The Kurier website has been revamped, meaning that the calibre recipe should be updated.
Suggested patch to fix character encoding issues and structural changes, below:
Code:
*** kurier.recipe Mon Feb 6 07:47:02 2012
--- kurier.recipe.orig Sat Feb 4 17:43:04 2012
***************
*** 13,22 ****
publisher = 'KURIER'
category = 'news, politics, Austria'
oldest_article = 2
! max_articles_per_feed = 100
! timeout = 30
! encoding = None
no_stylesheets = True
use_embedded_content = False
language = 'de_AT'
remove_empty_feeds = True
--- 13,21 ----
publisher = 'KURIER'
category = 'news, politics, Austria'
oldest_article = 2
! max_articles_per_feed = 200
no_stylesheets = True
+ encoding = 'cp1252'
use_embedded_content = False
language = 'de_AT'
remove_empty_feeds = True
***************
*** 30,40 ****
, 'language' : language
}
! 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_attributes = ['width','height']
feeds = [
--- 29,37 ----
, 'language' : language
}
! remove_tags = [dict(attrs={'class':['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_attributes = ['width','height']
feeds = [
***************
*** 44,50 ****
,(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'Sport' , u'http://kurier.at/newsfeed/detail/sport_rss.xml' )
]
def preprocess_html(self, soup):
--- 41,47 ----
,(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' )
]
def preprocess_html(self, soup):