#!/usr/bin/env python __license__ = 'GPL v3' __copyright__ = '2008-2011, Lionel Bergeret ' ''' lavenir.net ''' from calibre.web.feeds.news import BasicNewsRecipe class LAvenir(BasicNewsRecipe): title = u'L\'Avenir' __author__ = u'Lionel Bergeret' description = u'News from Belgium in French' publisher = u'lavenir.net' category = 'news, Belgium' oldest_article = 3 language = 'fr' max_articles_per_feed = 20 no_stylesheets = True use_embedded_content = False timefmt = ' [%d %b %Y]' keep_only_tags = [ dict(name='div', attrs={'class': 'photo'}), dict(name='p', attrs={ 'class': 'intro'}), dict(name='div', attrs={'class': 'article-body'}) ] feeds = [ (u'Belgique', u'http://www.lavenir.net/rss.aspx?foto=1&intro=1§ion=info&info=df156511-c24f-4f21-81c3-a5d439a9cf4b'), (u'Monde', u'http://www.lavenir.net/rss.aspx?foto=1&intro=1§ion=info&info=1642237c-66b9-4e8a-a8c1-288d61fefe7e'), (u'Societe', u'http://www.lavenir.net/rss.aspx?foto=1&intro=1§ion=info&info=12e1a2f4-7e03-4cf1-afec-016869072317') ] 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 = 'http://www.lavenir.net/extra/Static/journal/Pdf/1/UNE_Nationale.PDF' return cover_url