Debian Codegraph @

recipes/lepoint.recipe

raw
1 # -*- coding: utf-8 -*-
2 __license__ = 'GPL v3'
3 __copyright__ = '2011 Aurélien Chabot <[email protected]>'
4 '''
5 LePoint.fr
6 '''
7 from calibre.web.feeds.recipes import BasicNewsRecipe
8
9
10 class lepoint(BasicNewsRecipe):
11 title = 'Le Point'
12 __author__ = 'calibre'
13 description = 'Actualités'
14 encoding = 'utf-8'
15 publisher = 'LePoint.fr'
16 category = 'news, France, world'
17 language = 'fr'
18
19 use_embedded_content = False
20 timefmt = ' [%d %b %Y]'
21 max_articles_per_feed = 15
22 no_stylesheets = True
23 remove_empty_feeds = True
24 filterDuplicates = True
25
26 extra_css = '''
27 h1 {font-size:xx-large; font-family:Arial,Helvetica,sans-serif;}
28 .chapo {font-size:xx-small; font-family:Arial,Helvetica,sans-serif;}
29 .info_article {font-size:xx-small; color:#4D4D4D; font-family:Arial,Helvetica,sans-serif;}
30 .media_article {font-size:xx-small; color:#4D4D4D; font-family:Arial,Helvetica,sans-serif;}
31 .article {font-size:medium; font-family:Arial,Helvetica,sans-serif;}
32 '''
33
34 remove_tags = [
35 dict(name='iframe'),
36 dict(name='div', attrs={'class': ['entete_chroniqueur']}),
37 dict(name='div', attrs={'class': ['col_article']}),
38 dict(name='div', attrs={'class': ['signature_article']}),
39 dict(name='div', attrs={'class': ['util_font util_article']}),
40 dict(name='div', attrs={'class': ['util_article bottom']}),
41 ]
42
43 keep_only_tags = [dict(name='div', attrs={'class': ['page_article']})]
44
45 remove_tags_after = dict(name='div', attrs={'class': ['util_article bottom']})
46
47 feeds = [
48 ('À la une', 'http://www.lepoint.fr/rss.xml'),
49 ('International', 'http://www.lepoint.fr/monde/rss.xml'),
50 ('Tech/Web', 'http://www.lepoint.fr/high-tech-internet/rss.xml'),
51 ('Sciences', 'http://www.lepoint.fr/science/rss.xml'),
52 ('Economie', 'http://www.lepoint.fr/economie/rss.xml'),
53 ('Socièté', 'http://www.lepoint.fr/societe/rss.xml'),
54 ('Politique', 'http://www.lepoint.fr/politique/rss.xml'),
55 ('Médias', 'http://www.lepoint.fr/medias/rss.xml'),
56 ('Culture', 'http://www.lepoint.fr/culture/rss.xml'),
57 ('Santé', 'http://www.lepoint.fr/sante/rss.xml'),
58 ('Sport', 'http://www.lepoint.fr/sport/rss.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://www.lepoint.fr/images/commun/logo.png'
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