mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
93 lines
3.6 KiB
Python
93 lines
3.6 KiB
Python
#!/usr/bin/env python
|
|
# vim:fileencoding=UTF-8
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '30 June 2012, desUBIKado'
|
|
__author__ = 'desUBIKado'
|
|
__description__ = 'Diario de actualidad, moda y belleza'
|
|
__version__ = 'v0.03'
|
|
__date__ = '28, Jul 2016'
|
|
'''
|
|
http://www.hola.com/
|
|
'''
|
|
|
|
import re
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class hola_es(BasicNewsRecipe):
|
|
author = 'desUBIKado'
|
|
description = 'Diario de actualidad, moda y belleza'
|
|
title = u'¡Hola!'
|
|
publisher = 'Hola S.L.'
|
|
category = 'Spanish celebrities, Entertainment News, Royalty, Daily Variety, Hollywood'
|
|
language = 'es'
|
|
masthead_url = 'http://imagenes.hola.com/comunes/2008/logo-holacom.gif'
|
|
timefmt = '[%a, %d %b, %Y]'
|
|
oldest_article = 7
|
|
delay = 1
|
|
encoding = 'utf-8'
|
|
max_articles_per_feed = 100
|
|
use_embedded_content = False
|
|
remove_empty_feeds = True
|
|
remove_javascript = True
|
|
no_stylesheets = True
|
|
|
|
feeds = [
|
|
|
|
(u'Famosos', u'http://www.hola.com/famosos/rss.xml'),
|
|
(u'Realeza', u'http://www.hola.com/realeza/rss.xml'),
|
|
(u'Cine', u'http://www.hola.com/cine/rss.xml'),
|
|
(u'M\xfasica', u'http://www.hola.com/musica/rss.xml'),
|
|
(u'Moda y modelos', u'http://www.hola.com/moda/portada/rss.xml'),
|
|
(u'Belleza y salud', u'http://www.hola.com/belleza/portada/rss.xml'),
|
|
(u'Ni\xf1os', u'http://www.hola.com/ninos/rss.xml')
|
|
]
|
|
|
|
keep_only_tags = [
|
|
dict(name='article', attrs={'class': ['body col-md-8 col-xs-12']})]
|
|
|
|
remove_tags = [dict(name='div', attrs={'class': ['comments', 'news-share', 'sponsored-news']}),
|
|
dict(name='div', attrs={'itemprop': ['logo']}),
|
|
dict(name='span', attrs={'class': ['hidden']}),
|
|
dict(name='p', attrs={'class': ['hidden']}),
|
|
dict(name='section', attrs={'class': ['news-tags']})
|
|
]
|
|
|
|
remove_tags_after = dict(name='div', attrs={'class': 'comments'})
|
|
|
|
# <span>VER GALERÍA<i data-icon="1" class="icon"></i></span>
|
|
preprocess_regexps = [
|
|
# Quitar VER GALERÍA
|
|
(re.compile(r'<span>VER GALER', re.DOTALL | re.IGNORECASE), lambda m: '<!--'),
|
|
(re.compile(r'class="icon"></i></span>',
|
|
re.DOTALL | re.IGNORECASE), lambda m: '-->'),
|
|
# Quitar enlaces varios
|
|
(re.compile(r'<p><a href="http://www.hola.com',
|
|
re.DOTALL | re.IGNORECASE), lambda m: '<!--'),
|
|
(re.compile(r'<p style="text-align: center;">',
|
|
re.DOTALL | re.IGNORECASE), lambda m: '<!--'),
|
|
(re.compile(r'<p style="line-height: 20.8px;"><a href="http://www.hola.com',
|
|
re.DOTALL | re.IGNORECASE), lambda m: '<!--'),
|
|
(re.compile(r'</strong></a></p>',
|
|
re.DOTALL | re.IGNORECASE), lambda m: '-->')
|
|
]
|
|
|
|
# Recuperamos la portada de papel (la imagen 520 tiene mayor resolucion)
|
|
# http://www.hola.com/imagenes/revista/3727/portada-revista-hola-520.jpg
|
|
def get_cover_url(self):
|
|
index = 'http://www.hola.com/abono/ediciondigital/'
|
|
soup = self.index_to_soup(index)
|
|
for image in soup.findAll('img', src=True):
|
|
if image['src'].endswith('portada-revista-hola-520.jpg'):
|
|
return 'http://www.hola.com' + image['src']
|
|
return None
|
|
|
|
def get_article_url(self, article):
|
|
url = article.get('guid', None)
|
|
return url
|
|
|
|
extra_css = '''
|
|
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:30px;}
|
|
h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal; font-style:italic; font-size:18px;}
|
|
'''
|