Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Kurier

Browse Source
This commit is contained in:
Kovid Goyal 2016-06-26 13:25:46 +05:30
parent ecc428c98b
commit fdd5a99328
1 changed files with 30 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

47
recipes/kurier.recipe
View File

@ -1,9 +1,15 @@
#!/usr/bin/env python2
# vim:fileencoding=utf-8
from __future__ import unicode_literals, division, absolute_import, print_function
__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
kurier.at
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class Kurier(BasicNewsRecipe):
@ -15,13 +21,11 @@ class Kurier(BasicNewsRecipe):
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
publication_type = 'newspaper'
extra_css = ' body{font-family: Verdana,Helvetica,sans-serif } img{margin-bottom: 0.4em} .bild_us{font-size: x-small} '
conversion_options = {
'comment' : description
@ -30,22 +34,31 @@ class Kurier(BasicNewsRecipe):
, '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 = [
(u'Nachrichten', u'http://kurier.at/rss/nachrichten_nachrichten_rss.xml' )
,(u'Techno' , u'http://kurier.at/rss/techno_techno_rss.xml' )
,(u'Wirtschaft' , u'http://kurier.at/rss/wirtschaft_wirtschaft_rss.xml' )
,(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' )
]
('Politik', 'http://kurier.at/politik/xml/rss'),
('Wirtschaft', 'http://kurier.at/wirtschaft/xml/rss'),
('Chronik', 'http://kurier.at/chronik/xml/rss'),
('Kultur', 'http://kurier.at/kultur/xml/rss'),
('Leben', 'http://kurier.at/leben/xml/rss'),
('Menschen', 'http://kurier.at/menschen/xml/rss'),
('Sport', 'http://kurier.at/sport/xml/rss')
]
keep_only_tags = [
dict(name='article', attrs={'class':re.compile('main-article')})
]
remove_tags = [
dict(name='div', attrs={'class':'social-media-container'}),
dict(name='section', attrs={'class':'tags'}),
dict(name='section', attrs={'class':re.compile('comment-box')}),
dict(name='section', attrs={'class':re.compile('related-content')}),
dict(name='section', attrs={'class':re.compile('article-slider')}),
dict(name='section', attrs={'class':re.compile('commentcontainer')}),
dict(name='blockquote')
]
remove_attributes = ['width','height']
def preprocess_html(self, soup):
for item in soup.findAll(style=True):