calibre/resources/recipes/lanacion.recipe

59 lines
3.3 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2008-2010, Darko Miletic <darko.miletic at gmail.com>'
'''
lanacion.com.ar
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Lanacion(BasicNewsRecipe):
title = 'La Nacion'
__author__ = 'Darko Miletic'
description = 'Noticias de Argentina y el resto del mundo'
publisher = 'La Nacion S.A.'
category = 'news, politics, Argentina'
oldest_article = 2
max_articles_per_feed = 100
use_embedded_content = False
no_stylesheets = True
language = 'es'
encoding = 'cp1252'
masthead_url = 'http://www.lanacion.com.ar/imgs/layout/logos/ln341x47.gif'
extra_css = ' h1{font-family: Georgia,serif} body{font-family: Arial,sans-serif} img{margin-top: 0.5em; margin-bottom: 0.2em} .notaEpigrafe{font-size: x-small} '
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher': publisher
, 'language' : language
}
keep_only_tags = [dict(name='div', attrs={'class':'nota floatFix'})]
remove_tags = [
dict(name='div' , attrs={'class':'notaComentario floatFix noprint' })
,dict(name='ul' , attrs={'class':'cajaHerramientas cajaTop noprint'})
,dict(name='div' , attrs={'class':'cajaHerramientas noprint' })
,dict(attrs={'class':['titulosMultimedia','derecha','techo color']})
,dict(name=['iframe','embed','object'])
]
remove_attributes = ['height','width']
feeds = [
(u'Ultimas noticias' , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?origen=2' )
,(u'Diario de hoy' , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?origen=1' )
,(u'Politica' , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=30' )
,(u'Economia' , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=272' )
,(u'Deportes' , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=131' )
,(u'Informacion General' , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=21' )
,(u'Cultura' , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=1' )
,(u'Opinion' , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=28' )
,(u'Espectaculos' , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=120' )
,(u'Exterior' , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=7' )
,(u'Ciencia/Salud' , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=498' )
,(u'Revista' , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=494' )
]
def preprocess_html(self, soup):
return self.adeify_images(soup)