Update 20 Minutos

This commit is contained in:
Kovid Goyal 2011-01-31 17:12:22 -07:00
parent 5849b45d11
commit c47bacb016

View File

@ -1,25 +1,25 @@
# -*- coding: utf-8
__license__ = 'GPL v3' __license__ = 'GPL v3'
__author__ = 'Luis Hernandez' __author__ = 'Luis Hernandez'
__copyright__ = 'Luis Hernandez<tolyluis@gmail.com>' __copyright__ = 'Luis Hernandez<tolyluis@gmail.com>'
description = 'Periódico gratuito en español - v0.8 - 27 Jan 2011' __version__ = 'v0.85'
__date__ = '31 January 2011'
''' '''
www.20minutos.es www.20minutos.es
''' '''
import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1294946868(BasicNewsRecipe): class AdvancedUserRecipe1294946868(BasicNewsRecipe):
title = u'20 Minutos' title = u'20 Minutos new'
publisher = u'Grupo 20 Minutos' publisher = u'Grupo 20 Minutos'
__author__ = 'Luis Hernández' __author__ = 'Luis Hernandez'
description = 'Periódico gratuito en español' description = 'Free spanish newspaper'
cover_url = 'http://estaticos.20minutos.es/mmedia/especiales/corporativo/css/img/logotipos_grupo20minutos.gif' cover_url = 'http://estaticos.20minutos.es/mmedia/especiales/corporativo/css/img/logotipos_grupo20minutos.gif'
oldest_article = 5 oldest_article = 2
max_articles_per_feed = 100 max_articles_per_feed = 100
remove_javascript = True remove_javascript = True
@ -29,6 +29,7 @@ class AdvancedUserRecipe1294946868(BasicNewsRecipe):
encoding = 'ISO-8859-1' encoding = 'ISO-8859-1'
language = 'es' language = 'es'
timefmt = '[%a, %d %b, %Y]' timefmt = '[%a, %d %b, %Y]'
remove_empty_feeds = True
keep_only_tags = [ keep_only_tags = [
dict(name='div', attrs={'id':['content','vinetas',]}) dict(name='div', attrs={'id':['content','vinetas',]})
@ -43,13 +44,21 @@ class AdvancedUserRecipe1294946868(BasicNewsRecipe):
remove_tags = [ remove_tags = [
dict(name='ol', attrs={'class':['navigation',]}) dict(name='ol', attrs={'class':['navigation',]})
,dict(name='span', attrs={'class':['action']}) ,dict(name='span', attrs={'class':['action']})
,dict(name='div', attrs={'class':['twitter comments-list hidden','related-news','col','photo-gallery','calendario','article-comment','postto estirar','otras_vinetas estirar','kment','user-actions']}) ,dict(name='div', attrs={'class':['twitter comments-list hidden','related-news','col','photo-gallery','photo-gallery side-art-block','calendario','article-comment','postto estirar','otras_vinetas estirar','kment','user-actions']})
,dict(name='div', attrs={'id':['twitter-destacados','eco-tabs','inner','vineta_calendario','vinetistas clearfix','otras_vinetas estirar','MIN1','main','SUP1','INT']}) ,dict(name='div', attrs={'id':['twitter-destacados','eco-tabs','inner','vineta_calendario','vinetistas clearfix','otras_vinetas estirar','MIN1','main','SUP1','INT']})
,dict(name='ul', attrs={'class':['article-user-actions','stripped-list']}) ,dict(name='ul', attrs={'class':['article-user-actions','stripped-list']})
,dict(name='ul', attrs={'id':['site-links']}) ,dict(name='ul', attrs={'id':['site-links']})
,dict(name='li', attrs={'class':['puntuacion','enviar','compartir']}) ,dict(name='li', attrs={'class':['puntuacion','enviar','compartir']})
] ]
extra_css = """
p{text-align: justify; font-size: 100%}
body{ text-align: left; font-size:100% }
h3{font-family: sans-serif; font-size:150%; font-weight:bold; text-align: justify; }
"""
preprocess_regexps = [(re.compile(r'<a href="http://estaticos.*?[0-999]px;" target="_blank">', re.DOTALL), lambda m: '')]
feeds = [ feeds = [
(u'Portada' , u'http://www.20minutos.es/rss/') (u'Portada' , u'http://www.20minutos.es/rss/')
,(u'Nacional' , u'http://www.20minutos.es/rss/nacional/') ,(u'Nacional' , u'http://www.20minutos.es/rss/nacional/')