Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix #803589 (Updated recipe for Infobae)

Browse Source
This commit is contained in:
Kovid Goyal 2011-06-29 12:23:05 -06:00
parent ca69bebe03
commit a26d1a519f
1 changed files with 41 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

62
recipes/infobae.recipe
View File

@ -1,5 +1,5 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008-2010, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2008-2011, Darko Miletic <darko.miletic at gmail.com>'
''' '''
infobae.com infobae.com
''' '''
@ -9,7 +9,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
class Infobae(BasicNewsRecipe): class Infobae(BasicNewsRecipe):
title = 'Infobae.com' title = 'Infobae.com'
__author__ = 'Darko Miletic and Sujata Raman' __author__ = 'Darko Miletic and Sujata Raman'
description = 'Informacion Libre las 24 horas' description = 'Infobae.com es el sitio de noticias con mayor actualizacion de Latinoamérica. Noticias actualizadas las 24 horas, los 365 días del año.'
publisher = 'Infobae.com' publisher = 'Infobae.com'
category = 'news, politics, Argentina' category = 'news, politics, Argentina'
oldest_article = 1 oldest_article = 1
@ -17,13 +17,13 @@ class Infobae(BasicNewsRecipe):
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
language = 'es_AR' language = 'es_AR'
encoding = 'cp1252' encoding = 'utf8'
masthead_url = 'http://www.infobae.com/imgs/header/header.gif' masthead_url = 'http://www.infobae.com/media/img/static/logo-infobae.gif'
remove_javascript = True
remove_empty_feeds = True remove_empty_feeds = True
extra_css = ''' extra_css = '''
body{font-family:Arial,Helvetica,sans-serif;} body{font-family: Arial,Helvetica,sans-serif}
.popUpTitulo{color:#0D4261; font-size: xx-large} img{display: block}
.categoria{font-size: small; text-transform: uppercase}
''' '''
conversion_options = { conversion_options = {
@ -31,26 +31,44 @@ class Infobae(BasicNewsRecipe):
, 'tags' : category , 'tags' : category
, 'publisher' : publisher , 'publisher' : publisher
, 'language' : language , 'language' : language
, 'linearize_tables' : True
} }
keep_only_tags = [dict(attrs={'class':['titularnota','nota','post-title','post-entry','entry-title','entry-info','entry-content']})]
feeds = [ remove_tags_after = dict(attrs={'class':['interior-noticia','nota-desc','tags']})
(u'Noticias' , u'http://www.infobae.com/adjuntos/html/RSS/hoy.xml' ) remove_tags = [
,(u'Salud' , u'http://www.infobae.com/adjuntos/html/RSS/salud.xml' ) dict(name=['base','meta','link','iframe','object','embed','ins'])
,(u'Tecnologia', u'http://www.infobae.com/adjuntos/html/RSS/tecnologia.xml') ,dict(attrs={'class':['barranota','tags']})
,(u'Deportes' , u'http://www.infobae.com/adjuntos/html/RSS/deportes.xml' )
] ]
def print_version(self, url): feeds = [
article_part = url.rpartition('/')[2] (u'Saludable' , u'http://www.infobae.com/rss/saludable.xml')
article_id= article_part.partition('-')[0] ,(u'Economia' , u'http://www.infobae.com/rss/economia.xml' )
return 'http://www.infobae.com/notas/nota_imprimir.php?Idx=' + article_id ,(u'En Numeros', u'http://www.infobae.com/rss/rating.xml' )
,(u'Finanzas' , u'http://www.infobae.com/rss/finanzas.xml' )
,(u'Mundo' , u'http://www.infobae.com/rss/mundo.xml' )
,(u'Sociedad' , u'http://www.infobae.com/rss/sociedad.xml' )
,(u'Politica' , u'http://www.infobae.com/rss/politica.xml' )
,(u'Deportes' , u'http://www.infobae.com/rss/deportes.xml' )
]
def postprocess_html(self, soup, first): def preprocess_html(self, soup):
for tag in soup.findAll(name='strong'): for item in soup.findAll(style=True):
tag.name = 'b' del item['style']
for item in soup.findAll('a'):
limg = item.find('img')
if item.string is not None:
str = item.string
item.replaceWith(str)
else:
if limg:
item.name = 'div'
item.attrs = []
else:
str = self.tag_to_string(item)
item.replaceWith(str)
for item in soup.findAll('img'):
if not item.has_key('alt'):
item['alt'] = 'image'
return soup return soup