mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
72 lines
2.1 KiB
Python
72 lines
2.1 KiB
Python
#!/usr/bin/env python
|
|
##
|
|
# Title: Diario El Pueblo 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__ = '2013, Carlos Alves <carlosalves90@gmail.com>'
|
|
'''
|
|
diarioelpueblo.com.uy
|
|
'''
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class General(BasicNewsRecipe):
|
|
title = 'Diario El Pueblo'
|
|
__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-alt blog'})]
|
|
|
|
remove_tags = [
|
|
dict(
|
|
name='div',
|
|
attrs={
|
|
'class': ['hr', 'titlebar', 'volver-arriba-right', 'navigation']
|
|
}
|
|
),
|
|
dict(name='div', attrs={
|
|
'id': 'comment suckerfish crp_related'.split(),
|
|
}),
|
|
dict(name='h3', attrs={
|
|
'class': ['post_date']
|
|
}),
|
|
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://www.diarioelpueblo.com.uy/feed')]
|
|
|
|
def get_cover_url(self):
|
|
return None
|
|
|
|
def preprocess_html(self, soup):
|
|
for item in soup.findAll(style=True):
|
|
del item['style']
|
|
return soup
|