| 1 |
#!/usr/bin/env python |
| 2 |
## |
| 3 |
# Title: Padreydecano.com News, Sports, and Blog |
| 4 |
# Contact: Carlos Alves - <[email protected]> |
| 5 |
## |
| 6 |
# License: GNU General Public License v3 - http://www.gnu.org/copyleft/gpl.html |
| 7 |
# Copyright: Carlos Alves - <[email protected]> |
| 8 |
## |
| 9 |
# Written: September 2013 |
| 10 |
# Last Edited: 2018-02-13 |
| 11 |
## |
| 12 |
__license__ = 'GPL v3' |
| 13 |
__author__ = '2016, Carlos Alves <[email protected]>' |
| 14 |
|
| 15 |
''' |
| 16 |
padreydecano.com |
| 17 |
''' |
| 18 |
|
| 19 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 20 |
|
| 21 |
|
| 22 |
class General(BasicNewsRecipe): |
| 23 |
title = 'Padre y Decano' |
| 24 |
__author__ = 'Carlos Alves' |
| 25 |
description = 'El sitio del pueblo' |
| 26 |
tags = 'soccer, futbol, Peñarol' |
| 27 |
language = 'es_UY' |
| 28 |
timefmt = '[%a, %d %b, %Y]' |
| 29 |
use_embedded_content = False |
| 30 |
recursion = 5 |
| 31 |
encoding = None |
| 32 |
remove_javascript = True |
| 33 |
no_stylesheets = True |
| 34 |
|
| 35 |
oldest_article = 10 |
| 36 |
max_articles_per_feed = 100 |
| 37 |
keep_only_tags = [dict(name='h1', attrs={'class': 'entry-title'}), dict(name='div', attrs={'class': 'entry-content clearfix'})] |
| 38 |
|
| 39 |
remove_tags = [ |
| 40 |
dict(name='div', attrs={'class': ['br', 'hr', 'titlebar', 'navigation']}), |
| 41 |
dict(name='dl', attrs={'class': 'gallery-item'}), |
| 42 |
dict(name=['object', 'link']), |
| 43 |
] |
| 44 |
|
| 45 |
extra_css = ''' |
| 46 |
h1{font-family: Georgia,"Times New Roman",Times,serif} |
| 47 |
h3{font-family: Georgia,"Times New Roman",Times,serif} |
| 48 |
h2{font-family: Georgia,"Times New Roman",Times,serif} |
| 49 |
p{font-family: Verdana,Arial,Helvetica,sans-serif} |
| 50 |
body{font-family: Verdana,Arial,Helvetica,sans-serif} |
| 51 |
img{margin-bottom: 0.4em; display:block;} |
| 52 |
''' |
| 53 |
|
| 54 |
feeds = [('Padre y Decano | Club Atlético Peñarol', 'http://www.padreydecano.com/cms/feed/')] |
| 55 |
|
| 56 |
def get_cover_url(self): |
| 57 |
return None |
| 58 |
|
| 59 |
def preprocess_html(self, soup): |
| 60 |
for item in soup.findAll(style=True): |
| 61 |
del item['style'] |
| 62 |
return soup |