogs', u'http://www.cicero.de/blogs.xml'), #seems not to be in use at the moment
+             ]
 
     def print_version(self, url):
-        return 'http://www.cicero.de/page_print.php?' + url.rpartition('?')[2]
+          return url + '?print'
+
+#    def get_cover_url(self):
+#          return 'http://www.cicero.de/sites/all/themes/cicero/logo.png' # need to find a good logo on their home page!
+

recipes/cio_magazine.recipe

@@ -0,0 +1,128 @@
+# Los primeros comentarios son las dificultades que he tenido con el Piton
+# Cuando da error UTF8 revisa los comentarios (acentos). En notepad++ Search, Goto, posicion y lo ves.
+# Editar con Notepad++ Si pone - donde no debe es que ha indentado mal... Edit - Blank operations - tab to space
+# He entendido lo que significa el from... son paths dentro de pylib.zip...
+# Con from importa solo un simbolo...con import,la libreria completa
+from calibre.web.feeds.news import BasicNewsRecipe
+# sys no hace falta... lo intente usar para escribir en stderr
+from calibre import strftime
+# Para convertir el tiempo del articulo
+import string, re
+# Para usar expresiones regulares
+# Visto en pylib.zip... la primera letra es mayuscula
+# Estas dos ultimas han sido un vago intento de establecer una cookie (no usado)
+
+class CIO_Magazine(BasicNewsRecipe):
+    title      = 'CIO Magazine'
+    oldest_article = 14
+    max_articles_per_feed = 100
+    auto_cleanup = True
+    __author__ = 'Julio Map'
+    description = 'CIO is the leading information brand for today-s busy Chief information Officer - CIO Magazine bi-monthly '
+    language              = 'en'
+    encoding              = 'utf8'
+    cover_url = 'http://www.cio.com/homepage/images/hp-cio-logo-linkedin.png'
+
+    remove_tags_before = dict(name='div', attrs={'id':'container'})
+# Absolutamente innecesario... al final he visto un print_version (ver mas adelante)
+
+# Dentro de una revista dada...
+# issue_details contiene el titulo y las secciones de este ejemplar
+# DetailModule esta dentro de issue_details contiene las urls y resumenes
+# Dentro de un articulo dado...
+# Article-default-body contiene el texto. Pero como digo, he encontrado una print_version
+
+    no_stylesheets = True
+    remove_javascript     = True
+
+    def print_version(self,url):
+    # A esta funcion le llama el sistema... no hay que llamarla uno mismo (porque seria llamada dos veces)
+    # Existe una version imprimible de los articulos cambiando
+    # http://www.cio.com/article/<num>/<titulo> por
+    # http://www.cio.com/article/print/<num> que contiene todas las paginas dentro del div id=container
+        if url.startswith('/'):
+            url = 'http://www.cio.com'+url
+        segments = url.split('/')
+        printURL = '/'.join(segments[0:4]) + '/print/' + segments[4] +'#'
+        return printURL
+
+
+    def parse_index(self):
+    ###########################################################################
+    #    This method should be implemented in recipes that parse a website
+    # instead of feeds to generate a list of articles. Typical uses are for
+    # news sources that have a Print Edition webpage that lists all the
+    # articles in the current print edition. If this function is implemented,
+    # it will be used in preference to BasicNewsRecipe.parse_feeds().
+    #
+    # It must return a list. Each element of the list must be a 2-element
+    # tuple of the form ('feed title', list of articles).
+    #
+    # Each list of articles must contain dictionaries of the form:
+    #
+    # {
+    # 'title'       : article title,
+    # 'url'         : URL of print version,
+    # 'date'        : The publication date of the article as a string,
+    # 'description' : A summary of the article
+    # 'content'     : The full article (can be an empty string). This is used by FullContentProfile
+    # }
+    #
+    # For an example, see the recipe for downloading The Atlantic.
+    # In addition, you can add 'author' for the author of the article.
+    ###############################################################################
+
+    # Primero buscamos cual es la ultima revista que se ha creado
+        soupinicial = self.index_to_soup('http://www.cio.com/magazine')
+        # Es el primer enlace que hay en el DIV con class content_body
+        a= soupinicial.find(True, attrs={'class':'content_body'}).find('a', href=True)
+        INDEX = re.sub(r'\?.*', '', a['href'])
+        # Como cio.com usa enlaces relativos, le anteponemos el domain name.
+        if INDEX.startswith('/'): # protegiendonos de que dejen de usarlos
+            INDEX = 'http://www.cio.com'+INDEX
+        # Y nos aseguramos en los logs que lo estamos haciendo bien
+        print ("INDEX en parse_index: ", INDEX)
+
+    # Ya sabemos cual es la revista... procesemosla.
+        soup = self.index_to_soup(INDEX)
+
+        articles = {}
+        key = None
+        feeds = []
+        # Para empezar nos quedamos solo con dos DIV, 'heading' y ' issue_item'
+        # Del primero sacamos las categorias (key) y del segundo las urls y resumenes
+        for div in soup.findAll(True,
+             attrs={'class':['heading', 'issue_item']}):
+
+             if div['class'] == 'heading':
+                 key = string.capwords(self.tag_to_string(div.span))
+                 print ("Key: ",key) # Esto es para depurar
+                 articles[key] = []
+                 feeds.append(key)
+
+             elif div['class'] == 'issue_item':
+                 a = div.find('a', href=True)
+                 if not a:
+                     continue
+                 url = re.sub(r'\?.*', '', a['href'])
+                 print("url: ",url) # Esto es para depurar
+                 title = self.tag_to_string(a, use_alt=True).strip() # Ya para nota, quitar al final las dos ultimas palabras
+                 pubdate = strftime('%a, %d %b') # No es la fecha de publicacion sino la de colecta
+                 summary = div.find('p') # Dentro de la div 'issue_item' el unico parrafo que hay es el resumen
+                 description = '' # Si hay summary la description sera el summary... si no, la dejamos en blanco
+
+                 if summary:
+                     description = self.tag_to_string(summary, use_alt=False)
+                     print ("Description = ", description)
+
+
+                 feed = key if key is not None else 'Uncategorized' # Esto esta copiado del NY times
+                 if not articles.has_key(feed):
+                     articles[feed] = []
+                 if not 'podcasts' in url:
+                     articles[feed].append(
+                               dict(title=title, url=url, date=pubdate,
+                                    description=description,
+                                    content=''))
+        feeds = [(key, articles[key]) for key in feeds if articles.has_key(key)]
+        return feeds

recipes/counterpunch.recipe

@@ -1,40 +1,10 @@
-import re
-from lxml.html import parse
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Counterpunch(BasicNewsRecipe):
-    '''
+    title          = u'Counterpunch'
-    Parses counterpunch.com for articles
+    oldest_article = 7
-    '''
+    max_articles_per_feed = 100
-    title = 'Counterpunch'
+    auto_cleanup = True
-    description = 'Daily political opinion from www.Counterpunch.com'
-    language = 'en'
-    __author__ = 'O. Emmerson'
-    keep_only_tags = [dict(name='td', attrs={'width': '522'})]
-    max_articles_per_feed = 10
 
-    def parse_index(self):
+    feeds          = [(u'Counterpunch', u'http://www.counterpunch.org/category/article/feed/')]
-        feeds = []
-        title, url = 'Counterpunch', 'http://www.counterpunch.com'
-        articles = self.parse_page(url)
-        if articles:
-            feeds.append((title, articles))
-        return feeds
-
-    def parse_page(self, url):
-        parsed_page = parse(url).getroot()
-        articles = []
-        unwanted_text = re.compile('Website\ of\ the|I\ urge\ you|Subscribe\ now|DONATE|\@asis\.com|donation\ button|click\ over\ to\ our')
-        parsed_articles = [a for a in parsed_page.cssselect("html>body>table tr>td>p[class='style2']") if not unwanted_text.search(a.text_content())]
-        for art in parsed_articles:
-            try:
-                author = art.text
-                title = art.cssselect("a")[0].text + ' by {0}'.format(author)
-                art_url = 'http://www.counterpunch.com/' + art.cssselect("a")[0].attrib['href']
-                articles.append({'title': title, 'url': art_url})
-            except Exception as e:
-                e
-                #print('Handler Error: ', e, 'title :', a.text_content())
-                pass
-        return articles
 

recipes/dobreprogamy.recipe

@@ -1,5 +1,5 @@
 from calibre.web.feeds.news import BasicNewsRecipe
-
+import re
 
 class Dobreprogramy_pl(BasicNewsRecipe):
     title = 'Dobreprogramy.pl'
@@ -15,6 +15,7 @@ class Dobreprogramy_pl(BasicNewsRecipe):
     extra_css      = '.title {font-size:22px;}'
     oldest_article = 8
     max_articles_per_feed = 100
+    preprocess_regexps = [(re.compile(ur'<div id="\S+360pmp4">Twoja przeglądarka nie obsługuje Flasha i HTML5 lub wyłączono obsługę JavaScript...</div>'), lambda match: '') ]
     remove_tags = [dict(name='div', attrs={'class':['komentarze', 'block', 'portalInfo', 'menuBar', 'topBar']})]
     keep_only_tags = [dict(name='div', attrs={'class':['mainBar', 'newsContent', 'postTitle title', 'postInfo', 'contentText', 'content']})]
     feeds = [(u'Aktualności', 'http://feeds.feedburner.com/dobreprogramy/Aktualnosci'),

recipes/dzieje_pl.recipe

@@ -0,0 +1,17 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Dzieje(BasicNewsRecipe):
+    title          = u'dzieje.pl'
+    __author__        = 'fenuks'
+    description   = 'Dzieje - history of Poland'
+    cover_url      = 'http://www.dzieje.pl/sites/default/files/dzieje_logo.png'
+    category       = 'history'
+    language       = 'pl'
+    oldest_article = 8
+    max_articles_per_feed = 100
+    remove_javascript=True
+    no_stylesheets= True
+    remove_tags_before= dict(name='h1', attrs={'class':'title'})
+    remove_tags_after= dict(id='dogory')
+    remove_tags=[dict(id='dogory')]
+    feeds          = [(u'Dzieje', u'http://dzieje.pl/rss.xml')]

recipes/economist.recipe

@@ -77,32 +77,23 @@ class Economist(BasicNewsRecipe):
                 continue
             self.log('Found section: %s'%section_title)
             articles = []
-            for h5 in section.findAll('h5'):
+            subsection = ''
-                article_title = self.tag_to_string(h5).strip()
+            for node in section.findAll(attrs={'class':'article'}):
-                if not article_title:
+                subsec = node.findPreviousSibling('h5')
-                    continue
+                if subsec is not None:
-                data = h5.findNextSibling(attrs={'class':'article'})
+                    subsection = self.tag_to_string(subsec)
-                if data is None: continue
+                prefix = (subsection+': ') if subsection else ''
-                a = data.find('a', href=True)
+                a = node.find('a', href=True)
-                if a is None: continue
+                if a is not None:
-                url = a['href']
+                    url = a['href']
-                if url.startswith('/'): url = 'http://www.economist.com'+url
+                    if url.startswith('/'): url = 'http://www.economist.com'+url
-                url += '/print'
+                    url += '/print'
-                article_title += ': %s'%self.tag_to_string(a).strip()
+                    title = self.tag_to_string(a)
-                articles.append({'title':article_title, 'url':url,
+                    if title:
-                    'description':'', 'date':''})
+                        title = prefix + title
-            if not articles:
+                        self.log('\tFound article:', title)
-                # We have last or first section
+                        articles.append({'title':title, 'url':url,
-                for art in section.findAll(attrs={'class':'article'}):
+                        'description':'', 'date':''})
-                    a = art.find('a', href=True)
-                    if a is not None:
-                        url = a['href']
-                        if url.startswith('/'): url = 'http://www.economist.com'+url
-                        url += '/print'
-                        title = self.tag_to_string(a)
-                        if title:
-                            articles.append({'title':title, 'url':url,
-                            'description':'', 'date':''})
 
             if articles:
                 if section_title not in feeds:

recipes/economist_free.recipe

@@ -69,32 +69,23 @@ class Economist(BasicNewsRecipe):
                 continue
             self.log('Found section: %s'%section_title)
             articles = []
-            for h5 in section.findAll('h5'):
+            subsection = ''
-                article_title = self.tag_to_string(h5).strip()
+            for node in section.findAll(attrs={'class':'article'}):
-                if not article_title:
+                subsec = node.findPreviousSibling('h5')
-                    continue
+                if subsec is not None:
-                data = h5.findNextSibling(attrs={'class':'article'})
+                    subsection = self.tag_to_string(subsec)
-                if data is None: continue
+                prefix = (subsection+': ') if subsection else ''
-                a = data.find('a', href=True)
+                a = node.find('a', href=True)
-                if a is None: continue
+                if a is not None:
-                url = a['href']
+                    url = a['href']
-                if url.startswith('/'): url = 'http://www.economist.com'+url
+                    if url.startswith('/'): url = 'http://www.economist.com'+url
-                url += '/print'
+                    url += '/print'
-                article_title += ': %s'%self.tag_to_string(a).strip()
+                    title = self.tag_to_string(a)
-                articles.append({'title':article_title, 'url':url,
+                    if title:
-                    'description':'', 'date':''})
+                        title = prefix + title
-            if not articles:
+                        self.log('\tFound article:', title)
-                # We have last or first section
+                        articles.append({'title':title, 'url':url,
-                for art in section.findAll(attrs={'class':'article'}):
+                        'description':'', 'date':''})
-                    a = art.find('a', href=True)
-                    if a is not None:
-                        url = a['href']
-                        if url.startswith('/'): url = 'http://www.economist.com'+url
-                        url += '/print'
-                        title = self.tag_to_string(a)
-                        if title:
-                            articles.append({'title':title, 'url':url,
-                            'description':'', 'date':''})
 
             if articles:
                 if section_title not in feeds:

recipes/elektroda_pl.recipe

@@ -0,0 +1,15 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Elektroda(BasicNewsRecipe):
+    title          = u'Elektroda'
+    oldest_article = 8
+    __author__        = 'fenuks'
+    description   = 'Elektroda.pl'
+    cover_url      = 'http://demotywatory.elektroda.pl/Thunderpic/logo.gif'
+    category       = 'electronics'
+    language       = 'pl'
+    max_articles_per_feed = 100
+    remove_tags_before=dict(name='span', attrs={'class':'postbody'})
+    remove_tags_after=dict(name='td', attrs={'class':'spaceRow'})
+    remove_tags=[dict(name='a', attrs={'href':'#top'})]
+    feeds          = [(u'Elektroda', u'http://www.elektroda.pl/rtvforum/rss.php')]

recipes/film_web.recipe

@@ -31,10 +31,10 @@ class Filmweb_pl(BasicNewsRecipe):
                          (u'Recenzje redakcji', u'http://www.filmweb.pl/feed/reviews/latest'),
                          (u'Recenzje użytkowników', u'http://www.filmweb.pl/feed/user-reviews/latest')]
 
-    def skip_ad_pages(self, soup):
+    def skip_ad_pages(self, soup):   
-        skip_tag = soup.find('a', attrs={'class':'welcomeScreenButton'})['href']
+        skip_tag = soup.find('a', attrs={'class':'welcomeScreenButton'})
-        #self.log.warn(skip_tag)
         if skip_tag is not None:
-            return self.index_to_soup(skip_tag, raw=True)
+            self.log.warn('skip_tag')
-        else:
+            self.log.warn(skip_tag)
-            None
+            return self.index_to_soup(skip_tag['href'], raw=True)
+        

recipes/fleshbot.recipe

@@ -16,13 +16,13 @@ class Fleshbot(BasicNewsRecipe):
     max_articles_per_feed = 100
     no_stylesheets        = True
     encoding              = 'utf-8'
-    use_embedded_content  = False
+    use_embedded_content  = True
     language              = 'en'
-    masthead_url          = 'http://cache.fleshbot.com/assets/base/img/thumbs140x140/fleshbot.com.png'
+    masthead_url          = 'http://cache.gawkerassets.com/assets/kotaku.com/img/logo.png'
     extra_css             = '''
 	body{font-family: "Lucida Grande",Helvetica,Arial,sans-serif}
 	img{margin-bottom: 1em}
-	h1{font-family :Arial,Helvetica,sans-serif; font-size:x-large}
+	h1{font-family :Arial,Helvetica,sans-serif; font-size:large}
 	              '''
     conversion_options = {
                           'comment'   : description
@@ -31,13 +31,12 @@ class Fleshbot(BasicNewsRecipe):
                         , 'language'  : language
                         }
 
-    remove_attributes  = ['width','height']
+    feeds = [(u'Articles', u'http://feeds.gawker.com/fleshbot/vip?format=xml')]
-    keep_only_tags     = [dict(attrs={'class':'content permalink'})]
+
-    remove_tags_before = dict(name='h1')
+    remove_tags = [
-    remove_tags        = [dict(attrs={'class':'contactinfo'})]
+            {'class': 'feedflare'},
-    remove_tags_after  = dict(attrs={'class':'contactinfo'})
+    ]
 
-    feeds = [(u'Articles', u'http://feeds.gawker.com/fleshbot/full')]
 
     def preprocess_html(self, soup):
         return self.adeify_images(soup)

recipes/gildia_pl.recipe

@@ -0,0 +1,26 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Gildia(BasicNewsRecipe):
+    title          = u'Gildia.pl'
+    __author__        = 'fenuks'
+    description   = 'Gildia - cultural site'
+    cover_url      = 'http://www.film.gildia.pl/_n_/portal/redakcja/logo/logo-gildia.pl-500.jpg'
+    category       = 'culture'
+    language       = 'pl'
+    oldest_article = 8
+    max_articles_per_feed = 100
+    no_stylesheets=True
+    remove_tags=[dict(name='div', attrs={'class':'backlink'}), dict(name='div', attrs={'class':'im_img'}), dict(name='div', attrs={'class':'addthis_toolbox addthis_default_style'})]
+    keep_only_tags=dict(name='div', attrs={'class':'widetext'})
+    feeds          = [(u'Gry', u'http://www.gry.gildia.pl/rss'), (u'Literatura', u'http://www.literatura.gildia.pl/rss'), (u'Film', u'http://www.film.gildia.pl/rss'), (u'Horror', u'http://www.horror.gildia.pl/rss'), (u'Konwenty', u'http://www.konwenty.gildia.pl/rss'), (u'Plansz\xf3wki', u'http://www.planszowki.gildia.pl/rss'), (u'Manga i anime', u'http://www.manga.gildia.pl/rss'), (u'Star Wars', u'http://www.starwars.gildia.pl/rss'), (u'Techno', u'http://www.techno.gildia.pl/rss'), (u'Historia', u'http://www.historia.gildia.pl/rss'), (u'Magia', u'http://www.magia.gildia.pl/rss'), (u'Bitewniaki', u'http://www.bitewniaki.gildia.pl/rss'), (u'RPG', u'http://www.rpg.gildia.pl/rss'), (u'LARP', u'http://www.larp.gildia.pl/rss'), (u'Muzyka', u'http://www.muzyka.gildia.pl/rss'), (u'Nauka', u'http://www.nauka.gildia.pl/rss')]
+
+
+    def skip_ad_pages(self, soup):
+        content = soup.find('div', attrs={'class':'news'})
+        skip_tag= content.findAll(name='a')
+        if skip_tag is not None:
+            for link in skip_tag:
+                if 'recenzja' in link['href']:
+                    self.log.warn('odnosnik')
+                    self.log.warn(link['href'])
+                    return self.index_to_soup(link['href'], raw=True)

recipes/greenlinux_pl.recipe

@@ -0,0 +1,13 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class GreenLinux(BasicNewsRecipe):
+    title          = u'GreenLinux.pl'
+    __author__  = 'fenuks'
+    category       = 'IT'
+    language       = 'pl'
+    cover_url = 'http://lh5.ggpht.com/_xd_6Y9kXhEc/S8tjyqlfhfI/AAAAAAAAAYU/zFNTp07ZQko/top.png'
+    oldest_article = 15
+    max_articles_per_feed = 100
+    auto_cleanup = True
+
+    feeds          = [(u'Newsy', u'http://feeds.feedburner.com/greenlinux')]

recipes/gry_online_pl.recipe

@@ -0,0 +1,38 @@
+from calibre.web.feeds.recipes import BasicNewsRecipe
+
+class Gry_online_pl(BasicNewsRecipe):
+    title          = u'Gry-Online.pl'
+    __author__        = 'fenuks'
+    description   = 'Gry-Online.pl - computer games'
+    category       = 'games'
+    language       = 'pl'
+    oldest_article = 13
+    INDEX= 'http://www.gry-online.pl/'
+    cover_url='http://www.gry-online.pl/img/1st_10/1st-gol-logo.png'
+    max_articles_per_feed = 100
+    no_stylesheets= True
+    extra_css              = 'p.wn1{font-size:22px;}'
+    remove_tags_after= [dict(name='div', attrs={'class':['tresc-newsa']})]
+    keep_only_tags = [dict(name='div', attrs={'class':['txthead']}), dict(name='p', attrs={'class':['wtx1', 'wn1', 'wob']}), dict(name='a', attrs={'class':['num_str_nex']})]
+    #remove_tags= [dict(name='div', attrs={'class':['news_plat']})]
+    feeds          = [(u'Newsy', 'http://www.gry-online.pl/rss/news.xml'), ('Teksty', u'http://www.gry-online.pl/rss/teksty.xml')]
+
+
+    def append_page(self, soup, appendtag):
+        nexturl = soup.find('a', attrs={'class':'num_str_nex'})
+        if appendtag.find('a', attrs={'class':'num_str_nex'}) is not None:
+            appendtag.find('a', attrs={'class':'num_str_nex'}).replaceWith('\n')
+        if nexturl is not None:
+            if 'strona' in nexturl.div.string:
+                nexturl= self.INDEX + nexturl['href']
+                soup2 = self.index_to_soup(nexturl)
+                pagetext = soup2.findAll(name='p', attrs={'class':['wtx1', 'wn1', 'wob']})
+                for tag in pagetext:
+                    pos = len(appendtag.contents)
+                    appendtag.insert(pos, tag)
+                self.append_page(soup2, appendtag)
+
+
+    def preprocess_html(self, soup):
+         self.append_page(soup, soup.body)
+         return soup

recipes/guardian.recipe

@@ -15,8 +15,10 @@ class Guardian(BasicNewsRecipe):
     title = u'The Guardian and The Observer'
     if date.today().weekday() == 6:
         base_url = "http://www.guardian.co.uk/theobserver"
+        cover_pic = 'Observer digital edition'
     else:
         base_url = "http://www.guardian.co.uk/theguardian"
+        cover_pic = 'Guardian digital edition'
 
     __author__ = 'Seabound and Sujata Raman'
     language = 'en_GB'
@@ -79,7 +81,7 @@ class Guardian(BasicNewsRecipe):
         # soup = self.index_to_soup("http://www.guardian.co.uk/theobserver")
         soup = self.index_to_soup(self.base_url)
         # find cover pic
-        img = soup.find( 'img',attrs ={'alt':'Guardian digital edition'})
+        img = soup.find( 'img',attrs ={'alt':self.cover_pic})
         if img is not None:
             self.cover_url = img['src']
         # end find cover pic

recipes/h7_tumspor.recipe

@@ -0,0 +1,50 @@
+# -*- coding: utf-8 -*-
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Haber7TS (BasicNewsRecipe):
+
+    title               = u'H7 TÜMSPOR'
+    __author__            = u'thomass'
+    description            =  ' Haber 7 TÜMSPOR sitesinden tüm branşlarda spor haberleri '
+    oldest_article         =2
+    max_articles_per_feed  =100
+    no_stylesheets         = True
+    #delay                  = 1
+    #use_embedded_content   = False
+    encoding               = 'ISO 8859-9'
+    publisher              = 'thomass'
+    category               = 'güncel, haber, türkçe,spor,futbol'
+    language               = 'tr'
+    publication_type = 'newspaper'
+
+    conversion_options = {
+                            'tags'            : category
+                            ,'language'        : language
+                            ,'publisher'       : publisher
+                            ,'linearize_tables': True
+                         }
+    extra_css              = '  #newsheadcon h1{font-weight: bold; font-size: 18px;color:#0000FF} '
+    keep_only_tags    = [dict(name='div', attrs={'class':['intNews','leftmidmerge']})]
+    remove_tags  = [dict(name='div', attrs={'id':['blocktitle','banner46860body']}),dict(name='div', attrs={'class':[ 'Breadcrumb','shr','mobile/home.jpg','etiket','yorumYazNew','shr','y-list','banner','lftBannerShowcase','comments','interNews','lftBanner','midblock','rightblock','comnum','commentcon',]}) ,dict(name='a', attrs={'class':['saveto','sendto','comlink','newsshare',]}),dict(name='iframe', attrs={'name':['frm111','frm107']}) ,dict(name='ul', attrs={'class':['nocPagi','leftmidmerge']})]
+    cover_img_url = 'http://image.tumspor.com/v2/images/tasarim/images/logo.jpg'
+    masthead_url = 'http://image.tumspor.com/v2/images/tasarim/images/logo.jpg'
+    remove_empty_feeds= True
+
+    feeds          = [
+                      ( u'Futbol', u'http://open.dapper.net/services/h7tsfutbol'),
+                      ( u'Basketbol', u'http://open.dapper.net/services/h7tsbasket'),
+                      ( u'Tenis', u'http://open.dapper.net/services/h7tstenis'),
+                      ( u'NBA', u'http://open.dapper.net/services/h7tsnba'),
+                      ( u'Diğer Sporlar', u'http://open.dapper.net/services/h7tsdiger'),
+                      ( u'Yazarlar & Magazin', u'http://open.dapper.net/services/h7tsyazarmagazin'),
+                        ]
+    def preprocess_html(self, soup):
+         for alink in soup.findAll('a'):
+            if alink.string is not None:
+               tstr = alink.string
+               alink.replaceWith(tstr)
+         return soup
+   # def print_version(self, url):
+    # return url.replace('http://www.aksiyon.com.tr/aksiyon/newsDetail_getNewsById.action?load=detay&', 'http://www.aksiyon.com.tr/aksiyon/mobile_detailn.action?')
+

recipes/haber7.recipe

@@ -0,0 +1,60 @@
+# -*- coding: utf-8 -*-
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Haber7 (BasicNewsRecipe):
+
+    title               = u'Haber 7'
+    __author__            = u'thomass'
+    description            =  ' Haber 7 sitesinden haberler '
+    oldest_article         =2
+    max_articles_per_feed  =100
+    no_stylesheets         = True
+    #delay                  = 1
+    #use_embedded_content   = False
+    encoding               = 'ISO 8859-9'
+    publisher              = 'thomass'
+    category               = 'güncel, haber, türkçe'
+    language               = 'tr'
+    publication_type = 'newspaper'
+
+    conversion_options = {
+                            'tags'            : category
+                            ,'language'        : language
+                            ,'publisher'       : publisher
+                            ,'linearize_tables': True
+                         }
+    extra_css              = 'body{ font-size: 12px}h2{font-weight: bold; font-size: 18px;color:#0000FF} #newsheadcon h1{font-weight: bold; font-size: 18px;color:#0000FF}'
+
+    keep_only_tags    = [dict(name='div', attrs={'class':['intNews','leftmidmerge']})]
+    remove_tags  = [dict(name='div', attrs={'id':['blocktitle','banner46860body']}),dict(name='div', attrs={'class':[ 'Breadcrumb','shr','mobile/home.jpg','etiket','yorumYazNew','shr','y-list','banner','lftBannerShowcase','comments','interNews','lftBanner','midblock','rightblock','comnum','commentcon',]}) ,dict(name='a', attrs={'class':['saveto','sendto','comlink','newsshare',]}),dict(name='iframe', attrs={'name':['frm111','frm107']}) ,dict(name='ul', attrs={'class':['nocPagi','leftmidmerge']})]
+
+    cover_img_url = 'http://dl.dropbox.com/u/39726752/haber7.JPG'
+    masthead_url = 'http://dl.dropbox.com/u/39726752/haber7.JPG'
+    remove_empty_feeds= True
+
+    feeds          = [
+                     ( u'Siyaset', u'http://open.dapper.net/services/h7siyaset'),
+                      ( u'Güncel', u'http://open.dapper.net/services/h7guncel'),
+                      ( u'Yaşam', u'http://open.dapper.net/services/h7yasam'),
+                      ( u'Ekonomi', u'http://open.dapper.net/services/h7ekonomi'),
+                      ( u'3. Sayfa', u'http://open.dapper.net/services/h73sayfa'),
+                      ( u'Dünya', u'http://open.dapper.net/services/h7dunya'),
+                      ( u'Medya', u'http://open.dapper.net/services/h7medya'),
+
+                      ( u'Yazarlar', u'http://open.dapper.net/services/h7yazarlar'),
+                      ( u'Bilim', u'http://open.dapper.net/services/h7bilim'),
+                      ( u'Eğitim', u'http://open.dapper.net/services/h7egitim'),
+                      ( u'Spor', u'http://open.dapper.net/services/h7sporv3'),
+
+
+                        ]
+    def preprocess_html(self, soup):
+         for alink in soup.findAll('a'):
+            if alink.string is not None:
+               tstr = alink.string
+               alink.replaceWith(tstr)
+         return soup
+   # def print_version(self, url):
+    # return url.replace('http://www.aksiyon.com.tr/aksiyon/newsDetail_getNewsById.action?load=detay&', 'http://www.aksiyon.com.tr/aksiyon/mobile_detailn.action?')
+

recipes/hackernews.recipe

@@ -7,6 +7,7 @@ Hacker News
 from calibre.web.feeds.news import BasicNewsRecipe
 from calibre.ptempfile import PersistentTemporaryFile
 from urlparse import urlparse
+import re
 
 class HackerNews(BasicNewsRecipe):
     title                 = 'Hacker News'
@@ -14,8 +15,8 @@ class HackerNews(BasicNewsRecipe):
     description           = u'Hacker News, run by Y Combinator. Anything that good hackers would find interesting, with a focus on programming and startups.'
     publisher             = 'Y Combinator'
     category              = 'news, programming, it, technology'
-    masthead_url          = 'http://i55.tinypic.com/2u6io76.png'
+    masthead_url          = 'http://img585.imageshack.us/img585/5011/hnle.png'
-    cover_url             = 'http://i55.tinypic.com/2u6io76.png'
+    cover_url             = 'http://img585.imageshack.us/img585/5011/hnle.png'
     delay                 = 1
     max_articles_per_feed = 30
     use_embedded_content  = False
@@ -42,12 +43,42 @@ class HackerNews(BasicNewsRecipe):
 
     def get_hn_content(self, url):
         self.log('get_hn_content(' + url + ')')
-        # this could be improved
+        soup = self.index_to_soup(url)
-        br = self.get_browser()
+        main = soup.find('tr').findNextSiblings('tr', limit=2)[1].td
-        f = br.open(url)
+
-        html = f.read()
+        title = self.tag_to_string(main.find('td', 'title'))
-        f.close()
+        link = main.find('td', 'title').find('a')['href']
-        return html
+        if link.startswith('item?'):
+            link = 'http://news.ycombinator.com/' + link
+        readable_link = link.rpartition('http://')[2].rpartition('https://')[2]
+        subtext = self.tag_to_string(main.find('td', 'subtext'))
+
+        title_content_td = main.find('td', 'title').findParent('tr').findNextSiblings('tr', limit=3)[2].findAll('td', limit=2)[1]
+        title_content = u''
+        if not title_content_td.find('form'):
+            title_content_td.name ='div'
+            title_content = title_content_td.prettify()
+
+        comments = u''
+        for td in main.findAll('td', 'default'):
+            comhead = td.find('span', 'comhead')
+            if comhead:
+                com_title = u'<h4>' + self.tag_to_string(comhead).replace(' | link', '') + u'</h4>'
+                comhead.parent.extract()
+                br = td.find('br')
+                if br:
+                    br.extract()
+                reply = td.find('a', attrs = {'href' : re.compile('^reply?')})
+                if reply:
+                    reply.parent.extract()
+                td.name = 'div'
+                indent_width = (int(td.parent.find('td').img['width']) * 2) / 3
+                td['style'] = 'padding-left: ' + str(indent_width) + 'px'
+                comments = comments + com_title + td.prettify()
+
+        body = u'<h3>' + title + u'</h3><p><a href="' + link + u'">' + readable_link + u'</a><br/><strong>' + subtext +  u'</strong></p>' + title_content + u'<br/>'
+        body = body + comments
+        return u'<html><title>' + title + u'</title><body>' + body + '</body></html>'
 
     def get_obfuscated_article(self, url):
         if url.startswith('http://news.ycombinator.com'):
@@ -83,4 +114,10 @@ class HackerNews(BasicNewsRecipe):
         article.text_summary = self.prettyify_url(article.url)
         article.summary = article.text_summary
 
+#    def parse_index(self):
+#        feeds = []
+#        feeds.append((u'Hacker News',[{'title': 'Testing', 'url': 'http://news.ycombinator.com/item?id=2935944'}]))
+#        return feeds
+
+
 

recipes/hbr.recipe

@@ -11,9 +11,14 @@ class HBR(BasicNewsRecipe):
     timefmt                = ' [%B %Y]'
     language = 'en'
     no_stylesheets = True
+    recipe_disabled = ('hbr.org has started requiring the use of javascript'
+            ' to log into their website. This is unsupported in calibre, so'
+            ' this recipe has been disabled. If you would like to see '
+            ' HBR supported in calibre, contact hbr.org and ask them'
+            ' to provide a javascript free login method.')
 
-    LOGIN_URL = 'http://hbr.org/login?request_url=/'
+    LOGIN_URL = 'https://hbr.org/login?request_url=/'
-    LOGOUT_URL = 'http://hbr.org/logout?request_url=/'
+    LOGOUT_URL = 'https://hbr.org/logout?request_url=/'
 
     INDEX = 'http://hbr.org/archive-toc/BR'
 
@@ -44,7 +49,7 @@ class HBR(BasicNewsRecipe):
         br['signin-form:username'] = self.username
         br['signin-form:password'] = self.password
         raw = br.submit().read()
-        if 'My Account' not in raw:
+        if '>Sign out<' not in raw:
             raise Exception('Failed to login, are you sure your username and password are correct?')
         try:
             link = br.find_link(text='Sign out')

recipes/hbr_blogs.recipe

@@ -5,10 +5,15 @@ class HBR(BasicNewsRecipe):
 
     title = 'Harvard Business Review Blogs'
     description = 'To subscribe go to http://hbr.harvardbusiness.org'
-    needs_subscription = True
     __author__ = 'Kovid Goyal'
     language = 'en'
     no_stylesheets = True
+    #recipe_disabled = ('hbr.org has started requiring the use of javascript'
+    #        ' to log into their website. This is unsupported in calibre, so'
+    #        ' this recipe has been disabled. If you would like to see '
+    #        ' HBR supported in calibre, contact hbr.org and ask them'
+    #        ' to provide a javascript free login method.')
+    needs_subscription = False
 
     LOGIN_URL = 'http://hbr.org/login?request_url=/'
     LOGOUT_URL = 'http://hbr.org/logout?request_url=/'
@@ -36,6 +41,7 @@ class HBR(BasicNewsRecipe):
     def get_browser(self):
         br = BasicNewsRecipe.get_browser(self)
         self.logout_url = None
+        return br
 
         #'''
         br.open(self.LOGIN_URL)

recipes/hindustan_times.recipe

@@ -0,0 +1,29 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class HindustanTimes(BasicNewsRecipe):
+    title          = u'Hindustan Times'
+    language       = 'en_IN'
+    __author__     = 'Krittika Goyal'
+    oldest_article = 1 #days
+    max_articles_per_feed = 25
+    use_embedded_content = False
+
+    no_stylesheets = True
+    auto_cleanup = True
+
+    feeds          = [
+            ('News',
+            'http://feeds.hindustantimes.com/HT-NewsSectionPage-Topstories'),
+            ('Views',
+            'http://feeds.hindustantimes.com/HT-ViewsSectionpage-Topstories'),
+            ('Cricket',
+            'http://feeds.hindustantimes.com/HT-Cricket-TopStories'),
+            ('Business',
+            'http://feeds.hindustantimes.com/HT-BusinessSectionpage-TopStories'),
+            ('Entertainment',
+            'http://feeds.hindustantimes.com/HT-HomePage-Entertainment'),
+            ('Lifestyle',
+            'http://feeds.hindustantimes.com/HT-Homepage-LifestyleNews'),
+]
+
+

recipes/hira.recipe

@@ -0,0 +1,52 @@
+# coding=utf-8
+
+from calibre.web.feeds.recipes import BasicNewsRecipe
+
+class Hira(BasicNewsRecipe):
+    title                  = 'Hira'
+    __author__             = 'thomass'
+    description            = 'مجلة حراء مجلة علمية ثقافية فكرية تصدر كل شهرين، تعنى بالعلوم الطبيعية والإنسانية والاجتماعية وتحاور أسرار النفس البشرية وآفاق الكون الشاسعة بالمنظور القرآني الإيماني في تآلف وتناسب بين العلم والإيمان، والعقل والقلب، والفكر والواقع.'
+    oldest_article         = 63
+    max_articles_per_feed  = 50
+    no_stylesheets         = True
+    #delay                 = 1
+    use_embedded_content   = False
+    encoding               = 'utf-8'
+    publisher              = 'thomass'
+    category               = 'News'
+    language               = 'ar'
+    publication_type       = 'magazine'
+    extra_css              = ' .title-detail-wrap{ font-weight: bold ;text-align:right;color:#FF0000;font-size:25px}.title-detail{ font-family:sans-serif;text-align:right;}  '
+
+
+    conversion_options = {
+                            'tags'            : category
+                            ,'language'        : language
+                            ,'publisher'       : publisher
+                            ,'linearize_tables': True
+                            ,'base-font-size':'10'
+                         }
+    #html2lrf_options = []
+    keep_only_tags    = [
+                            dict(name='div', attrs={'class':['title-detail']})
+                        ]
+
+    remove_tags       = [
+                            dict(name='div', attrs={'class':['clear', 'bbsp']}),
+                        ]
+
+    remove_attributes = [
+                            'width','height'
+                        ]
+
+    feeds             = [
+                            (u'حراء', 'http://open.dapper.net/services/hira'),
+                        ]
+
+    def preprocess_html(self, soup):
+        for alink in soup.findAll('a'):
+            if alink.string is not None:
+               tstr = alink.string
+               alink.replaceWith(tstr)
+        return soup
+

recipes/historia_pl.recipe

@@ -0,0 +1,13 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Historia_org_pl(BasicNewsRecipe):
+    title          = u'Historia.org.pl'
+    __author__        = 'fenuks'
+    description   = u'history site'
+    cover_url      = 'http://lh3.googleusercontent.com/_QeRQus12wGg/TOvHsZ2GN7I/AAAAAAAAD_o/LY1JZDnq7ro/logo5.jpg'
+    category       = 'history'
+    language       = 'pl'
+    oldest_article = 8
+    max_articles_per_feed = 100
+
+    feeds          = [(u'Artykuły', u'http://www.historia.org.pl/index.php?format=feed&type=rss')]

recipes/idg_se.recipe

@@ -4,19 +4,19 @@ from calibre.web.feeds.news import BasicNewsRecipe
 
 class IDGse(BasicNewsRecipe):
     title               = 'IDG'
-    description = 'IDG.se'
-    language = 'se'
     __author__ = 'zapt0'
+    language = 'sv'
+    description = 'IDG.se'
     oldest_article = 1
-    max_articles_per_feed = 40
+    max_articles_per_feed = 256
     no_stylesheets = True
     encoding = 'ISO-8859-1'
     remove_javascript = True
 
-    feeds          = [(u'Senaste nytt',u'http://feeds.idg.se/idg/vzzs')]
+    feeds          = [(u'Dagens IDG-nyheter',u'http://feeds.idg.se/idg/ETkj?format=xml')]
 
     def print_version(self,url):
-            return url + '?articleRenderMode=print&m=print'
+        return url + '?articleRenderMode=print&m=print'
 
     def get_cover_url(this):
         return 'http://idgmedia.idg.se/polopoly_fs/2.3275!images/idgmedia_logo_75.jpg'
@@ -30,4 +30,3 @@ class IDGse(BasicNewsRecipe):
                                     dict(name='div', attrs={'id':['preamble_ad']}),
                                     dict(name='ul', attrs={'class':['share']})
                                 ]
-

recipes/india_today.recipe

@@ -1,76 +1,25 @@
+
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class IndiaToday(BasicNewsRecipe):
-
+    title          = u'India Today'
-    title = 'India Today'
+    language       = 'en_IN'
-    __author__ = 'Kovid Goyal'
+    __author__     = 'Krittika Goyal'
-    language = 'en_IN'
+    oldest_article = 15 #days
-    timefmt = ' [%d %m, %Y]'
+    max_articles_per_feed = 25
-
-    oldest_article = 700
-    max_articles_per_feed = 10
 
     no_stylesheets = True
+    auto_cleanup = True
 
-    remove_tags_before = dict(id='content_story_title')
+    feeds          = [
-    remove_tags_after = dict(id='rightblockdiv')
+('Latest News', 'http://indiatoday.intoday.in/rss/article.jsp?sid=4'),
-    remove_tags = [dict(id=['rightblockdiv', 'share_links'])]
+('Cover Story', 'http://indiatoday.intoday.in/rss/article.jsp?sid=30'),
-
+('Nation', 'http://indiatoday.intoday.in/rss/article.jsp?sid=36'),
-    extra_css = '#content_story_title { font-size: 170%; font-weight: bold;}'
+('States', 'http://indiatoday.intoday.in/rss/article.jsp?sid=21'),
-    conversion_options = { 'linearize_tables': True }
+('Economy', 'http://indiatoday.intoday.in/rss/article.jsp?sid=34'),
-
+('World', 'http://indiatoday.intoday.in/rss/article.jsp?sid=61'),
-    def it_get_index(self):
+('Sport', 'http://indiatoday.intoday.in/rss/article.jsp?sid=41'),
-        soup = self.index_to_soup('http://indiatoday.intoday.in/site/archive')
-        a = soup.find('a', href=lambda x: x and 'issueId=' in x)
-        url = 'http://indiatoday.intoday.in/site/'+a.get('href')
-        img = a.find('img')
-        self.cover_url = img.get('src')
-        return self.index_to_soup(url)
-
-    def parse_index(self):
-        soup = self.it_get_index()
-        feeds, current_section, current_articles = [], None, []
-        for x in soup.findAll(name=['h1', 'a']):
-            if x.name == 'h1':
-                if current_section and current_articles:
-                    feeds.append((current_section, current_articles))
-                current_section = self.tag_to_string(x)
-                current_articles = []
-                self.log('\tFound section:', current_section)
-            elif x.name == 'a' and 'Story' in x.get('href', ''):
-                title = self.tag_to_string(x)
-                url = x.get('href')
-                url = url.replace(' ', '%20')
-                if not url.startswith('/'):
-                    url = 'http://indiatoday.intoday.in/site/' + url
-                if title and url:
-                    url += '?complete=1'
-                    self.log('\tFound article:', title)
-                    self.log('\t\t', url)
-                    desc = ''
-                    h3 = x.parent.findNextSibling('h3')
-                    if h3 is not None:
-                        desc = 'By ' + self.tag_to_string(h3)
-                        h4 = h3.findNextSibling('h4')
-                        if h4 is not None:
-                            desc = self.tag_to_string(h4) + ' ' + desc
-                    if desc:
-                        self.log('\t\t', desc)
-                    current_articles.append({'title':title, 'description':desc,
-                        'url':url, 'date':''})
-
-        if current_section and current_articles:
-            feeds.append((current_section, current_articles))
-
-        return feeds
-
-    def postprocess_html(self, soup, first):
-        a = soup.find(text='Print')
-        if a is not None:
-            tr = a.findParent('tr')
-            if tr is not None:
-                tr.extract()
-        return soup
 
+]
 
 

recipes/inquirer_net.recipe

@@ -7,56 +7,33 @@ www.inquirer.net
 '''
 
 from calibre.web.feeds.recipes import BasicNewsRecipe
-from calibre.ebooks.BeautifulSoup import Tag
 
 class InquirerNet(BasicNewsRecipe):
     title                  = 'Inquirer.net'
-    __author__             = 'Darko Miletic'
+    __author__             = 'Krittika Goyal'
     description            = 'News from Philipines'
     oldest_article         = 2
     max_articles_per_feed  = 100
     no_stylesheets         = True
     use_embedded_content   = False
-    encoding               = 'cp1252'
+    encoding               = 'utf8'
     publisher              = 'inquirer.net'
     category               = 'news, politics, philipines'
     lang                   = 'en'
     language = 'en'
 
-    extra_css              = ' .fontheadline{font-size: x-large} .fontsubheadline{font-size: large} .fontkick{font-size: medium}'
+    use_embedded_content = False
 
-    html2lrf_options = [
+    no_stylesheets = True
-                          '--comment', description
+    auto_cleanup = True
-                        , '--category', category
-                        , '--publisher', publisher
-                        , '--ignore-tables'
-                        ]
-
-    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True'
-
-    remove_tags = [dict(name=['object','link','script','iframe','form'])]
 
     feeds = [
-               (u'Breaking news', u'http://services.inquirer.net/rss/breakingnews.xml'             )
+               (u'Inquirer', u'http://www.inquirer.net/fullfeed')
-              ,(u'Top stories'  , u'http://services.inquirer.net/rss/topstories.xml'               )
-              ,(u'Sports'       , u'http://services.inquirer.net/rss/brk_breakingnews.xml'         )
-              ,(u'InfoTech'     , u'http://services.inquirer.net/rss/infotech_tech.xml'            )
-              ,(u'InfoTech'     , u'http://services.inquirer.net/rss/infotech_tech.xml'            )
-              ,(u'Business'     , u'http://services.inquirer.net/rss/inq7money_breaking_news.xml'  )
-              ,(u'Editorial'    , u'http://services.inquirer.net/rss/opinion_editorial.xml'        )
-              ,(u'Global Nation', u'http://services.inquirer.net/rss/globalnation_breakingnews.xml')
             ]
 
-    def preprocess_html(self, soup):
+    def get_browser(self):
-        mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)])
+        br = BasicNewsRecipe.get_browser(self)
-        mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=utf-8")])
+        br.set_handle_gzip(True)
-        soup.head.insert(0,mlang)
+        return br
-        soup.head.insert(1,mcharset)
+
-        for item in soup.findAll(style=True):
-            del item['style']
-        return soup
 
-    def print_version(self, url):
-        rest, sep, art = url.rpartition('/view/')
-        art_id, sp, rrest = art.partition('/')
-        return 'http://services.inquirer.net/print/print.php?article_id=' + art_id

recipes/japan_times.recipe

@@ -1,7 +1,5 @@
-#!/usr/bin/env  python
-
 __license__   = 'GPL v3'
-__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
+__copyright__ = '2008-2011, Darko Miletic <darko.miletic at gmail.com>'
 '''
 japantimes.co.jp
 '''
@@ -9,24 +7,61 @@ japantimes.co.jp
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class JapanTimes(BasicNewsRecipe):
-    title                 = u'The Japan Times'
+    title                 = 'The Japan Times'
     __author__            = 'Darko Miletic'
-    description           = 'News from Japan'
+    description           = "Daily news and features on Japan from the most widely read English-language newspaper in Japan. Coverage includes national news, business news, sports news, commentary and features on living in Japan, entertainment, the arts, education and more."
-    language = 'en'
+    language              = 'en_JP'
-    
+    category              = 'news, politics, japan'
-    oldest_article        = 7
+    publisher             = 'The Japan Times'
-    max_articles_per_feed = 100
+    oldest_article        = 5
+    max_articles_per_feed = 150
     no_stylesheets        = True
     use_embedded_content  = False
+    encoding              = 'utf8'
+    publication_type      = 'newspaper'
+    masthead_url          = 'http://search.japantimes.co.jp/images/header_title.gif'
+    extra_css             = 'body{font-family: Geneva,Arial,Helvetica,sans-serif}'
 
-    keep_only_tags    = [ dict(name='div', attrs={'id':'searchresult'}) ]
+    conversion_options = {
-    remove_tags_after = [ dict(name='div', attrs={'id':'mainbody'    }) ]
+                          'comment'          : description
+                        , 'tags'             : category
+                        , 'publisher'        : publisher
+                        , 'language'         : language
+                        , 'linearize_tables' : True
+                        }
+
+
+    keep_only_tags    = [dict(name='div', attrs={'id':'printresult'})]
     remove_tags       = [
-                           dict(name='div'  , attrs={'id':'ads' })
+                          dict(name=['iframe','meta','link','embed','object','base'])
-                          ,dict(name='table', attrs={'width':470})
+                         ,dict(attrs={'id':'searchfooter'})
                         ]
+    feeds             = [(u'The Japan Times', u'http://feeds.feedburner.com/japantimes')]
+    remove_attributes = ['border']
 
+    def get_article_url(self, article):
+        rurl = BasicNewsRecipe.get_article_url(self, article)
+        return rurl.partition('?')[0]
 
-    feeds          = [
+    def print_version(self, url):
-                        (u'The Japan Times', u'http://feedproxy.google.com/japantimes')
+        return url.replace('/cgi-bin/','/print/')
-                     ]
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        for item in soup.findAll('img'):
+            if not item.has_key('alt'):
+               item['alt'] = 'image'
+        for item in soup.findAll('photo'):
+            item.name = 'div'
+        for item in soup.head.findAll('paragraph'):
+            item.extract()
+        for item in soup.findAll('wwfilename'):
+            item.extract()
+        for item in soup.findAll('jtcategory'):
+            item.extract()
+        for item in soup.findAll('nomooter'):
+            item.extract()
+        for item in soup.body.findAll('paragraph'):
+            item.name = 'p'
+        return soup

recipes/kopalniawiedzy.recipe

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 __license__   = 'GPL v3'
 __copyright__ = '2011, Attis <attis@attis.one.pl>'
 __version__ = 'v. 0.1'
@@ -16,21 +15,21 @@ class KopalniaWiedzy(BasicNewsRecipe):
 		oldest_article = 7
 		max_articles_per_feed = 100
 		INDEX          = u'http://kopalniawiedzy.pl/'
-		remove_javascript     = True
+		remove_javascript     = True    
 		no_stylesheets        = True
-
+		
-		remove_tags    = [{'name':'p', 'attrs': {'class': 'keywords'} }]
+		remove_tags    = [{'name':'p', 'attrs': {'class': 'keywords'} }, {'name':'div', 'attrs': {'class':'sexy-bookmarks sexy-bookmarks-bg-caring'}}]
 		remove_tags_after = dict(attrs={'class':'ad-square'})
 		keep_only_tags    = [dict(name="div", attrs={'id':'articleContent'})]
 		extra_css      = '.topimage {margin-top: 30px}'
-
+		
 		preprocess_regexps = [
 				(re.compile(u'<a .* rel="lightboxText" .*><img (.*)></a>'),
 				lambda match: '<img class="topimage" ' + match.group(1) + '>' ),
 				(re.compile(u'<br  /><br  />'),
 				lambda match: '<br\/>')
 			]
-
+		
 		feeds = [
 			(u'Biologia', u'http://kopalniawiedzy.pl/wiadomosci_biologia.rss'),
 			(u'Medycyna', u'http://kopalniawiedzy.pl/wiadomosci_medycyna.rss'),
@@ -39,10 +38,10 @@ class KopalniaWiedzy(BasicNewsRecipe):
 			(u'Ciekawostki', u'http://kopalniawiedzy.pl/wiadomosci_ciekawostki.rss'),
 			(u'Artykuły', u'http://kopalniawiedzy.pl/artykuly.rss')
 		]
-
+		
 		def is_link_wanted(self, url, tag):
 			return tag['class'] == 'next'
-
+			
 		def remove_beyond(self, tag, next):
 				while tag is not None and getattr(tag, 'name', None) != 'body':
 						after = getattr(tag, next)
@@ -51,30 +50,30 @@ class KopalniaWiedzy(BasicNewsRecipe):
 								after.extract()
 								after = ns
 						tag = tag.parent
-
+		
 		def append_page(self, soup, appendtag, position):
 				pager = soup.find('a',attrs={'class':'next'})
 				if pager:
 					nexturl = self.INDEX + pager['href']
 					soup2 = self.index_to_soup(nexturl)
 					texttag = soup2.find('div', attrs={'id':'articleContent'})
-
+					
 					tag = texttag.find(attrs={'class':'pages'})
 					self.remove_beyond(tag, 'nextSibling')
-
+					
 					newpos = len(texttag.contents)
 					self.append_page(soup2,texttag,newpos)
 
 					appendtag.insert(position,texttag)
 
