calibre/recipes/padreydecano.recipe
2015-01-23 19:08:21 +05:30

51 lines
1.7 KiB
Python

#!/usr/bin/env python2
__license__ = 'GPL v3'
__author__ = '2013, Carlos Alves <carlosalves90@gmail.com>'
'''
padreydecano.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class General(BasicNewsRecipe):
title = 'Padre y Decano'
__author__ = 'Carlos Alves'
description = 'El sitio del pueblo'
tags = 'soccer, futbol, Peñarol'
language = 'es_UY'
timefmt = '[%a, %d %b, %Y]'
use_embedded_content = False
recursion = 5
encoding = None
remove_javascript = True
no_stylesheets = True
oldest_article = 2
max_articles_per_feed = 100
keep_only_tags = [
dict(name='h1', attrs={'class':'entry-title'}),
dict(name='div', attrs={'class':'entry-content clearfix'})
]
remove_tags = [
dict(name='div', attrs={'class':['br', 'hr', 'titlebar', 'navigation']}),
dict(name='dl', attrs={'class':'gallery-item'}),
dict(name=['object','link'])
]
extra_css = '''
h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
p {font-family:Arial,Helvetica,sans-serif;}
'''
feeds = [
(u'Padre y Decano | Club Atlético Peñarol', u'http://www.padreydecano.com/cms/feed/')
]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup