Update El Mercurio Chile

Fixes #1465795 [Updated recipe for El Mercurio](https://bugs.launchpad.net/calibre/+bug/1465795)
This commit is contained in:
Kovid Goyal 2015-06-17 03:06:16 +05:30
parent 8f9229cab4
commit 1cf5cbd00f
2 changed files with 44 additions and 20 deletions

View File

@ -1,23 +1,26 @@
#!/usr/bin/env python2
# -*- coding: latin-1 mode: python -*-
__license__ = 'GPL v3'
__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
__copyright__ = '2009-2015, Darko Miletic <darko.miletic at gmail.com>'
__docformat__ = 'restructuredtext es'
'''
emol.com
www.emol.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class ElMercurio(BasicNewsRecipe):
title = 'El Mercurio online'
title = 'Emol.com - El sitio de noticias online de Chile'
__author__ = 'Darko Miletic'
description = 'El sitio de noticias online de Chile'
publisher = 'El Mercurio'
publisher = 'El Mercurio S.A.P.'
category = 'news, politics, Chile'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'cp1252'
masthead_url = 'http://www.emol.com/especiales/logo_emol/logo_emol.gif'
encoding = 'utf8'
masthead_url = 'http://static.emol.cl/emol50/img/logo_emol.gif'
remove_javascript = True
use_embedded_content = False
language = 'es_CL'
@ -30,21 +33,42 @@ class ElMercurio(BasicNewsRecipe):
, 'language' : language
}
keep_only_tags = [dict(name='div', attrs={'id':['cont_iz_titulobajada','cont_iz_creditos_1_a','cont_iz_cuerpo']})]
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'})]
remove_attributes = ['height','width']
feeds = [
(u'Noticias de ultima hora', u'http://rss.emol.com/rss.asp?canal=0')
,(u'Nacional', u'http://rss.emol.com/rss.asp?canal=1')
,(u'Mundo', u'http://rss.emol.com/rss.asp?canal=2')
,(u'Deportes', u'http://rss.emol.com/rss.asp?canal=4')
,(u'Magazine', u'http://rss.emol.com/rss.asp?canal=6')
,(u'Tecnologia', u'http://rss.emol.com/rss.asp?canal=5')
(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 preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup
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)
#date,sep,rest = self.tag_to_string(ptag).partition('|')
articles.append({
'title' :title
,'date' :''
,'url' :url
,'description':description
})
totalfeeds.append((feedtitle, articles))
return totalfeeds

Binary file not shown.

Before

Width:  |  Height:  |  Size: 2.3 KiB

After

Width:  |  Height:  |  Size: 669 B