calibre/recipes/10minutos.recipe
Kovid Goyal 29cd8d64ea
Change shebangs to python from python2
Also remove a few other miscellaneous references to python2
2020-08-22 18:47:51 +05:30

66 lines
1.9 KiB
Python

#!/usr/bin/env python
##
# Title: Diario 10minutos.com.uy News and Sports Calibre Recipe
# Contact: Carlos Alves - <carlosalves90@gmail.com>
##
# License: GNU General Public License v3 - http://www.gnu.org/copyleft/gpl.html
# Copyright: Carlos Alves - <carlosalves90@gmail.com>
##
# Written: September 2013
# Last Edited: 2018-02-13
##
__license__ = 'GPL v3'
__author__ = '2016, Carlos Alves <carlosalves90@gmail.com>'
'''
10minutos.com.uy
'''
from calibre.web.feeds.news import BasicNewsRecipe
class General(BasicNewsRecipe):
title = '10minutos'
__author__ = 'Carlos Alves'
description = 'Noticias de Salto - Uruguay'
tags = 'news, sports'
language = 'es_UY'
timefmt = '[%a, %d %b, %Y]'
use_embedded_content = False
recursion = 5
encoding = 'utf8'
remove_javascript = True
no_stylesheets = True
oldest_article = 2
max_articles_per_feed = 100
keep_only_tags = [dict(name='div', attrs={'class': 'post-content'})]
remove_tags = [
dict(name='div', attrs={'class': ['hr', 'titlebar', 'navigation']}),
dict(name='div', attrs={'class': 'sharedaddy sd-sharing-enabled'}),
dict(name='p', attrs={'class': 'post-meta'}),
dict(name=['object', 'link'])
]
extra_css = '''
h1{font-family: Georgia,"Times New Roman",Times,serif}
h3{font-family: Georgia,"Times New Roman",Times,serif}
h2{font-family: Georgia,"Times New Roman",Times,serif}
p{font-family: Verdana,Arial,Helvetica,sans-serif}
body{font-family: Verdana,Arial,Helvetica,sans-serif}
img{margin-bottom: 0.4em; display:block;}
'''
feeds = [
(u'Articulos', u'http://10minutos.com.uy/?feed=rss2')
]
def get_cover_url(self):
return None
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup