home *** CD-ROM | disk | FTP | other *** search
- #!/usr/bin/env python
-
- __license__ = 'GPL v3'
- __copyright__ = u'2010, Tomasz Dlugosz <tomek3d@gmail.com>'
- '''
- rmf24.pl
- '''
-
- import re
- from calibre.web.feeds.news import BasicNewsRecipe
-
- class RMF24_ESKN(BasicNewsRecipe):
- title = u'Rmf24.pl - Ekonomia Sport Kultura Nauka'
- description = u'Ekonomia, sport, kultura i nauka ze strony rmf24.pl'
- language = 'pl'
- oldest_article = 7
- max_articles_per_feed = 100
- __author__ = u'Tomasz D\u0142ugosz'
- no_stylesheets = True
- remove_javascript = True
-
- feeds = [(u'Ekonomia', u'http://www.rmf24.pl/ekonomia/feed'),
- (u'Sport', u'http://www.rmf24.pl/sport/feed'),
- (u'Kultura', u'http://www.rmf24.pl/kultura/feed'),
- (u'Nauka', u'http://www.rmf24.pl/nauka/feed')]
-
- keep_only_tags = [dict(name='div', attrs={'class':'box articleSingle print'})]
-
- remove_tags = [
- dict(name='div', attrs={'class':'toTop'}),
- dict(name='div', attrs={'class':'category'}),
- dict(name='div', attrs={'class':'REMOVE'}),
- dict(name='div', attrs={'class':'embed embedAd'})]
-
- extra_css = '''
- h1 { font-size: 1.2em; }
- '''
-
- preprocess_regexps = [
- (re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
- [
- (r'<h2>Zdj.cie</h2>', lambda match: ''),
- (r'embed embed(Left|Right|Center) articleEmbed(Audio|Wideo articleEmbedVideo|ArticleFull|ArticleTitle|ArticleListTitle|AlbumHorizontal)">', lambda match: 'REMOVE">'),
- (r'<a href="http://www.facebook.com/pages/RMF24pl/.*?>RMF24.pl</a> on Facebook</div>', lambda match: '</div>')
- ]
- ]
-