Debian Codegraph @

recipes/libertad_digital.recipe

raw
1 __license__ = 'GPL v3'
2 __copyright__ = '2013, Darko Miletic <darko.miletic at gmail.com>'
3 '''
4 www.libertaddigital.com
5 '''
6
7 from calibre.web.feeds.news import BasicNewsRecipe
8
9
10 class LibertadDigital(BasicNewsRecipe):
11 title = 'Libertad Digital'
12 __author__ = 'Darko Miletic'
13 description = 'En Libertad Digital encontraras noticias y opinion sobre: España, el Mundo, Internet, sociedad, economia y deportes'
14 publisher = 'Libertad Digital S.A.'
15 category = 'noticias, ultima hora, españa, internet, mundo, economia, sociedad, Libertad Digital'
16 oldest_article = 2
17 max_articles_per_feed = 200
18 no_stylesheets = True
19 encoding = 'cp1252'
20 use_embedded_content = False
21 language = 'es'
22 remove_empty_feeds = True
23 publication_type = 'website'
24 masthead_url = 'http://s.libertaddigital.com/images/logo.gif'
25 extra_css = '''
26 body{font-family: Verdana,sans-serif }
27 img{margin-bottom: 0.4em; display:block}
28 '''
29
30 conversion_options = {'comment': description, 'tags': category, 'publisher': publisher, 'language': language}
31
32 remove_tags = [dict(name=['meta', 'link', 'iframe', 'embed', 'object']), dict(name='p', attrs={'class': 'copyright'})]
33 remove_attributes = ['lang']
34
35 feeds = [
36 ('Portada', 'http://feeds2.feedburner.com/libertaddigital/deportes'),
37 ('Opinion', 'http://feeds2.feedburner.com/libertaddigital/opinion'),
38 ('España', 'http://feeds2.feedburner.com/libertaddigital/nacional'),
39 ('Internacional', 'http://feeds2.feedburner.com/libertaddigital/internacional'),
40 ('Libre Mercado', 'http://feeds2.feedburner.com/libertaddigital/economia'),
41 ('Chic', 'http://feeds2.feedburner.com/libertaddigital/el-candelabro'),
42 ('Internet', 'http://feeds2.feedburner.com/libertaddigital/internet'),
43 ('Deportes', 'http://feeds2.feedburner.com/libertaddigital/deportes'),
44 ]
45
46 def get_article_url(self, article):
47 return article.get('guid', None)
48
49 def print_version(self, url):
50 art, sep, rest = url.rpartition('/')
51 aart, asep, artid = art.rpartition('-')
52 return 'http://www.libertaddigital.com/c.php?op=imprimir&id=' + artid
53
54 def preprocess_html(self, soup):
55 for item in soup.findAll(style=True):
56 del item['style']
57 return soup