Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Pagina - 12

Browse Source 
Fixes #1674182 [Updated recipe for Pagina 12](https://bugs.launchpad.net/calibre/+bug/1674182)
This commit is contained in:
Kovid Goyal 2017-03-20 08:05:51 +05:30
parent ad4366681e
commit 6bbcdf6bc0
1 changed files with 36 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
recipes/pagina12.recipe
View File

@ -2,11 +2,11 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008-2016, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2008-2017, Darko Miletic <darko.miletic at gmail.com>'
''' '''
pagina12.com.ar pagina12.com.ar
''' '''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
@ -54,7 +54,21 @@ class Pagina12(BasicNewsRecipe):
] ]
feeds = [ feeds = [
(u'Edicion impresa', u'https://www.pagina12.com.ar/rss/edicion-impresa'), (u'El Pais' , u'https://www.pagina12.com.ar/rss/secciones/el-pais/notas'),
(u'Economia' , u'https://www.pagina12.com.ar/rss/secciones/economia/notas'),
(u'Sociedad' , u'https://www.pagina12.com.ar/rss/secciones/sociedad/notas'),
(u'El Mundo' , u'https://www.pagina12.com.ar/rss/secciones/el-mundo/notas'),
(u'Deportes' , u'https://www.pagina12.com.ar/rss/secciones/deportes/notas'),
(u'Cultura' , u'https://www.pagina12.com.ar/rss/secciones/cultura/notas'),
(u'Universidad' , u'https://www.pagina12.com.ar/rss/secciones/universidad/notas'),
(u'Ciencia' , u'https://www.pagina12.com.ar/rss/secciones/ciencia/notas'),
(u'Psicologia' , u'https://www.pagina12.com.ar/rss/secciones/psicologia/notas'),
(u'Ajedrez' , u'https://www.pagina12.com.ar/rss/secciones/ajedrez/notas'),
(u'La Ventana' , u'https://www.pagina12.com.ar/rss/secciones/la-ventana/notas'),
(u'Dialogos' , u'https://www.pagina12.com.ar/rss/secciones/dialogos/notas'),
(u'Hoy' , u'https://www.pagina12.com.ar/rss/secciones/hoy/notas'),
(u'Plastica' , u'https://www.pagina12.com.ar/rss/secciones/plastica/notas'),
(u'Carta de Lectores', u'https://www.pagina12.com.ar/rss/secciones/cartas-de-lectores/notas'),
(u'Espectaculos' , u'https://www.pagina12.com.ar/rss/suplementos/cultura-y-espectaculos/notas'), (u'Espectaculos' , u'https://www.pagina12.com.ar/rss/suplementos/cultura-y-espectaculos/notas'),
(u'Radar' , u'https://www.pagina12.com.ar/rss/suplementos/radar/notas'), (u'Radar' , u'https://www.pagina12.com.ar/rss/suplementos/radar/notas'),
(u'Radar libros' , u'https://www.pagina12.com.ar/rss/suplementos/radar-libros/notas'), (u'Radar libros' , u'https://www.pagina12.com.ar/rss/suplementos/radar-libros/notas'),
@ -76,8 +90,11 @@ class Pagina12(BasicNewsRecipe):
return url return url
def get_cover_url(self): def get_cover_url(self):
soup = self.index_to_soup(self.PREFIX) lurl = strftime('https://www.pagina12.com.ar/edicion-impresa/%d-%m-%Y')
for image in soup.findAll('img', alt=True): soup = self.index_to_soup(lurl)
if image['alt'].startswith('Tapa del dia'): mydiv = soup.find('div', {'class' : lambda x: x and 'printed-edition-cover' in x.split()})
return self.PREFIX + image['data-src'] if mydiv:
for image in mydiv.findAll('img'):
if image['data-src'].startswith('https://images.pagina12.com.ar/styles/width700/public/'):
return image['data-src']
return None return None