calibre/recipes/fronda.recipe
2011-05-08 09:36:46 -06:00

40 lines
1.5 KiB
Python

#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = u'2010, Tomasz Dlugosz <tomek3d@gmail.com>'
'''
fronda.pl
'''
from calibre.web.feeds.news import BasicNewsRecipe
import re
class Fronda(BasicNewsRecipe):
title = u'Fronda.pl'
publisher = u'Fronda.pl'
description = u'Portal po\u015bwi\u0119cony - Infformacje'
language = 'pl'
__author__ = u'Tomasz D\u0142ugosz'
oldest_article = 7
max_articles_per_feed = 100
use_embedded_content = False
feeds = [(u'Infformacje', u'http://fronda.pl/news/feed')]
keep_only_tags = [dict(name='h2', attrs={'class':'news_title'}),
dict(name='div', attrs={'class':'naglowek_tresc'}),
dict(name='div', attrs={'id':'czytaj'}) ]
remove_tags = [dict(name='a', attrs={'class':'print'})]
preprocess_regexps = [
(re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
[ (r'<p><a href="http://fronda.pl/sklepy">.*</a></p>', lambda match: ''),
(r'<p><a href="http://fronda.pl/pasaz">.*</a></p>', lambda match: ''),
(r'<h3><strong>W.* lektury.*</a></p></div>', lambda match: '</div>'),
(r'<h3>Zobacz t.*?</div>', lambda match: '</div>'),
(r'<p[^>]*>&nbsp;</p>', lambda match: ''),
(r'<p><span style=".*?"><br /></span></p> ', lambda match: ''),
(r'<a style=\'float:right;margin-top:3px;\' href="http://www.facebook.com/share.php?.*?</a>', lambda match: '')]
]