mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
(Imroved El Pais) Fix #8095 (Completely new recipe for El Pais)
This commit is contained in:
Kovid Goyal
parent
85bf7da1fb
commit
a323051dcd
@ -1,86 +1,95 @@
|
|||||||
# -*- coding: utf-8 -*-
|
|
||||||
__license__ = 'GPL v3'
|
__license__ = 'GPL v3'
|
||||||
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
|
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
|
||||||
'''
|
'''
|
||||||
www.elpais.com/diario/
|
www.elpais.com
|
||||||
'''
|
'''
|
||||||
|
|
||||||
from calibre import strftime
|
|
||||||
from calibre.web.feeds.news import BasicNewsRecipe
|
from calibre.web.feeds.news import BasicNewsRecipe
|
||||||
|
|
||||||
class ElPaisImpresa(BasicNewsRecipe):
|
class ElPais_RSS(BasicNewsRecipe):
|
||||||
title = u'El Pa\xeds - edicion impresa'
|
title = 'El Pais'
|
||||||
__author__ = 'Darko Miletic'
|
__author__ = 'Darko Miletic'
|
||||||
description = u'el periodico global en Espa\xf1ol'
|
description = 'el periodico global en Castellano'
|
||||||
publisher = 'EDICIONES EL PAIS, S.L.'
|
publisher = 'EDICIONES EL PAIS, S.L.'
|
||||||
category = 'news, politics,Spain,actualidad,noticias,informacion,videos,fotografias,audios,graficos,nacional,internacional,deportes,economia,tecnologia,cultura,gente,television,sociedad,opinion,blogs,foros,chats,encuestas,entrevistas,participacion'
|
category = 'news, politics, finances, world, spain'
|
||||||
|
oldest_article = 2
|
||||||
|
max_articles_per_feed = 200
|
||||||
no_stylesheets = True
|
no_stylesheets = True
|
||||||
encoding = 'latin1'
|
encoding = 'cp1252'
|
||||||
use_embedded_content = False
|
use_embedded_content = False
|
||||||
language = 'es'
|
language = 'es_ES'
|
||||||
|
remove_empty_feeds = True
|
||||||
publication_type = 'newspaper'
|
publication_type = 'newspaper'
|
||||||
masthead_url = 'http://www.elpais.com/im/tit_logo_global.gif'
|
masthead_url = 'http://www.elpais.com/im/tit_logo.gif'
|
||||||
index = 'http://www.elpais.com/diario/'
|
extra_css = """
|
||||||
extra_css = ' p{text-align: justify} body{ text-align: left; font-family: Georgia,"Times New Roman",Times,serif } h2{font-family: Arial,Helvetica,sans-serif} img{margin-bottom: 0.4em} '
|
body{font-family: Georgia,"Times New Roman",Times,serif }
|
||||||
|
h3{font-family: Arial,Helvetica,sans-serif}
|
||||||
|
img{margin-bottom: 0.4em; display:block}
|
||||||
|
"""
|
||||||
|
|
||||||
conversion_options = {
|
conversion_options = {
|
||||||
'comment' : description
|
'comment' : description
|
||||||
, 'tags' : category
|
, 'tags' : category
|
||||||
, 'publisher' : publisher
|
, 'publisher' : publisher
|
||||||
, 'language' : language
|
, 'language' : language
|
||||||
}
|
}
|
||||||
|
|
||||||
feeds = [
|
keep_only_tags = [dict(attrs={'class':['cabecera_noticia estirar','cabecera_noticia','','contenido_noticia']})]
|
||||||
(u'Internacional' , index + u'internacional/' )
|
remove_tags = [
|
||||||
,(u'Espa\xf1a' , index + u'espana/' )
|
dict(name=['meta','link','base','iframe','embed','object'])
|
||||||
,(u'Economia' , index + u'economia/' )
|
,dict(attrs={'class':['info_complementa','estructura_2col_der','votos estirar','votos']})
|
||||||
,(u'Opinion' , index + u'opinion/' )
|
,dict(attrs={'id':'utilidades'})
|
||||||
,(u'Vi\xf1etas' , index + u'vineta/' )
|
]
|
||||||
,(u'Sociedad' , index + u'sociedad/' )
|
remove_tags_after = dict(attrs={'id':'utilidades'})
|
||||||
,(u'Cultura' , index + u'cultura/' )
|
remove_attributes = ['lang','border','width','height']
|
||||||
,(u'Tendencias' , index + u'tendencias/' )
|
|
||||||
,(u'Gente' , index + u'gente/' )
|
|
||||||
,(u'Obituarios' , index + u'obituarios/' )
|
|
||||||
,(u'Deportes' , index + u'deportes/' )
|
|
||||||
,(u'Pantallas' , index + u'radioytv/' )
|
|
||||||
,(u'Ultima' , index + u'ultima/' )
|
|
||||||
,(u'Educacion' , index + u'educacion/' )
|
|
||||||
,(u'Saludo' , index + u'salud/' )
|
|
||||||
,(u'Ciberpais' , index + u'ciberpais/' )
|
|
||||||
,(u'EP3' , index + u'ep3/' )
|
|
||||||
,(u'Cine' , index + u'cine/' )
|
|
||||||
,(u'Babelia' , index + u'babelia/' )
|
|
||||||
,(u'El viajero' , index + u'viajero/' )
|
|
||||||
,(u'Negocios' , index + u'negocios/' )
|
|
||||||
,(u'Domingo' , index + u'domingo/' )
|
|
||||||
,(u'El Pais semanal' , index + u'eps/' )
|
|
||||||
,(u'Quadern Catalunya' , index + u'quadern-catalunya/' )
|
|
||||||
]
|
|
||||||
|
|
||||||
keep_only_tags=[dict(attrs={'class':['cabecera_noticia','contenido_noticia']})]
|
feeds = [
|
||||||
remove_attributes=['width','height']
|
(u'Lo ultimo' , u'http://www.elpais.com/rss/feed.html?feedId=17046')
|
||||||
remove_tags=[dict(name='link')]
|
,(u'America Latina' , u'http://www.elpais.com/rss/feed.html?feedId=17041')
|
||||||
|
,(u'Mexico' , u'http://www.elpais.com/rss/feed.html?feedId=17042')
|
||||||
def parse_index(self):
|
,(u'Europa' , u'http://www.elpais.com/rss/feed.html?feedId=17043')
|
||||||
totalfeeds = []
|
,(u'Estados Unidos' , u'http://www.elpais.com/rss/feed.html?feedId=17044')
|
||||||
lfeeds = self.get_feeds()
|
,(u'Oriente proximo' , u'http://www.elpais.com/rss/feed.html?feedId=17045')
|
||||||
for feedobj in lfeeds:
|
,(u'Espana' , u'http://www.elpais.com/rss/feed.html?feedId=1002' )
|
||||||
feedtitle, feedurl = feedobj
|
,(u'Andalucia' , u'http://www.elpais.com/rss/feed.html?feedId=17057')
|
||||||
self.report_progress(0, _('Fetching feed')+' %s...'%(feedtitle if feedtitle else feedurl))
|
,(u'Catalunia' , u'http://www.elpais.com/rss/feed.html?feedId=17059')
|
||||||
articles = []
|
,(u'Comunidad Valenciana' , u'http://www.elpais.com/rss/feed.html?feedId=17061')
|
||||||
soup = self.index_to_soup(feedurl)
|
,(u'Madrid' , u'http://www.elpais.com/rss/feed.html?feedId=1016' )
|
||||||
for item in soup.findAll('a',attrs={'class':['g19r003','g19i003','g17r003','g17i003']}):
|
,(u'Pais Vasco' , u'http://www.elpais.com/rss/feed.html?feedId=17062')
|
||||||
url = 'http://www.elpais.com' + item['href'].rpartition('/')[0]
|
,(u'Galicia' , u'http://www.elpais.com/rss/feed.html?feedId=17063')
|
||||||
title = self.tag_to_string(item)
|
,(u'Opinion' , u'http://www.elpais.com/rss/feed.html?feedId=1003' )
|
||||||
date = strftime(self.timefmt)
|
,(u'Sociedad' , u'http://www.elpais.com/rss/feed.html?feedId=1004' )
|
||||||
articles.append({
|
,(u'Deportes' , u'http://www.elpais.com/rss/feed.html?feedId=1007' )
|
||||||
'title' :title
|
,(u'Cultura' , u'http://www.elpais.com/rss/feed.html?feedId=1008' )
|
||||||
,'date' :date
|
,(u'Cine' , u'http://www.elpais.com/rss/feed.html?feedId=17052')
|
||||||
,'url' :url
|
,(u'Literatura' , u'http://www.elpais.com/rss/feed.html?feedId=17053')
|
||||||
,'description':''
|
,(u'Musica' , u'http://www.elpais.com/rss/feed.html?feedId=17051')
|
||||||
})
|
,(u'Arte' , u'http://www.elpais.com/rss/feed.html?feedId=17060')
|
||||||
totalfeeds.append((feedtitle, articles))
|
,(u'Tecnologia' , u'http://www.elpais.com/rss/feed.html?feedId=1005' )
|
||||||
return totalfeeds
|
,(u'Economia' , u'http://www.elpais.com/rss/feed.html?feedId=1006' )
|
||||||
|
,(u'Ciencia' , u'http://www.elpais.com/rss/feed.html?feedId=17068')
|
||||||
|
,(u'Salud' , u'http://www.elpais.com/rss/feed.html?feedId=17074')
|
||||||
|
,(u'Ocio' , u'http://www.elpais.com/rss/feed.html?feedId=17075')
|
||||||
|
,(u'Justicia y Leyes' , u'http://www.elpais.com/rss/feed.html?feedId=17069')
|
||||||
|
,(u'Guerras y conflictos' , u'http://www.elpais.com/rss/feed.html?feedId=17070')
|
||||||
|
,(u'Politica' , u'http://www.elpais.com/rss/feed.html?feedId=17073')
|
||||||
|
]
|
||||||
|
|
||||||
def print_version(self, url):
|
def print_version(self, url):
|
||||||
return url + '?print=1'
|
return url + '?print=1'
|
||||||
|
|
||||||
|
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
|
||||||
|
|||||||
Loading…
x
Reference in New Issue
Block a user