 
-		def preprocess_html(self, soup):
+		def preprocess_html(self, soup): 
 				self.append_page(soup, soup.body, 3)
-
+				
 				for item in soup.findAll('div',attrs={'class':'pages'}):
 					item.extract()
-
+					
 				for item in soup.findAll('p', attrs={'class':'wykop'}):
 					item.extract()
-
+					
 				return soup

recipes/ksiazka_pl.recipe

@@ -0,0 +1,28 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+import re
+class Ksiazka_net_pl(BasicNewsRecipe):
+    title          = u'ksiazka.net.pl'
+    __author__        = 'fenuks'
+    description   = u'Ksiazka.net.pl - book vortal'
+    cover_url      = 'http://www.ksiazka.net.pl/fileadmin/templates/ksiazka.net.pl/images/1PortalKsiegarski-logo.jpg'
+    category       = 'books'
+    language       = 'pl'
+    oldest_article = 8
+    max_articles_per_feed = 100
+    no_stylesheets= True
+    #extra_css      = 'img {float: right;}'
+    preprocess_regexps = [(re.compile(ur'Podoba mi się, kupuję:'), lambda match: '<br />')]
+    remove_tags_before= dict(name='div', attrs={'class':'m-body'})
+    remove_tags_after= dict(name='div', attrs={'class':'m-body-link'})
+    remove_tags=[dict(attrs={'class':['mk_library-icon', 'm-body-link', 'tagi']})]
+    feeds          = [(u'Wiadomości', u'http://www.ksiazka.net.pl/?id=wiadomosci&type=100'), 
+	      (u'Książki', u'http://www.ksiazka.net.pl/?id=ksiazki&type=100'), 
+	      (u'Rynek', u'http://www.ksiazka.net.pl/?id=rynek&type=100')]
+
+    def image_url_processor(self, baseurl, url):
+        if (('file://' in url) and ('www.ksiazka.net.pl/' not in url)):
+            return 'http://www.ksiazka.net.pl/' + url[8:]
+        elif 'http://' not in url:
+            return 'http://www.ksiazka.net.pl/' + url
+        else:
+            return url

recipes/latimes.recipe

@@ -46,7 +46,9 @@ class LATimes(BasicNewsRecipe):
     remove_tags_after=dict(name='p', attrs={'class':'copyright'})
     remove_tags = [
                      dict(name=['meta','link','iframe','object','embed'])
-                    ,dict(attrs={'class':['toolSet','articlerail','googleAd','entry-footer-left','entry-footer-right','entry-footer-social','google-ad-story-bottom','sphereTools']})
+                    ,dict(attrs={'class':['toolSet','articlerail','googleAd','entry-footer-left',
+                        'entry-footer-right','entry-footer-social','google-ad-story-bottom',
+                        'sphereTools', 'nextgen-share-tools']})
                     ,dict(attrs={'id':['article-promo','googleads','moduleArticleToolsContainer','gallery-subcontent']})
                   ]
     remove_attributes=['lang','xmlns:fb','xmlns:og','border','xtags','i','article_body']

recipes/lomza.recipe

@@ -0,0 +1,14 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Lomza(BasicNewsRecipe):
+    title          = u'4Lomza'
+    __author__        = 'fenuks'
+    description   = u'4Łomża - regional site'
+    cover_url      = 'http://www.4lomza.pl/i/logo4lomza_m.jpg'
+    language       = 'pl' 
+    oldest_article = 15
+    no_styleseets=True
+    max_articles_per_feed = 100
+    remove_tags=[dict(name='div', attrs={'class':['bxbanner', 'drukuj', 'wyslijznajomemu']})]
+    keep_only_tags=[dict(name='div', attrs={'class':'wiadomosc'})]
+    feeds          = [(u'Łomża', u'http://feeds.feedburner.com/4lomza.pl')]

recipes/macleans.recipe

@@ -4,25 +4,17 @@ from calibre.web.feeds.news import BasicNewsRecipe
 class AdvancedUserRecipe1308306308(BasicNewsRecipe):
     title          = u'Macleans Magazine'
     language = 'en_CA'
-    __author__ = 'sexymax15'
+    __author__ = 'Medius'
-    oldest_article = 30
+    oldest_article = 7
-    max_articles_per_feed = 12
+    cover_url = 'http://www.rogersmagazines.com/rms_covers/md/CLE_md.jpg'
 
     use_embedded_content = False
 
     remove_empty_feeds = True
     no_stylesheets = True
     remove_javascript = True
-    remove_tags = [dict(name ='img'),dict (id='header'),{'class':'postmetadata'}]
+    remove_tags = [dict(id='header'),{'class':'comment'}]
-    remove_tags_after = {'class':'postmetadata'}
+    remove_tags_after = {'class':'pagination'}
 
-    feeds          = [(u'Blog Central', u'http://www2.macleans.ca/category/blog-central/feed/'),
+    feeds          = [(u'Canada', u'http://www2.macleans.ca/category/canada/feed/'),
- (u'Canada', u'http://www2.macleans.ca/category/canada/feed/'),
+(u'World', u'http://www2.macleans.ca/category/news-politics/world/feed/'), (u'Business', u'http://www2.macleans.ca/category/business/feed/'), (u'Arts & Culture', u'http://www2.macleans.ca/category/arts/feed/'), (u'Opinion', u'http://www2.macleans.ca/category/opinion/feed/'), (u'Health', u'http://www2.macleans.ca/category/life/health/feed/'), (u'Sports', u'http://www2.macleans.ca/category/life/sports/feed/'), (u'Environment', u'http://www2.macleans.ca/category/life/environment/feed/'), (u'Technology', u'http://www2.macleans.ca/category/life/technology/feed/'), (u'Travel', u'http://www2.macleans.ca/category/life/travel/feed/'), (u'Blog Central', u'http://www2.macleans.ca/category/blog-central/feed/')]
-(u'World', u'http://www2.macleans.ca/category/world-from-the-magazine/feed/'),
-(u'Business', u'http://www2.macleans.ca/category/business/feed/'),
-(u'Arts & Culture', u'http://www2.macleans.ca/category/arts-culture/feed/'),
-(u'Opinion', u'http://www2.macleans.ca/category/opinion/feed/'),
-(u'Health', u'http://www2.macleans.ca/category/health-from-the-magazine/feed/'),
- (u'Environment', u'http://www2.macleans.ca/category/environment-from-the-magazine/feed/')]
-    def print_version(self, url):
-        return url + 'print/'

recipes/metro_news_nl.recipe

@@ -2,7 +2,6 @@ from calibre.web.feeds.news import BasicNewsRecipe
 
 class AdvancedUserRecipe1306097511(BasicNewsRecipe):
     title = u'Metro Nieuws NL'
-    description = u'Metro Nieuws - NL'
 # Version 1.2, updated cover image to match the changed website.
 # added info date on title
     oldest_article = 2
@@ -11,14 +10,14 @@ class AdvancedUserRecipe1306097511(BasicNewsRecipe):
     description    = u'Metro Nederland'
     language       = u'nl'
     simultaneous_downloads = 5
-    delay          = 1
+    #delay          = 1
-#    timefmt        = ' [%A, %d %B, %Y]'
+    auto_cleanup = True
+    auto_cleanup_keep = '//div[@class="article-image-caption-2column"]|//div[@id="date"]'
     timefmt        = ' [%A, %d %b %Y]'
     no_stylesheets = True
     remove_javascript = True
     remove_empty_feeds = True
     cover_url      = 'http://www.oldreadmetro.com/img/en/metroholland/last/1/small.jpg'
-    remove_empty_feeds = True
     publication_type = 'newspaper'
     remove_tags_before = dict(name='div', attrs={'id':'date'})
     remove_tags_after = dict(name='div', attrs={'id':'column-1-3'})

recipes/ming_pao.recipe

@@ -12,10 +12,15 @@ __UseChineseTitle__ = False
 __KeepImages__ = True
 # (HK only) Turn below to true if you wish to use life.mingpao.com as the main article source
 __UseLife__ = True
+# (HK only) if __UseLife__ is true, turn this on if you want to include the column section
+__InclCols__ = False
 
 
 '''
 Change Log:
+2011/09/21: fetching "column" section is made optional. Default is False
+2011/09/18: parse "column" section stuff from source text file directly.
+2011/09/07: disable "column" section as it is no longer offered free.
 2011/06/26: add fetching Vancouver and Toronto versions of the paper, also provide captions for images using life.mingpao fetch source
             provide options to remove all images in the file
 2011/05/12: switch the main parse source to life.mingpao.com, which has more photos on the article pages
@@ -51,16 +56,19 @@ class MPRecipe(BasicNewsRecipe):
         title       = 'Ming Pao - Hong Kong'
         description = 'Hong Kong Chinese Newspaper (http://news.mingpao.com)'
         category    = 'Chinese, News, Hong Kong'
-        extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px;} font>b {font-size:200%; font-weight:bold;}'
+        extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px;} font>b {font-size:200%; font-weight:bold;} div[class=heading] {font-size:200%; font-weight:bold;} div[class=images] {font-size:50%;}'
         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 title
                           dict(name='font', attrs={'color':['AA0000']}), # for column articles title
+                          dict(attrs={'class':['heading']}),  # for heading from txt
                           dict(attrs={'id':['newscontent']}), # entertainment and column page content
                           dict(attrs={'id':['newscontent01','newscontent02']}),
+                          dict(attrs={'class':['content']}),  # for content from txt
                           dict(attrs={'class':['photo']}),
                           dict(name='table', attrs={'width':['100%'], 'border':['0'], 'cellspacing':['5'], 'cellpadding':['0']}),  # content in printed version of life.mingpao.com
-                          dict(name='img', attrs={'width':['180'], 'alt':['按圖放大']}) # images for source from life.mingpao.com
+                          dict(name='img', attrs={'width':['180'], 'alt':['按圖放大']}), # images for source from life.mingpao.com
+                          dict(attrs={'class':['images']})   # for images from txt
                           ]
         if __KeepImages__:
             remove_tags = [dict(name='style'),
@@ -230,12 +238,20 @@ class MPRecipe(BasicNewsRecipe):
                                            (u'\u570b\u969b World', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalta', 'nal'),
                                            (u'\u7d93\u6fdf Finance', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalea', 'nal'),
                                            (u'\u9ad4\u80b2 Sport', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalsp', 'nal'),
-                                           (u'\u5f71\u8996 Film/TV', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalma', 'nal'),
+                                           (u'\u5f71\u8996 Film/TV', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalma', 'nal')
-                                           (u'\u5c08\u6b04 Columns', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=ncolumn', 'ncl')]:
+                                          ]:
                     articles = self.parse_section2(url, keystr)
                     if articles:
                         feeds.append((title, articles))
 
+                if __InclCols__ == True:
+                    # parse column section articles directly from .txt files
+                    for title, url, keystr in [(u'\u5c08\u6b04 Columns', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=ncolumn', 'ncl')
+                                              ]:
+                        articles = self.parse_section2_txt(url, keystr)
+                        if articles:
+                            feeds.append((title, articles))
+
                 for title, url in [(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)
@@ -356,6 +372,24 @@ class MPRecipe(BasicNewsRecipe):
         current_articles.reverse()
         return current_articles
 
+    # parse from text file of life.mingpao.com
+    def parse_section2_txt(self, url, keystr):
+        self.get_fetchdate()
+        soup = self.index_to_soup(url)
+        a = soup.findAll('a', href=True)
+        a.reverse()
+        current_articles = []
+        included_urls = []
+        for i in a:
+            title = self.tag_to_string(i)
+            url = 'http://life.mingpao.com/cfm/' + i.get('href', False)
+            if (url not in included_urls) and (not url.rfind('.txt') == -1) and (not url.rfind(keystr) == -1):
+                url = url.replace('cfm/dailynews3.cfm?File=', 'ftp/Life3/')  # use printed version of the article
+                current_articles.append({'title': title, 'url': url, 'description': ''})
+                included_urls.append(url)
+        current_articles.reverse()
+        return current_articles
+
     # parse from www.mingpaovan.com
     def parse_section3(self, url, baseUrl):
         self.get_fetchdate()
@@ -438,6 +472,39 @@ class MPRecipe(BasicNewsRecipe):
         current_articles.reverse()
         return current_articles
 
+    # preprocess those .txt based files
+    def preprocess_raw_html(self, raw_html, url):
+        if url.rfind('ftp') == -1:
+            return raw_html
+        else:
+            splitter = re.compile(r'\n') # Match non-digits
+            new_raw_html = '<html><head><title>Untitled</title></head><body><div class="images">'
+            next_is_img_txt = False
+            title_started = False
+            met_article_start_char = False
+            for item in splitter.split(raw_html):
+                if item.startswith(u'\u3010'):
+                    met_article_start_char = True
+                    new_raw_html = new_raw_html + '</div><div class="content"><p>' + item + '<p>\n'
+                else:
+                    if next_is_img_txt == False:
+                        if item.startswith('='):
+                            next_is_img_txt = True
+                            new_raw_html += '<img src="' + str(item)[1:].strip() + '.jpg" /><p>\n'
+                        else:
+                            if met_article_start_char == False:
+                                if title_started == False:
+                                    new_raw_html = new_raw_html + '</div><div class="heading">' + item + '\n'
+                                    title_started = True
+                                else:
+                                    new_raw_html = new_raw_html + item + '\n'
+                            else:
+                                new_raw_html = new_raw_html + item + '<p>\n'
+                    else:
+                        next_is_img_txt = False
+                        new_raw_html = new_raw_html + item + '\n'
+            return new_raw_html + '</div></body></html>'
+
     def preprocess_html(self, soup):
         for item in soup.findAll(style=True):
             del item['style']
@@ -591,4 +658,3 @@ class MPRecipe(BasicNewsRecipe):
 
         with nested(open(opf_path, 'wb'), open(ncx_path, 'wb')) as (opf_file, ncx_file):
             opf.render(opf_file, ncx_file)
-

recipes/nikkei_news.recipe

@@ -37,24 +37,24 @@ class NikkeiNet_paper_subscription(BasicNewsRecipe):
         #br.set_debug_responses(True)
 
         if self.username is not None and self.password is not None:
-            print "----------------------------open top page----------------------------------------"
+            print "-------------------------open top page-------------------------------------"
             br.open('http://www.nikkei.com/')
-            print "----------------------------open first login form--------------------------------"
+            print "-------------------------open first login form-----------------------------"
             link = br.links(url_regex="www.nikkei.com/etc/accounts/login").next()
             br.follow_link(link)
             #response = br.response()
             #print response.get_data()
-            print "----------------------------JS redirect(send autoPostForm)-----------------------"
+            print "-------------------------JS redirect(send autoPostForm)--------------------"
             br.select_form(name='autoPostForm')
             br.submit()
             #response = br.response()
-            print "----------------------------got login form---------------------------------------"
+            print "-------------------------got login form------------------------------------"
             br.select_form(name='LA0210Form01')
             br['LA0210Form01:LA0210Email']    = self.username
             br['LA0210Form01:LA0210Password'] = self.password
             br.submit()
             #response = br.response()
-            print "----------------------------JS redirect------------------------------------------"
+            print "-------------------------JS redirect---------------------------------------"
             br.select_form(nr=0)
             br.submit()
 
@@ -64,18 +64,23 @@ class NikkeiNet_paper_subscription(BasicNewsRecipe):
         return br
 
     def cleanup(self):
-        print "----------------------------logout-----------------------------------------------"
+        print "-------------------------logout--------------------------------------------"
         self.browser.open('https://regist.nikkei.com/ds/etc/accounts/logout')
 
     def parse_index(self):
-        print "----------------------------get index of paper-----------------------------------"
+        print "-------------------------get index of paper--------------------------------"
         result = []
         soup = self.index_to_soup('http://www.nikkei.com/paper/')
         #soup = self.index_to_soup(self.test_data())
-        for sect in soup.findAll('div', 'cmn-section kn-special JSID_baseSection'):
+        sections = soup.findAll('div', 'cmn-section kn-special JSID_baseSection')
+	if len(sections) == 0:
+            sections = soup.findAll('div', 'cmn-section kn-special')
+        for sect in sections:
             sect_title = sect.find('h3', 'cmnc-title').string
             sect_result = []
             for elem in sect.findAll(attrs={'class':['cmn-article_title']}):
+                if elem.span.a == None  or  elem.span.a['href'].startswith('javascript') :
+                    continue
                 url = 'http://www.nikkei.com' + elem.span.a['href']
                 url = re.sub("/article/", "/print-article/", url) # print version.
                 span = elem.span.a.span
@@ -84,6 +89,5 @@ class NikkeiNet_paper_subscription(BasicNewsRecipe):
                     sect_result.append(dict(title=title, url=url, date='',
                                             description='', content=''))
             result.append([sect_title, sect_result])
-        #pp.pprint(result)
         return result
 

recipes/ntv_spor.recipe

@@ -0,0 +1,34 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class AdvancedUserRecipe1313512459(BasicNewsRecipe):
+    title          = u'NTVSpor'
+    __author__            = 'A Erdogan'
+    description           = 'News from Turkey'
+    publisher             = 'NTVSpor.net'
+    category              = 'sports, Turkey'
+    oldest_article        = 7
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    masthead_url          = 'http://www.ntvspor.net/HTML/r/i/l.png'
+    language              = 'tr'
+
+    extra_css             ='''
+                        body{font-family:Arial,Helvetica,sans-serif; font-size:small; align:left;  color:#000000}
+                        h1{font-size:large; color:#000000}
+ 	    h2{font-size:small; color:#000000}
+	    p{font-size:small; color:#000000}
+                     '''
+
+    conversion_options = {
+                          'comment'   : description
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
+                        }
+
+    remove_tags = [dict(name=['embed','il','ul','iframe','object','link','base']), dict(name='div', attrs={'id':'contentPhotoGallery'}), dict(name='div', attrs={'class':'SocialMediaWrapper'}), dict(name='div', attrs={'class':'grid2'}), dict(name='div', attrs={'class':'grid8'}), dict(name='div', attrs={'id':'anonsBar'}), dict(name='div', attrs={'id':'header'})]
+    remove_tags_before = dict(name='h1', attrs={'style':['margin-top: 6px;']})
+    remove_tags_after = dict(name='div', attrs={'id':'newsBody'})
+    feeds          = [(u'NTVSpor', u'http://www.ntvspor.net/Rss/anasayfa')]
+

recipes/ntv_tr.recipe

@@ -0,0 +1,45 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class NTVMSNBC(BasicNewsRecipe):
+    title          = u'NTV'
+    __author__            = 'A Erdogan'
+    description           = 'News from Turkey'
+    publisher             = 'NTV'
+    category              = 'news, politics, Turkey'
+    oldest_article        = 7
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    masthead_url          = 'http://www.ntvmsnbc.com/images/MSNBC/msnbc_ban.gif'
+    language              = 'tr'
+
+
+    remove_tags_before = dict(name='h1')
+    remove_tags_after = dict(attrs={'id':'haberDetayYazi'})
+    extra_css             ='''
+                        body{font-family:Arial,Helvetica,sans-serif; font-size:small; align:left;  color:#000000}
+                        h1{font-size:large; color:#000000}
+ 	    h2{font-size:small; color:#000000}
+	    p{font-size:small; color:#000000}
+                     '''
+
+    conversion_options = {
+                          'comment'   : description
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
+                        }
+
+    remove_tags = [dict(name=['embed','il','ul','iframe','object','link','base']), dict(name='div', attrs={'style':['padding: 0pt 10px 10px;']}), dict(name='div', attrs={'style':['padding: 0pt 10px 10px;']}),  dict(name='div', attrs={'class':['textSmallGrey w320']}), dict(name='div', attrs={'style':['font-family:Arial; font-size:16px;font-weight:bold; font-color:#003366; margin-bottom:20px; margin-top:20px; border-bottom:solid 1px;border-color: #CCC; padding-bottom:2px;']})]
+    remove_tags_before = dict(name='h1')
+    remove_tags_after = dict(name='div', attrs={'style':['font-family:Arial; font-size:16px;font-weight:bold; font-color:#003366; margin-bottom:20px; margin-top:20px; border-bottom:solid 1px;border-color: #CCC; padding-bottom:2px;']})
+
+    feeds          = [(u'NTV', u'http://www.ntvmsnbc.com/id/3032091/device/rss/rss.xml')]
+
+    def print_version(self, url):
+        articleid = url.rpartition('/id/')[2]
+        return 'http://www.ntvmsnbc.com/id/' + articleid + '/print/1/displaymode/1098/'
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)
+

