# 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') ] 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: '')] keep_only_tags = [dict(name='div', attrs={'class': ['article-detail']})]