Debian Codegraph @

recipes/lexpress.recipe

raw
1 # -*- coding: utf-8 -*-
2 __license__ = 'GPL v3'
3 __copyright__ = '2011 Aurélien Chabot <[email protected]>'
4 '''
5 Lexpress.fr
6 '''
7 from calibre.web.feeds.recipes import BasicNewsRecipe
8
9
10 def classes(classes):
11 q = frozenset(classes.split(' '))
12 return dict(attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)})
13
14
15 class lepoint(BasicNewsRecipe):
16 title = "L'express"
17 __author__ = 'calibre'
18 description = 'Actualités'
19 publisher = 'LExpress.fr'
20 category = 'Actualité, France, Monde'
21 language = 'fr'
22
23 use_embedded_content = False
24 timefmt = ' [%d %b %Y]'
25 max_articles_per_feed = 15
26 no_stylesheets = True
27 remove_empty_feeds = True
28 filterDuplicates = True
29
30 extra_css = '''
31 h1 {font-size:xx-large; font-family:Arial,Helvetica,sans-serif;}
32 .current_parent, p.heure, .ouverture {font-size:xx-small; color:#4D4D4D; font-family:Arial,Helvetica,sans-serif;}
33 #contenu-article {font-size:medium; font-family:Arial,Helvetica,sans-serif;}
34 .entete { font-weiht:bold;}
35 '''
36
37 remove_tags = [
38 dict(name='iframe'),
39 dict(name='div', attrs={'class': ['barre-outil-fb']}),
40 dict(name='div', attrs={'class': ['barre-outils']}),
41 dict(id='bloc-sommaire'),
42 dict(id='footer-article'),
43 ]
44
45 keep_only_tags = [classes('article_header_content article_content')]
46
47 feeds = [
48 ('À la une', 'http://www.lexpress.fr/rss/alaune.xml'),
49 ('International', 'http://www.lexpress.fr/rss/monde.xml'),
50 ('Tech/Web', 'http://www.lexpress.fr/rss/high-tech.xml'),
51 ('Sciences/Santé', 'http://www.lexpress.fr/rss/science-et-sante.xml'),
52 ('Envronnement', 'http://www.lexpress.fr/rss/environnement.xml'),
53 ('Economie', 'http://www.lepoint.fr/economie/rss.xml'),
54 ('Socièté', 'http://www.lexpress.fr/rss/societe.xml'),
55 ('Politique', 'http://www.lexpress.fr/rss/politique.xml'),
56 ('Médias', 'http://www.lexpress.fr/rss/medias.xml'),
57 ('Culture', 'http://www.lexpress.fr/rss/culture.xml'),
58 ('Sport', 'http://www.lexpress.fr/rss/sport.xml'),
59 ]
60
61 def preprocess_html(self, soup):
62 for item in soup.findAll(style=True):
63 del item['style']
64 return soup
65
66 def get_masthead_url(self):
67 masthead = 'http://static.lexpress.fr/imgstat/logo_lexpress.gif'
68 br = BasicNewsRecipe.get_browser(self)
69 try:
70 br.open(masthead)
71 except Exception:
72 self.log('\nCover unavailable')
73 masthead = None
74 return masthead