calibre/recipes/clarin.recipe

87 lines
3.7 KiB
Python

#!/usr/bin/env python2
# -*- mode: python -*-
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
__license__ = 'GPL v3'
__copyright__ = '2008-2016, 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/images/logo_clarin.svg'
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
}
keep_only_tags = [
dict(name='p' , attrs={'class' : 'volanta'}),
dict(name='h1' , attrs={'itemprop': 'headline'}),
dict(name='div', attrs={'class' : 'bajada'}),
dict(name='div', attrs={'class' : 'body-nota'})
]
remove_tags = [
dict(name=['meta', 'base', 'link', 'iframe', 'embed', 'object']),
dict(attrs={'class': ['tags-bar', 'breadcrumb', 'share-bar', 'share']}),
dict(name='div', attrs={'class': lambda x: x and 'r-nota' in x.split()}),
dict(attrs={'id': ['relacionadas']}),
dict(name='a', attrs={'class':'content-new'})
]
remove_tags_after = dict(name='div', attrs={'id': 'relacionadas'})
remove_attributes = ['lang']
feeds = [
(u'Lo Ultimo', u'http://www.clarin.com/rss/lo-ultimo/'),
(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' # noqa
})
br.open(self.LOGIN, data)
return br