calibre/recipes/infobae.recipe

57 lines
2.1 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2008-2010, Darko Miletic <darko.miletic at gmail.com>'
'''
infobae.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Infobae(BasicNewsRecipe):
title = 'Infobae.com'
__author__ = 'Darko Miletic and Sujata Raman'
description = 'Informacion Libre las 24 horas'
publisher = 'Infobae.com'
category = 'news, politics, Argentina'
oldest_article = 1
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
language = 'es_AR'
encoding = 'cp1252'
masthead_url = 'http://www.infobae.com/imgs/header/header.gif'
remove_javascript = True
remove_empty_feeds = True
extra_css = '''
body{font-family:Arial,Helvetica,sans-serif;}
.popUpTitulo{color:#0D4261; font-size: xx-large}
'''
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
, 'linearize_tables' : True
}
feeds = [
(u'Noticias' , u'http://www.infobae.com/adjuntos/html/RSS/hoy.xml' )
,(u'Salud' , u'http://www.infobae.com/adjuntos/html/RSS/salud.xml' )
,(u'Tecnologia', u'http://www.infobae.com/adjuntos/html/RSS/tecnologia.xml')
,(u'Deportes' , u'http://www.infobae.com/adjuntos/html/RSS/deportes.xml' )
]
def print_version(self, url):
article_part = url.rpartition('/')[2]
article_id= article_part.partition('-')[0]
return 'http://www.infobae.com/notas/nota_imprimir.php?Idx=' + article_id
def postprocess_html(self, soup, first):
for tag in soup.findAll(name='strong'):
tag.name = 'b'
return soup