from calibre.web.feeds.news import BasicNewsRecipe class Gameplay_pl(BasicNewsRecipe): title = u'Gameplay.pl' oldest_article = 7 __author__ = 'fenuks' description = u'gameplay.pl - serwis o naszych zainteresowaniach, grach, filmach, książkach, muzyce, fotografii i konsolach.' category = 'games, movies, books, music' language = 'pl' index = 'https://gameplay.pl' masthead_url = 'https://gameplay.pl/img/gpy_top_logo.png' cover_url = 'https://gameplay.pl/img/gpy_top_logo.png' max_articles_per_feed = 100 remove_javascript = True no_stylesheets = True keep_only_tags = [dict( name='div', attrs={'class':'news-container'})] remove_tags = [ dict(name='div', attrs={'class': [ 'galeria', 'noedit center im', 'news_list', 'news_list_autor', 'stop_bot', 'tagi', 'news_tagi', 'social-16']}), dict(attrs={'usemap': '#map'}), dict(name='a', attrs={'class': ['pin-it-button', 'twitter-share-button']}) ] feeds = [(u'Wiadomo\u015bci', u'https://gameplay.pl/rss/')] def image_url_processor(self, baseurl, url): if 'https' not in url: return 'https://gameplay.pl' + url[2:] else: return url def preprocess_html(self, soup): for a in soup('a', href=True): if '../' in a['href']: a['href'] = self.index + a['href'][2:] return soup