ZwEEKLkB

1# -*- mode: python -*-
2# -*- coding: utf-8 -*-
3
4__license__   = 'GPL v3'
5__copyright__ = '2008-2016, Darko Miletic <darko.miletic at gmail.com>'
6
7from calibre.web.feeds.news import BasicNewsRecipe
8
9class Economista(BasicNewsRecipe):
10
11# Datos generales del sitio
12
13    title                 = 'El Economista'
14    __author__            = 'Unknown'
15    description           = 'Diario de noticias y análisis económico'
16    publisher             = 'Unknown'
17    category              = 'news, politics, economy, finances, Argentina'
18    language              = 'es_AR'
19    publication_type      = 'newsportal' 
20
21# Configuración del scrapper
22
23    oldest_article        = 1
24    no_stylesheets        = True
25    encoding              = 'utf8'
26    use_embedded_content  = False
27    remove_empty_feeds    = True
28    ignore_duplicate_articles = {'url'}
29    timeout = 120
30
31# Imágenes
32
33    masthead_url = 'http://www.eleconomista.com.ar/wp-content/uploads/2016/04/logonuevo.png'
34    cover_url = 'http://www.eleconomista.com.ar/images/tapa.jpg'
35
36# Fuentes del contenido a descargar
37
38    feeds = [(u'Noticias del día', u'http://www.eleconomista.com.ar/rss')]
39
40# Control de contenido a descargar
41
42    remove_tags_before = dict(attrs={'class': 'entry-title page-header'})
43
44    remove_tags = [dict(attrs={'class': ['yuzo_related_post style-1','post-meta text-left','addtoany_share_save_container addtoany_content_top']}),
45                   dict(attrs={'id': ['breadcrumbs']})]
46
47    remove_tags_after = dict(attrs={'class': 'yuzo_related_post style-1'})
48
49# Formato del contenido descargado
50
51    extra_css = """
52                    .header p { margin: 1 !important; }
53                    .entry-content p { margin: 0 !important; }
54                    .entry-content blockquote { margin: 0 !important; }
55                """