Fix Fudzilla

resources/recipes/fudzilla.recipe

@@ -1,27 +1,41 @@
 #!/usr/bin/env  python
 
 __license__   = 'GPL v3'
-__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
+__copyright__ = '2010 Starson17'
 '''
 fudzilla.com
 '''
 
+import re
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Fudzilla(BasicNewsRecipe):
     title                 = u'Fudzilla'
-    __author__            = 'Darko Miletic'
+    __author__            = 'Starson17'
     language = 'en'
 
     description           = 'Tech news'
     oldest_article        = 7
+    remove_javascript = True
     max_articles_per_feed = 100
     no_stylesheets        = True
     use_embedded_content  = False
 
-    feeds = [ (u'Posts', u'http://www.fudzilla.com/index.php?option=com_rss&feed=RSS2.0&no_html=1')]
 
-    def print_version(self, url):
-        nurl = url.replace('http://www.fudzilla.com/index.php','http://www.fudzilla.com/index2.php')
-        nmain, nsep, nrest = nurl.partition('&Itemid=')
-        return  nmain + '&pop=1&page=0&Itemid=1'
+    remove_tags_before = dict(name='div', attrs={'class':['padding']})
+
+    remove_tags = [dict(name='td', attrs={'class':['left','right']}),
+                   dict(name='div', attrs={'id':['toolbar','buttons']}), 
+                   dict(name='div', attrs={'class':['artbannersxtd','back_button']}), 
+                   dict(name='span', attrs={'class':['pathway']}), 
+                   dict(name='th', attrs={'class':['pagenav_next','pagenav_prev']}), 
+                   dict(name='table', attrs={'class':['headlines']}), 
+                   ]
+
+    feeds = [
+             (u'Posts', u'http://www.fudzilla.com/index.php?option=com_rss&feed=RSS2.0&no_html=1')
+             ]
+
+    preprocess_regexps = [
+        (re.compile(r'<p class="MsoNormal"> Welcome.*</p> ', re.DOTALL|re.IGNORECASE), lambda match: '')
+        ]