diff --git a/recipes/gkt.recipe b/recipes/gkt.recipe index 45c1ecd782..6da219cb3a 100644 --- a/recipes/gkt.recipe +++ b/recipes/gkt.recipe @@ -7,7 +7,6 @@ class Politics(BasicNewsRecipe): __author__ = 'Kovid Goyal' oldest_article = 7 # days max_articles_per_feed = 20 - use_embedded_content = False no_stylesheets = True no_javascript = True @@ -15,7 +14,7 @@ class Politics(BasicNewsRecipe): 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]'): + for a in root.xpath('//div[@class="post-content"]/h1/a[@href]'): title = self.tag_to_string(a).strip() url = a.get('href') if title and url: @@ -26,14 +25,15 @@ class Politics(BasicNewsRecipe): 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 + h3 = root.xpath('//h3[@class="widget-title"]')[1] + for a in h3.getparent().xpath('descendant::li/a[@href]'): + category = self.tag_to_string(a).strip() + if 'PDF' in category: + continue + 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)) return ans