La Capital de Rosario by Darko Miletic

Fixes #1209289 [New recipe for La Capital de Rosario](https://bugs.launchpad.net/calibre/+bug/1209289)
This commit is contained in:
Kovid Goyal 2013-08-07 21:36:10 +05:30
parent 8b5e9ed035
commit 39e76dfedf
2 changed files with 76 additions and 0 deletions

BIN
recipes/icons/lacapital.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.1 KiB

76
recipes/lacapital.recipe Normal file
View File

@ -0,0 +1,76 @@
__license__ = 'GPL v3'
__copyright__ = '2013, Darko Miletic <darko.miletic at gmail.com>'
'''
www.lacapital.com.ar
'''
from calibre.web.feeds.news import BasicNewsRecipe
class LaCapital(BasicNewsRecipe):
title = 'La Capital de Rosario'
__author__ = 'Darko Miletic'
description = 'Noticias, actualidad y toda la informacion de Rosario y la region'
publisher = 'Diario La Capital S. A.'
category = 'news, politics, Rosario, Santa Fe, Argentina'
oldest_article = 2
max_articles_per_feed = 200
no_stylesheets = True
encoding = 'utf8'
use_embedded_content = False
language = 'es_AR'
remove_empty_feeds = True
publication_type = 'newspaper'
masthead_url = 'http://www.lacapital.com.ar/system/modules/com.tfsla.diario.core/resources/images/logoLaCapital_noCom.png'
extra_css = """
body{font-family: Georgia,"Times New Roman",Times,serif }
img{margin-bottom: 0.4em; display:block}
"""
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
keep_only_tags=[dict(attrs={'class':'leer'})]
remove_tags_after=dict(attrs={'class':'notaA'})
remove_tags = [
dict(name=['meta','link','iframe','object'])
,dict(name='div', attrs={'class':['herramientas','almargen','relacionadas']})
]
feeds = [
(u'Portada' , u'http://www.lacapital.com.ar/rss/home.xml' )
,(u'La Ciudad' , u'http://www.lacapital.com.ar/rss/laciudad.xml' )
,(u'Politica' , u'http://www.lacapital.com.ar/rss/politica.xml' )
,(u'Economia' , u'http://www.lacapital.com.ar/rss/economia.xml' )
,(u'La Region' , u'http://www.lacapital.com.ar/rss/laregion.xml' )
,(u'Informacion General' , u'http://www.lacapital.com.ar/rss/informaciongral.xml' )
,(u'El Mundo' , u'http://www.lacapital.com.ar/rss/elmundo.xml' )
,(u'Opinion' , u'http://www.lacapital.com.ar/rss/opinion.xml' )
,(u'Cartas de lectores' , u'http://www.lacapital.com.ar/rss/cartasdelectores.xml')
,(u'Escenario' , u'http://www.lacapital.com.ar/rss/escenario.xml' )
,(u'Policiales' , u'http://www.lacapital.com.ar/rss/policiales.xml' )
,(u'Ovacion' , u'http://www.lacapital.com.ar/rss/ovacion.xml' )
,(u'Turismo' , u'http://www.lacapital.com.ar/rss/turismo.xml' )
,(u'Economia' , u'http://www.lacapital.com.ar/rss/economia.xml' )
,(u'Señales' , u'http://www.lacapital.com.ar/rss/senales.xml' )
,(u'Educacion' , u'http://www.lacapital.com.ar/rss/educacion.xml' )
,(u'Estilo' , u'http://www.lacapital.com.ar/rss/estilo.xml' )
,(u'Salud' , u'http://www.lacapital.com.ar/rss/salud.xml' )
,(u'Tecnologia' , u'http://www.lacapital.com.ar/rss/tecnologia.xml' )
]
def get_cover_url(self):
soup = self.index_to_soup('http://www.lacapital.com.ar/impresa/tapa.html')
for image in soup.findAll('img',alt=True):
if image['alt'].startswith('Tapa de papel'):
return image['src']
return None
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup