Debian Codegraph @

recipes/zdnet.fr.recipe

raw
1 # -*- coding: utf-8 -*-
2 __license__ = 'GPL v3'
3 __copyright__ = '2011 Aurélien Chabot <[email protected]>'
4
5 '''
6 Fetch zdnet.fr
7 '''
8
9 from calibre.web.feeds.news import BasicNewsRecipe
10
11
12 class zdnet(BasicNewsRecipe):
13 title = 'ZDNet.fr'
14 __author__ = 'calibre'
15 description = 'Actualités'
16 encoding = 'utf-8'
17 publisher = 'ZDNet.fr'
18 category = 'Actualité, Informatique, IT'
19 language = 'fr'
20
21 use_embedded_content = False
22 timefmt = ' [%d %b %Y]'
23 max_articles_per_feed = 15
24 no_stylesheets = True
25 remove_empty_feeds = True
26 filterDuplicates = True
27
28 extra_css = '''
29 h1 {font-size:xx-large; font-family:Arial,Helvetica,sans-serif;}
30 .contentmetadata p {font-size:xx-small; color:#4D4D4D; font-family:Arial,Helvetica,sans-serif;}
31 #content {font-size:medium; font-family:Arial,Helvetica,sans-serif;}
32 '''
33
34 remove_tags = [
35 dict(name='iframe'),
36 dict(name='div', attrs={'class': ['toolbox']}),
37 dict(name='div', attrs={'class': ['clear clearfix']}),
38 dict(id='emailtoafriend'),
39 dict(id='storyaudio'),
40 dict(id='fbtwContainer'),
41 dict(name='h5'),
42 ]
43
44 remove_tags_before = dict(id='leftcol')
45 remove_tags_after = dict(id='content')
46
47 feeds = [
48 ('Informatique', 'http://www.zdnet.fr/feeds/rss/actualites/informatique/'),
49 ('Internet', 'http://www.zdnet.fr/feeds/rss/actualites/internet/'),
50 ('Telecom', 'http://www.zdnet.fr/feeds/rss/actualites/telecoms/'),
51 ]
52
53 def preprocess_html(self, soup):
54 for item in soup.findAll(style=True):
55 del item['style']
56 return soup
57
58 def get_masthead_url(self):
59 masthead = 'http://www.zdnet.fr/images/base/logo.png'
60 br = BasicNewsRecipe.get_browser(self)
61 try:
62 br.open(masthead)
63 except Exception:
64 self.log('\nCover unavailable')
65 masthead = None
66 return masthead