Updated FAZ.NET recipe to produce EPUB that does not crash the SONY readers.

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

@@ -1,29 +1,50 @@
 __license__   = 'GPL v3'
-__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
+__copyright__ = '2008-2009, Kovid Goyal <kovid at kovidgoyal.net>, Darko Miletic <darko at gmail.com>'
 '''
 Profile to download FAZ.net
 '''
-import re
+
 from calibre.web.feeds.news import BasicNewsRecipe
  
-
 class FazNet(BasicNewsRecipe): 
-
+    title                 = 'FAZ NET'
-    title = 'FAZ NET'
+    __author__            = 'Kovid Goyal, Darko Miletic'
-    __author__ = 'Kovid Goyal'
+    description           = 'Frankfurter Allgemeine Zeitung'
-    description = 'Frankfurter Allgemeine Zeitung'
+    publisher             = 'FAZ Electronic Media GmbH'
-    use_embedded_content   = False
+    category              = 'news, politics, Germany'
-    language = _('German') 
+    use_embedded_content  = False
+    language              = _('German') 
     max_articles_per_feed = 30 
+    no_stylesheets        = True
+    encoding              = 'utf-8'
+    remove_javascript     = True
 
-    preprocess_regexps = [
+    html2lrf_options = [
-       (re.compile(r'Zum Thema</span>.*?</BODY>', re.IGNORECASE | re.DOTALL), 
+                          '--comment', description
-        lambda match : ''),
+                        , '--category', category
-    ]    
+                        , '--publisher', publisher
+                        ]
+    
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' 
+    
+    keep_only_tags = [dict(name='div', attrs={'class':'Article'})]
+
+    remove_tags = [
+                     dict(name=['object','link','embed','base'])
+                    ,dict(name='div', attrs={'class':['LinkBoxModulSmall','ModulVerlagsInfo']})
+                  ]
     
 
     feeds = [ ('FAZ.NET', 'http://www.faz.net/s/Rub/Tpl~Epartner~SRss_.xml') ] 
 
     def print_version(self, url):
-        return url.replace('.html?rss_aktuell', '~Afor~Eprint.html') 
+        article, sep, rest = url.partition('?')    
+        return article.replace('.html', '~Afor~Eprint.html') 
 
+    def preprocess_html(self, soup):
+        mtag = '<meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>'
+        soup.head.insert(0,mtag)        
+        del soup.body['onload']
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup