from calibre.web.feeds.news import BasicNewsRecipe from calibre.ebooks.BeautifulSoup import BeautifulSoup class Gram_pl(BasicNewsRecipe): title = u'Gram.pl' __author__ = 'fenuks' description = u'Serwis społecznościowy o grach: recenzje, newsy, zapowiedzi, encyklopedia gier, forum. Gry PC, PS3, X360, PS Vita, sprzęt dla graczy.' category = 'games' language = 'pl' oldest_article = 8 index='http://www.gram.pl' max_articles_per_feed = 100 ignore_duplicate_articles = {'title', 'url'} no_stylesheets= True #extra_css = 'h2 {font-style: italic; font-size:20px;} .picbox div {float: left;}' cover_url=u'http://www.gram.pl/www/01/img/grampl_zima.png' keep_only_tags= [dict(id='articleModule')] remove_tags = [dict(attrs={'class':['breadCrump', 'dymek', 'articleFooter']})] feeds = [(u'Informacje', u'http://www.gram.pl/feed_news.asp'), (u'Publikacje', u'http://www.gram.pl/feed_news.asp?type=articles'), (u'Kolektyw- Indie Games', u'http://indie.gram.pl/feed/'), #(u'Kolektyw- Moto Games', u'http://www.motogames.gram.pl/news.rss') ] def parse_feeds (self): feeds = BasicNewsRecipe.parse_feeds(self) for feed in feeds: for article in feed.articles[:]: if 'REKLAMA SKLEP' in article.title.upper() or u'ARTYKUŁ:' in article.title.upper(): feed.articles.remove(article) return feeds def preprocess_html(self, soup): tag=soup.find(name='div', attrs={'class':'summary'}) if tag: tag.find(attrs={'class':'pros'}).insert(0, BeautifulSoup('