from calibre.web.feeds.news import BasicNewsRecipe from calibre.ebooks.BeautifulSoup import BeautifulSoup class Elektroda(BasicNewsRecipe): title = u'Elektroda' oldest_article = 8 __author__ = 'fenuks' description = 'Międzynarodowy portal elektroniczny udostępniający bogate zasoby z dziedziny elektroniki oraz forum dyskusyjne.' cover_url = 'http://demotywatory.elektroda.pl/Thunderpic/logo.gif' category = 'electronics' language = 'pl' max_articles_per_feed = 100 no_stylesheets = True feeds = [(u'Elektroda', u'http://www.elektroda.pl/rtvforum/rss.php')] keep_only_tags = [dict(name='div', attrs={'class': 'title-wrap pull-left'}), dict(name='ul', attrs={'class': 'topic-lists clearfix'}) ] def preprocess_html(self, soup): tag = soup.find('span', attrs={'class': 'postbody'}) if tag: pos = len(tag.contents) tag.insert(pos, BeautifulSoup('
')) return soup def parse_feeds(self): feeds = BasicNewsRecipe.parse_feeds(self) for feed in feeds: for article in feed.articles[:]: article.title = article.title[article.title.find("::") + 3:] return feeds