Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 18:54:09 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update el_pais.recipe

Browse Source 
Removed unrelated text
Added author of the article
Downloads all pictures
Improves downloaded pictures quality
Downloads cover if available
Updated some feeds
Adds some style to author's name, photographer's name, picture text
Added publication_type
This commit is contained in:
Álvaro Beiró 2023-03-13 11:15:21 +01:00 committed by GitHub
parent c76f2b123c
commit 6e4c378228
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 34 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

41
recipes/el_pais.recipe
View File

@ -1,8 +1,8 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__author__ = 'Jordi Balcells, based on an earlier version by Lorenzo Vigentini & Kovid Goyal'
__author__ = 'Alvaro Beiro, improving Jordi Balcells work based on an earlier version by Lorenzo Vigentini & Kovid Goyal'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
description = 'Main daily newspaper from Spain - v1.04 (19, October 2010)'
description = 'Main daily newspaper from Spain - v1.05 (13, March 2023)'
__docformat__ = 'restructuredtext en'
'''
@ -13,12 +13,13 @@ from calibre.web.feeds.news import BasicNewsRecipe
class ElPais(BasicNewsRecipe):
__author__ = 'Kovid Goyal & Lorenzo Vigentini & Jordi Balcells'
__author__ = 'Kovid Goyal & Lorenzo Vigentini & Jordi Balcells & Alvaro Beiro'
description = 'Main daily newspaper from Spain'
title = u'El Pais'
title = u'El Pa\xeds'
publisher = u'Ediciones El Pa\xeds SL'
category = 'News, politics, culture, economy, general interest'
publication_type = 'newspaper'
language = 'es'
timefmt = '[%a, %d %b, %Y]'
@ -31,6 +32,8 @@ class ElPais(BasicNewsRecipe):
remove_javascript = True
no_stylesheets = True
extra_css = 'span._db {max-width: 100%; height: auto;} .a_m_p {font-size: .75rem;} .a_m_m {text-transform: uppercase; padding-top: 0.5rem;} div.a_md_a {text-align: center; text-transform: uppercase; font-size: .8rem;}'
keep_only_tags = [
dict(attrs={'class': [
@ -41,6 +44,8 @@ class ElPais(BasicNewsRecipe):
'articulo-titulares',
'articulo-apertura',
'articulo__contenedor'
'a_e_m',
'a_md_a',
]}),
dict(name='div', attrs={'class': 'a_c',}),
@ -57,20 +62,26 @@ class ElPais(BasicNewsRecipe):
'more_info',
'articulo-apoyos',
'top10',
'a_ei',
'w-cta',
'ph-v_b',
]
},
),
dict(id='cta_id'),
dict(name='svg'),
]
remove_attributes = ['width', 'height']
feeds = [
(u'Espa\xf1a', u'https://feeds.elpais.com/mrss-s/pages/ep/site/elpais.com/section/espana/portada'),
(u'Internacional',
u'https://feeds.elpais.com/mrss-s/pages/ep/site/elpais.com/section/internacional/portada'),
(u'Opini\xf3n', u'https://elpais.com/rss/elpais/opinion.xml'),
(u'Economía', u'https://feeds.elpais.com/mrss-s/pages/ep/site/elpais.com/section/economia/portada'),
(u'Opinión', u'http://ep00.epimg.net/rss/elpais/opinion.xml'),
(u'Ciencia', u'https://feeds.elpais.com/mrss-s/pages/ep/site/elpais.com/section/ciencia/portada'),
(u'Tecnolog\xeda',
(u'Tecnología',
u'https://feeds.elpais.com/mrss-s/pages/ep/site/elpais.com/section/tecnologia/portada'),
(u'Cultura', u'https://feeds.elpais.com/mrss-s/pages/ep/site/elpais.com/section/cultura/portada'),
(u'Estilo', u'https://feeds.elpais.com/mrss-s/pages/ep/site/elpais.com/section/estilo/portada'),
@ -79,3 +90,19 @@ class ElPais(BasicNewsRecipe):
(u'Sociedad', u'https://feeds.elpais.com/mrss-s/pages/ep/site/elpais.com/section/sociedad/portada'),
(u'Blogs', u'http://ep01.epimg.net/rss/elpais/blogs.xml'),
]
def get_cover_url(self):
from datetime import date
cover = 'https://srv00.epimg.net/pdf/elpais/snapshot/' + str(date.today().year) + '/' + date.today().strftime('%m') + '/elpais/' + str(date.today().year) + date.today().strftime('%m') + date.today().strftime('%d') + 'Big.jpg'
br = BasicNewsRecipe.get_browser(self)
try:
br.open(cover)
except:
self.log("\nCover unavailable")
cover = None
return cover
def image_url_processor(cls, baseurl, url):
splitUrl = url.split("cloudfront-")
parsedUrl = 'https://cloudfront-' + splitUrl[1]
return parsedUrl