#!/usr/bin/env python # vim:fileencoding=utf-8 # License: GPLv3 Copyright: 2016, Kovid Goyal from __future__ import absolute_import, division, print_function, unicode_literals import re from calibre.web.feeds.news import BasicNewsRecipe def classes(classes): q = frozenset(classes.split(' ')) return dict(attrs={ 'class': lambda x: x and frozenset(x.split()).intersection(q)}) class TheHindu(BasicNewsRecipe): title = u'The Business Line' language = 'en_IN' oldest_article = 7 __author__ = 'Dhiru' max_articles_per_feed = 100 no_stylesheets = True keep_only_tags = [ dict(name='h1'), classes('textbyline article-image contentbody'), ] remove_tags = [ ] extra_css = '.photo-caption { font-size: smaller }' def preprocess_html(self, soup, *a): for img in soup.findAll(attrs={'data-proxy-image': True}): img['src'] = re.sub(r'/alternates/[^/]+', '/alternates/LANDSCAPE_730', img['data-proxy-image'], flags=re.I) return soup def parse_index(self): soup = self.index_to_soup( 'https://www.thehindubusinessline.com/todays-paper/tp-index') div = soup.find(attrs={'class': 'left-column'}) feeds = [] current_section = None current_articles = [] for x in div.findAll(['h2', 'li']): if current_section and x.name == 'li': a = x.find('a', href=True) if a is not None: title = self.tag_to_string(a) current_articles.append({'url': a['href'], 'title': title, 'date': '', 'description': ''}) self.log('\t' + title) if x.name == 'h2': if current_section and current_articles: feeds.append((current_section, current_articles)) current_section = self.tag_to_string(x).strip().capitalize() self.log(current_section) current_articles = [] return feeds