This patch was created with `diff -uNr kurier.recipe.old kurier.recipe.new` against the kurier.recipe file in trunk.
Hope it's OK now.
Code:
--- kurier.recipe.old 2012-02-12 22:53:26.000000000 +0000
+++ kurier.recipe.new 2012-02-12 22:54:21.000000000 +0000
@@ -13,9 +13,10 @@
publisher = 'KURIER'
category = 'news, politics, Austria'
oldest_article = 2
- max_articles_per_feed = 200
+ max_articles_per_feed = 100
+ timeout = 30
+ encoding = None
no_stylesheets = True
- encoding = 'cp1252'
use_embedded_content = False
language = 'de_AT'
remove_empty_feeds = True
@@ -29,9 +30,11 @@
, 'language' : language
}
- remove_tags = [dict(attrs={'class':['functionsleiste','functions','social_positionierung','contenttabs','drucken','versenden','leserbrief','kommentieren','addthis_button']})]
+ remove_tags = [ dict(attrs={'id':['artikel_expand_symbol2','imgzoom_close2']}),
+ dict(attrs={'class':['linkextern','functionsleiste','functions','social_positionierung','contenttabs','drucken','versenden','leserbrief','kommentieren','addthis_button']})
+ ]
keep_only_tags = [dict(attrs={'id':'content'})]
- remove_tags_after = dict(attrs={'id':'author'})
+ remove_tags_after = [dict(attrs={'id':'author'})]
remove_attributes = ['width','height']
feeds = [
@@ -41,7 +44,7 @@
,(u'Kultur' , u'http://kurier.at/rss/kultur_kultur_rss.xml' )
,(u'Freizeit' , u'http://kurier.at/rss/freizeit_freizeit_rss.xml' )
,(u'Wetter' , u'http://kurier.at/rss/oewetter_rss.xml' )
- ,(u'Verkehr' , u'http://kurier.at/rss/verkehr_rss.xml' )
+ ,(u'Sport' , u'http://kurier.at/newsfeed/detail/sport_rss.xml' )
]
def preprocess_html(self, soup):