...

recipes/the_scotsman.recipe

@@ -1,4 +1,3 @@
-
 __license__   = 'GPL v3'
 __copyright__ = '2008 - 2011, Darko Miletic <darko.miletic at gmail.com>'
 '''
@@ -17,7 +16,6 @@ class TheScotsman(BasicNewsRecipe):
     max_articles_per_feed = 100
     no_stylesheets        = True
     use_embedded_content  = False
-    auto_cleanup = True
     language              = 'en_GB'
     encoding              = 'utf-8'
     publication_type      = 'newspaper'
@@ -25,14 +23,7 @@ class TheScotsman(BasicNewsRecipe):
     masthead_url          = 'http://www.scotsman.com/webimage/swts_thescotsman_image_e_7_25526!image/3142543874.png_gen/derivatives/default/3142543874.png'
     extra_css             = 'body{font-family: Arial,Helvetica,sans-serif}'
 
-    
-    #keep_only_tags    = [dict(attrs={'class':'editorialSection'})]
-    #remove_tags_after = dict(attrs={'class':'socialBookmarkPanel'})
-    #remove_tags       = [
-                           #dict(name=['meta','iframe','object','embed','link']),
-                           #dict(attrs={'class':['secondaryArticlesNav','socialBookmarkPanel']}),
-                           #dict(attrs={'id':'relatedArticles'})
-                        #]
+    keep_only_tags    = [dict(name='div', attrs={'class':'article'})]
     remove_attributes = ['lang']
 
     conversion_options = {
@@ -56,10 +47,3 @@ class TheScotsman(BasicNewsRecipe):
                         ('Opinion'      , 'http://www.scotsman.com/cmlink/1.957054')
                      ]
 
-    #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'
-        #return soup