#!/usr/bin/env python # vim:fileencoding=utf-8 __license__ = 'GPL v3' __copyright__ = '2010, Darko Miletic ' ''' izvestia.ru ''' from calibre.web.feeds.news import BasicNewsRecipe class Izvestia(BasicNewsRecipe): title = 'Izvestia' __author__ = 'Darko Miletic (with fixes by bugmen00t)' description = 'News from Russia' publisher = 'Izvestia' category = 'news, politics, Russia' oldest_article = 5 max_articles_per_feed = 100 auto_cleanup = False no_stylesheets = True use_embedded_content = False language = 'ru' publication_type = 'newspaper' cover_url = u'https://cdn.iz.ru/profiles/portal/themes/purple/images/favicons/apple-icon-180x180.png' remove_tags_before = dict(name='div', attrs={'role': 'article'}) remove_tags_after = dict(name='div', attrs={'role': 'article'}) remove_tags = [ dict(name='div', attrs={'class': 'article_page__left__top__views'}), dict(name='div', attrs={'class': 'hash_tags'}), dict(name='div', attrs={'class': 'get_yandex_subscription_links'}), dict(name='div', attrs={'class': 'article_buttons_block'}), dict(name='div', attrs={'class': 'rubrics_btn'}), dict(name='div', attrs={'class': 'hidden'}), dict(name='div', attrs={'class': 'share_bottom2'}), dict(name='div', attrs={'class': 'recommendation-block'}), dict(name='div', attrs={'class': 'plug-text'}), dict(name='div', attrs={'class': 'get_news_link'}), dict(name='div', attrs={'itemprop': 'address'}) ] feeds = [(u'Новости', u'https://iz.ru/xml/rss/all.xml')] def preprocess_html(self, soup): for img in soup.findAll('img', attrs={'data-src': True}): img['src'] = img['data-src'] return soup