#!/usr/bin/python # -*- coding: utf-8 -*- __license__ = 'GPL v3' __copyright__ = '2010, Vadim Dyadkin, dyadkin@gmail.com' __author__ = 'Vadim Dyadkin' from calibre.web.feeds.news import BasicNewsRecipe class Computerra(BasicNewsRecipe): title = u'\u041a\u043e\u043c\u043f\u044c\u044e\u0442\u0435\u0440\u0440\u0430' recursion = 50 oldest_article = 100 __author__ = 'Vadim Dyadkin' max_articles_per_feed = 100 use_embedded_content = False simultaneous_downloads = 5 language = 'ru' description = u'\u041a\u043e\u043c\u043f\u044c\u044e\u0442\u0435\u0440\u044b, \u043e\u043a\u043e\u043b\u043e\u043d\u0430\u0443\u0447\u043d\u044b\u0435 \u0438 \u043e\u043a\u043e\u043b\u043e\u0444\u0438\u043b\u043e\u0441\u043e\u0444\u0441\u043a\u0438\u0435 \u0441\u0442\u0430\u0442\u044c\u0438, \u0433\u0430\u0434\u0436\u0435\u0442\u044b.' keep_only_tags = [dict(name='div', attrs={'id': 'content'}),] feeds = [(u'\u041a\u043e\u043c\u043f\u044c\u044e\u0442\u0435\u0440\u0440\u0430', 'http://feeds.feedburner.com/ct_news/'),] remove_tags = [dict(name='div', attrs={'id': ['fin', 'idc-container', 'idc-noscript',]}), dict(name='ul', attrs={'class': "related_post"}), dict(name='p', attrs={'class': 'info'}), dict(name='a', attrs={'rel': 'tag', 'class': 'twitter-share-button', 'type': 'button_count'}), dict(name='h2', attrs={}),] extra_css = 'body { text-align: justify; }' def get_article_url(self, article): return article.get('feedburner:origLink', article.get('guid'))