Updated recipe for El Universal

This commit is contained in:
Kovid Goyal 2009-10-30 09:35:12 -06:00
parent b3de4fa7b1
commit ee3be40500

View File

@ -10,7 +10,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
class ElUniversal(BasicNewsRecipe):
title = 'El Universal'
__author__ = 'Darko Miletic'
__author__ = 'Darko Miletic and Sujata Raman'
description = 'News from Mexico'
oldest_article = 1
max_articles_per_feed = 100
@ -22,25 +22,79 @@ class ElUniversal(BasicNewsRecipe):
remove_javascript = True
language = 'es'
extra_css = '''
body{font-family:Arial,Helvetica,sans-serif; font-size:x-small;}
.geoGris30{font-family:Georgia,"Times New Roman",Times,serif; font-size:large; color:#003366; font-weight:bold;}
.arnegro16{font-family:Georgia,"Times New Roman",Times,serif; font-weight:bold; font-size:small;}
.tbazull2{font-family:"trebuchet ms",Arial,Helvetica,sans-serif; color:#336699; font-size:xx-small;}
.tbgrisf11{font-family:"trebuchet ms",Arial,Helvetica,sans-serif; color: #666666; font-size:xx-small;}
.verrojo13{font-family:"trebuchet ms",Arial,Helvetica,sans-serif; color: #CC0033; font-size:xx-small;}
.trnegro13{font-family:"trebuchet ms",Arial,Helvetica,sans-serif; font-size:xx-small;}
.txt-fotogaleria{font-family:"trebuchet ms",Arial,Helvetica,sans-serif; font-size:xx-small;}
'''
keep_only_tags = [ dict(name='table', attrs={'width':"633"}),dict(name='table', attrs={'width':"629"}),]
html2lrf_options = [
'--comment', description
, '--category', category
, '--publisher', publisher
, '--ignore-tables'
remove_tags = [
dict(name='table', attrs={'bgcolor':"#f5f5f5"}),
dict(name='td', attrs={'bgcolor':"#f7f8f9"}),
dict(name='td', attrs={'bgcolor':"#f5f5f5"}),
dict(name='table', attrs={'width':"302"}),
dict(name='table', attrs={'width':"214"}),
dict(name='table', attrs={'width':"112"}),
dict(name='table', attrs={'width':"980"}),
dict(name='td', attrs={'height':"1"}),
dict(name='td', attrs={'height':"4"}),
dict(name='td', attrs={'height':"20"}),
dict(name='td', attrs={'height':"10"}),
dict(name='td', attrs={'class':["trrojo11","trbris11","trrojo12","arrojo12s","tbazul13"]}),
dict(name='div', attrs={'id':["mapg","ver_off_todosloscom","todosloscom"]}),
dict(name='span', attrs={'class':["trazul18b","trrojo11","trnaranja11","trbris11","georojo18b","geogris18"]}),
dict(name='span', attrs={'class':["detalles-opinion"]}),
dict(name='a', attrs={'class':["arnaranja12b","trbris11","arazul12rel","trrojo10"]}),
dict(name='img', src = "/img/icono_imprimir.gif"),
dict(name='img', src = "/img/icono_enviar_mail.gif"),
dict(name='img', src = "/img/icono_fuente_g.gif"),
dict(name='img', src = "/img/icono_fuente_m.gif"),
dict(name='img', src = "/img/icono_fuente_c.gif"),
dict(name='img', src = "/img/icono_compartir.gif"),
dict(name='img', src = "/img/icono_enviar_coment.gif"),
dict(name='img', src = "http://www.eluniversal.com.mx/n_img/bot-notasrel.gif"),
dict(name='img', src = "http://www.eluniversal.com.mx/n_img/fr.gif"),
dict(name='img', src = "/img/espiral2.gif"),
dict(name='img', src = "http://www.eluniversal.com.mx/n_img/b"),
dict(name='img', src = "/img/icono_enviar_coment.gifot-notasrel.gif"),
dict(name='img', src = "/n_img/icono_tipo3.gif"),
dict(name='img', src = "/n_img/icono_tipo2.gif"),
dict(name='img', src = "/n_img/icono_print.gif"),
dict(name='img', src = "/n_img/icono_mail2.gif"),
dict(name='img', src = "/n_img/im-comentarios-2a.gif"),
dict(name='img', src = "/n_img/im-comentarios-1a.gif"),
dict(name='img', src = "/img/icono_coment.gif"),
dict(name='img', src = "http://www.eluniversal.com.mx/n_img/bot-sitiosrel.gif"),
dict(name='img', src = "/n_img/icono_tipomenos.gif"),
dict(name='img', src = "/img/futbol/19.jpg"),
dict(name='img', alt = "Facebook"),
dict(name='img', alt = "Twitter"),
dict(name='img', alt = "Google"),
dict(name='img', alt = "LinkedIn"),
dict(name='img', alt = "Viadeo"),
dict(name='img', alt = "Digg"),
dict(name='img', alt = "Delicious"),
dict(name='img', alt = "Meneame"),
dict(name='img', alt = "Yahoo"),
dict(name='img', alt = "Technorati"),
dict(name='a',text =["Compartir","Facebook","Twitter","Google","LinkedIn","Viadeo","Digg","Delicious","Meneame","Yahoo","Technorati"]),
dict(name='select'),
dict(name='a', attrs={'class':"tbgriscompartir"}),
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True'
remove_tags = [dict(name='link')]
feeds = [
(u'Minuto por Minuto', u'http://www.eluniversal.com.mx/rss/universalmxm.xml' )
,(u'Mundo' , u'http://www.eluniversal.com.mx/rss/mundo.xml' )
,(u'Mexico' , u'http://www.eluniversal.com.mx/rss/mexico.xml' )
,(u'Estados' , u'http://www.eluniversal.com.mx/rss/estados.xml' )
,(u'Finanzas' , u'http://www.eluniversal.com.mx/rss/finanzas.xml' )
,(u'Deportes' , u'http://www.eluniversal.com.mx/rss/deportes.xml' )
(u'Deportes' , u'http://www.eluniversal.com.mx/rss/deportes.xml' )
,(u'Espectaculos' , u'http://www.eluniversal.com.mx/rss/espectaculos.xml' )
,(u'Cultura' , u'http://www.eluniversal.com.mx/rss/cultura.xml' )
,(u'Ciencia' , u'http://www.eluniversal.com.mx/rss/ciencia.xml' )
@ -48,19 +102,24 @@ class ElUniversal(BasicNewsRecipe):
,(u'Sociedad' , u'http://www.eluniversal.com.mx/rss/sociedad.xml' )
]
def print_version(self, url):
return url.replace('/notas/','/notas/vi_')
# def print_version(self, url):
# return url.replace('/notas/','/notas/vi_')
def preprocess_html(self, soup):
mtag = '<meta http-equiv="Content-Language" content="es-MX"/><meta http-equiv="Content-Type" content="text/html; charset=utf-8">'
soup.head.insert(0,mtag)
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll(font=True):
del item['font']
for item in soup.findAll(face=True):
del item['face']
for item in soup.findAll(helvetica=True):
del item['helvetica']
for tag in soup.findAll(name='td',attrs={'class': 'arazul50'}):
tag.insert(0,"<h1>")
tag.insert(2,"</h1>")
return soup
def postprocess_html(self, soup,first):
for tag in soup.findAll(name=['table', 'span','i']):
tag.name = 'div'
for item in soup.findAll(align = "right"):
del item['align']
return soup