Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-06-23 15:30:45 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update El Pais

Browse Source 
Fixes #1546751 [el_pais recipe no longer works](https://bugs.launchpad.net/calibre/+bug/1546751)
This commit is contained in:
Kovid Goyal 2016-02-18 08:32:31 +05:30
parent ed20dd6233
commit ce902f5dbd
1 changed files with 11 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
recipes/el_pais.recipe
View File

@ -9,8 +9,6 @@ __docformat__ = 'restructuredtext en'
elpais.es
'''
from time import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class ElPais(BasicNewsRecipe):
@ -33,17 +31,10 @@ class ElPais(BasicNewsRecipe):
remove_javascript = True
no_stylesheets = True
keep_only_tags = [ dict(name='div', attrs={'class':['cabecera_noticia_reportaje estirar','cabecera_noticia_opinion estirar','cabecera_noticia estirar','contenido_noticia','cuerpo_noticia','caja_despiece']})]
extra_css = ' p{text-align: justify; font-size: 100%} body{ text-align: left; font-family: serif; font-size: 100% } h1{ font-family: sans-serif; font-size:200%; font-weight: bolder; text-align: justify; } h2{ font-family: sans-serif; font-size:150%; font-weight: 500; text-align: justify } h3{ font-family: sans-serif; font-size:125%; font-weight: 500; text-align: justify } img{margin-bottom: 0.4em} '
remove_tags = [
dict(name='div', attrs={'class':['zona_superior','pie_enlaces_inferiores','contorno_f','ampliar']}),
dict(name='div', attrs={'class':['limpiar','mod_apoyo','borde_sup','votos estirar','info_complementa','info_relacionada','buscador_m','nav_ant_sig']}),
dict(name='div', attrs={'id':['suscribirse suscrito','google_noticia','utilidades','coment','foros_not','pie','lomas','calendar']}),
dict(name='p', attrs={'class':'nav_meses'}),
dict(attrs={'class':['enlaces_m','miniaturas_m','nav_miniaturas_m']})
]
keep_only_tags = [
dict(name='h1'), dict(itemprop=['articleBody', 'image', 'caption']),
dict(attrs={'class':['articulo-subtitulos', 'articulo-apertura ']}),
]
feeds = [
(u'Titulares de portada', u'http://www.elpais.com/rss/feed.html?feedId=1022'),
@ -63,6 +54,10 @@ class ElPais(BasicNewsRecipe):
(u'Vi\xf1etas', u'http://www.elpais.com/rss/feed.html?feedId=17058')
]
def get_cover_url(self):
return 'http://img5.kiosko.net/' + strftime("%Y/%m/%d") + '/es/elpais.750.jpg'
def preprocess_html(self, soup):
for img in soup.findAll('img', srcset=True):
try:
img['src'] = filter(None, img['srcset'].split())[0]
except IndexError:
continue
return soup