#!/usr/bin/env python __license__ = 'GPL v3' __copyright__ = '2008-2011, Lionel Bergeret ' ''' dhnet.be ''' from calibre import strftime from calibre.web.feeds.news import BasicNewsRecipe class DHNetBe(BasicNewsRecipe): title = u'La Derniere Heure' __author__ = u'Lionel Bergeret' description = u'News from Belgium in French' publisher = u'dhnet.be' category = 'news, Belgium' oldest_article = 3 language = 'fr' masthead_url = 'http://www.dhnet.be/images/homepage_logo_dh.gif' max_articles_per_feed = 20 no_stylesheets = True use_embedded_content = False timefmt = ' [%d %b %Y]' keep_only_tags = [ dict(name='div', attrs={'id': 'articleText'}), dict( name='div', attrs={'id': 'articlePicureAndLinks'}) ] feeds = [ (u'La Une', u'http://www.dhnet.be/rss'), (u'La Une Sports', u'http://www.dhnet.be/rss/dhsports/'), (u'La Une Info', u'http://www.dhnet.be/rss/dhinfos/') ] def preprocess_html(self, soup): for alink in soup.findAll('a'): if alink.string is not None: tstr = alink.string alink.replaceWith(tstr) return soup def get_cover_url(self): cover_url = strftime( 'http://pdf-online.dhnet.be/pdfonline/image/%Y%m%d/dh_%Y%m%d_nam_infoge_001.pdf.L.jpg') return cover_url