#!/usr/bin/env python __license__ = 'GPL v3' __author__ = '2010, Gustavo Azambuja ' ''' http://www.montevideo.com.uy ''' from calibre.web.feeds.news import BasicNewsRecipe class Noticias(BasicNewsRecipe): title = 'Montevideo COMM' __author__ = 'Gustavo Azambuja' description = 'Noticias de Uruguay' language = 'es_UY' timefmt = '[%a, %d %b, %Y]' use_embedded_content = False recursion = 5 encoding = 'utf-8' remove_javascript = True no_stylesheets = True oldest_article = 2 max_articles_per_feed = 100 keep_only_tags = [dict(id=['txt'])] remove_tags = [ dict(name=['object', 'link']) ] remove_attributes = ['width', 'height', 'style', 'font', 'color'] 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'Destacados', u'http://www.montevideo.com.uy/anxml.aspx?58'), (u'Noticias', u'http://www.montevideo.com.uy/anxml.aspx?59'), (u'Tecnologia', u'http://www.montevideo.com.uy/anxml.aspx?133'), (u'Tiempo Libre', u'http://www.montevideo.com.uy/anxml.aspx?60'), # (u'Deportes', u'http://www.montevideo.com.uy/anxml.aspx?968'), # (u'Pantallazo', u'http://www.montevideo.com.uy/anxml.aspx?1022'), (u'Gastronomia', u'http://www.montevideo.com.uy/anxml.aspx?1023') ] def get_cover_url(self): return 'http://sphotos.ak.fbcdn.net/hphotos-ak-snc1/hs276.snc1/10319_147339559330_147337559330_2625816_6636564_n.jpg' def preprocess_html(self, soup): for item in soup.findAll(style=True): del item['style'] return soup