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

39 lines
1.2 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 plRecipe(BasicNewsRecipe):
__author__ = 'bubak'
title = u'Parlamentn\u00ed Listy'
publisher = u''
description = ''
oldest_article = 1
max_articles_per_feed = 20
feeds = [
(u'Parlamentní listy.cz', u'http://www.parlamentnilisty.cz/export/rss.aspx')
]
#encoding = 'iso-8859-2'
language = 'cs'
cover_url = 'http://www.parlamentnilisty.cz/design/listy-logo2.png'
remove_javascript = True
no_stylesheets = True
use_embedded_content = False
remove_attributes = []
remove_tags = [dict(name='div', attrs={'class':['articledetailboxin','crumbs', 'relatedarticles articledetailbox']}),
dict(name='div', attrs={'class':['socialshare-1 noprint', 'socialshare-2 noprint']}),
dict(name='div', attrs={'id':'widget'}),
dict(name='div', attrs={'class':'article-discussion-box noprint'})]
preprocess_regexps = [(re.compile(r'<(span|strong)[^>]*>\s*Ptejte se politik.*', re.DOTALL|re.IGNORECASE), lambda match: '</body>')]
keep_only_tags = [dict(name='div', attrs={'class':['article-detail']})]