recipes/pagina_12_print_ed.recipe

@@ -0,0 +1,95 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
+'''
+pagina12.com.ar
+'''
+import re
+
+from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.ebooks.BeautifulSoup import Tag, NavigableString
+
+class Pagina12(BasicNewsRecipe):
+
+    title      = 'Pagina/12 - Edicion Impresa'
+    __author__ = 'Pablo Marfil'
+    description = 'Diario argentino'
+    INDEX = 'http://www.pagina12.com.ar/diario/secciones/index.html'
+    language = 'es'
+    encoding              = 'cp1252'
+    remove_tags_before = dict(id='fecha')
+    remove_tags_after  = dict(id='fin')
+    remove_tags        = [dict(id=['fecha', 'fin', 'pageControls','logo','logo_suple','fecha_suple','volver'])]
+    masthead_url          = 'http://www.pagina12.com.ar/commons/imgs/logo-home.gif'
+    no_stylesheets = True
+
+    preprocess_regexps= [(re.compile(r'<!DOCTYPE[^>]+>', re.I), lambda m:'')]
+
+
+
+
+    def get_cover_url(self):
+        soup = self.index_to_soup('http://www.pagina12.com.ar/diario/principal/diario/index.html')
+        for image in soup.findAll('img',alt=True):
+           if image['alt'].startswith('Tapa de la fecha'):
+              return image['src']
+              print image
+        return None
+
+
+    def parse_index(self):
+        articles = []
+        numero = 1
+        raw = self.index_to_soup('http://www.pagina12.com.ar/diario/secciones/index.html', raw=True)
+        raw = re.sub(r'(?i)<!DOCTYPE[^>]+>', '', raw)
+        soup = self.index_to_soup(raw)
+
+        feeds = []
+
+        seen_titles = set([])
+        for section in soup.findAll('div','seccionx'):
+            numero+=1
+            print (numero)
+            section_title = self.tag_to_string(section.find('div','desplegable_titulo on_principal right'))
+            self.log('Found section:', section_title)
+            articles = []
+            for post in section.findAll('h2'):
+                h = post.find('a', href=True)
+                title = self.tag_to_string(h)
+                if title in seen_titles:
+                    continue
+                seen_titles.add(title)
+                a = post.find('a', href=True)
+                url = a['href']
+                if url.startswith('/'):
+                    url = 'http://pagina12.com.ar/imprimir'+url
+                p = post.find('div', attrs={'h2'})
+                desc = None
+                self.log('\tFound article:', title, 'at', url)
+                if p is not None:
+                    desc = self.tag_to_string(p)
+                    self.log('\t\t', desc)
+                articles.append({'title':title, 'url':url, 'description':desc,
+                    'date':''})
+            if articles:
+                feeds.append((section_title, articles))
+        return feeds
+
+
+    def postprocess_html(self, soup, first):
+        for table in soup.findAll('table', align='right'):
+            img = table.find('img')
+            if img is not None:
+                img.extract()
+                caption = self.tag_to_string(table).strip()
+                div = Tag(soup, 'div')
+                div['style'] = 'text-align:center'
+                div.insert(0, img)
+                div.insert(1, Tag(soup, 'br'))
+                if caption:
+                    div.insert(2, NavigableString(caption))
+                table.replaceWith(div)
+
+        return soup
+

recipes/pc_world.recipe

@@ -51,14 +51,13 @@ class pcWorld(BasicNewsRecipe):
     keep_only_tags     = [
                             dict(name='div', attrs={'class':'article'})
                         ]
-
     remove_tags        = [
                             dict(name='div', attrs={'class':['toolBar','mac_tags','toolBar  btmTools','recommend longRecommend','recommend shortRecommend','textAds']}),
                             dict(name='div', attrs={'id':['sidebar','comments','mac_tags']}),
-                            dict(name='ul', attrs={'class':'tools'}),
+                            dict(name='ul', attrs={'class':['tools', 'tools clearfix']}),
-                            dict(name='li', attrs={'class':'sub'})
+                            dict(name='li', attrs={'class':'sub'}),
+                            dict(name='p', attrs={'id':'userDesire'})
                         ]
-
     feeds          = [
                        (u'PCWorld Headlines', u'http://feeds.pcworld.com/pcworld/latestnews'),
                        (u'How-To', u'http://feeds.pcworld.com/pcworld/update/howto'),

recipes/people_us_mashup.recipe

@@ -14,54 +14,11 @@ class PeopleMag(BasicNewsRecipe):
     use_embedded_content  = False
     oldest_article = 2
     max_articles_per_feed = 50
+    use_embedded_content = False
 
-    extra_css = '''
+    no_stylesheets = True
-        h1{font-family:verdana,arial,helvetica,sans-serif; font-size: large;}
+    auto_cleanup = True
-        h2{font-family:verdana,arial,helvetica,sans-serif; font-size: small;}
+    auto_cleanup_keep = '//div[@id="article-image"]'
-        .body-content{font-family:verdana,arial,helvetica,sans-serif; font-size: small;}
-        .byline {font-size: small; color: #666666; font-style:italic; }
-        .lastline {font-size: small; color: #666666; font-style:italic;}
-        .contact {font-size: small; color: #666666;}
-        .contact p {font-size: small; color: #666666;}
-        .photoCaption { font-family:verdana,arial,helvetica,sans-serif; font-size:x-small;}
-        .photoCredit{ font-family:verdana,arial,helvetica,sans-serif; font-size:x-small; color:#666666;}
-        .article_timestamp{font-size:x-small; color:#666666;}
-        a {font-family:verdana,arial,helvetica,sans-serif; font-size: x-small;}
-                '''
-
-
-    keep_only_tags = [
-              dict(name='div', attrs={'class': 'panel_news_article_main'}), 	
-	        dict(name='div', attrs={'class':'article_content'}),
-              dict(name='div', attrs={'class': 'headline'}),
-              dict(name='div', attrs={'class': 'post'}),
-              dict(name='div', attrs={'class': 'packageheadlines'}),
-              dict(name='div', attrs={'class': 'snap_preview'}),
-              dict(name='div', attrs={'id': 'articlebody'})
-                   ]
-
-    remove_tags = [
-         dict(name='div', attrs={'class':'share_comments'}),
-         dict(name='p', attrs={'class':'twitter_facebook'}),
-         dict(name='div', attrs={'class':'share_comments_bottom'}),
-         dict(name='h2', attrs={'id':'related_content'}),
-   	   dict(name='div', attrs={'class':'next_article'}),
-	   dict(name='div', attrs={'class':'prev_article'}),
-           dict(name='ul', attrs={'id':'sharebar'}),
-         dict(name='div', attrs={'class':'sharelinkcont'}),
-         dict(name='div', attrs={'class':'categories'}),
-         dict(name='ul', attrs={'class':'categories'}),
-         dict(name='div', attrs={'class':'related_content'}),
-         dict(name='div', attrs={'id':'promo'}),
-         dict(name='div', attrs={'class':'linksWrapper'}),
-         dict(name='p', attrs={'class':'tag tvnews'}),
-        dict(name='p', attrs={'class':'tag movienews'}),
-        dict(name='p', attrs={'class':'tag musicnews'}),
-        dict(name='p', attrs={'class':'tag couples'}),
-        dict(name='p', attrs={'class':'tag gooddeeds'}),
-        dict(name='p', attrs={'class':'tag weddings'}),
-        dict(name='p', attrs={'class':'tag health'})
-]
 
 
     feeds = [
@@ -69,26 +26,4 @@ class PeopleMag(BasicNewsRecipe):
         ('US Headlines', 'http://www.usmagazine.com/celebrity_news/rss')
         ]
 
-    def get_article_url(self, article):
-        ans = article.link
 
-        try:
-            self.log('Looking for full story link in', ans)
-            soup = self.index_to_soup(ans)
-            x = soup.find(text="View All")
-
-            if x is not None:
-                ans = ans + '?viewAll=y'
-                self.log('Found full story link', ans)
-        except:
-            pass
-        return ans
-
-    def postprocess_html(self, soup,first):
-
-         for tag in soup.findAll(name='div',attrs={'class':"container_ate_qandatitle"}):
-                tag.extract()
-         for tag in soup.findAll(name='br'):
-                tag.extract()
-
-         return soup

recipes/philly.recipe

@@ -1,45 +1,35 @@
-#!/usr/bin/env  python
 from calibre.web.feeds.news import BasicNewsRecipe
 
-class AdvancedUserRecipe1308312288(BasicNewsRecipe):
+class BasicUserRecipe1314970845(BasicNewsRecipe):
     title          = u'Philadelphia Inquirer'
-    __author__ = 'sexymax15'
+    oldest_article = 3
-    language = 'en'
+    max_articles_per_feed = 50
-    description = 'Daily news from the Philadelphia Inquirer'
+    auto_cleanup = True
-    oldest_article = 15
+    language=  'en'
-    max_articles_per_feed = 20
+    __author__ = 'bing'
-    use_embedded_content = False
+    requires_version = (0, 8, 16)
-    remove_empty_feeds = True
-    no_stylesheets = True
-    remove_javascript = True
 
-   # remove_tags_before = {'class':'article_timestamp'}
+    feeds          = [
-    #remove_tags_after = {'class':'graylabel'}
+            (u'Front Page', u'http://www.philly.com/inquirer_front_page.rss'),
-    keep_only_tags= [dict(name=['h1','p'])]
+            (u'Philly.com News', u'http://www.philly.com/philly_news.rss'),
-    remove_tags = [dict(name=['hr','dl','dt','img','meta','iframe','link','script','form','input','label']),
+            (u'National/World (Philly.com)', u'http://www.philly.com/philly_news_nation.rss'),
-dict(id=['toggleConfirmEmailDiv','toggleTOS','toggleUsernameMsgDiv','toggleConfirmYear','navT1_philly','secondaryNav','navPlacement','globalPrimaryNav'
+            (u'Politics (Philly.com)', u'http://www.philly.com/philly_politics.rss'),
-,'ugc-footer-philly','bv_footer_include','footer','header',
+            (u'Local (Philly.com)', u'http://www.philly.com/philly_news_local.rss'),
-'container_rag_bottom','section_rectangle','contentrightside'])
+            (u'South Jersey News', u'http://www.philly.com/inq_news_south_jersey.rss'),
-,{'class':['megamenu3 megamenu','container misc','container_inner misc_inner'
+            (u'Sports', u'http://www.philly.com/inquirer_sports.rss'),
-,'misccontainer_left_32','headlineonly','misccontainer_middle_32'
+            (u'Tech News', u'http://www.philly.com/philly_tech.rss'),
-,'misccontainer_right_32','headline formBegin',
+            (u'Daily Magazine', u'http://www.philly.com/inq_magazine_daily.rss'),
-'post_balloon','relatedlist','linkssubhead','b_sq','dotted-rule-above'
+            (u'Weekend', u'http://www.philly.com/inq_entertainment_weekend.rss'),
-,'container','headlines-digest','graylabel','container_inner'
+            (u'Business', u'http://www.philly.com/inq_business.rss'),
-,'rlinks_colorbar1','rlinks_colorbar2','supercontainer','container_5col_left','container_image_left',
+            (u'Education', u'http://www.philly.com/inquirer_education.rss'),
-'digest-headline2','digest-lead','container_5col_leftmiddle',
+            (u'Books', u'http://www.philly.com/inq_books.rss'),
-'container_5col_middlemiddle','container_5col_rightmiddle'
+            (u'Entertainment', u'http://www.philly.com/inq_entertainment.rss'),
-,'container_5col_right','divclear','supercontainer_outer force-width',
+            (u'Food', u'http://www.philly.com/inq_food.rss'),
-'supercontainer','containertitle  kicker-title',
+            (u'Health and Science', u'http://www.philly.com/inquirer_health_science.rss'),
-'pollquestion','pollchoice','photomore','pollbutton','container rssbox','containertitle video ',
+            (u'Home and Design', u'http://www.philly.com/inq_home_design.rss'),
-'containertitle_image ','container_tabtwo','selected'
+            (u'News Columnists', u'http://www.philly.com/inq_columnists.rss'),
-,'shadetabs','selected','tabcontentstyle','tabcontent','inner_container'
+            (u'Editorial', u'http://www.philly.com/inq_news_editorial.rss'),
-,'arrow','container_ad','containertitlespacer','adUnit','tracking','sitemsg_911 clearfix']}]
+            (u'Travel', u'http://www.philly.com/inquirer_travel.rss'),
-
+            (u'Obituaries', u'http://www.philly.com/inquirer_obituaries.rss')
-    extra_css             = """
+    ]
-                               h1{font-family: Georgia,serif; font-size: xx-large}
-
-                            """
-
-
-    feeds          = [(u'News', u'http://www.philly.com/philly_news.rss')]
 

recipes/rtnews.recipe

@@ -0,0 +1,64 @@
+__license__   = 'GPL v3'
+__copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>'
+'''
+rt.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class RT_eng(BasicNewsRecipe):
+    title                 = 'RT in English'
+    __author__            = 'Darko Miletic'
+    description           = 'RT is the first Russian 24/7 English-language news channel which brings the Russian view on global news.'
+    publisher             = 'Autonomous Nonprofit Organization "TV-Novosti"'
+    category              = 'news, politics, economy, finances, Russia, world'
+    oldest_article        = 2
+    no_stylesheets        = True
+    encoding              = 'utf8'
+    masthead_url          = 'http://rt.com/s/css/img/printlogo.gif'
+    use_embedded_content  = False
+    remove_empty_feeds    = True
+    language              = 'en_RU'
+    publication_type      = 'newsportal'
+    extra_css             = """
+                                body{font-family: Arial,Helvetica,sans-serif}
+                                h1{font-family: Georgia,"Times New Roman",Times,serif}
+                                .grey{color: gray}
+                                .fs12{font-size: small}
+                            """
+
+
+    conversion_options = {
+                          'comment'  : description
+                        , 'tags'     : category
+                        , 'publisher': publisher
+                        , 'language' : language
+                        }
+
+    keep_only_tags    = [dict(name='div', attrs={'class':'all'})]
+    remove_tags       = [
+                           dict(name=['object','link','embed','iframe','meta','link'])
+                          ,dict(attrs={'class':'crumbs oh'})
+                        ]
+    remove_attributes = ['clear']
+
+    feeds = [
+               (u'Politics'   , u'http://rt.com/politics/rss/'            )
+              ,(u'USA'        , u'http://rt.com/usa/news/rss/'            )
+              ,(u'Business'   , u'http://rt.com/business/news/rss/'       )
+              ,(u'Sport'      , u'http://rt.com/sport/rss/'               )
+              ,(u'Art&Culture', u'http://rt.com/art-and-culture/news/rss/')
+            ]
+
+    def print_version(self, url):
+        return url + 'print/'
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        for item in soup.findAll('a'):
+            str = item.string
+            if str is None:
+               str = self.tag_to_string(item)
+            item.replaceWith(str)
+        return soup

recipes/staradvertiser.recipe

@@ -1,5 +1,5 @@
 __license__   = 'GPL v3'
-__copyright__ = '2009-2011, Darko Miletic <darko.miletic at gmail.com>'
+__copyright__ = '2011, M. Ching modified from work 2009-2011 Darko Miletic <darko.miletic at gmail.com>'
 '''
 staradvertiser.com
 '''
@@ -7,12 +7,13 @@ staradvertiser.com
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Starbulletin(BasicNewsRecipe):
-    title                 = 'Honolulu Star Advertiser'
+    title                 = 'Honolulu Star-Advertiser'
     __author__            = 'Darko Miletic'
     description           = 'Latest national and local Hawaii sports news'
     publisher             = 'Honolulu Star-Advertiser'
     category              = 'news, Honolulu, Hawaii'
     oldest_article        = 2
+    needs_subscription    = True
     max_articles_per_feed = 100
     language              = 'en'
     no_stylesheets        = True
@@ -20,12 +21,12 @@ class Starbulletin(BasicNewsRecipe):
     encoding              = 'utf8'
     publication_type      = 'newspaper'
     masthead_url          = 'http://media.staradvertiser.com/designimages/star-advertiser-logo-small.gif'
-    extra_css             = """ 
+#    extra_css             = """
-                                body{font-family: Verdana,Arial,Helvetica,sans-serif} 
+#                                body{font-family: Verdana,Arial,Helvetica,sans-serif}
-                                h1,.brown,.postCredit{color: #663300} 
+#                                h1,.brown,.hsa_postCredit{color: #663300}
-                                .storyDeck{font-size: 1.2em; font-weight: bold}
+#                                .storyDeck{font-size: 1.2em; font-weight: bold}
-                                img{display: block}
+#                                img{display: block}
-                            """
+#                            """
 
     conversion_options = {
                           'comment'          : description
@@ -35,26 +36,38 @@ class Starbulletin(BasicNewsRecipe):
                         , 'linearize_tables' : True
                         }
     keep_only_tags = [
-                         dict(attrs={'id':'storyTitle'})
+                         dict(attrs={'id':'hsa_storyTitle'})
-                        ,dict(attrs={'class':['storyDeck','postCredit']})
+			,dict(attrs={'id':'hsa_storyTitle article-important'})
-                        ,dict(name='span',attrs={'class':'brown'})
+                        ,dict(attrs={'class':['hsa_dateStamp','hsa_postCredit','storyDeck']})
+                        ,dict(name='span',attrs={'class':['hsa_dateStamp','hsa_postCredit']})
+			,dict(name='span',attrs={'class':['hsa_dateStamp article-important','hsa_postCredit article-important']})
+                        ,dict(name='div',attrs={'class':'storytext article-important'})
                         ,dict(name='div',attrs={'class':'storytext'})
                      ]
     remove_tags = [
-                     dict(name=['object','link','script','span','meta','base','iframe'])
+                     dict(name=['object','link','script','meta','base','iframe'])
+# removed 'span' from preceding list to permit keeping of author and timestamp
                     ,dict(attrs={'class':['insideStoryImage','insideStoryAd']})
 					,dict(attrs={'name':'fb_share'})
                   ]
 
