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

Fix #2106252 [Updated recipe for Pagina12](https://bugs.launchpad.net/calibre/+bug/2106252)

Browse Source
This commit is contained in:
Kovid Goyal 2025-04-05 02:02:26 +05:30
parent 52cf1a1cc6
commit 7008725bb8
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 19 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
recipes/pagina12.recipe
View File

@ -2,7 +2,7 @@
# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
__copyright__ = '2008-2024, Darko Miletic <darko.miletic at gmail.com>'
__copyright__ = '2008-2025, Darko Miletic <darko.miletic at gmail.com>'
'''
pagina12.com.ar
'''
@ -51,17 +51,16 @@ class Pagina12(BasicNewsRecipe):
remove_tags = [
dict(name=['meta', 'link']),
dict(attrs={'class':'article-main-media-social show-for-medium'})
dict(attrs={'class':['article-main-media-social show-for-medium', 'social-share-bar', 'iframely-embed medium-embedded-content']})
]
keep_only_tags=[
dict(name='div', attrs={'class':[
'article-header',
'article-titles',
'article-main-media-header',
'article-main-media',
'article-text'
]})
dict(name='h2', attrs={'class': lambda x: x and 'h4' in x}),
dict(name='h1'),
dict(name='h2', attrs={'class': lambda x: x and 'h3' in x}),
dict(name='div', attrs={'class': 'author'}),
dict(name='div', attrs={'class': lambda x: x and 'article-main-media-image__container' in x}),
dict(name='div', attrs={'class': lambda x: x and 'article-main-content' in x})
]
def get_browser(self):
@ -76,22 +75,22 @@ class Pagina12(BasicNewsRecipe):
return br
feeds = [
(u'Diario de hoy', u'https://www.pagina12.com.ar/rss/edicion-impresa'),
(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'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'),
(u'M2', u'https://www.pagina12.com.ar/rss/suplementos/m2/notas'),
(u'Rosario 12', u'https://www.pagina12.com.ar/rss/suplementos/rosario12/notas')
(u'Diario de hoy' , u'https://www.pagina12.com.ar/rss/edicion-impresa'),
(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'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'),
(u'M2' , u'https://www.pagina12.com.ar/rss/suplementos/m2/notas'),
(u'Rosario 12' , u'https://www.pagina12.com.ar/rss/suplementos/rosario12/notas')
]
def get_cover_url(self):
lurl = strftime('https://www.pagina12.com.ar/edicion-impresa/%d-%m-%Y')
soup = self.index_to_soup(lurl)
mydiv = soup.find('div', {'class': lambda x: x and 'printed-edition-cover' in x.split()})
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['src'].startswith('https://images.pagina12.com.ar/styles/width700/public/'):