#!/usr/bin/env python2 __license__ = 'GPL v3' __author__ = '2013, Carlos Alves ' ''' unoticias.com.uy ''' from calibre.web.feeds.news import BasicNewsRecipe class General(BasicNewsRecipe): title = 'UNoticias' __author__ = 'Carlos Alves' description = 'Noticias Uruguay' tags = 'news, sports, politics' language = 'es_UY' timefmt = '[%a, %d %b, %Y]' use_embedded_content = False recursion = 5 encoding = 'ISO-8859-1' remove_javascript = True no_stylesheets = True oldest_article = 2 max_articles_per_feed = 100 keep_only_tags = [ dict(name='h1', attrs={'class':'nombre'}), dict(name='h2', attrs={'class':'copete t20'}), dict(name='div', attrs={'class':'desc'}) ] remove_tags = [ dict(name='div', attrs={'class':['br', 'hr', 'titlebar', 'navigation']}), dict(name='div', attrs={'id':'comment'}), dict(name=['object','link']) ] extra_css = ''' h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;} h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;} h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;} p {font-family:Arial,Helvetica,sans-serif;} ''' feeds = [ (u'Nacionales', u'http://www.unoticias.com.uy/RSS/nacionales.xml'), (u'Deportes', u'http://www.unoticias.com.uy/RSS/deportes.xml'), (u'Sociedad', u'http://www.unoticias.com.uy/RSS/Sociedad.xml') ] def get_cover_url(self): return 'http://www.unoticias.com.uy/artworks/logos/logo_small.gif' def preprocess_html(self, soup): for item in soup.findAll(style=True): del item['style'] return soup