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 El Pais

Browse Source 
Fixes #1909831 [Make El Pais recipe work again: Fix RSS feeds and article classes](https://bugs.launchpad.net/calibre/+bug/1909831)
This commit is contained in:
Kovid Goyal 2021-01-02 09:38:39 +05:30
parent adef43ddab
commit 533aa3206e
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 35 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

66
recipes/el_pais.recipe
View File

@ -23,8 +23,8 @@ class ElPais(BasicNewsRecipe):
language = 'es' language = 'es'
timefmt = '[%a, %d %b, %Y]' timefmt = '[%a, %d %b, %Y]'
oldest_article = 2 oldest_article = 2.1
max_articles_per_feed = 15 max_articles_per_feed = 25
use_embedded_content = False use_embedded_content = False
recursion = 5 recursion = 5
@ -33,38 +33,42 @@ class ElPais(BasicNewsRecipe):
no_stylesheets = True no_stylesheets = True
keep_only_tags = [ keep_only_tags = [
dict(name='h1'), dict(itemprop=['articleBody', 'image', 'caption']), dict(attrs={'class': [
dict(attrs={'class': ['articulo-subtitulos', 'articulo-apertura ']}), 'article_header',
'article_body',
'a_t',
'a_st',
'articulo-titulares',
'articulo-apertura',
'articulo__contenedor'
]}),
]
remove_tags = [
dict(attrs={'class': [
'sumario__interior',
'articulo-trust',
'compartir',
'articulo-tags',
'outbrain',
'more_info',
'articulo-apoyos',
'top10',
]}),
] ]
feeds = [ feeds = [
(u'Titulares de portada', u'http://www.elpais.com/rss/feed.html?feedId=1022'), (u'Espa\xf1a', u'https://feeds.elpais.com/mrss-s/pages/ep/site/elpais.com/section/espana/portada'),
(u'Internacional', (u'Internacional',
u'http://www.elpais.com/rss/feed.html?feedId=1001'), u'https://feeds.elpais.com/mrss-s/pages/ep/site/elpais.com/section/internacional/portada'),
(u'Espa\xf1a', u'http://www.elpais.com/rss/feed.html?feedId=1002'), (u'Opini\xf3n', u'https://elpais.com/rss/elpais/opinion.xml'),
(u'Deportes', u'http://www.elpais.com/rss/feed.html?feedId=1007'), (u'Ciencia', u'https://feeds.elpais.com/mrss-s/pages/ep/site/elpais.com/section/ciencia/portada'),
(u'Econom\xeda',
u'http://www.elpais.com/rss/feed.html?feedId=1006'),
(u'Pol\xedtica',
u'http://www.elpais.com/rss/feed.html?feedId=17073'),
(u'Tecnolog\xeda', (u'Tecnolog\xeda',
u'http://www.elpais.com/rss/feed.html?feedId=1005'), u'https://feeds.elpais.com/mrss-s/pages/ep/site/elpais.com/section/tecnologia/portada'),
(u'Cultura', u'http://www.elpais.com/rss/feed.html?feedId=1008'), (u'Cultura', u'https://feeds.elpais.com/mrss-s/pages/ep/site/elpais.com/section/cultura/portada'),
(u'Gente', u'http://www.elpais.com/rss/feed.html?feedId=1009'), (u'Estilo', u'https://feeds.elpais.com/mrss-s/pages/ep/site/elpais.com/section/estilo/portada'),
(u'Sociedad', u'http://www.elpais.com/rss/feed.html?feedId=1004'), (u'Deportes', u'https://feeds.elpais.com/mrss-s/pages/ep/site/elpais.com/section/deportes/portada'),
(u'Opini\xf3n', u'http://www.elpais.com/rss/feed.html?feedId=1003'), (u'Televisión', u'https://feeds.elpais.com/mrss-s/pages/ep/site/elpais.com/section/television/portada'),
(u'Ciencia', u'http://www.elpais.com/rss/feed.html?feedId=17068'), (u'Sociedad', u'https://feeds.elpais.com/mrss-s/pages/ep/site/elpais.com/section/sociedad/portada'),
(u'Justicia y leyes', (u'Blogs', u'http://ep01.epimg.net/rss/elpais/blogs.xml'),
u'http://www.elpais.com/rss/feed.html?feedId=17069'),
(u'Medio ambiente',
u'http://www.elpais.com/rss/feed.html?feedId=17071'),
(u'Vi\xf1etas', u'http://www.elpais.com/rss/feed.html?feedId=17058')
] ]
def preprocess_html(self, soup):
for img in soup.findAll('img', srcset=True):
try:
img['src'] = list(filter(None, img['srcset'].split()))[0]
except IndexError:
continue
return soup