from calibre.web.feeds.news import BasicNewsRecipe, classes class SwarajyaMag(BasicNewsRecipe): title = u'Swarajya Magazine' __author__ = 'unkn0wn' description = 'Swarajya - a big tent for liberal right of centre discourse that reaches out, engages and caters to the new India.' language = 'en_IN' no_stylesheets = True remove_javascript = True use_embedded_content = False remove_attributes = ['height', 'width', 'style'] encoding = 'utf-8' keep_only_tags = [ dict(name='article') ] remove_tags = [ dict(name=['svg', 'button', 'source']), classes('swarajya_patron_block hs-tooltip-content hidden'), ] def preprocess_html(self, soup): for span in soup.findAll('span'): if self.tag_to_string(span).strip() == 'Tags': div = span.findParent('div') if div: div.extract() return soup def parse_index(self): soup = self.index_to_soup('https://swarajyamag.com/all-issues') a = soup.find('a', href=lambda x: x and x.startswith('https://swarajyamag.com/issue/')) url = a['href'] self.log('Downloading issue:', url) self.cover_url = a.img['src'] soup = self.index_to_soup(url) ans = [] for div in soup.findAll('div', attrs={'class':'rounded'}): url = div.findParent('a')['href'] if url.startswith('/'): url = 'https://swarajyamag.com' + url h4 = div.find('h4') title = self.tag_to_string(h4) d = h4.next_sibling desc = 'By ' + self.tag_to_string(d).strip() self.log(title, ' at ', url, '\n', desc) ans.append({'title': title, 'url': url, 'description': desc}) return [('Articles', ans)]