calibre/recipes/eluniverso_ec.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

62 lines
2.4 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
eluniverso.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class ElUniverso_Ecuador(BasicNewsRecipe):
title = 'El Universo - Ecuador'
__author__ = 'Darko Miletic'
description = 'Noticias del Ecuador y el resto del mundo'
publisher = 'El Universo'
category = 'news, politics, Ecuador'
oldest_article = 2
max_articles_per_feed = 200
no_stylesheets = True
encoding = 'utf8'
use_embedded_content = False
language = 'es_EC'
remove_empty_feeds = True
publication_type = 'newspaper'
masthead_url = 'http://servicios2.eluniverso.com/versiones/v1/img/Hd/lg_ElUniverso.gif'
extra_css = """
body{font-family: Verdana,Arial,Helvetica,sans-serif; color: #333333 }
h2{font-family: Georgia,"Times New Roman",Times,serif; color: #1B2D60}
"""
conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
}
remove_tags = [
dict(attrs={'class': ['flechs', 'multiBox', 'colRecursos']}), dict(
name=['meta', 'link', 'embed', 'object', 'iframe', 'base'])
]
keep_only_tags = [dict(attrs={'class': 'Nota'})]
remove_tags_after = dict(attrs={'id': 'TextoPrint'})
remove_tags_before = dict(attrs={'id': 'FechaPrint'})
feeds = [
(u'Portada', u'http://www.eluniverso.com/rss/portada.xml'),
(u'Politica', u'http://www.eluniverso.com/rss/politica.xml'),
(u'Economia', u'http://www.eluniverso.com/rss/economia.xml'),
(u'Sucesos', u'http://www.eluniverso.com/rss/sucesos.xml'),
(u'Migracion', u'http://www.eluniverso.com/rss/migrantes_tema.xml'),
(u'El Pais', u'http://www.eluniverso.com/rss/elpais.xml'),
(u'Internacionales', u'http://www.eluniverso.com/rss/internacionales.xml'),
(u'Deportes', u'http://www.eluniverso.com/rss/deportes.xml'),
(u'Gran Guayaquill', u'http://www.eluniverso.com/rss/gran_guayaquil.xml'),
(u'Entretenimiento', u'http://www.eluniverso.com/rss/arteyespectaculos.xml'),
(u'Vida', u'http://www.eluniverso.com/rss/tuvida.xml'),
(u'Opinion', u'http://www.eluniverso.com/rss/opinion.xml')
]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup