Debian Codegraph @

recipes/ilsole24ore.recipe

raw
1 __author__ = 'Marco Saraceno'
2 __copyright__ = '2010, Marco Saraceno <marcosaraceno at gmail.com>'
3 description = 'Italian daily newspaper - v 1.1 (Mar14,2011)'
4
5 '''
6 http://www.ilsole24ore.com
7 '''
8
9 from calibre.web.feeds.news import BasicNewsRecipe
10
11
12 def classes(classes):
13 q = frozenset(classes.split(' '))
14 return dict(attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)})
15
16
17 class IlSole24Ore(BasicNewsRecipe):
18 __author__ = 'Marco Saraceno'
19 description = 'Italian financial daily newspaper'
20
21 cover_url = 'http://www.shopping24.ilsole24ore.com/ProductRelated/rds/img/logo_sole.gif'
22 title = 'Il Sole 24 Ore'
23 publisher = 'Gruppo editoriale GRUPPO 24ORE'
24 category = 'News, politics, culture, economy, financial, Italian'
25
26 language = 'it'
27 timefmt = '[%a, %d %b, %Y]'
28
29 oldest_article = 2
30 max_articles_per_feed = 100
31 use_embedded_content = False
32 extra_css = '.headline {font-size: x-large;} \n .fact { padding-top: 10pt }'
33 no_stylesheets = True
34
35 keep_only_tags = [classes('ahead atext')]
36 remove_tags = [classes('ahead-ltool')]
37
38 def get_article_url(self, article):
39 link = article.get('link', None)
40 if link is None:
41 return article
42 if link.split('/')[-1] == 'story01.htm':
43 link = link.split('/')[-2]
44 t = (
45 ('0B', '.'),
46 ('0C', '/'),
47 ('0D', '?'),
48 ('0E', '-'),
49 ('0F', '='),
50 ('0G', '&'),
51 ('0N', '.com'),
52 ('0L0S', 'www.'),
53 ('0A', '0'),
54 )
55 for a, b in t:
56 link = link.replace(a, b)
57 link = 'http://' + link
58 return link
59
60 feeds = [
61 ('Italia', 'https://www.ilsole24ore.com/rss/italia.xml'),
62 ('Mondo', 'https://www.ilsole24ore.com/rss/mondo.xml'),
63 ('Economia', 'https://www.ilsole24ore.com/rss/economia.xml'),
64 ('Finanzia', 'https://www.ilsole24ore.com/rss/finanza.xml'),
65 ('Commenti', 'https://www.ilsole24ore.com/rss/commenti.xml'),
66 ('Risparmio', 'https://www.ilsole24ore.com/rss/risparmio.xml'),
67 ('Norme e Tributi', 'https://www.ilsole24ore.com/rss/norme-e-tributi.xml'),
68 ('Management', 'https://www.ilsole24ore.com/rss/management.xml'),
69 ('Cultura', 'https://www.ilsole24ore.com/rss/cultura.xml'),
70 ('Tecnologia', 'https://www.ilsole24ore.com/rss/tecnologia.xml'),
71 ('Food', 'https://www.ilsole24ore.com/rss/food.xml'),
72 ('Moda', 'https://www.ilsole24ore.com/rss/moda.xml'),
73 ('Motori', 'https://www.ilsole24ore.com/rss/motori.xml'),
74 ('Casa', 'https://www.ilsole24ore.com/rss/casa.xml'),
75 ('Viaggi', 'https://www.ilsole24ore.com/rss/viaggi.xml'),
76 ('Salute', 'https://www.ilsole24ore.com/rss/salute.xml'),
77 ('Arteconomy', 'https://www.ilsole24ore.com/rss/arteconomy.xml'),
78 ('Sport', 'https://www.ilsole24ore.com/rss/sport24.xml'),
79 ]
80
81 def print_version(self, url):
82 return url.replace('.shtml', '_PRN.shtml')