calibre/recipes/marca.recipe
Kovid Goyal 567040ee1e Perform PEP8 compliance checks on the entire codebase
Some bits of PEP 8 are turned off via setup.cfg
2016-07-29 21:25:17 +05:30

50 lines
1.7 KiB
Plaintext

# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
__copyright__ = '2009-2011, Darko Miletic <darko.miletic at gmail.com>'
'''
www.marca.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Marca(BasicNewsRecipe):
title = 'Marca'
__author__ = 'Darko Miletic'
description = 'Noticias deportivas'
publisher = 'marca.com'
category = 'news, sports, Spain'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
delay = 1
encoding = 'iso-8859-15'
language = 'es'
publication_type = 'newsportal'
masthead_url = 'http://estaticos.marca.com/deporte/img/v3.0/img_marca-com.png'
extra_css = """
body{font-family: Tahoma,Geneva,sans-serif}
h1,h2,h3,h4,h5,h6{font-family: 'LatoBlack',Tahoma,Geneva,sans-serif}
.cab_articulo h4 {font-family: Georgia,"Times New Roman",Times,serif}
.antetitulo{text-transform: uppercase}
"""
feeds = [(u'Portada', u'http://estaticos.marca.com/rss/portada.xml')]
keep_only_tags = [
dict(name='div', attrs={'class': ['cab_articulo', 'cuerpo_articulo']})]
remove_attributes = ['lang']
remove_tags = [
dict(name=['object', 'link', 'script', 'embed', 'iframe',
'meta', 'base']), dict(name='div', attrs={'class': 'tabs'})
]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup
def get_article_url(self, article):
return article.get('guid', None)