← Back to branch summary

~ubuntu-branches/debian/wheezy/calibre/wheezy

« back to all changes in this revision

Viewing changes to recipes/scmp.recipe

  • Committer: Bazaar Package Importer
  • Author(s): Martin Pitt
  • Date: 2011-10-04 10:29:28 UTC
  • mfrom: (29.3.5 sid)
  • Revision ID: james.westby@ubuntu.com-20111004102928-lbwg8cyjscq1tiz7
Tags: 0.8.21+dfsg-1
http://bugs.debian.org/642517
http://bugs.debian.org/644029
* New upstream release. (Closes: #642517)
* debian/control: Revert accidental X-Ubuntu-Original-Maintainer change.
  (Closes: #644029)

Show diffs side-by-side

added added

removed removed

Lines of Context:
recipes/scmp.recipe
 
1
__license__   = 'GPL v3'
 
2
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
 
3
'''
 
4
scmp.com
 
5
'''
 
6
 
 
7
import re
 
8
from calibre.web.feeds.news import BasicNewsRecipe
 
9
 
 
10
class SCMP(BasicNewsRecipe):
 
11
    title                 = 'South China Morning Post'
 
12
    __author__            = 'llam'
 
13
    description           = "SCMP.com, Hong Kong's premier online English daily provides exclusive up-to-date news, audio video news, podcasts, RSS Feeds, Blogs, breaking news, top stories, award winning news and analysis on Hong Kong and China."
 
14
    publisher             = 'South China Morning Post Publishers Ltd.'
 
15
    category              = 'SCMP, Online news, Hong Kong News, China news, Business news, English newspaper, daily newspaper, Lifestyle news, Sport news, Audio Video news, Asia news, World news, economy news, investor relations news, RSS Feeds'
 
16
    oldest_article        = 2
 
17
    delay                 = 1
 
18
    max_articles_per_feed = 200
 
19
    no_stylesheets        = True
 
20
    encoding              = 'utf-8'
 
21
    use_embedded_content  = False
 
22
    language              = 'en_CN'
 
23
    remove_empty_feeds    = True
 
24
    needs_subscription    = True
 
25
    publication_type      = 'newspaper'
 
26
    masthead_url          = 'http://www.scmp.com/images/logo_scmp_home.gif'
 
27
    extra_css             = ' body{font-family: Arial,Helvetica,sans-serif } '
 
28
 
 
29
    conversion_options = {
 
30
                          'comment'   : description
 
31
                        , 'tags'      : category
 
32
                        , 'publisher' : publisher
 
33
                        , 'language'  : language
 
34
                        }
 
35
 
 
36
    def get_browser(self):
 
37
        br = BasicNewsRecipe.get_browser()
 
38
        #br.set_debug_http(True)
 
39
        #br.set_debug_responses(True)
 
40
        #br.set_debug_redirects(True)
 
41
        if self.username is not None and self.password is not None:
 
42
           br.open('http://www.scmp.com/portal/site/SCMP/')
 
43
           br.select_form(name='loginForm')
 
44
           br['Login'   ] = self.username
 
45
           br['Password'] = self.password
 
46
           br.submit()
 
47
        return br
 
48
 
 
49
    remove_attributes=['width','height','border']
 
50
 
 
51
    keep_only_tags = [
 
52
                        dict(attrs={'id':['ART','photoBox']})
 
53
                       ,dict(attrs={'class':['article_label','article_byline','article_body']})
 
54
                     ]
 
55
 
 
56
    preprocess_regexps = [
 
57
       (re.compile(r'<P><table((?!<table).)*class="embscreen"((?!</table>).)*</table>', re.DOTALL|re.IGNORECASE),
 
58
        lambda match: ''),
 
59
    ]
 
60
 
 
61
    feeds = [
 
62
              (u'Business'     , u'http://www.scmp.com/rss/business.xml'       )
 
63
             ,(u'Hong Kong'    , u'http://www.scmp.com/rss/hong_kong.xml'      )
 
64
             ,(u'China'        , u'http://www.scmp.com/rss/china.xml'          )
 
65
             ,(u'Asia & World' , u'http://www.scmp.com/rss/news_asia_world.xml')
 
66
             ,(u'Opinion'      , u'http://www.scmp.com/rss/opinion.xml'        )
 
67
             ,(u'LifeSTYLE'    , u'http://www.scmp.com/rss/lifestyle.xml'      )
 
68
             ,(u'Sport'        , u'http://www.scmp.com/rss/sport.xml'          )
 
69
            ]
 
70
 
 
71
    def print_version(self, url):
 
72
        rpart, sep, rest = url.rpartition('&')
 
73
        return rpart #+ sep + urllib.quote_plus(rest)
 
74
 
 
75
    def preprocess_html(self, soup):
 
76
        for item in soup.findAll(style=True):
 
77
            del item['style']
 
78
        items = soup.findAll(src="/images/label_icon.gif")
 
79
        [item.extract() for item in items]
 
80
        return self.adeify_images(soup)