calibre/recipes/elpais_semanal.recipe
2019-03-22 23:47:49 +05:30

52 lines
1.9 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
www.elpais.com/suple/eps/
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class ElPaisSemanal(BasicNewsRecipe):
title = 'El Pais semanal'
__author__ = 'Darko Miletic'
description = 'Revista semanal de diario El Pais'
publisher = 'EL PAIS S.L.'
category = 'news, politics, Spain'
no_stylesheets = True
encoding = 'cp1252'
use_embedded_content = False
language = 'es'
publication_type = 'magazine'
masthead_url = 'http://www.elpais.com/im/tit_logo_int.gif'
index = 'http://www.elpais.com/suple/eps/'
extra_css = ' p{text-align: justify} body{ text-align: left; font-family: Georgia,"Times New Roman",Times,serif } h2{font-family: Arial,Helvetica,sans-serif} img{margin-bottom: 0.4em} ' # noqa
conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
}
keep_only_tags = [
dict(attrs={'class': ['cabecera_noticia', 'contenido_noticia']})]
remove_attributes = ['width', 'height']
remove_tags = [dict(name='link')]
def parse_index(self):
articles = []
soup = self.index_to_soup(self.index)
for item in soup.findAll('a', attrs={'class': ['g19i003', 'g17r003', 'g17i003']}, href=True):
description = ''
title_prefix = ''
feed_link = item
url = 'http://www.elpais.com' + item['href'].rpartition('/')[0]
title = title_prefix + self.tag_to_string(feed_link)
date = strftime(self.timefmt)
articles.append({
'title': title, 'date': date, 'url': url, 'description': description
})
return [(soup.head.title.string, articles)]
def print_version(self, url):
return url + '?print=1'