No se si esto es lo que queriais...
Código:
class AdvancedUserRecipe1289098587(BasicNewsRecipe):
title = u'GUIA PROGRAMACION TV'
oldest_article = 1
max_articles_per_feed = 20
__author__ = ' KRorschachZ./Rickydh'
description = 'Tv rss'
timefmt = ' [%d %b, %Y]'
language = 'es_ES'
no_stylesheets = True
remove_javascript = True
keep_only_tags = [
dict(name='div', attrs={'id':'show'}),
dict(name='div', attrs={'class':'intro-datasheet'})
]
remove_tags = [
dict(name='div', attrs={'class':'toolbox'}),
dict(name='div', attrs={'class':'rater inline'})
]
remove_tags_after = [
dict(name='div', attrs={'class':'toolbox'}),
dict(name='div', attrs={'class':'rater inline'})
]
feeds = [
(u'Noticias TV', u'http://www.sincroguia.tv/rss/rss.php?types=news')
,(u'TVE 1', u'http://www.miguiatv.com/rss/tve1.xml')
,(u'TVE 2', u'http://www.miguiatv.com/rss/la2.xml')
,(u'ANT 3', u'http://www.miguiatv.com/rss/antena3.xml')
,(u'Cuatro TV', u'http://www.miguiatv.com/rss/cuatro.xml')
,(u'Tele 5', u'http://www.miguiatv.com/rss/telecinco.xml')
,(u'La Sexta', u'http://www.miguiatv.com/rss/la-sexta.xml')
,(u'Peliculas', u'http://www.laguiatv.com/rss/feeds/peliculas.xml')
]
# remove_attributes = ['width','height']
extra_css = '''
h2{font-family: serif; font-size: small; font-weight: bold; color: #000000; text-align: justify}
h1{font-family: serif; font-size: 120%; font-weight: bold; color: #000000; text-align: justify}
.desc{ font-family: sans-serif; font-size: 130%; font-weight: bold; text-align: justify }
.txt_articulo{ font-family: sans-serif; font-size: medium; text-align: justify }
.contentheading{font-family: serif; font-size: large; font-weight: bold; color: #000000; text-align: center}
'''
# def preprocess_html(self, soup):
# for item in soup.findAll(style=True):
# del item['style']
# del item['link']
# return soup
--
Saludos