Diariodesevilla.es

[rickydh]

Hola.

Espero que os guste.

__license__   = 'GPL v3'
__author__ = 'Ricardo Jurado'
__copyright__ = 'Ricardo Jurado'
__version__ = 'v0.1'
__date__ = '21 February 2011'

'''
http://www.diariodesevilla.es/
'''

class AdvancedUserRecipe1296604369(BasicNewsRecipe):

   title = u'diariodesevilla.es'
   masthead_url = 'http://www.diariodesevilla.es/img/c_h_sevilla.jpg'
   cover_url = 'http://www.diariodesevilla.es/img/c_h_sevilla.jpg'
   publisher = u'Joly Digital'
   __author__ = 'Ricardo Jurado'
   description = 'Noticias de Sevilla, Andalucia, nacionales y del mundo'
   category = 'News,Sevilla,Andalucia,Spain'

   oldest_article = 2
   max_articles_per_feed = 20
   no_stylesheets = True
   use_embedded_content = False
   encoding = 'ISO-8859-1'
   remove_javascript = True
   language = 'es'

   extra_css = """
	p{text-align: justify; font-size: 100%}
	body{ text-align: left; font-size:100% }
	h2{font-family: sans-serif; font-size:130%; font-weight:bold; text-align: justify; }
	.subtitle{font-family:Arial,Helvetica,sans-serif; font-size:100%; font-weight:bold; }
	.info{font-family:Arial,Helvetica,sans-serif; font-size:80%; margin-bottom: 1em;}
	"""

   keep_only_tags = [
	dict(name='div', attrs={'class':'eCrumbs'}),
	dict(name='div', attrs={'class':'titles'}),
	dict(name='div', attrs={'class':'content'})
	]

   remove_tags = [
	dict(name='ul', attrs={'class':'options'})
	]

   remove_tags_after = [
	dict(name='div', attrs={'class':'body'})
	]

   feeds = [
	(u'ARTICULOS', u'http://www.diariodesevilla.es/rss/articles.php')
	]

--
Saludos.