mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
76 lines
3.1 KiB
Plaintext
76 lines
3.1 KiB
Plaintext
__license__ = 'GPL v3'
|
|
__copyright__ = '2013, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
www.lacapital.com.ar
|
|
'''
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class LaCapital(BasicNewsRecipe):
|
|
title = 'La Capital de Rosario'
|
|
__author__ = 'Darko Miletic'
|
|
description = 'Noticias, actualidad y toda la informacion de Rosario y la region'
|
|
publisher = 'Diario La Capital S. A.'
|
|
category = 'news, politics, Rosario, Santa Fe, Argentina'
|
|
oldest_article = 2
|
|
max_articles_per_feed = 200
|
|
no_stylesheets = True
|
|
encoding = 'utf8'
|
|
use_embedded_content = False
|
|
language = 'es_AR'
|
|
remove_empty_feeds = True
|
|
publication_type = 'newspaper'
|
|
masthead_url = 'http://www.lacapital.com.ar/system/modules/com.tfsla.diario.core/resources/images/logoLaCapital_noCom.png'
|
|
extra_css = """
|
|
body{font-family: Georgia,"Times New Roman",Times,serif }
|
|
img{margin-bottom: 0.4em; display:block}
|
|
"""
|
|
|
|
conversion_options = {
|
|
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
|
|
}
|
|
|
|
keep_only_tags = [dict(attrs={'class': 'leer'})]
|
|
remove_tags_after = dict(attrs={'class': 'notaA'})
|
|
remove_tags = [
|
|
dict(name=['meta', 'link', 'iframe', 'object']), dict(
|
|
name='div', attrs={'class': ['herramientas', 'almargen', 'relacionadas']})
|
|
]
|
|
|
|
feeds = [
|
|
|
|
(u'Portada', u'http://www.lacapital.com.ar/rss/home.xml'),
|
|
(u'La Ciudad', u'http://www.lacapital.com.ar/rss/laciudad.xml'),
|
|
(u'Politica', u'http://www.lacapital.com.ar/rss/politica.xml'),
|
|
(u'Economia', u'http://www.lacapital.com.ar/rss/economia.xml'),
|
|
(u'La Region', u'http://www.lacapital.com.ar/rss/laregion.xml'),
|
|
(u'Informacion General', u'http://www.lacapital.com.ar/rss/informaciongral.xml'),
|
|
(u'El Mundo', u'http://www.lacapital.com.ar/rss/elmundo.xml'),
|
|
(u'Opinion', u'http://www.lacapital.com.ar/rss/opinion.xml'),
|
|
(u'Cartas de lectores', u'http://www.lacapital.com.ar/rss/cartasdelectores.xml'),
|
|
(u'Escenario', u'http://www.lacapital.com.ar/rss/escenario.xml'),
|
|
(u'Policiales', u'http://www.lacapital.com.ar/rss/policiales.xml'),
|
|
(u'Ovacion', u'http://www.lacapital.com.ar/rss/ovacion.xml'),
|
|
(u'Turismo', u'http://www.lacapital.com.ar/rss/turismo.xml'),
|
|
(u'Economia', u'http://www.lacapital.com.ar/rss/economia.xml'),
|
|
(u'Señales', u'http://www.lacapital.com.ar/rss/senales.xml'),
|
|
(u'Educacion', u'http://www.lacapital.com.ar/rss/educacion.xml'),
|
|
(u'Estilo', u'http://www.lacapital.com.ar/rss/estilo.xml'),
|
|
(u'Salud', u'http://www.lacapital.com.ar/rss/salud.xml'),
|
|
(u'Tecnologia', u'http://www.lacapital.com.ar/rss/tecnologia.xml')
|
|
]
|
|
|
|
def get_cover_url(self):
|
|
soup = self.index_to_soup(
|
|
'http://www.lacapital.com.ar/impresa/tapa.html')
|
|
for image in soup.findAll('img', alt=True):
|
|
if image['alt'].startswith('Tapa de papel'):
|
|
return image['src']
|
|
return None
|
|
|
|
def preprocess_html(self, soup):
|
|
for item in soup.findAll(style=True):
|
|
del item['style']
|
|
return soup
|