#!/usr/bin/env python __license__ = 'GPL v3' __author__ = 'Gabriele Marini, based on Darko Miletic' __copyright__ = '2009-2010, Darko Miletic ' description = 'Italian daily newspaper - 02-05-2010' ''' http://www.adnkronos.com/ ''' from calibre.web.feeds.news import BasicNewsRecipe class Adnkronos(BasicNewsRecipe): __author__ = 'Gabriele Marini' description = 'News agency' cover_url = 'http://www.adnkronos.com/IGN6/img/popup_ign.jpg' title = 'Adnkronos' publisher = 'Adnkronos Group - ews agency' category = 'News, politics, culture, economy, general interest' language = 'it' timefmt = '[%a, %d %b, %Y]' oldest_article = 7 max_articles_per_feed = 80 use_embedded_content = False recursion = 10 remove_javascript = True def get_article_url(self, article): link = article.get('id', article.get('guid', None)) return link extra_css = ' .newsAbstract{font-style: italic} ' keep_only_tags = [dict(name='div', attrs={'class': ['breadCrumbs', 'newsTop', 'newsText']})] remove_tags = [dict(name='div', attrs={'class': ['leogoo', 'leogoo2']})] feeds = [ ('Prima Pagina', 'http://rss.adnkronos.com/RSS_PrimaPagina.xml'), ('Ultima Ora', 'http://rss.adnkronos.com/RSS_Ultimora.xml'), ('Politica', 'http://rss.adnkronos.com/RSS_Politica.xml'), ('Esteri', 'http://rss.adnkronos.com/RSS_Esteri.xml'), ('Cronoca', 'http://rss.adnkronos.com/RSS_Cronaca.xml'), ('Economia', 'http://rss.adnkronos.com/RSS_Economia.xml'), ('Finanza', 'http://rss.adnkronos.com/RSS_Finanza.xml'), ('CyberNews', 'http://rss.adnkronos.com/RSS_CyberNews.xml'), ('Spettacolo', 'http://rss.adnkronos.com/RSS_Spettacolo.xml'), ('Cultura', 'http://rss.adnkronos.com/RSS_Cultura.xml'), ('Sport', 'http://rss.adnkronos.com/RSS_Sport.xml'), ('Sostenibilita', 'http://rss.adnkronos.com/RSS_Sostenibilita.xml'), ('Salute', 'http://rss.adnkronos.com/RSS_Salute.xml'), ]