mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
71 lines
2.6 KiB
Python
71 lines
2.6 KiB
Python
#!/usr/bin/env python
|
|
# -*- coding: utf-8 mode: python -*-
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2009-2015, Darko Miletic <darko.miletic at gmail.com>'
|
|
__docformat__ = 'restructuredtext es'
|
|
'''
|
|
www.emol.com
|
|
'''
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class ElMercurio(BasicNewsRecipe):
|
|
title = 'Emol.com - El sitio de noticias online de Chile'
|
|
__author__ = 'Darko Miletic'
|
|
description = 'El sitio de noticias online de Chile'
|
|
publisher = 'El Mercurio S.A.P.'
|
|
category = 'news, politics, Chile'
|
|
oldest_article = 2
|
|
max_articles_per_feed = 100
|
|
no_stylesheets = True
|
|
encoding = 'utf8'
|
|
masthead_url = 'http://static.emol.cl/emol50/img/logo_emol.gif'
|
|
remove_javascript = True
|
|
use_embedded_content = False
|
|
language = 'es_CL'
|
|
|
|
conversion_options = {
|
|
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
|
|
}
|
|
|
|
keep_only_tags = [
|
|
dict(name='div', attrs={'class': ['cont_iz_titulobajada', 'info-notaemol-por',
|
|
'info-notaemol-porfecha']}), dict(name='div', attrs={'id': 'texto_noticia'})
|
|
]
|
|
remove_tags = [
|
|
dict(name='div', attrs={'id': 'cont_iz_cuerpo_relacionados'})]
|
|
|
|
feeds = [
|
|
|
|
(u'Nacional', u'http://www.emol.com/noticias/nacional/todas.aspx'),
|
|
(u'Mundo', u'http://www.emol.com/noticias/internacional/todas.aspx'),
|
|
(u'Deportes', u'http://www.emol.com/noticias/deportes/todas.aspx'),
|
|
(u'Espectaculos', u'http://www.emol.com/noticias/cultura/todas.aspx'),
|
|
(u'Tecnologia', u'http://www.emol.com/noticias/economia/todas.aspx')
|
|
]
|
|
|
|
def parse_index(self):
|
|
totalfeeds = []
|
|
lfeeds = self.get_feeds()
|
|
for feedobj in lfeeds:
|
|
feedtitle, feedurl = feedobj
|
|
self.report_progress(0, _('Fetching feed') + ' %s...' %
|
|
(feedtitle if feedtitle else feedurl))
|
|
articles = []
|
|
soup = self.index_to_soup(feedurl)
|
|
arts = soup.find('div', attrs={'id': 'caja_listado_noticia_todas'})
|
|
if arts:
|
|
for item in arts.findAll('div', attrs={'class': 'listado'}):
|
|
atag = item.find('a')
|
|
ptag = item.find('span')
|
|
url = atag['href']
|
|
title = self.tag_to_string(atag)
|
|
description = self.tag_to_string(ptag)
|
|
articles.append({
|
|
'title': title, 'date': '', 'url': url, 'description': description
|
|
})
|
|
totalfeeds.append((feedtitle, articles))
|
|
return totalfeeds
|