from calibre.web.feeds.news import BasicNewsRecipe class Politics(BasicNewsRecipe): title = u'General Knowledge Today' language = 'en_IN' __author__ = 'Kovid Goyal' oldest_article = 7 # days max_articles_per_feed = 20 use_embedded_content = False no_stylesheets = True no_javascript = True auto_cleanup = True def parse_gkt_section(self, url): root = self.index_to_soup(url, as_tree=True) for a in root.xpath('//h1[@class="post-title"]/a[@href]'): title = self.tag_to_string(a).strip() url = a.get('href') if title and url: self.log('\tFound article:', title, 'at', url) yield {'title':title, 'url':url} def parse_index(self): url = 'http://www.gktoday.in/' root = self.index_to_soup(url, as_tree=True) ans = [] for h3 in root.xpath('//h3[@class="widget-title" and contains(text(), "Current Affairs Category")]'): for a in h3.getparent().xpath('descendant::li/a[@href]'): category = self.tag_to_string(a).strip() url = a.get('href') self.log('Found section:', category) articles = list(self.parse_gkt_section(url)) + list(self.parse_gkt_section(url + '/page/2')) if articles: ans.append((category, articles)) break return ans