calibre/recipes/demagog.cz.recipe
2012-11-18 23:53:33 +05:30

40 lines
1.1 KiB
Plaintext

# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from __future__ import unicode_literals
from calibre.web.feeds.recipes import BasicNewsRecipe
import re
class demagogRecipe(BasicNewsRecipe):
__author__ = 'bubak'
title = u'Demagog.cz'
publisher = u''
description = 'demagog.cz'
oldest_article = 6
max_articles_per_feed = 20
use_embedded_content = False
remove_empty_feeds = True
feeds = [
(u'Aktuality', u'http://demagog.cz/rss')
]
#encoding = 'iso-8859-2'
language = 'cs'
cover_url = 'http://demagog.cz/content/images/demagog.cz.png'
remove_javascript = True
no_stylesheets = True
extra_css = """
.vyrok_suhrn{margin-top:50px; }
.vyrok{margin-bottom:30px; }
"""
remove_tags = [dict(name='a', attrs={'class':'vyrok_odovodnenie_tgl'}),
dict(name='img', attrs={'class':'vyrok_fotografia'})]
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='div', attrs={'class':'vyrok_text_after'})
preprocess_regexps = [(re.compile(r'(<div class="vyrok_suhrn">)', re.DOTALL|re.IGNORECASE), lambda match: '\1<hr>')]