-    feeds = [
+    def get_browser(self):
-              (u'Headlines' , u'http://www.staradvertiser.com/staradvertiser_headlines.rss' )
+        br = BasicNewsRecipe.get_browser()
-             ,(u'News'      , u'http://www.staradvertiser.com/news/index.rss'               )
+        if self.username is not None and self.password is not None:
-             ,(u'Sports'    , u'http://www.staradvertiser.com/sports/index.rss'             )
+            br.open('http://www.staradvertiser.com/manage/Login/')
-             ,(u'Features'  , u'http://www.staradvertiser.com/features/index.rss'           )
+            br.select_form(name='loginForm')
-             ,(u'Editorials', u'http://www.staradvertiser.com/editorials/index.rss'         )
+            br['email']   = self.username
-             ,(u'Business'  , u'http://www.staradvertiser.com/business/index.rss'           )
+            br['password'] = self.password
-             ,(u'Travel'    , u'http://www.staradvertiser.com/travel/index.rss'             )
+            br.submit()
-            ]
+        return br
+
+    feeds          = [
+		       (u'Breaking News', u'http://www.staradvertiser.com/news/breaking/index.rss')
+		      ,(u'News', u'http://www.staradvertiser.com/newspremium/index.rss')
+		      ,(u'Business', u'http://www.staradvertiser.com/businesspremium/index.rss')
+		      ,(u'Sports', u'http://www.staradvertiser.com/sportspremium/index.rss')
+		      ,(u'Features', u'http://www.staradvertiser.com/featurespremium/index.rss')
+		     ]
 
     def preprocess_html(self, soup):
         for item in soup.findAll(style=True):
@@ -75,4 +88,4 @@ class Starbulletin(BasicNewsRecipe):
             if not item.has_key('alt'):
                item['alt'] = 'image'
         return soup
-            
+

recipes/tablety_pl.recipe

@@ -0,0 +1,12 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Tablety_pl(BasicNewsRecipe):
+    title          = u'Tablety.pl'
+    __author__        = 'fenuks'
+    description   = u'tablety.pl - latest tablet news'
+    cover_url      = 'http://www.tablety.pl/wp-content/themes/kolektyw/img/logo.png'
+    category       = 'IT'
+    language       = 'pl'
+    oldest_article = 8
+    max_articles_per_feed = 100
+    feeds          = [(u'Najnowsze posty', u'http://www.tablety.pl/feed/')]

recipes/taipei.recipe

@@ -0,0 +1,30 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class TN(BasicNewsRecipe):
+    title          = u'Taipei Times'
+    language       = 'en_CN'
+    __author__     = 'Krittika Goyal'
+    oldest_article = 1 #days
+    max_articles_per_feed = 25
+    use_embedded_content = False
+
+    no_stylesheets = True
+    auto_cleanup = True
+    auto_cleanup_keep = '//*[@class="main_ipic"]'
+
+    feeds          = [
+('Editorials',
+ 'http://www.taipeitimes.com/xml/editorials.rss'),
+('Taiwan',
+ 'http://www.taipeitimes.com/xml/taiwan.rss'),
+('Features',
+ 'http://www.taipeitimes.com/xml/feat.rss'),
+('Business',
+ 'http://www.taipeitimes.com/xml/biz.rss'),
+('World',
+ 'http://www.taipeitimes.com/xml/world.rss'),
+('Sports',
+ 'http://www.taipeitimes.com/xml/sport.rss'),
+]
+
+

recipes/time_magazine.recipe

@@ -15,12 +15,12 @@ class Time(BasicNewsRecipe):
     #        ' publish complete articles on the web.')
     title                 = u'Time'
     __author__            = 'Kovid Goyal'
-    description           = 'Weekly magazine'
+    description           = ('Weekly US magazine.')
     encoding = 'utf-8'
     no_stylesheets        = True
     language = 'en'
     remove_javascript     = True
-
+    #needs_subscription = 'optional'
 
     keep_only_tags = [
             {
@@ -41,6 +41,21 @@ class Time(BasicNewsRecipe):
     preprocess_regexps = [(re.compile(
         r'<meta .+/>'), lambda m:'')]
 
+    def get_browser(self):
+        br = BasicNewsRecipe.get_browser(self)
+        if False and self.username and self.password:
+            # This site uses javascript in its login process
+            res = br.open('http://www.time.com/time/magazine')
+            br.select_form(nr=1)
+            br['username'] = self.username
+            br['password'] = self.password
+            res = br.submit()
+            raw = res.read()
+            if '>Log Out<' not in raw:
+                raise ValueError('Failed to login to time.com, check'
+                        ' your username and password')
+        return br
+
     def parse_index(self):
         raw = self.index_to_soup('http://www.time.com/time/magazine', raw=True)
         root = html.fromstring(raw)

recipes/twitchfilms.recipe

@@ -1,12 +1,9 @@
-#!/usr/bin/env  python
-
 __license__   = 'GPL v3'
-__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+__copyright__ = '2009-2011, Darko Miletic <darko.miletic at gmail.com>'
 '''
-twitchfilm.net/site/
+twitchfilm.net/news/
 '''
 from calibre.web.feeds.news import BasicNewsRecipe
-from calibre.ebooks.BeautifulSoup import Tag
 
 class Twitchfilm(BasicNewsRecipe):
     title                 = 'Twitch Films'
@@ -15,29 +12,46 @@ class Twitchfilm(BasicNewsRecipe):
     oldest_article        = 30
     max_articles_per_feed = 100
     no_stylesheets        = True
-    use_embedded_content  = True
+    use_embedded_content  = False
     encoding              = 'utf-8'
     publisher             = 'Twitch'
+    masthead_url          = 'http://twitchfilm.com/img/logo.png'
     category              = 'twitch, twitchfilm, movie news, movie reviews, cult cinema, independent cinema, anime, foreign cinema, geek talk'
-    language = 'en'
+    language              = 'en'
-
-    lang                  = 'en-US'
 
     conversion_options = {
-                          'comment'          : description
+                          'comment'  : description
-                        , 'tags'             : category
+                        , 'tags'     : category
-                        , 'publisher'        : publisher
+                        , 'publisher': publisher
-                        , 'language'         : lang
+                        , 'language' : language
-                        , 'pretty_print'     : True
                         }
 
-    remove_tags = [dict(name='div', attrs={'class':'feedflare'})]
+    keep_only_tags=[dict(attrs={'class':'asset-header'})]
+    remove_tags_after=dict(attrs={'class':'asset-body'})
+    remove_tags = [  dict(name='div', attrs={'class':['social','categories']})
+                   , dict(attrs={'id':'main-asset'})
+                   , dict(name=['meta','link','iframe','embed','object'])
+                  ]
 
-    feeds = [(u'News', u'http://feedproxy.google.com/TwitchEverything')]
+    feeds = [(u'News', u'http://feeds.twitchfilm.net/TwitchEverything')]
 
     def preprocess_html(self, soup):
-        mtag = Tag(soup,'meta',[('http-equiv','Content-Type'),('context','text/html; charset=utf-8')])
+        for item in soup.findAll(style=True):
-        soup.head.insert(0,mtag)
+            del item['style']    
-        soup.html['lang'] = self.lang
+        for item in soup.findAll('a'):
-        return self.adeify_images(soup)
+            limg = item.find('img')
+            if item.string is not None:
+               str = item.string
+               item.replaceWith(str)
+            else:
+               if limg:
+                  item.name = 'div'
+                  item.attrs = []
+               else:
+                   str = self.tag_to_string(item)
+                   item.replaceWith(str)
+        for item in soup.findAll('img'):
+            if not item.has_key('alt'):
+               item['alt'] = 'image'
+        return soup
 

recipes/ubuntu_pl.recipe

@@ -0,0 +1,16 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Ubuntu_pl(BasicNewsRecipe):
+    title          = u'UBUNTU.pl'
+    __author__        = 'fenuks'
+    description   = 'UBUNTU.pl - polish ubuntu community site'
+    cover_url      = 'http://ubuntu.pl/img/logo.jpg'
+    category       = 'linux, IT'
+    language       = 'pl'
+    no_stylesheets = True
+    oldest_article = 8
+    max_articles_per_feed = 100
+    extra_css      = '#main {text-align:left;}'
+    keep_only_tags= [dict(name='td', attrs={'class':'teaser-node-mc'}), dict(name='h3', attrs={'class':'entry-title'}), dict(name='div', attrs={'class':'entry-content'})]
+    remove_tags_after= [dict(name='div' , attrs={'class':'content'})]
+    feeds          = [('Czytelnia Ubuntu', 'http://feeds.feedburner.com/ubuntu-czytelnia'), (u'WikiGames', u'http://feeds.feedburner.com/WikiGames')]

recipes/usatoday.recipe

@@ -13,6 +13,7 @@ class USAToday(BasicNewsRecipe):
     title = 'USA Today'
     __author__ = 'Kovid Goyal'
     oldest_article = 1
+    publication_type = 'newspaper'
     timefmt  = ''
     max_articles_per_feed = 20
     language = 'en'

recipes/wsj.recipe

@@ -94,9 +94,11 @@ class WallStreetJournal(BasicNewsRecipe):
         if date is not None:
             self.timefmt = ' [%s]'%self.tag_to_string(date)
 
-        cov = soup.find('a', attrs={'class':'icon pdf'}, href=True)
+        cov = soup.find('div', attrs={'class':'itpSectionHeaderPdf'})
         if cov is not None:
-            self.cover_url = cov['href']
+            a = cov.find('a', href=True)
+            if a is not None:
+                self.cover_url = a['href']
 
         feeds = []
         div = soup.find('div', attrs={'class':'itpHeader'})

resources/default_tweaks.py

@@ -61,18 +61,27 @@ authors_completer_append_separator = False
 # selecting 'manage authors', and pressing 'Recalculate all author sort values'.
 # The author name suffixes are words that are ignored when they occur at the
 # end of an author name. The case of the suffix is ignored and trailing
-# periods are automatically handled.
+# periods are automatically handled. The same is true for prefixes.
 # The author name copy words are a set of words which if they occur in an
-# author name cause the automatically geenrated author sort string to be
+# author name cause the automatically generated author sort string to be
 # identical to the author name. This means that the sort for a string like Acme
 # Inc. will be Acme Inc. instead of Inc., Acme
 author_sort_copy_method = 'comma'
 author_name_suffixes = ('Jr', 'Sr', 'Inc', 'Ph.D', 'Phd',
                         'MD', 'M.D', 'I', 'II', 'III', 'IV',
                         'Junior', 'Senior')
+author_name_prefixes = ('Mr', 'Mrs', 'Ms', 'Dr', 'Prof')
 author_name_copywords = ('Corporation', 'Company', 'Co.', 'Agency', 'Council',
         'Committee', 'Inc.', 'Institute', 'Society', 'Club', 'Team')
 
+#: Splitting multiple author names
+# By default, calibre splits a string containing multiple author names on
+# ampersands and the words "and" and "with". You can customize the splitting
+# by changing the regular expression below. Strings are split on whatever the
+# specified regular expression matches.
+# Default: r'(?i),?\s+(and|with)\s+'
+authors_split_regex = r'(?i),?\s+(and|with)\s+'
+
 #: Use author sort in Tag Browser
 # Set which author field to display in the tags pane (the list of authors,
 # series, publishers etc on the left hand side). The choices are author and

resources/templates/rtf.xsl

@@ -98,7 +98,7 @@
                     <xsl:apply-templates/>
                </emph>
             </xsl:when>
-            <xsl:when test = "@underlined">
+            <xsl:when test = "@underlined and @underlined != 'false'">
                <emph rend = "paragraph-emph-underlined">
                     <xsl:apply-templates/>
                </emph>
@@ -220,7 +220,7 @@
     </xsl:template>
 
     <xsl:template name="parse-styles-attrs">
-        <!--<xsl:text>position:relative;</xsl:text>-->
+        <!--<xsl:text>position:relative;</xsl:text>
         <xsl:if test="@space-before">
             <xsl:text>padding-top:</xsl:text>
             <xsl:value-of select="@space-before"/>
@@ -230,7 +230,7 @@
             <xsl:text>padding-bottom:</xsl:text>
             <xsl:value-of select="@space-after"/>
             <xsl:text>pt;</xsl:text>
-        </xsl:if>
+        </xsl:if>-->
         <xsl:if test="@left-indent">
             <xsl:text>padding-left:</xsl:text>
             <xsl:value-of select="@left-indent"/>
@@ -256,15 +256,15 @@
             <xsl:value-of select="'italic'"/>
             <xsl:text>;</xsl:text>
         </xsl:if>
-        <xsl:if test="@underline and @underline != 'false'">
+        <xsl:if test="@underlined and @underlined != 'false'">
             <xsl:text>text-decoration:underline</xsl:text>
             <xsl:text>;</xsl:text>
         </xsl:if>
-        <xsl:if test="@line-spacing">
+        <!--<xsl:if test="@line-spacing">
             <xsl:text>line-height:</xsl:text>
             <xsl:value-of select="@line-spacing"/>
             <xsl:text>pt;</xsl:text>
-        </xsl:if>
+        </xsl:if>-->
         <xsl:if test="(@align = 'just')">
             <xsl:text>text-align: justify;</xsl:text>
         </xsl:if>
@@ -314,7 +314,6 @@
                     </xsl:attribute>
                     <xsl:apply-templates/>
                 </xsl:element>
-
             </xsl:otherwise>
         </xsl:choose>
     </xsl:template>
@@ -446,8 +445,15 @@
 
     <xsl:template match = "rtf:field[@type='hyperlink']">
         <xsl:element name ="a">
-            <xsl:attribute name = "href">
+            <xsl:attribute name = "href"><xsl:if test="not(contains(@link, '/'))">#</xsl:if><xsl:value-of select = "@link"/></xsl:attribute>
-               <xsl:value-of select = "@link"/>
+            <xsl:apply-templates/>
+        </xsl:element>
+    </xsl:template>
+	
+    <xsl:template match = "rtf:field[@type='bookmark-start']">
+        <xsl:element name ="a">
+            <xsl:attribute name = "id">
+               <xsl:value-of select = "@number"/>
             </xsl:attribute>
             <xsl:apply-templates/>
         </xsl:element>

setup/check.py

@@ -63,10 +63,10 @@ class Check(Command):
             for f in x[-1]:
                 y = self.j(x[0], f)
                 mtime = os.stat(y).st_mtime
-                if f.endswith('.py') and f not in ('ptempfile.py', 'feedparser.py',
+                if (f.endswith('.py') and f not in ('ptempfile.py', 'feedparser.py',
-                    'pyparsing.py', 'markdown.py') and \
+                    'pyparsing.py', 'markdown.py') and
-                    'genshi' not in y and cache.get(y, 0) != mtime and \
+                    'genshi' not in y and cache.get(y, 0) != mtime and
-                    'prs500/driver.py' not in y:
+                    'prs500/driver.py' not in y):
                         yield y, mtime
 
         for x in os.walk(self.j(self.d(self.SRC), 'recipes')):

setup/iso_639/bg.po

@@ -8,17 +8,18 @@
 msgid ""
 msgstr ""
 "Project-Id-Version: iso_639_3\n"
-"Report-Msgid-Bugs-To: Debian iso-codes team <pkg-isocodes-devel@lists.alioth."
+"Report-Msgid-Bugs-To: Debian iso-codes team <pkg-isocodes-"
-"debian.org>\n"
+"devel@lists.alioth.debian.org>\n"
-"POT-Creation-Date: 2011-05-27 14:59+0200\n"
+"POT-Creation-Date: 2011-09-02 16:21+0000\n"
-"PO-Revision-Date: 2011-07-10 19:40+0300\n"
+"PO-Revision-Date: 2011-08-27 04:12+0000\n"
-"Last-Translator: Roumen Petrov <transl@roumenpetrov.info>\n"
+"Last-Translator: Roumen Petrov <Unknown>\n"
 "Language-Team: Bulgarian <dict@fsa-bg.org>\n"
-"Language: bg\n"
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=UTF-8\n"
 "Content-Transfer-Encoding: 8bit\n"
-"Plural-Forms: nplurals=2; plural=(n != 1);\n"
+"X-Launchpad-Export-Date: 2011-09-03 04:56+0000\n"
+"X-Generator: Launchpad (build 13830)\n"
+"Language: bg\n"
 
 #. name for aaa
 msgid "Ghotuo"

setup/iso_639/br.po

@@ -9,16 +9,18 @@
 msgid ""
 msgstr ""
 "Project-Id-Version: iso_639_3\n"
-"Report-Msgid-Bugs-To: Debian iso-codes team <pkg-isocodes-devel@lists.alioth."
+"Report-Msgid-Bugs-To: Debian iso-codes team <pkg-isocodes-"
-"debian.org>\n"
+"devel@lists.alioth.debian.org>\n"
-"POT-Creation-Date: 2011-05-27 14:59+0200\n"
+"POT-Creation-Date: 2011-09-02 16:21+0000\n"
-"PO-Revision-Date: 2009-04-19 06:03+0000\n"
+"PO-Revision-Date: 2011-08-27 07:57+0000\n"
-"Last-Translator: Denis <Unknown>\n"
+"Last-Translator: Kovid Goyal <Unknown>\n"
 "Language-Team: Breton <brenux@free.fr>\n"
-"Language: br\n"
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=UTF-8\n"
 "Content-Transfer-Encoding: 8bit\n"
+"X-Launchpad-Export-Date: 2011-09-03 04:56+0000\n"
+"X-Generator: Launchpad (build 13830)\n"
+"Language: br\n"
 
 #. name for aaa
 msgid "Ghotuo"
@@ -125,9 +127,8 @@ msgid "Ayta, Ambala"
 msgstr "Ayta, Ambala"
 
 #. name for abd
-#, fuzzy
 msgid "Manide"
-msgstr "Bade"
+msgstr ""
 
 #. name for abe
 msgid "Abnaki, Western"
@@ -174,9 +175,8 @@ msgid "Abon"
 msgstr "Abon"
 
 #. name for abp
-#, fuzzy
 msgid "Ayta, Abellen"
-msgstr "Ayta, Abenlen"
+msgstr ""
 
 #. name for abq
 msgid "Abaza"
@@ -599,9 +599,8 @@ msgid "Aguacateco"
 msgstr "Aguakateko"
 
 #. name for agv
-#, fuzzy
 msgid "Dumagat, Remontado"
-msgstr "Agta, Remontado"
+msgstr ""
 
 #. name for agw
 msgid "Kahua"
@@ -1288,9 +1287,8 @@ msgid "Bukiyip"
 msgstr "Bukiyip"
 
 #. name for apf
-#, fuzzy
 msgid "Agta, Pahanan"
-msgstr "Ayta, Bataan"
+msgstr ""
 
 #. name for apg
 msgid "Ampanang"
@@ -1325,9 +1323,8 @@ msgid "Apinayé"
 msgstr "Apinaye"
 
 #. name for apo
-#, fuzzy
 msgid "Ambul"
-msgstr "Ambulas"
+msgstr ""
 
 #. name for app
 msgid "Apma"
@@ -1402,9 +1399,8 @@ msgid "Arhâ"
 msgstr "Arhâ"
 
