from calibre.web.feeds.recipes import BasicNewsRecipe class NYTimes(BasicNewsRecipe): title = 'Focus' __author__ = 'Krittika Goyal' language = 'pl' description = 'Polish scientific monthly magazine' timefmt = ' [%d %b, %Y]' needs_subscription = False no_stylesheets = True keep_only_tags = dict(name='article', attrs={'class': 'content'}) remove_tags_after = dict(name='div', attrs={'class': 'inner_article'}) remove_tags = [ dict(name='div', attrs={'class': ['social_btns']}), ] # TO GET ARTICLE TOC def nejm_get_index(self): return self.index_to_soup('http://www.focus.pl/') # To parse artice toc def parse_index(self): soup = self.nejm_get_index() toc = soup.find('div', id='wrapper') articles = [] feeds = [] section_title = 'Focus Articles' for x in toc.findAll(True): if x.name == 'h1': # Article found a = x.find('a') if a is None: continue title = self.tag_to_string(a) url = a.get('href', False) if not url or not title: continue # if url.startswith('story'): url = 'http://www.focus.pl' + url self.log('\t\tFound article:', title) self.log('\t\t\t', url) articles.append({'title': title, 'url': url, 'description': '', 'date': ''}) feeds.append((section_title, articles)) return feeds