mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
67 lines
2.0 KiB
Python
67 lines
2.0 KiB
Python
#!/usr/bin/env python2
|
|
##
|
|
# Title: Padreydecano.com News, Sports, and Blog Calibre Recipe
|
|
# Contact: Carlos Alves - <carlos@carlosalves.info>
|
|
##
|
|
# License: GNU General Public License v3 - http://www.gnu.org/copyleft/gpl.html
|
|
# Copyright: Carlos Alves - <carlos@carlosalves.info>
|
|
##
|
|
# Written: September 2013
|
|
# Last Edited: 2016-01-11
|
|
##
|
|
__license__ = 'GPL v3'
|
|
__author__ = '2016, Carlos Alves <carlos@carlosalves.info>'
|
|
|
|
'''
|
|
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 = 10
|
|
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 get_cover_url(self):
|
|
return 'http://www.padreydecano.com/cms/wp-content/uploads/2011/09/editorial.jpg'
|
|
|
|
def preprocess_html(self, soup):
|
|
for item in soup.findAll(style=True):
|
|
del item['style']
|
|
return soup
|