From 6bd12a445002c5ea6c65ccccd236e50698ae2b9c Mon Sep 17 00:00:00 2001
From: Kovid Goyal <kovid@kovidgoyal.net>
Date: Sun, 7 Apr 2013 16:39:01 +0530
Subject: [PATCH] Update The Onion

---
 recipes/theonion.recipe | 46 +++++++++--------------------------------
 1 file changed, 10 insertions(+), 36 deletions(-)

diff --git a/recipes/theonion.recipe b/recipes/theonion.recipe
index b0eacbb5e0..d177e0978d 100644
--- a/recipes/theonion.recipe
+++ b/recipes/theonion.recipe
@@ -36,47 +36,21 @@ class TheOnion(BasicNewsRecipe):
                         , 'publisher': publisher
                         , 'language' : language
                         }
-
-    keep_only_tags = [
-                         dict(name='h2', attrs={'class':['section_title','title']})
-                        ,dict(attrs={'class':['main_image','meta','article_photo_lead','article_body']})
-                        ,dict(attrs={'id':['entries']})
-                     ]
-    remove_attributes=['lang','rel']
-    remove_tags_after = dict(attrs={'class':['article_body','feature_content']})
+    keep_only_tags = [dict(name='article', attrs={'class':'full-article'})]
     remove_tags = [
-                     dict(name=['object','link','iframe','base','meta'])
-                    ,dict(name='div', attrs={'class':['toolbar_side','graphical_feature','toolbar_bottom']})
-                    ,dict(name='div', attrs={'id':['recent_slider','sidebar','pagination','related_media']})
-                  ]
-
+        dict(name=['nav', 'aside', 'section', 'meta']),
+        {'attrs':{'class':lambda x: x and ('share-tools' in x or 'ad-zone' in x)}},
+    ]
 
     feeds = [
               (u'Daily'  , u'http://feeds.theonion.com/theonion/daily' )
              ,(u'Sports' , u'http://feeds.theonion.com/theonion/sports' )
             ]
 
-    def get_article_url(self, article):
-        artl = BasicNewsRecipe.get_article_url(self, article)
-        if artl.startswith('http://www.theonion.com/audio/'):
-           artl = None
-        return artl
-
-    def preprocess_html(self, soup):
-        for item in soup.findAll(style=True):
-            del item['style']
-        for item in soup.findAll('a'):
-            limg = item.find('img')
-            if item.string is not None:
-               str = item.string
-               item.replaceWith(str)
-            else:
-               if limg:
-                  item.name  = 'div'
-                  item.attrs = []
-                  if not limg.has_key('alt'):
-                     limg['alt'] = 'image'
-               else:
-                   str = self.tag_to_string(item)
-                   item.replaceWith(str)
+    def preprocess_html(self, soup, *args):
+        for img in soup.findAll('img', attrs={'data-src':True}):
+            if img['data-src']:
+                img['src'] = img['data-src']
         return soup
+
+