#!/usr/bin/env python2 ## # Last Edited: 2016-01-11 Carlos Alves ## __license__ = 'GPL v3' __author__ = '2010, Gustavo Azambuja ' ''' 180.com.uy ''' from calibre.web.feeds.news import BasicNewsRecipe class Noticias(BasicNewsRecipe): title = '180.com.uy' __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 remove_tags_after = dict(name='article') keep_only_tags = [ dict(name='h3', attrs={'class': 'title'}), dict(name='div', attrs={'class': 'copete'}), dict(name='article', attrs={'class': 'texto'}) ] 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'Titulares', u'http://www.180.com.uy/feed.php') ] def get_cover_url(self): pass def preprocess_html(self, soup): for item in soup.findAll(style=True): del item['style'] return soup