calibre/recipes/el_pais_uy.recipe
Kovid Goyal f207feb95f
pep8
2018-02-14 02:26:03 +05:30

78 lines
2.5 KiB
Python

#!/usr/bin/env python2
##
# Last Edited: 2018-02-13 Carlos Alves <carlosalves90@gmail.com>
##
__license__ = 'GPL v3'
__author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
'''
http://www.elpais.com.uy/
'''
from calibre.web.feeds.news import BasicNewsRecipe
class General(BasicNewsRecipe):
title = 'El Pais - Uruguay'
__author__ = 'Gustavo Azambuja'
description = 'Noticias de Uruguay y el resto del mundo'
publisher = 'EL PAIS S.A.'
category = 'news, politics, Uruguay'
language = 'es_UY'
timefmt = '[%a, %d %b, %Y]'
use_embedded_content = False
recursion = 2
encoding = 'utf-8'
publication_type = 'newspaper'
remove_javascript = True
no_stylesheets = True
oldest_article = 2
max_articles_per_feed = 20
keep_only_tags = [
dict(name='h1', attrs={'class': 'title'}),
dict(name='div', attrs={'class': 'composite-captioned-image'}),
dict(name='div', attrs={'class': 'content-modules'})
]
conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
}
remove_tags = [
dict(name='div', attrs={
'class': ['date_text', 'comments', 'form_section', 'share_it']}),
dict(name='div', attrs={
'id': ['relatedPosts', 'spacer', 'banner_izquierda', 'right_container']}),
dict(name='p', attrs={'class': 'FacebookLikeButton'}),
dict(name=['object', 'form']),
dict(name=['object', 'table'])]
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'Ultimo Momento',
u'https://www.elpais.com.uy/rss/')
]
def get_cover_url(self):
cover_url = None
index = 'https://www.elpais.com.uy/impresa/'
soup = self.index_to_soup(index)
link_item = soup.find('a', attrs={'class': 'page-link link-module'})
# print link_item
if link_item:
cover_url = 'https://www.elpais.com.uy' + link_item.get('href')
return cover_url
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup