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 Pagina12

Browse Source 
Fixes #2073611 [Updated recipe for Pagina 12](https://bugs.launchpad.net/calibre/+bug/2073611)
This commit is contained in:
Kovid Goyal 2024-07-19 20:20:27 +05:30
parent e4755c3df2
commit 3bcf2c0d1b
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
2 changed files with 16 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
recipes/pagina12.recipe
View File

@ -2,7 +2,7 @@
# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
__copyright__ = '2008-2018, Darko Miletic <darko.miletic at gmail.com>'
__copyright__ = '2008-2024, Darko Miletic <darko.miletic at gmail.com>'
'''
pagina12.com.ar
'''
@ -28,6 +28,7 @@ class Pagina12(BasicNewsRecipe):
delay = 1
simultaneous_downloads = 1
timeout = 8
needs_subscription = 'optional'
ignore_duplicate_articles = {'url'}
articles_are_obfuscated = True
temp_files = []
@ -63,29 +64,23 @@ class Pagina12(BasicNewsRecipe):
]})
]
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
br.open('https://www.pagina12.com.ar/')
if self.username is not None and self.password is not None:
br.open('https://auth.pagina12.com.ar/ingresar?redirect=https://www.pagina12.com.ar')
br.select_form(id='login')
br['email'] = self.username
br['password'] = self.password
br.submit()
return br
feeds = [
(u'Diario de hoy' , 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'Cartas 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'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'Cash' , u'https://www.pagina12.com.ar/rss/suplementos/cash/notas'),
(u'Turismo' , u'https://www.pagina12.com.ar/rss/suplementos/turismo/notas'),
(u'Libero' , u'https://www.pagina12.com.ar/rss/suplementos/libero/notas'),
(u'NO' , u'https://www.pagina12.com.ar/rss/suplementos/no/notas'),
(u'Las 12' , u'https://www.pagina12.com.ar/rss/suplementos/las12/notas'),
(u'Soy' , u'https://www.pagina12.com.ar/rss/suplementos/soy/notas'),
@ -99,8 +94,8 @@ class Pagina12(BasicNewsRecipe):
mydiv = soup.find('div', {'class' : lambda x: x and 'printed-edition-cover' in x.split()})
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']
if image['src'].startswith('https://images.pagina12.com.ar/styles/width700/public/'):
return image['src']
return None
def get_obfuscated_article(self, url):

1
recipes/wsj.recipe
View File

@ -6,6 +6,7 @@ from itertools import zip_longest
from calibre.ebooks.BeautifulSoup import BeautifulSoup
from calibre.web.feeds.news import BasicNewsRecipe, classes
def media_bucket(x):
if x.get('type', '') == 'image':
if x.get('subtype', '') == 'graphic' or 'images.wsj.net' not in x['manifest-url']: