~ubuntu-branches/ubuntu/karmic/calibre/karmic

« back to all changes in this revision

Viewing changes to src/calibre/web/feeds/recipes/recipe_jb_online.py

  • Committer: Bazaar Package Importer
  • Author(s): Martin Pitt
  • Date: 2009-07-30 12:49:41 UTC
  • mfrom: (1.3.2 upstream)
  • Revision ID: james.westby@ubuntu.com-20090730124941-qjdsmri25zt8zocn
Tags: 0.6.3+dfsg-0ubuntu1
* New upstream release. Please see http://calibre.kovidgoyal.net/new_in_6/
  for the list of new features and changes.
* remove_postinstall.patch: Update for new version.
* build_debug.patch: Does not apply any more, disable for now. Might not be
  necessary any more.
* debian/copyright: Fix reference to versionless GPL.
* debian/rules: Drop obsolete dh_desktop call.
* debian/rules: Add workaround for weird Python 2.6 setuptools behaviour of
  putting compiled .so files into src/calibre/plugins/calibre/plugins
  instead of src/calibre/plugins.
* debian/rules: Drop hal fdi moving, new upstream version does not use hal
  any more. Drop hal dependency, too.
* debian/rules: Install udev rules into /lib/udev/rules.d.
* Add debian/calibre.preinst: Remove unmodified
  /etc/udev/rules.d/95-calibre.rules on upgrade.
* debian/control: Bump Python dependencies to 2.6, since upstream needs
  it now.

Show diffs side-by-side

added added

removed removed

Lines of Context:
1
 
#!/usr/bin/env  python
2
 
 
3
 
__license__   = 'GPL v3'
4
 
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
5
 
'''
6
 
jbonline.terra.com.br
7
 
'''
8
 
 
 
1
#!/usr/bin/env  python
 
2
 
 
3
__license__   = 'GPL v3'
 
4
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
 
5
'''
 
6
jbonline.terra.com.br
 
7
'''
 
8
 
9
9
from calibre.web.feeds.news import BasicNewsRecipe
10
10
 
11
 
class JBOnline(BasicNewsRecipe):
12
 
    title                 = 'Jornal Brasileiro Online'
13
 
    __author__            = 'Darko Miletic'
14
 
    description           = 'News from Brasil'
15
 
    publisher             = 'Jornal Brasileiro'
16
 
    category              = 'news, politics, Brasil'    
17
 
    oldest_article        = 2
18
 
    max_articles_per_feed = 100
19
 
    no_stylesheets        = True
20
 
    use_embedded_content  = False
21
 
    encoding              = 'cp1252'
22
 
    cover_url             = 'http://jbonline.terra.com.br/img/logo_01.gif'
23
 
    remove_javascript     = True
24
 
    
25
 
    html2lrf_options = [
 
11
class JBOnline(BasicNewsRecipe):
 
12
    title                 = 'Jornal Brasileiro Online'
 
13
    __author__            = 'Darko Miletic'
 
14
    description           = 'News from Brasil'
 
15
    publisher             = 'Jornal Brasileiro'
 
16
    category              = 'news, politics, Brasil'
 
17
    oldest_article        = 2
 
18
    max_articles_per_feed = 100
 
19
    no_stylesheets        = True
 
20
    use_embedded_content  = False
 
21
    encoding              = 'cp1252'
 
22
    cover_url             = 'http://jbonline.terra.com.br/img/logo_01.gif'
 
23
    remove_javascript     = True
 
24
 
 
25
    html2lrf_options = [
26
26
                          '--comment', description
27
 
                        , '--category', category
28
 
                        , '--publisher', publisher
29
 
                        ]
30
 
    
31
 
    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' 
32
 
                        
33
 
    keep_only_tags = [dict(name='div', attrs={'id':'corpoNoticia'})]
34
 
 
35
 
    remove_tags = [dict(name=['script','object','form'])]
36
 
    
37
 
    feeds = [(u'Todos as editorias', u'http://jbonline.terra.com.br/extra/rsstrjb.xml')]
38
 
 
39
 
    def preprocess_html(self, soup):
40
 
        ifr = soup.find('iframe')
41
 
        if ifr:
42
 
           ifr.extract()
43
 
        for item in soup.findAll(style=True):
44
 
            del item['style']           
45
 
        return soup
46
 
 
47
 
    language = _('Portugese')
 
 
b'\\ No newline at end of file'
 
27
                        , '--category', category
 
28
                        , '--publisher', publisher
 
29
                        ]
 
30
 
 
31
    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
 
32
 
 
33
    keep_only_tags = [dict(name='div', attrs={'id':'corpoNoticia'})]
 
34
 
 
35
    remove_tags = [dict(name=['script','object','form'])]
 
36
 
 
37
    feeds = [(u'Todos as editorias', u'http://jbonline.terra.com.br/extra/rsstrjb.xml')]
 
38
 
 
39
    def preprocess_html(self, soup):
 
40
        ifr = soup.find('iframe')
 
41
        if ifr:
 
42
           ifr.extract()
 
43
        for item in soup.findAll(style=True):
 
44
            del item['style']
 
45
        return soup
 
46
 
 
47
    language = _('Portuguese')