Updated La Tercera

This commit is contained in:
Kovid Goyal 2011-08-18 22:10:11 -06:00
parent 171937f833
commit 0982feff0a

View File

@ -7,8 +7,9 @@ latercera.com
from calibre.web.feeds.news import BasicNewsRecipe
class LaTercera(BasicNewsRecipe):
news = True
title = 'La Tercera'
__author__ = 'Darko Miletic'
__author__ = 'Darko Miletic and Alex Mitrani'
description = 'El sitio de noticias online de Chile'
publisher = 'La Tercera'
category = 'news, politics, Chile'
@ -18,8 +19,8 @@ class LaTercera(BasicNewsRecipe):
encoding = 'cp1252'
use_embedded_content = False
remove_empty_feeds = True
language = 'es'
language = 'es_CL'
conversion_options = {
'comment' : description
, 'tags' : category
@ -28,28 +29,33 @@ class LaTercera(BasicNewsRecipe):
, 'linearize_tables' : True
}
keep_only_tags = [dict(name='div', attrs={'class':['span-16 articulo border','span-16 border','span-16']}) ]
keep_only_tags = [
dict(name='h1', attrs={'class':['titularArticulo']})
,dict(name='h4', attrs={'class':['bajadaArt']})
,dict(name='h5', attrs={'class':['autorArt']})
,dict(name='div', attrs={'class':['articleContent']})
]
remove_tags = [
dict(name=['ul','input','base'])
,dict(name='div', attrs={'id':['boxComentarios','shim','enviarAmigo']})
,dict(name='div', attrs={'class':['ad640','span-10 imgSet A','infoRelCol']})
,dict(name='p', attrs={'id':['mensajeError','mensajeEnviandoNoticia','mensajeExito']})
dict(name='div', attrs={'class':['boxCompartir','keywords']})
]
remove_tags_after = [
dict(name='div', attrs={'class':['keywords']})
]
feeds = [
(u'Noticias de ultima hora', u'http://www.latercera.com/app/rss?sc=TEFURVJDRVJB&ul=1')
feeds = [(u'La Tercera', u'http://www.latercera.com/app/rss?sc=TEFURVJDRVJB&ul=1')
,(u'Politica', u'http://www.latercera.com/app/rss?sc=TEFURVJDRVJB&category=674')
,(u'Nacional', u'http://www.latercera.com/app/rss?sc=TEFURVJDRVJB&category=680')
,(u'Politica', u'http://www.latercera.com/app/rss?sc=TEFURVJDRVJB&category=674')
,(u'Mundo', u'http://www.latercera.com/app/rss?sc=TEFURVJDRVJB&category=678')
,(u'Deportes', u'http://www.latercera.com/app/rss?sc=TEFURVJDRVJB&category=656')
,(u'Negocios', u'http://www.latercera.com/app/rss?sc=TEFURVJDRVJB&category=655')
,(u'Entretenimiento', u'http://www.latercera.com/app/rss?sc=TEFURVJDRVJB&category=661')
,(u'Motores', u'http://www.latercera.com/app/rss?sc=TEFURVJDRVJB&category=665')
,(u'Santiago', u'http://www.latercera.com/feed/manager?type=rss&sc=TEFURVJDRVJB&citId=9&categoryId=1731')
,(u'Tendencias', u'http://www.latercera.com/app/rss?sc=TEFURVJDRVJB&category=659')
,(u'Estilo', u'http://www.latercera.com/app/rss?sc=TEFURVJDRVJB&category=660')
,(u'Educacion', u'http://www.latercera.com/app/rss?sc=TEFURVJDRVJB&category=657')
,(u'Cultura', u'http://www.latercera.com/feed/manager?type=rss&sc=TEFURVJDRVJB&citId=9&categoryId=1453')
,(u'Entretención', u'http://www.latercera.com/app/rss?sc=TEFURVJDRVJB&category=661')
,(u'Deportes', u'http://www.latercera.com/app/rss?sc=TEFURVJDRVJB&category=656')
]
def preprocess_html(self, soup):