--Código:__license__ = 'GPL v3' __author__ = 'Ricardo Jurado' __copyright__ = 'Ricardo Jurado' __version__ = 'v0.1' __date__ = '07 February 2011' ''' http://www.larazon.es/ ''' class AdvancedUserRecipe1297031650(BasicNewsRecipe): title = u'LARAZON.es' publisher = u'' __author__ = 'Ricardo Jurado' description = 'Noticias' title = u'LARAZON.es' oldest_article = 2 max_articles_per_feed = 20 no_stylesheets = True use_embedded_content = False encoding = 'UTF-8' remove_javascript = True language = 'es' extra_css = """ p{text-align: justify; font-size: 100%} body{ text-align: left; font-size:100% } h3{font-family: sans-serif; font-size:120%; font-weight:bold; text-align: justify; } h2{font-family: sans-serif; font-size:140%; font-weight:bold; text-align: justify; } h1{font-family: sans-serif; font-size:150%; font-weight:bold; text-align: justify; } """ keep_only_tags = [ dict(name='div', attrs={'id':'solapas'}), dict(name='div', attrs={'class':'txt'}), dict(name='div', attrs={'class':'detalle-noticia'}) ] remove_tags = [ dict(name='div' , attrs={'class':['num-comentarios','clearFix dixio']}) ] remove_tags_after = [ dict(name='div' , attrs={'class':['detalle-noticia']}) ] feeds = [ (u'NOTICIAS GENERALES', u'http://www.larazon.es/rss') ]
Saludos.