 #. name for aqz
-#, fuzzy
 msgid "Akuntsu"
-msgstr "Awutu"
+msgstr ""
 
 #. name for ara
 msgid "Arabic"
@@ -2003,9 +1999,8 @@ msgid "Ayta, Sorsogon"
 msgstr "Ayta, Sorsogon"
 
 #. name for ayt
-#, fuzzy
 msgid "Ayta, Magbukun"
-msgstr "Ayta, Bataan"
+msgstr ""
 
 #. name for ayu
 msgid "Ayu"
@@ -2368,9 +2363,8 @@ msgid "Bade"
 msgstr "Bade"
 
 #. name for bdf
-#, fuzzy
 msgid "Biage"
-msgstr "Bade"
+msgstr ""
 
 #. name for bdg
 msgid "Bonggi"
@@ -2641,9 +2635,8 @@ msgid "Bondo"
 msgstr "Bondo"
 
 #. name for bfx
-#, fuzzy
 msgid "Bantayanon"
-msgstr "Bantawa"
+msgstr ""
 
 #. name for bfy
 msgid "Bagheli"
@@ -3110,9 +3103,8 @@ msgid "Bakumpai"
 msgstr ""
 
 #. name for bks
-#, fuzzy
 msgid "Sorsoganon, Northern"
-msgstr "Bai, Kreisteiz"
+msgstr ""
 
 #. name for bkt
 msgid "Boloki"
@@ -3355,9 +3347,8 @@ msgid "Bookan"
 msgstr ""
 
 #. name for bnc
-#, fuzzy
 msgid "Bontok"
-msgstr "Bondo"
+msgstr ""
 
 #. name for bnd
 msgid "Banda (Indonesia)"
@@ -4220,9 +4211,8 @@ msgid "Dibole"
 msgstr ""
 
 #. name for bvy
-#, fuzzy
 msgid "Baybayanon"
-msgstr "Babango"
+msgstr ""
 
 #. name for bvz
 msgid "Bauzi"
@@ -4453,9 +4443,8 @@ msgid "Baygo"
 msgstr ""
 
 #. name for byh
-#, fuzzy
 msgid "Bhujel"
-msgstr "Bhele"
+msgstr ""
 
 #. name for byi
 msgid "Buyu"
@@ -4794,9 +4783,8 @@ msgid "Cacua"
 msgstr ""
 
 #. name for cbw
-#, fuzzy
 msgid "Kinabalian"
-msgstr "Ainbai"
+msgstr ""
 
 #. name for cby
 msgid "Carabayo"
@@ -6487,9 +6475,8 @@ msgid "Duma"
 msgstr ""
 
 #. name for dmb
-#, fuzzy
 msgid "Dogon, Mombo"
-msgstr "One, Molmo"
+msgstr ""
 
 #. name for dmc
 msgid "Dimir"
@@ -7008,9 +6995,8 @@ msgid "Ebughu"
 msgstr ""
 
 #. name for ebk
-#, fuzzy
 msgid "Bontok, Eastern"
-msgstr "Abnaki, Eastern"
+msgstr ""
 
 #. name for ebo
 msgid "Teke-Ebo"
@@ -7561,9 +7547,8 @@ msgid "Fars, Northwestern"
 msgstr ""
 
 #. name for fbl
-#, fuzzy
 msgid "Bikol, West Albay"
-msgstr "Bikolano, Albay"
+msgstr ""
 
 #. name for fcs
 msgid "Quebec Sign Language"
@@ -7726,9 +7711,8 @@ msgid "French, Old (842-ca. 1400)"
 msgstr ""
 
 #. name for frp
-#, fuzzy
 msgid "Arpitan"
-msgstr "Arta"
+msgstr ""
 
 #. name for frq
 msgid "Forak"
@@ -10823,9 +10807,8 @@ msgid "Ngile"
 msgstr ""
 
 #. name for jls
-#, fuzzy
 msgid "Jamaican Sign Language"
-msgstr "Yezh ar sinoù Amerika"
+msgstr ""
 
 #. name for jma
 msgid "Dima"
@@ -13540,9 +13523,8 @@ msgid "Kpatili"
 msgstr ""
 
 #. name for kyn
-#, fuzzy
 msgid "Binukidnon, Northern"
-msgstr "Bai, Kreisteiz"
+msgstr ""
 
 #. name for kyo
 msgid "Kelon"
@@ -13697,9 +13679,8 @@ msgid "Kalabra"
 msgstr ""
 
 #. name for laa
-#, fuzzy
 msgid "Subanen, Southern"
-msgstr "Bai, Hanternoz"
+msgstr ""
 
 #. name for lab
 msgid "Linear A"
@@ -13834,9 +13815,8 @@ msgid "Ladakhi"
 msgstr ""
 
 #. name for lbk
-#, fuzzy
 msgid "Bontok, Central"
-msgstr "Bicolano, Kreiz"
+msgstr ""
 
 #. name for lbl
 msgid "Bikol, Libon"
@@ -14567,9 +14547,8 @@ msgid "Lanoh"
 msgstr ""
 
 #. name for lni
-#, fuzzy
 msgid "Daantanai'"
-msgstr "Babatana"
+msgstr ""
 
 #. name for lnj
 msgid "Leningitij"
@@ -14832,18 +14811,16 @@ msgid "Trinidad and Tobago Sign Language"
 msgstr ""
 
 #. name for lsy
-#, fuzzy
 msgid "Mauritian Sign Language"
-msgstr "Yezh ar sinoù Aotrich"
+msgstr ""
 
 #. name for ltc
 msgid "Chinese, Late Middle"
 msgstr ""
 
 #. name for ltg
-#, fuzzy
 msgid "Latgalian"
-msgstr "Katalaneg"
+msgstr ""
 
 #. name for lti
 msgid "Leti (Indonesia)"
@@ -14974,9 +14951,8 @@ msgid "Lavukaleve"
 msgstr ""
 
 #. name for lvs
-#, fuzzy
 msgid "Latvian, Standard"
-msgstr "Arabeg dre ziouer"
+msgstr ""
 
 #. name for lvu
 msgid "Levuka"
@@ -16127,9 +16103,8 @@ msgid "Kituba (Congo)"
 msgstr ""
 
 #. name for mkx
-#, fuzzy
 msgid "Manobo, Kinamiging"
-msgstr "Manobo, Ata"
+msgstr ""
 
 #. name for mky
 msgid "Makian, East"
@@ -16476,9 +16451,8 @@ msgid "Morori"
 msgstr ""
 
 #. name for mom
-#, fuzzy
 msgid "Mangue"
-msgstr "Mapudungun"
+msgstr ""
 
 #. name for mon
 msgid "Mongolian"
@@ -16829,9 +16803,8 @@ msgid "Maremgi"
 msgstr ""
 
 #. name for mry
-#, fuzzy
 msgid "Mandaya"
-msgstr "Makayam"
+msgstr ""
 
 #. name for mrz
 msgid "Marind"
@@ -17026,9 +16999,8 @@ msgid "Asaro'o"
 msgstr ""
 
 #. name for mtw
-#, fuzzy
 msgid "Binukidnon, Southern"
-msgstr "Bai, Hanternoz"
+msgstr ""
 
 #. name for mtx
 msgid "Mixtec, Tidaá"
@@ -18327,9 +18299,8 @@ msgid "Nias"
 msgstr ""
 
 #. name for nib
-#, fuzzy
 msgid "Nakame"
-msgstr "Barama"
+msgstr ""
 
 #. name for nid
 msgid "Ngandi"
@@ -18892,9 +18863,8 @@ msgid "Noiri"
 msgstr ""
 
 #. name for noj
-#, fuzzy
 msgid "Nonuya"
-msgstr "Nanubae"
+msgstr ""
 
 #. name for nok
 msgid "Nooksack"
@@ -18985,9 +18955,8 @@ msgid "Napu"
 msgstr ""
 
 #. name for nqg
-#, fuzzy
 msgid "Nago, Southern"
-msgstr "Bai, Hanternoz"
+msgstr ""
 
 #. name for nqk
 msgid "Ede Nago, Kura"
@@ -19558,9 +19527,8 @@ msgid "Obispeño"
 msgstr ""
 
 #. name for obk
-#, fuzzy
 msgid "Bontok, Southern"
-msgstr "Bai, Hanternoz"
+msgstr ""
 
 #. name for obl
 msgid "Oblo"
@@ -20523,9 +20491,8 @@ msgid "Pomo, Southern"
 msgstr ""
 
 #. name for pes
-#, fuzzy
 msgid "Persian, Iranian"
-msgstr "Paranan"
+msgstr ""
 
 #. name for pev
 msgid "Pémono"
@@ -21564,9 +21531,8 @@ msgid "Poyanáwa"
 msgstr ""
 
 #. name for pys
-#, fuzzy
 msgid "Paraguayan Sign Language"
-msgstr "Yezh ar sinoù Afganistan"
+msgstr ""
 
 #. name for pyu
 msgid "Puyuma"
@@ -21921,9 +21887,8 @@ msgid "Palaung, Rumai"
 msgstr ""
 
 #. name for rbk
-#, fuzzy
 msgid "Bontok, Northern"
-msgstr "Bai, Kreisteiz"
+msgstr ""
 
 #. name for rbl
 msgid "Bikol, Miraya"
@@ -22890,9 +22855,8 @@ msgid "Irish, Old (to 900)"
 msgstr ""
 
 #. name for sgb
-#, fuzzy
 msgid "Ayta, Mag-antsi"
-msgstr "Ayta, Bataan"
+msgstr ""
 
 #. name for sgc
 msgid "Kipsigis"
@@ -22959,9 +22923,8 @@ msgid "Sierra Leone Sign Language"
 msgstr ""
 
 #. name for sgy
-#, fuzzy
 msgid "Sanglechi"
-msgstr "Balouchi"
+msgstr ""
 
 #. name for sgz
 msgid "Sursurunga"
@@ -23912,9 +23875,8 @@ msgid "Suruí"
 msgstr ""
 
 #. name for srv
-#, fuzzy
 msgid "Sorsoganon, Southern"
-msgstr "Aymara, Hanternoz"
+msgstr ""
 
 #. name for srw
 msgid "Serua"
@@ -25009,9 +24971,8 @@ msgid "Tagalog"
 msgstr ""
 
 #. name for tgn
-#, fuzzy
 msgid "Tandaganon"
-msgstr "Inabaknon"
+msgstr ""
 
 #. name for tgo
 msgid "Sudest"
@@ -26750,9 +26711,8 @@ msgid "Uma' Lung"
 msgstr ""
 
 #. name for ulw
-#, fuzzy
 msgid "Ulwa"
-msgstr "Alawa"
+msgstr ""
 
 #. name for uma
 msgid "Umatilla"
@@ -27115,9 +27075,8 @@ msgid "Babar, Southeast"
 msgstr ""
 
 #. name for vbk
-#, fuzzy
 msgid "Bontok, Southwestern"
-msgstr "Bai, Hanternoz"
+msgstr ""
 
 #. name for vec
 msgid "Venetian"
@@ -28352,9 +28311,8 @@ msgid "Breton, Middle"
 msgstr "Krennvrezhoneg"
 
 #. name for xbn
-#, fuzzy
 msgid "Kenaboi"
-msgstr "Karnai"
+msgstr ""
 
 #. name for xbo
 msgid "Bolgarian"
@@ -28581,9 +28539,8 @@ msgid "Kalkoti"
 msgstr ""
 
 #. name for xkb
-#, fuzzy
 msgid "Nago, Northern"
-msgstr "Bai, Kreisteiz"
+msgstr ""
 
 #. name for xkc
 msgid "Kho'ini"
@@ -28742,9 +28699,8 @@ msgid "Makhuwa-Marrevone"
 msgstr ""
 
 #. name for xmd
-#, fuzzy
 msgid "Mbudum"
-msgstr "Buduma"
+msgstr ""
 
 #. name for xme
 msgid "Median"
@@ -29335,9 +29291,8 @@ msgid "Banda-Yangere"
 msgstr ""
 
 #. name for yak
-#, fuzzy
 msgid "Yakama"
-msgstr "Barama"
+msgstr ""
 
 #. name for yal
 msgid "Yalunka"
@@ -29348,9 +29303,8 @@ msgid "Yamba"
 msgstr ""
 
 #. name for yan
-#, fuzzy
 msgid "Mayangna"
-msgstr "Ginyanga"
+msgstr ""
 
 #. name for yao
 msgid "Yao"
@@ -29705,9 +29659,8 @@ msgid "Yaul"
 msgstr ""
 
 #. name for ylb
-#, fuzzy
 msgid "Yaleba"
-msgstr "Baba"
+msgstr ""
 
 #. name for yle
 msgid "Yele"
@@ -29898,9 +29851,8 @@ msgid "Yombe"
 msgstr ""
 
 #. name for yon
-#, fuzzy
 msgid "Yongkom"
-msgstr "Bobongko"
+msgstr ""
 
 #. name for yor
 msgid "Yoruba"

setup/iso_639/crh.po

@@ -6,20 +6,18 @@
 msgid ""
 msgstr ""
 "Project-Id-Version: iso_639_3\n"
-"Report-Msgid-Bugs-To: Debian iso-codes team <pkg-isocodes-devel@lists.alioth."
+"Report-Msgid-Bugs-To: Debian iso-codes team <pkg-isocodes-"
-"debian.org>\n"
+"devel@lists.alioth.debian.org>\n"
-"POT-Creation-Date: 2011-05-27 14:59+0200\n"
+"POT-Creation-Date: 2011-09-02 16:21+0000\n"
-"PO-Revision-Date: 2009-03-01 03:27-0600\n"
+"PO-Revision-Date: 2011-08-27 03:17+0000\n"
 "Last-Translator: Reşat SABIQ <tilde.birlik@gmail.com>\n"
 "Language-Team: Crimean Tatar <tilde-birlik-tercime@lists.sourceforge.net>\n"
-"Language: crh\n"
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=UTF-8\n"
 "Content-Transfer-Encoding: 8bit\n"
-"X-Generator: KBabel 1.11.4\n"
+"X-Launchpad-Export-Date: 2011-09-03 04:58+0000\n"
-"X-Launchpad-Export-Date: 2009-03-01 08:44+0000\n"
+"X-Generator: Launchpad (build 13830)\n"
-"X-Generator: Launchpad (build Unknown)\n"
+"Language: crh\n"
-"Plural-Forms: nplurals=2; plural=n != 1;\n"
 
 #. name for aaa
 msgid "Ghotuo"
@@ -126,9 +124,8 @@ msgid "Ayta, Ambala"
 msgstr "Ayta, Ambala"
 
 #. name for abd
-#, fuzzy
 msgid "Manide"
-msgstr "Mander"
+msgstr ""
 
 #. name for abe
 msgid "Abnaki, Western"
@@ -175,9 +172,8 @@ msgid "Abon"
 msgstr "Abon"
 
 #. name for abp
-#, fuzzy
 msgid "Ayta, Abellen"
-msgstr "Ayta, Abenlen"
+msgstr ""
 
 #. name for abq
 msgid "Abaza"
@@ -600,9 +596,8 @@ msgid "Aguacateco"
 msgstr "Aguacateco"
 
 #. name for agv
-#, fuzzy
 msgid "Dumagat, Remontado"
-msgstr "Agta, Remontado"
+msgstr ""
 
 #. name for agw
 msgid "Kahua"
@@ -1289,9 +1284,8 @@ msgid "Bukiyip"
 msgstr "Bukiyip"
 
 #. name for apf
-#, fuzzy
 msgid "Agta, Pahanan"
-msgstr "Ayta, Bataan"
+msgstr ""
 
 #. name for apg
 msgid "Ampanang"
@@ -1326,9 +1320,8 @@ msgid "Apinayé"
 msgstr "Apinayé"
 
 #. name for apo
-#, fuzzy
 msgid "Ambul"
-msgstr "Ambulas"
+msgstr ""
 
 #. name for app
 msgid "Apma"
@@ -1379,9 +1372,8 @@ msgid "Archi"
 msgstr "Archi"
 
 #. name for aqd
-#, fuzzy
 msgid "Dogon, Ampari"
-msgstr "Dogon, Jamsay"
+msgstr ""
 
 #. name for aqg
 msgid "Arigidi"
@@ -1404,9 +1396,8 @@ msgid "Arhâ"
 msgstr "Arhâ"
 
 #. name for aqz
-#, fuzzy
 msgid "Akuntsu"
-msgstr "Awutu"
+msgstr ""
 
 #. name for ara
 msgid "Arabic"
@@ -2005,9 +1996,8 @@ msgid "Ayta, Sorsogon"
 msgstr "Ayta, Sorsogon"
 
 #. name for ayt
-#, fuzzy
 msgid "Ayta, Magbukun"
-msgstr "Ayta, Mag-Indi"
+msgstr ""
 
 #. name for ayu
 msgid "Ayu"
@@ -2370,9 +2360,8 @@ msgid "Bade"
 msgstr "Bade"
 
 #. name for bdf
-#, fuzzy
 msgid "Biage"
-msgstr "Bitare"
+msgstr ""
 
 #. name for bdg
 msgid "Bonggi"
@@ -2643,9 +2632,8 @@ msgid "Bondo"
 msgstr "Bondo"
 
 #. name for bfx
-#, fuzzy
 msgid "Bantayanon"
-msgstr "Bantoanon"
+msgstr ""
 
 #. name for bfy
 msgid "Bagheli"
@@ -3112,9 +3100,8 @@ msgid "Bakumpai"
 msgstr "Bakumpai"
 
 #. name for bks
-#, fuzzy
 msgid "Sorsoganon, Northern"
-msgstr "Sorsogon, Masbate"
+msgstr ""
 
 #. name for bkt
 msgid "Boloki"
@@ -3129,9 +3116,8 @@ msgid "Bekwarra"
 msgstr "Bekwarra"
 
 #. name for bkw
-#, fuzzy
 msgid "Bekwel"
-msgstr "Bekwil"
+msgstr ""
 
 #. name for bkx
 msgid "Baikeno"
@@ -3358,9 +3344,8 @@ msgid "Bookan"
 msgstr "Bookan"
 
 #. name for bnc
-#, fuzzy
 msgid "Bontok"
-msgstr "Bondo"
+msgstr ""
 
 #. name for bnd
 msgid "Banda (Indonesia)"
@@ -4223,9 +4208,8 @@ msgid "Dibole"
 msgstr "Dibole"
 
 #. name for bvy
-#, fuzzy
 msgid "Baybayanon"
-msgstr "Babango"
+msgstr ""
 
