2
# -*- coding: utf-8 -*-
5
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
10
from calibre.web.feeds.news import BasicNewsRecipe
11
from calibre.ebooks.BeautifulSoup import Tag
13
class Expansion(BasicNewsRecipe):
14
title = 'Diario Expansion'
15
__author__ = 'Darko Miletic'
16
description = 'Lider de informacion de mercados, economica y politica'
17
publisher = 'expansion.com'
18
category = 'news, politics, Spain'
20
max_articles_per_feed = 100
22
use_embedded_content = False
24
encoding = 'iso-8859-15'
25
language = _('Spanish')
29
'--comment' , description
30
, '--category' , category
31
, '--publisher', publisher
34
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
37
(u'Ultimas noticias', u'http://rss.expansion.com/rss/descarga.htm?data2=178')
38
,(u'Temas del dia' , u'http://rss.expansion.com/rss/descarga.htm?data2=178')
42
keep_only_tags = [dict(name='div', attrs={'id':'principal'})]
45
dict(name=['object','link','script'])
46
,dict(name='div', attrs={'class':['utilidades','tit_relacionadas']})
49
remove_tags_after = [dict(name='div', attrs={'class':'tit_relacionadas'})]
51
def preprocess_html(self, soup):
52
soup.html['dir' ] = self.direction
53
mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=utf-8")])
54
soup.head.insert(0,mcharset)
55
for item in soup.findAll(style=True):