4
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
9
from calibre.web.feeds.news import BasicNewsRecipe
10
from calibre.ebooks.BeautifulSoup import Tag
12
class MiradasAlSur(BasicNewsRecipe):
13
title = 'Miradas al Sur'
14
__author__ = 'Darko Miletic'
15
description = 'Revista Argentina'
16
publisher = 'ElArgentino.com'
17
category = 'news, politics, Argentina'
19
max_articles_per_feed = 100
21
use_embedded_content = False
23
language = _('Spanish')
26
INDEX = 'http://www.elargentino.com/medios/123/Miradas-al-Sur.html'
27
extra_css = ' .titulo{font-size: x-large; font-weight: bold} .volantaImp{font-size: small; font-weight: bold} '
30
'--comment' , description
31
, '--category' , category
32
, '--publisher', publisher
35
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\noverride_css=" p {text-indent: 0cm; margin-top: 0em; margin-bottom: 0.5em} "'
37
keep_only_tags = [dict(name='div', attrs={'class':'ContainerPop'})]
39
remove_tags = [dict(name='link')]
41
feeds = [(u'Articulos', u'http://www.elargentino.com/Highlights.aspx?ParentType=Section&ParentId=123&Content-Type=text/xml&ChannelDesc=Miradas%20al%20Sur')]
43
def print_version(self, url):
44
main, sep, article_part = url.partition('/nota-')
45
article_id, rsep, rrest = article_part.partition('-')
46
return u'http://www.elargentino.com/Impresion.aspx?Id=' + article_id
48
def preprocess_html(self, soup):
49
for item in soup.findAll(style=True):
51
soup.html['lang'] = self.lang
52
soup.html['dir' ] = self.direction
53
mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)])
54
mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=utf-8")])
55
soup.head.insert(0,mlang)
56
soup.head.insert(1,mcharset)
59
def get_cover_url(self):
61
soup = self.index_to_soup(self.INDEX)
62
cover_item = soup.find('div',attrs={'class':'colder'})
64
clean_url = self.image_url_processor(None,cover_item.div.img['src'])
65
cover_url = 'http://www.elargentino.com' + clean_url + '&height=600'
68
def image_url_processor(self, baseurl, url):
69
base, sep, rest = url.rpartition('?Id=')
70
img, sep2, rrest = rest.partition('&')
71
return base + sep + img