calibre/recipes/juventudrebelde.recipe

56 lines
2.2 KiB
Python

#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
'''
juventudrebelde.cu
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class Juventudrebelde(BasicNewsRecipe):
title = 'Juventud Rebelde'
__author__ = 'Darko Miletic'
description = 'Diario de la Juventud Cubana'
publisher = 'Juventud rebelde'
category = 'news, politics, Cuba'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'cp1252'
language = 'es_CU'
cover_url = strftime('http://www.juventudrebelde.cu/UserFiles/File/impreso/iportada-%Y-%m-%d.jpg')
remove_javascript = True
html2lrf_options = [
'--comment' , description
, '--category' , category
, '--publisher', publisher
, '--ignore-tables'
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True'
keep_only_tags = [dict(name='div', attrs={'id':'noticia'})]
feeds = [
(u'Generales', u'http://www.juventudrebelde.cu/rss/generales.php' )
,(u'Cuba', u'http://www.juventudrebelde.cu/rss/generales.php?seccion=cuba' )
,(u'Internacionales', u'http://www.juventudrebelde.cu/rss/generales.php?seccion=internacionales' )
,(u'Opinion', u'http://www.juventudrebelde.cu/rss/generales.php?seccion=opinion' )
,(u'Cultura', u'http://www.juventudrebelde.cu/rss/generales.php?seccion=cultura' )
,(u'Deportes', u'http://www.juventudrebelde.cu/rss/generales.php?seccion=deportes' )
,(u'Lectura', u'http://www.juventudrebelde.cu/rss/generales.php?seccion=lectura' )
]
def preprocess_html(self, soup):
mtag = '<meta http-equiv="Content-Language" content="es-CU"/>'
soup.head.insert(0,mtag)
for item in soup.findAll(style=True):
del item['style']
return soup