diff --git a/resources/recipes/elmundo.recipe b/resources/recipes/elmundo.recipe index 71e9008166..aea60de304 100644 --- a/resources/recipes/elmundo.recipe +++ b/resources/recipes/elmundo.recipe @@ -1,4 +1,3 @@ -#!/usr/bin/env python __license__ = 'GPL v3' __copyright__ = '2009, Darko Miletic ' @@ -19,22 +18,19 @@ class ElMundo(BasicNewsRecipe): no_stylesheets = True use_embedded_content = False encoding = 'iso8859_15' - cover_url = 'http://estaticos02.cache.el-mundo.net/papel/imagenes/v2.0/logoverde.gif' - remove_javascript = True + language = 'es' - html2lrf_options = [ - '--comment', description - , '--category', category - , '--publisher', publisher - ] + conversion_options = { + 'comments' : description + ,'tags' : category + ,'language' : language + ,'publisher' : publisher + } - html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' + keep_only_tags = [dict(name='div', attrs={'class':'noticia'})] + remove_tags_before = dict(attrs={'class':['titular','antetitulo'] }) + remove_tags_after = dict(name='div' , attrs={'id':['desarrollo_noticia','tamano']}) - - keep_only_tags = [ - dict(name='div', attrs={'id':['bloqueprincipal','noticia']}) - ,dict(name='div', attrs={'class':['contenido_noticia_01']}) - ] remove_tags = [ dict(name='div', attrs={'class':['herramientas','publicidad_google']}) ,dict(name='div', attrs={'id':'modulo_multimedia' }) @@ -44,6 +40,8 @@ class ElMundo(BasicNewsRecipe): feeds = [ (u'Portada' , u'http://rss.elmundo.es/rss/descarga.htm?data2=4' ) + ,(u'Deportes' , u'http://rss.elmundo.es/rss/descarga.htm?data2=14') + ,(u'Economia' , u'http://rss.elmundo.es/rss/descarga.htm?data2=7' ) ,(u'Espana' , u'http://rss.elmundo.es/rss/descarga.htm?data2=8' ) ,(u'Internacional' , u'http://rss.elmundo.es/rss/descarga.htm?data2=9' ) ,(u'Cultura' , u'http://rss.elmundo.es/rss/descarga.htm?data2=6' ) @@ -51,10 +49,3 @@ class ElMundo(BasicNewsRecipe): ,(u'Comunicacion' , u'http://rss.elmundo.es/rss/descarga.htm?data2=26') ,(u'Television' , u'http://rss.elmundo.es/rss/descarga.htm?data2=76') ] - - def preprocess_html(self, soup): - for item in soup.findAll(style=True): - del item['style'] - return soup - - language = 'es'