from calibre.web.feeds.news import BasicNewsRecipe class ESO(BasicNewsRecipe): title = u'ESO PL' __author__ = 'fenuks' description = u'ESO, Europejskie Obserwatorium Południowe, buduje i obsługuje najbardziej zaawansowane naziemne teleskopy astronomiczne na świecie' category = 'astronomy' language = 'pl' oldest_article = 7 max_articles_per_feed = 100 no_stylesheets = True remove_empty_feeds = True use_embedded_content = False cover_url = 'https://twimg0-a.akamaihd.net/profile_images/1922519424/eso-twitter-logo.png' keep_only_tags = [dict(attrs={'class':'subcl'})] remove_tags = [dict(id='lang_row'), dict(attrs={'class':['pr_typeid', 'pr_news_feature_link', 'outreach_usage', 'hidden']})] feeds = [(u'Wiadomo\u015bci', u'http://www.eso.org/public/poland/news/feed/'), (u'Og\u0142oszenia', u'http://www.eso.org/public/poland/announcements/feed/'), (u'Zdj\u0119cie tygodnia', u'http://www.eso.org/public/poland/images/potw/feed/')] def preprocess_html(self, soup): for a in soup.findAll('a', href=True): if a['href'].startswith('/'): a['href'] = 'http://www.eso.org' + a['href'] return soup