Updated Ars Technica recipe

src/calibre/web/feeds/recipes/recipe_ars_technica.py

@@ -1,50 +1,60 @@
 #!/usr/bin/env  python
-__license__   = 'GPL v3'
-__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
-__docformat__ = 'restructuredtext en'
 
+__license__   = 'GPL v3'
+__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
 '''
 arstechnica.com
 '''
 
 from calibre.web.feeds.news import BasicNewsRecipe
 
-class ArsTechnica(BasicNewsRecipe):
-    title          = 'Ars Technica'
-    description    = 'The art of technology'
-    oldest_article = 7
-    language = _('English')
-    no_stylesheets = True
-    __author__     = 'Michael Warner'
+class ArsTechnica2(BasicNewsRecipe):
+    title                 = u'Ars Technica'
+    language              = _('English')
+    __author__            = 'Darko Miletic'
+    description           = 'The art of technology'    
+    publisher             = 'Ars Technica'
+    category              = 'news, IT, technology'    
+    language              = _('English')
+    oldest_article        = 2
     max_articles_per_feed = 100
-    extra_css = """
-body {
-   font: normal 19px/180% Times, serif;
-}
+    no_stylesheets        = True
+    encoding              = 'utf8'
+    remove_javascript     = True
+    use_embedded_content  = False
+    
+    html2lrf_options = [
+                          '--comment', description
+                        , '--category', category
+                        , '--publisher', publisher
+                        ]
+    
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' 
+
+    keep_only_tags = [dict(name='div', attrs={'id':['news-item-info','news-item']})]
 
-h1, h2, h3, h4 {
-   font: bold 28px/100% Verdana, Arial, Helvetica, sans-serif;
-   margin-top: 19px
-}
-"""
     remove_tags = [
-                   dict(id="Masthead"),
-                   dict(id="Banner"),
-                   dict(id="Nav"),
-                   dict(name='div', attrs={'class':'ContentHeader'}), 
-                   dict(name='img'), 
-                   dict(name='div', attrs={'class':'Inset RelatedStories'}), 
-                   dict(name='div', attrs={'class':'Tags'}), 
-                   dict(name='div', attrs={'class':'PostOptions flat'}),
-                   dict(name='div', attrs={'class':'ContentFooter'}),
-                   dict(id="Sidebar"),
-                   dict(id="LatestPosts"),
-                   dict(id="Footer")]
-    feeds       = [(u'News and Features', u'http://feeds.arstechnica.com/arstechnica/BAaf'),
-                   (u'Nobel Intent (Science)', u'http://arstechnica.com/journals/science.rssx'),
-                   (u'Infinite Loop (Apple)', u'http://arstechnica.com/journals/apple.rssx'),
-                   (u'M-Dollar (Microsoft)', u'http://arstechnica.com/journals/microsoft.rssx'),
-                   (u'Open Ended (Linux)', u'http://arstechnica.com/journals/linux.rssx'),
-                   (u'Opposable Thumbs (Games)', u'http://arstechnica.com/journals/thumbs.rssx'),
-                   (u'Kit (Hardware)', u'http://arstechnica.com/journals/hardware.rssx'),
-                   (u'Journals', u'http://arstechnica.com/journals.rssx')]
+                     dict(name=['object','link','embed'])
+                    ,dict(name='div', attrs={'class':'related-stories'})
+                  ]
+
+    
+    feeds = [
+              (u'Infinite Loop (Apple content)'        , u'http://feeds.arstechnica.com/arstechnica/apple/'      )
+             ,(u'Opposable Thumbs (Gaming content)'    , u'http://feeds.arstechnica.com/arstechnica/gaming/'     )
+             ,(u'Gear and Gadgets'                     , u'http://feeds.arstechnica.com/arstechnica/gadgets/'    )
+             ,(u'Chipster (Hardware content)'          , u'http://feeds.arstechnica.com/arstechnica/hardware/'   )
+             ,(u'Uptime (IT content)'                  , u'http://feeds.arstechnica.com/arstechnica/business/'   )
+             ,(u'Open Ended (Open Source content)'     , u'http://feeds.arstechnica.com/arstechnica/open-source/')
+             ,(u'One Microsoft Way'                    , u'http://feeds.arstechnica.com/arstechnica/microsoft/'  )
+             ,(u'Nobel Intent (Science content)'       , u'http://feeds.arstechnica.com/arstechnica/science/'    )
+             ,(u'Law & Disorder (Tech policy content)' , u'http://feeds.arstechnica.com/arstechnica/tech-policy/')
+            ]
+
+    def preprocess_html(self, soup):
+        ftag = soup.find('div', attrs={'class':'news-item-byline'})
+        if ftag:
+           ftag.insert(4,'<br /><br />')
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup