mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
71 lines
2.5 KiB
Python
71 lines
2.5 KiB
Python
#!/usr/bin/env python2
|
|
__license__ = 'GPL v3'
|
|
__author__ = 'Jordi Balcells, based on an earlier version by Lorenzo Vigentini & Kovid Goyal'
|
|
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
|
|
description = 'Main daily newspaper from Spain - v1.04 (19, October 2010)'
|
|
__docformat__ = 'restructuredtext en'
|
|
|
|
'''
|
|
elpais.es
|
|
'''
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class ElPais(BasicNewsRecipe):
|
|
__author__ = 'Kovid Goyal & Lorenzo Vigentini & Jordi Balcells'
|
|
description = 'Main daily newspaper from Spain'
|
|
|
|
title = u'El Pais'
|
|
publisher = u'Ediciones El Pa\xeds SL'
|
|
category = 'News, politics, culture, economy, general interest'
|
|
|
|
language = 'es'
|
|
timefmt = '[%a, %d %b, %Y]'
|
|
|
|
oldest_article = 2
|
|
max_articles_per_feed = 15
|
|
|
|
use_embedded_content = False
|
|
recursion = 5
|
|
|
|
remove_javascript = True
|
|
no_stylesheets = True
|
|
|
|
keep_only_tags = [
|
|
dict(name='h1'), dict(itemprop=['articleBody', 'image', 'caption']),
|
|
dict(attrs={'class': ['articulo-subtitulos', 'articulo-apertura ']}),
|
|
]
|
|
|
|
feeds = [
|
|
(u'Titulares de portada', u'http://www.elpais.com/rss/feed.html?feedId=1022'),
|
|
(u'Internacional',
|
|
u'http://www.elpais.com/rss/feed.html?feedId=1001'),
|
|
(u'Espa\xf1a', u'http://www.elpais.com/rss/feed.html?feedId=1002'),
|
|
(u'Deportes', u'http://www.elpais.com/rss/feed.html?feedId=1007'),
|
|
(u'Econom\xeda',
|
|
u'http://www.elpais.com/rss/feed.html?feedId=1006'),
|
|
(u'Pol\xedtica',
|
|
u'http://www.elpais.com/rss/feed.html?feedId=17073'),
|
|
(u'Tecnolog\xeda',
|
|
u'http://www.elpais.com/rss/feed.html?feedId=1005'),
|
|
(u'Cultura', u'http://www.elpais.com/rss/feed.html?feedId=1008'),
|
|
(u'Gente', u'http://www.elpais.com/rss/feed.html?feedId=1009'),
|
|
(u'Sociedad', u'http://www.elpais.com/rss/feed.html?feedId=1004'),
|
|
(u'Opini\xf3n', u'http://www.elpais.com/rss/feed.html?feedId=1003'),
|
|
(u'Ciencia', u'http://www.elpais.com/rss/feed.html?feedId=17068'),
|
|
(u'Justicia y leyes',
|
|
u'http://www.elpais.com/rss/feed.html?feedId=17069'),
|
|
(u'Medio ambiente',
|
|
u'http://www.elpais.com/rss/feed.html?feedId=17071'),
|
|
(u'Vi\xf1etas', u'http://www.elpais.com/rss/feed.html?feedId=17058')
|
|
]
|
|
|
|
def preprocess_html(self, soup):
|
|
for img in soup.findAll('img', srcset=True):
|
|
try:
|
|
img['src'] = list(filter(None, img['srcset'].split()))[0]
|
|
except IndexError:
|
|
continue
|
|
return soup
|