Update Miradasalsur.

Fixes #1193922 [Updated recipe for Miradas al Sur](https://bugs.launchpad.net/calibre/+bug/1193922)
This commit is contained in:
Kovid Goyal 2013-06-24 09:56:07 +05:30
parent c8889644bd
commit e8e4dbc35b
2 changed files with 47 additions and 50 deletions

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.1 KiB

View File

@ -1,18 +1,17 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
__copyright__ = '2009-2013, Darko Miletic <darko.miletic at gmail.com>'
'''
elargentino.com
sur.infonews.com
'''
import datetime
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag
class MiradasAlSur(BasicNewsRecipe):
title = 'Miradas al Sur'
__author__ = 'Darko Miletic'
description = 'Revista Argentina'
description = 'Semanario Argentino'
publisher = 'ElArgentino.com'
category = 'news, politics, Argentina'
oldest_article = 7
@ -20,53 +19,51 @@ class MiradasAlSur(BasicNewsRecipe):
no_stylesheets = True
use_embedded_content = False
encoding = 'utf-8'
language = 'es_AR'
language = 'es_AR'
remove_empty_feeds = True
masthead_url = 'http://sur.infonews.com/sites/default/files/www_miradas_al_sur_com_logo.gif'
extra_css = """
body{font-family: Arial,Helvetica,sans-serif}
h1{font-family: Georgia,Times,serif}
.field-field-story-author{color: gray; font-size: small}
"""
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
, 'series' : title
}
keep_only_tags = [dict(name='div', attrs={'id':['content-header', 'content-area']})]
remove_tags = [
dict(name=['link','meta','iframe','embed','object']),
dict(name='form', attrs={'class':'fivestar-widget'}),
dict(attrs={'class':lambda x: x and 'terms-inline' in x.split()})
]
lang = 'es-AR'
direction = 'ltr'
INDEX = 'http://www.elargentino.com/medios/123/Miradas-al-Sur.html'
extra_css = ' .titulo{font-size: x-large; font-weight: bold} .volantaImp{font-size: small; font-weight: bold} '
html2lrf_options = [
'--comment' , description
, '--category' , category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\noverride_css=" p {text-indent: 0cm; margin-top: 0em; margin-bottom: 0.5em} "'
keep_only_tags = [dict(name='div', attrs={'class':'ContainerPop'})]
remove_tags = [dict(name='link')]
feeds = [(u'Articulos', u'http://www.elargentino.com/Highlights.aspx?ParentType=Section&ParentId=123&Content-Type=text/xml&ChannelDesc=Miradas%20al%20Sur')]
def print_version(self, url):
main, sep, article_part = url.partition('/nota-')
article_id, rsep, rrest = article_part.partition('-')
return u'http://www.elargentino.com/Impresion.aspx?Id=' + article_id
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
soup.html['lang'] = self.lang
soup.html['dir' ] = self.direction
mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)])
mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=utf-8")])
soup.head.insert(0,mlang)
soup.head.insert(1,mcharset)
return soup
feeds = [
(u'Politica' , u'http://sur.infonews.com/taxonomy/term/1/0/feed' ),
(u'Internacional' , u'http://sur.infonews.com/taxonomy/term/2/0/feed' ),
(u'Informe Especial' , u'http://sur.infonews.com/taxonomy/term/14/0/feed'),
(u'Delitos y pesquisas', u'http://sur.infonews.com/taxonomy/term/6/0/feed' ),
(u'Lesa Humanidad' , u'http://sur.infonews.com/taxonomy/term/7/0/feed' ),
(u'Cultura' , u'http://sur.infonews.com/taxonomy/term/8/0/feed' ),
(u'Deportes' , u'http://sur.infonews.com/taxonomy/term/9/0/feed' ),
(u'Contratapa' , u'http://sur.infonews.com/taxonomy/term/10/0/feed'),
]
def get_cover_url(self):
# determine the series number, unfortunately not gonna happen now
#self.conversion_options.update({'series_index':seriesnr})
cover_url = None
soup = self.index_to_soup(self.INDEX)
cover_item = soup.find('div',attrs={'class':'colder'})
cdate = datetime.date.today()
todayweekday = cdate.isoweekday()
if (todayweekday != 7):
cdate -= datetime.timedelta(days=todayweekday)
cover_page_url = cdate.strftime('http://sur.infonews.com/ediciones/%Y-%m-%d/tapa');
soup = self.index_to_soup(cover_page_url)
cover_item = soup.find('img', attrs={'class':lambda x: x and 'imagecache-tapa_edicion_full' in x.split()})
if cover_item:
clean_url = self.image_url_processor(None,cover_item.div.img['src'])
cover_url = 'http://www.elargentino.com' + clean_url + '&height=600'
cover_url = cover_item['src']
return cover_url
def image_url_processor(self, baseurl, url):
base, sep, rest = url.rpartition('?Id=')
img, sep2, rrest = rest.partition('&')
return base + sep + img