#!/usr/bin/env python2 ## # Title: Diario 10minutos.com.uy News and Sports Calibre Recipe # Contact: Carlos Alves - ## # License: GNU General Public License v3 - http://www.gnu.org/copyleft/gpl.html # Copyright: Carlos Alves - ## # Written: September 2013 # Last Edited: 2016-01-11 ## __license__ = 'GPL v3' __author__ = '2016, Carlos Alves ' ''' 10minutos.com.uy ''' from calibre.web.feeds.news import BasicNewsRecipe class General(BasicNewsRecipe): title = '10minutos' __author__ = 'Carlos Alves' description = 'Noticias de Salto - Uruguay' tags = 'news, sports' language = 'es_UY' timefmt = '[%a, %d %b, %Y]' use_embedded_content = False recursion = 5 encoding = 'utf8' remove_javascript = True no_stylesheets = True oldest_article = 2 max_articles_per_feed = 100 keep_only_tags = [dict(name='div', attrs={'class': 'post-content'})] remove_tags = [ dict(name='div', attrs={'class': ['hr', 'titlebar', 'navigation']}), dict(name='div', attrs={'class': 'sharedaddy sd-sharing-enabled'}), dict(name='p', attrs={'class': 'post-meta'}), 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'Articulos', u'http://10minutos.com.uy/?feed=rss2') ] def get_cover_url(self): return 'http://10minutos.com.uy/a/img/logo.png' def preprocess_html(self, soup): for item in soup.findAll(style=True): del item['style'] return soup