 #. name for bvz
 msgid "Bauzi"
@@ -4456,9 +4440,8 @@ msgid "Baygo"
 msgstr "Baygo"
 
 #. name for byh
-#, fuzzy
 msgid "Bhujel"
-msgstr "Bhele"
+msgstr ""
 
 #. name for byi
 msgid "Buyu"
@@ -4621,9 +4604,8 @@ msgid "Basa (Nigeria)"
 msgstr ""
 
 #. name for bzx
-#, fuzzy
 msgid "Bozo, Kɛlɛngaxo"
-msgstr "Bozo, Hainyaxo"
+msgstr ""
 
 #. name for bzy
 msgid "Obanliku"
@@ -4798,9 +4780,8 @@ msgid "Cacua"
 msgstr "Cacua"
 
 #. name for cbw
-#, fuzzy
 msgid "Kinabalian"
-msgstr "Kabardian"
+msgstr ""
 
 #. name for cby
 msgid "Carabayo"
@@ -6491,9 +6472,8 @@ msgid "Duma"
 msgstr "Duma"
 
 #. name for dmb
-#, fuzzy
 msgid "Dogon, Mombo"
-msgstr "Dogon, Kolum So"
+msgstr ""
 
 #. name for dmc
 msgid "Dimir"
@@ -6688,9 +6668,8 @@ msgid "Dair"
 msgstr "Dair"
 
 #. name for drc
-#, fuzzy
 msgid "Minderico"
-msgstr "Mindiri"
+msgstr ""
 
 #. name for drd
 msgid "Darmiya"
@@ -7013,9 +6992,8 @@ msgid "Ebughu"
 msgstr "Ebughu"
 
 #. name for ebk
-#, fuzzy
 msgid "Bontok, Eastern"
-msgstr "Abnaki, Şarqiy"
+msgstr ""
 
 #. name for ebo
 msgid "Teke-Ebo"
@@ -7230,9 +7208,8 @@ msgid "Emplawas"
 msgstr "Emplawas"
 
 #. name for emx
-#, fuzzy
 msgid "Erromintxela"
-msgstr "Edomite"
+msgstr ""
 
 #. name for emy
 msgid "Mayan, Epigraphic"
@@ -7567,9 +7544,8 @@ msgid "Fars, Northwestern"
 msgstr ""
 
 #. name for fbl
-#, fuzzy
 msgid "Bikol, West Albay"
-msgstr "Bicolano, Albay"
+msgstr ""
 
 #. name for fcs
 msgid "Quebec Sign Language"
@@ -7732,9 +7708,8 @@ msgid "French, Old (842-ca. 1400)"
 msgstr ""
 
 #. name for frp
-#, fuzzy
 msgid "Arpitan"
-msgstr "Arta"
+msgstr ""
 
 #. name for frq
 msgid "Forak"
@@ -10401,9 +10376,8 @@ msgid "Nkem-Nkum"
 msgstr "Nkem-Nkum"
 
 #. name for isk
-#, fuzzy
 msgid "Ishkashimi"
-msgstr "Sanglechi-Ishkashimi"
+msgstr ""
 
 #. name for isl
 msgid "Icelandic"
@@ -10830,9 +10804,8 @@ msgid "Ngile"
 msgstr "Ngile"
 
 #. name for jls
-#, fuzzy
 msgid "Jamaican Sign Language"
-msgstr "Zambiyalı İşaret Tili"
+msgstr ""
 
 #. name for jma
 msgid "Dima"
@@ -11215,9 +11188,8 @@ msgid "Keliko"
 msgstr "Keliko"
 
 #. name for kbp
-#, fuzzy
 msgid "Kabiyè"
-msgstr "Kabiyé"
+msgstr ""
 
 #. name for kbq
 msgid "Kamano"
@@ -12192,9 +12164,8 @@ msgid "Kendeje"
 msgstr "Kendeje"
 
 #. name for klg
-#, fuzzy
 msgid "Tagakaulo"
-msgstr "Tagalog"
+msgstr ""
 
 #. name for klh
 msgid "Weliki"
@@ -12217,9 +12188,8 @@ msgid "Kalagan, Kagan"
 msgstr "Kalagan, Kagan"
 
 #. name for klm
-#, fuzzy
 msgid "Migum"
-msgstr "Mogum"
+msgstr ""
 
 #. name for kln
 msgid "Kalenjin"
@@ -12286,9 +12256,8 @@ msgid "Dong, Southern"
 msgstr ""
 
 #. name for kmd
-#, fuzzy
 msgid "Kalinga, Majukayang"
-msgstr "Kalinga, Madukayang"
+msgstr ""
 
 #. name for kme
 msgid "Bakole"
@@ -13551,9 +13520,8 @@ msgid "Kpatili"
 msgstr "Kpatili"
 
 #. name for kyn
-#, fuzzy
 msgid "Binukidnon, Northern"
-msgstr "Özbekçe, Şimaliy"
+msgstr ""
 
 #. name for kyo
 msgid "Kelon"
@@ -13708,9 +13676,8 @@ msgid "Kalabra"
 msgstr "Kalabra"
 
 #. name for laa
-#, fuzzy
 msgid "Subanen, Southern"
-msgstr "Özbekçe, Cenübiy"
+msgstr ""
 
 #. name for lab
 msgid "Linear A"
@@ -13849,9 +13816,8 @@ msgid "Bontok, Central"
 msgstr ""
 
 #. name for lbl
-#, fuzzy
 msgid "Bikol, Libon"
-msgstr "Biao Mon"
+msgstr ""
 
 #. name for lbm
 msgid "Lodhi"
@@ -14578,9 +14544,8 @@ msgid "Lanoh"
 msgstr "Lanoh"
 
 #. name for lni
-#, fuzzy
 msgid "Daantanai'"
-msgstr "Lantanai"
+msgstr ""
 
 #. name for lnj
 msgid "Leningitij"
@@ -14843,18 +14808,16 @@ msgid "Trinidad and Tobago Sign Language"
 msgstr "Trinidad Tobago İşaret Tili"
 
 #. name for lsy
-#, fuzzy
 msgid "Mauritian Sign Language"
-msgstr "Maritime İşaret Tili"
+msgstr ""
 
 #. name for ltc
 msgid "Chinese, Late Middle"
 msgstr ""
 
 #. name for ltg
-#, fuzzy
 msgid "Latgalian"
-msgstr "Katalanca"
+msgstr ""
 
 #. name for lti
 msgid "Leti (Indonesia)"
@@ -14985,9 +14948,8 @@ msgid "Lavukaleve"
 msgstr "Lavukaleve"
 
 #. name for lvs
-#, fuzzy
 msgid "Latvian, Standard"
-msgstr "Letonyalı İşaret Tili"
+msgstr ""
 
 #. name for lvu
 msgid "Levuka"
@@ -15378,9 +15340,8 @@ msgid "Massalat"
 msgstr "Massalat"
 
 #. name for mdh
-#, fuzzy
 msgid "Maguindanaon"
-msgstr "Maguindanao"
+msgstr ""
 
 #. name for mdi
 msgid "Mamvu"
@@ -16139,9 +16100,8 @@ msgid "Kituba (Congo)"
 msgstr "Kituba (Kongo)"
 
 #. name for mkx
-#, fuzzy
 msgid "Manobo, Kinamiging"
-msgstr "Manobo, Cinamiguin"
+msgstr ""
 
 #. name for mky
 msgid "Makian, East"
@@ -16488,9 +16448,8 @@ msgid "Morori"
 msgstr "Morori"
 
 #. name for mom
-#, fuzzy
 msgid "Mangue"
-msgstr "Mang"
+msgstr ""
 
 #. name for mon
 msgid "Mongolian"
@@ -16769,9 +16728,8 @@ msgid "Elseng"
 msgstr "Elseng"
 
 #. name for mrg
-#, fuzzy
 msgid "Mising"
-msgstr "Maisin"
+msgstr ""
 
 #. name for mrh
 msgid "Chin, Mara"
@@ -16842,9 +16800,8 @@ msgid "Maremgi"
 msgstr "Maremgi"
 
 #. name for mry
-#, fuzzy
 msgid "Mandaya"
-msgstr "Mandara"
+msgstr ""
 
 #. name for mrz
 msgid "Marind"
@@ -17039,9 +16996,8 @@ msgid "Asaro'o"
 msgstr "Asaro'o"
 
 #. name for mtw
-#, fuzzy
 msgid "Binukidnon, Southern"
-msgstr "Sesotho"
+msgstr ""
 
 #. name for mtx
 msgid "Mixtec, Tidaá"
@@ -18340,9 +18296,8 @@ msgid "Nias"
 msgstr "Nias"
 
 #. name for nib
-#, fuzzy
 msgid "Nakame"
-msgstr "Nakama"
+msgstr ""
 
 #. name for nid
 msgid "Ngandi"
@@ -18905,9 +18860,8 @@ msgid "Noiri"
 msgstr "Noiri"
 
 #. name for noj
-#, fuzzy
 msgid "Nonuya"
-msgstr "Nkonya"
+msgstr ""
 
 #. name for nok
 msgid "Nooksack"
@@ -18998,9 +18952,8 @@ msgid "Napu"
 msgstr "Napu"
 
 #. name for nqg
-#, fuzzy
 msgid "Nago, Southern"
-msgstr "Sesotho"
+msgstr ""
 
 #. name for nqk
 msgid "Ede Nago, Kura"
@@ -19067,9 +19020,8 @@ msgid "Kalapuya, Northern"
 msgstr ""
 
 #. name for nru
-#, fuzzy
 msgid "Narua"
-msgstr "Sarua"
+msgstr ""
 
 #. name for nrx
 msgid "Ngurmbur"
@@ -19272,9 +19224,8 @@ msgid "Niuafo'ou"
 msgstr "Niuafo'ou"
 
 #. name for nun
-#, fuzzy
 msgid "Anong"
-msgstr "Konongo"
+msgstr ""
 
 #. name for nuo
 msgid "Nguôn"
@@ -19549,9 +19500,8 @@ msgid "Nzakambay"
 msgstr "Nzakambay"
 
 #. name for nzz
-#, fuzzy
 msgid "Dogon, Nanga Dama"
-msgstr "Dogon, Yanda Dom"
+msgstr ""
 
 #. name for oaa
 msgid "Orok"
@@ -19574,9 +19524,8 @@ msgid "Obispeño"
 msgstr "Obispeño"
 
 #. name for obk
-#, fuzzy
 msgid "Bontok, Southern"
-msgstr "Sesotho"
+msgstr ""
 
 #. name for obl
 msgid "Oblo"
@@ -20539,9 +20488,8 @@ msgid "Pomo, Southern"
 msgstr ""
 
 #. name for pes
-#, fuzzy
 msgid "Persian, Iranian"
-msgstr "Paranan"
+msgstr ""
 
 #. name for pev
 msgid "Pémono"
@@ -20588,9 +20536,8 @@ msgid "Rerep"
 msgstr "Rerep"
 
 #. name for pgl
-#, fuzzy
 msgid "Irish, Primitive"
-msgstr "Türkçe, Qırım; Qırımtatarca"
+msgstr ""
 
 #. name for pgn
 msgid "Paelignian"
@@ -21293,9 +21240,8 @@ msgid "Puri"
 msgstr "Puri"
 
 #. name for prs
-#, fuzzy
 msgid "Persian, Afghan"
-msgstr "Farsça"
+msgstr ""
 
 #. name for prt
 msgid "Phai"
@@ -21582,9 +21528,8 @@ msgid "Poyanáwa"
 msgstr "Poyanáwa"
 
 #. name for pys
-#, fuzzy
 msgid "Paraguayan Sign Language"
-msgstr "Uruguaylı İşaret Tili"
+msgstr ""
 
 #. name for pyu
 msgid "Puyuma"
@@ -21939,14 +21884,12 @@ msgid "Palaung, Rumai"
 msgstr "Palaung, Rumai"
 
 #. name for rbk
-#, fuzzy
 msgid "Bontok, Northern"
-msgstr "Sesotho"
+msgstr ""
 
 #. name for rbl
-#, fuzzy
 msgid "Bikol, Miraya"
-msgstr "Samo, Maya"
+msgstr ""
 
 #. name for rcf
 msgid "Creole French, Réunion"
@@ -22909,9 +22852,8 @@ msgid "Irish, Old (to 900)"
 msgstr ""
 
 #. name for sgb
-#, fuzzy
 msgid "Ayta, Mag-antsi"
-msgstr "Ayta, Mag-Indi"
+msgstr ""
 
 #. name for sgc
 msgid "Kipsigis"
@@ -22958,9 +22900,8 @@ msgid "Sangisari"
 msgstr "Sangisari"
 
 #. name for sgs
-#, fuzzy
 msgid "Samogitian"
-msgstr "Samoan"
+msgstr ""
 
 #. name for sgt
 msgid "Brokpake"
@@ -22979,9 +22920,8 @@ msgid "Sierra Leone Sign Language"
 msgstr "Sierra Leone İşaret Tili"
 
 #. name for sgy
-#, fuzzy
 msgid "Sanglechi"
-msgstr "Shangzhai"
+msgstr ""
 
 #. name for sgz
 msgid "Sursurunga"
@@ -23000,9 +22940,8 @@ msgid "Sonde"
 msgstr "Sonde"
 
 #. name for shd
-#, fuzzy
 msgid "Kundal Shahi"
-msgstr "Kudmali"
+msgstr ""
 
 #. name for she
 msgid "Sheko"
@@ -23933,9 +23872,8 @@ msgid "Suruí"
 msgstr "Suruí"
 
 #. name for srv
-#, fuzzy
 msgid "Sorsoganon, Southern"
-msgstr "Sesotho"
+msgstr ""
 
 #. name for srw
 msgid "Serua"
@@ -23966,9 +23904,8 @@ msgid "Siroi"
 msgstr "Siroi"
 
 #. name for sse
-#, fuzzy
 msgid "Sama, Bangingih"
-msgstr "Sama, Pangutaran"
+msgstr ""
 
 #. name for ssf
 msgid "Thao"
@@ -24799,9 +24736,8 @@ msgid "Tai Nüa"
 msgstr "Tai Nüa"
 
 #. name for tde
-#, fuzzy
 msgid "Dogon, Tiranige Diga"
-msgstr "Dogon, Tene Kan"
+msgstr ""
 
 #. name for tdf
 msgid "Talieng"
@@ -25032,9 +24968,8 @@ msgid "Tagalog"
 msgstr "Tagalog"
 
 #. name for tgn
-#, fuzzy
 msgid "Tandaganon"
-msgstr "Tondano"
+msgstr ""
 
 #. name for tgo
 msgid "Sudest"
@@ -25317,9 +25252,8 @@ msgid "Tukumanféd"
 msgstr "Tukumanféd"
 
 #. name for tkg
-#, fuzzy
 msgid "Malagasy, Tesaka"
-msgstr "Malagasy, Bara"
+msgstr ""
 
 #. name for tkl
 msgid "Tokelau"
@@ -26774,9 +26708,8 @@ msgid "Uma' Lung"
 msgstr "Uma' Lung"
 
 #. name for ulw
-#, fuzzy
 msgid "Ulwa"
-msgstr "Ukwa"
+msgstr ""
 
 #. name for uma
 msgid "Umatilla"
@@ -27139,9 +27072,8 @@ msgid "Babar, Southeast"
 msgstr ""
 
 #. name for vbk
-#, fuzzy
 msgid "Bontok, Southwestern"
-msgstr "Sesotho"
+msgstr ""
 
 #. name for vec
 msgid "Venetian"
@@ -28376,9 +28308,8 @@ msgid "Breton, Middle"
 msgstr ""
 
 #. name for xbn
-#, fuzzy
 msgid "Kenaboi"
-msgstr "Kenati"
+msgstr ""
 
 #. name for xbo
 msgid "Bolgarian"
@@ -28605,9 +28536,8 @@ msgid "Kalkoti"
 msgstr "Kalkoti"
 
 #. name for xkb
-#, fuzzy
 msgid "Nago, Northern"
-msgstr "Naga, Nocte"
+msgstr ""
 
 #. name for xkc
 msgid "Kho'ini"
@@ -28766,9 +28696,8 @@ msgid "Makhuwa-Marrevone"
 msgstr "Makhuwa-Marrevone"
 
 #. name for xmd
-#, fuzzy
 msgid "Mbudum"
-msgstr "Buduma"
+msgstr ""
 
 #. name for xme
 msgid "Median"
@@ -28835,9 +28764,8 @@ msgid "Kamu"
 msgstr "Kamu"
 
 #. name for xmv
-#, fuzzy
 msgid "Malagasy, Tankarana"
-msgstr "Malagasy, Antankarana"
+msgstr ""
 
 #. name for xmw
 msgid "Malagasy, Tsimihety"
@@ -28888,9 +28816,8 @@ msgid "Kanashi"
 msgstr "Kanashi"
 
 #. name for xnt
-#, fuzzy
 msgid "Narragansett"
-msgstr "Karagas"
+msgstr ""
 
 #. name for xoc
 msgid "O'chi'chi'"
@@ -29361,9 +29288,8 @@ msgid "Banda-Yangere"
 msgstr "Banda-Yangere"
 
 #. name for yak
-#, fuzzy
 msgid "Yakama"
-msgstr "Nakama"
+msgstr ""
 
 #. name for yal
 msgid "Yalunka"
@@ -29374,9 +29300,8 @@ msgid "Yamba"
 msgstr "Yamba"
 
 #. name for yan
-#, fuzzy
 msgid "Mayangna"
-msgstr "Mayaguduna"
+msgstr ""
 
 #. name for yao
 msgid "Yao"
@@ -29731,9 +29656,8 @@ msgid "Yaul"
 msgstr "Yaul"
 
 #. name for ylb
-#, fuzzy
 msgid "Yaleba"
-msgstr "Yareba"
+msgstr ""
 
 #. name for yle
 msgid "Yele"
@@ -29924,9 +29848,8 @@ msgid "Yombe"
 msgstr "Yombe"
 
 #. name for yon
-#, fuzzy
 msgid "Yongkom"
-msgstr "Yonggom"
+msgstr ""
 
 #. name for yor
 msgid "Yoruba"
@@ -30777,9 +30700,8 @@ msgid "Mirgan"
 msgstr "Mirgan"
 
 #. name for zrn
-#, fuzzy
 msgid "Zerenkel"
-msgstr "Zirenkel"
+msgstr ""
 
 #. name for zro
 msgid "Záparo"