Debian Codegraph @

recipes/tweakers_net.recipe

raw
1 #!/usr/bin/env python
2 # vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
3 from __future__ import with_statement
4
5 __license__ = 'GPL v3'
6 __copyright__ = '2009, Kovid Goyal <[email protected]>'
7 __docformat__ = 'restructuredtext en'
8 ''' Changelog
9 2012-04-27 DrMerry:
10 Added cover picture
11 removed some extra tags
12 '''
13
14 import re
15
16 from calibre.web.feeds.news import BasicNewsRecipe
17
18
19 class Tweakers(BasicNewsRecipe):
20 title = 'Tweakers.net'
21 __author__ = 'Kovid Goyal'
22 language = 'nl'
23 oldest_article = 4
24 max_articles_per_feed = 40
25 cover_url = 'http://tweakers.net/ext/launch/g/logo.gif'
26
27 keep_only_tags = [dict(name='div', attrs={'class': 'columnwrapper news'}), dict(name='div', attrs={'class': 'article'})]
28
29 remove_tags = [
30 dict(name='div', attrs={'class': 'reacties'}),
31 {'id': ['utracker', 'socialButtons', 'b_ac']},
32 {'class': ['sidebar', 'advertorial']},
33 {'class': re.compile(r'nextPrevious')},
34 ]
35 no_stylesheets = True
36 filter_regexps = [r'ads\.doubleclick\.net', r'ad\.doubleclick\.net']
37
38 feeds = [('Tweakers.net', 'http://tweakers.net/feeds/nieuws.xml')]
39
40 def preprocess_html(self, soup):
41 for a in soup.findAll('a', href=True, rel=True):
42 if a['rel'].startswith('imageview'):
43 a['src'] = a['href']
44 del a['href']
45 a.name = 'img'
46 for x in a.findAll(True):
47 x.extract()
48 return soup
49
50 def postprocess_html(self, soup, first):
51 for base in soup.findAll('base'):
52 base.extract()
53 return soup