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 Impreso

Browse Source 
Fixes #1299650 [Updated recipe for El Pais](https://bugs.launchpad.net/calibre/+bug/1299650)
This commit is contained in:
Kovid Goyal 2014-03-30 08:10:53 +05:30
parent 2a333aa46a
commit b3e6939edf
1 changed files with 35 additions and 59 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
recipes/elpais_impreso.recipe
View File

@ -1,16 +1,17 @@
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai # vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2010-2012, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2010-2014, Darko Miletic <darko.miletic at gmail.com>'
''' '''
www.elpais.com elpais.com
''' '''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class ElPais_RSS(BasicNewsRecipe): class ElPais_RSS(BasicNewsRecipe):
title = u'El País' title = u'El País'
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic'
description = u'Noticias de última hora sobre la actualidad en España y el mundo: política, economía, deportes, cultura, sociedad, tecnología, gente, opinión, viajes, moda, televisión, los blogs y las firmas de EL PAÍS. Además especiales, vídeos, fotos, audios, gráficos, entrevistas, promociones y todos los servicios de EL PAÍS.' description = u'Noticias de última hora sobre la actualidad en España y el mundo: política, economía, deportes, cultura, sociedad, tecnología, gente, opinión, viajes, moda, televisión, los blogs y las firmas de EL PAÍS. Además especiales, vídeos, fotos, audios, gráficos, entrevistas, promociones y todos los servicios de EL PAÍS.' # noqa
publisher = 'EDICIONES EL PAIS, S.L.' publisher = 'EDICIONES EL PAIS, S.L.'
category = 'news, politics, finances, world, spain' category = 'news, politics, finances, world, spain'
oldest_article = 2 oldest_article = 2
@ -22,6 +23,7 @@ class ElPais_RSS(BasicNewsRecipe):
remove_empty_feeds = True remove_empty_feeds = True
publication_type = 'newspaper' publication_type = 'newspaper'
masthead_url = 'http://ep01.epimg.net/iconos/v1.x/v1.0/logos/cabecera_portada.png' masthead_url = 'http://ep01.epimg.net/iconos/v1.x/v1.0/logos/cabecera_portada.png'
cover_url = strftime('http://srv00.epimg.net/pdf/elpais/1aPagina/%Y/%m/ep-%Y%m%d.pdf')
extra_css = """ extra_css = """
h1{font-family: Georgia,"Times New Roman",Times,serif } h1{font-family: Georgia,"Times New Roman",Times,serif }
#subtitulo_noticia, .firma, .figcaption{font-size: small} #subtitulo_noticia, .firma, .figcaption{font-size: small}
@ -80,35 +82,9 @@ class ElPais_RSS(BasicNewsRecipe):
def get_article_url(self, article): def get_article_url(self, article):
url = BasicNewsRecipe.get_article_url(self, article) url = BasicNewsRecipe.get_article_url(self, article)
if url and (not('/album/' in url) and not('/futbol/partido/' in url)): if url and (not('/album/' in url) and not('/futbol/partido/' in url)):
urlverified = self.browser.open_novisit(url).geturl() return url
return urlverified
self.log('Skipping non-article', url) self.log('Skipping non-article', url)
return None return None
def get_cover_url(self):
soup = self.index_to_soup('http://elpais.com/')
for image in soup.findAll('img'):
if image['src'].endswith('elpaisTodayMiddle.jpg'):
sstr = image['src']
return sstr.replace('elpaisTodayMiddle.jpg', 'elpaisToday.jpg')
return None
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll('a'):
if item.string is not None:
tstr = item.string
item.replaceWith(tstr)
else:
item.name='span'
for atrs in ['href','target','alt','title']:
if item.has_key(atrs):
del item[atrs]
for item in soup.findAll('img',alt=False):
item['alt'] = 'image'
return soup
def preprocess_raw_html(self, raw, url): def preprocess_raw_html(self, raw, url):
return '<html><head><title>Untitled</title>'+raw[raw.find('</head>'):] return '<html><head><title>Untitled</title>'+raw[raw.find('</head>'):]