#!/usr/bin/env python2 ## # Last Edited: 2016-01-11 Carlos Alves ## __license__ = 'GPL v3' __author__ = '2010, Yuri Alvarez' __copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net' ''' elobservador.com.uy ''' from calibre.web.feeds.news import BasicNewsRecipe class Noticias(BasicNewsRecipe): title = 'El Observador' __author__ = 'yrvn' description = 'Noticias desde Uruguay' tags = 'news, sports, entretainment' 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='h1', attrs={'class': 'detail-title newDetailTextChange'}), dict(name='div', attrs={'class': 'cuerpo air newDetailTextChange'}) ] remove_tags = [ dict(name='div', attrs={ 'class': ['fecha', 'copyright', 'story_right']}), dict(name='div', attrs={'class': ['photo', 'social']}), dict(name='div', attrs={'id': 'widget'}), 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'Portada', u'http://www.elobservador.com.uy/rss/home.xml'), ] def get_cover_url(self): return 'http://css.elobservador.com.uy/css/181/images/logo.svg' def preprocess_html(self, soup): for item in soup.findAll(style=True): del item['style'] return soup