__license__ = 'GPL v3' __copyright__ = '2010, Hiroshi Miura ' ''' www.jiji.com ''' from calibre.web.feeds.news import BasicNewsRecipe class JijiDotCom(BasicNewsRecipe): title = u'\u6642\u4e8b\u901a\u4fe1' __author__ = 'Hiroshi Miura' description = 'World News from Jiji Press' publisher = 'Jiji Press Ltd.' category = 'news' oldest_article = 6 max_articles_per_feed = 100 encoding = 'euc_jisx0213' language = 'ja' masthead_url = 'http://jen.jiji.com/images/logo_jijipress.gif' top_url = 'http://www.jiji.com/' feeds = [(u'\u30cb\u30e5\u30fc\u30b9', u'http://www.jiji.com/rss/ranking.rdf')] remove_tags_before = dict(id="article-area") remove_tags_after = dict(id="ad_google") def get_cover_url(self): cover_url = 'http://www.jiji.com/img/top_header_logo2.gif' soup = self.index_to_soup(self.top_url) cover_item = soup.find('div', attrs={'class': 'top-pad-photos'}) if cover_item: cover_url = self.top_url + cover_item.img['src'] return cover_url