calibre/recipes/clarin.recipe
Kovid Goyal a123dba172 Update Clarin
Fixes #1499725 [Updated recipe for Clarin](https://bugs.launchpad.net/calibre/+bug/1499725)
2015-09-25 22:43:33 +05:30

81 lines
3.8 KiB
Plaintext

from __future__ import unicode_literals
__license__ = 'GPL v3'
__copyright__ = '2008-2015, Darko Miletic <darko.miletic at gmail.com>'
'''
clarin.com
'''
import urllib
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class Clarin(BasicNewsRecipe):
title = 'Clarín'
__author__ = 'Darko Miletic'
description = 'Clarin.com. Noticias de la Argentina y el mundo. Información actualizada las 24 horas y en español. Informate ya'
publisher = 'Grupo Clarin'
category = 'news, politics, Argentina'
oldest_article = 2
max_articles_per_feed = 100
use_embedded_content = False
no_stylesheets = True
encoding = 'utf8'
delay = 1
language = 'es_AR'
publication_type = 'newspaper'
needs_subscription = 'optional'
INDEX = 'http://www.clarin.com'
LOGIN = 'https://app-pase.clarin.com/pase-registracion/app/pase/ingresarNavegable?execution=e1s1'
masthead_url = 'http://www.clarin.com/static/CLAClarinV3/images/logo.png'
cover_url = strftime('http://tapas.clarin.com/tapa/%Y/%m/%d/%Y%m%d_thumb.jpg')
extra_css = """
body{font-family: Arial,Helvetica,sans-serif}
h2{font-family: Georgia,serif; font-size: xx-large}
.info,.nombre-autor,.hora{font-size: small}
.columnista-datos ul{list-style-type: none;}
"""
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher': publisher
, 'language' : language
}
remove_tags_before = dict(attrs={'class':'int-nota-title'})
remove_tags = [
dict(name=['meta','base','link','iframe','embed','object']),
dict(attrs={'class':['tags-bar','breadcrumb','share-bar']}),
dict(attrs={'id':['relacionadas']})
]
remove_tags_after = dict(name='div', attrs={'id':'relacionadas'})
remove_attributes = ['lang']
feeds = [
(u'Pagina principal', u'http://www.clarin.com/rss/')
,(u'Politica' , u'http://www.clarin.com/rss/politica/')
,(u'Deportes' , u'http://www.clarin.com/rss/deportes/')
,(u'Mundo' , u'http://www.clarin.com/rss/mundo/')
,(u'Espectaculos' , u'http://www.clarin.com/rss/espectaculos/')
,(u'Sociedad' , u'http://www.clarin.com/rss/sociedad/')
,(u'Ciudades' , u'http://www.clarin.com/rss/ciudades/')
,(u'Policiales' , u'http://www.clarin.com/rss/policiales/')
,(u'Internet' , u'http://www.clarin.com/rss/internet/')
]
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
br.open(self.INDEX)
if self.username is not None and self.password is not None:
data = urllib.urlencode({'ingresar_ingresar_paseForm':'ingresar_ingresar_paseForm'
,'ingresar_ingresar_email_paseInputComponent':self.username
,'ingresar_ingresar_palabraClave_paseInputComponent':self.password
,'ingresar_ingresar_ingresar_paseButton':'Ingresar'
,'javax.faces.ViewState':'e1s1'
})
br.open(self.LOGIN, data)
return br
def get_article_url(self, article):
return article.get('guid', None)