home *** CD-ROM | disk | FTP | other *** search
/ Chip 2011 November / CHIP_2011_11.iso / Programy / Narzedzia / Calibre / calibre-0.8.18.msi / file_280 / business_insider.recipe < prev    next >
Encoding:
Text File  |  2011-09-09  |  3.0 KB  |  70 lines
  1. __license__   = 'GPL v3'
  2. __copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
  3. '''
  4. www.businessinsider.com
  5. '''
  6.  
  7. from calibre.web.feeds.news import BasicNewsRecipe
  8.  
  9. class Business_insider(BasicNewsRecipe):
  10.     title                 = 'Business Insider'
  11.     __author__            = 'Darko Miletic'
  12.     description           = 'Noticias de Argentina y el resto del mundo'
  13.     publisher             = 'Business Insider, Inc.'
  14.     category              = 'news, politics, finances, world'
  15.     oldest_article        = 2
  16.     max_articles_per_feed = 200
  17.     no_stylesheets        = True
  18.     encoding              = 'utf8'
  19.     use_embedded_content  = True
  20.     language              = 'en'
  21.     remove_empty_feeds    = True
  22.     publication_type      = 'newsportal'
  23.     masthead_url          = 'http://static.businessinsider.com/assets/images/logos/tbi_print.jpg'
  24.     extra_css             = """
  25.                                body{font-family: Arial,Helvetica,sans-serif }
  26.                                img{margin-bottom: 0.4em; display:block}
  27.                             """
  28.  
  29.     conversion_options = {
  30.                           'comment'   : description
  31.                         , 'tags'      : category
  32.                         , 'publisher' : publisher
  33.                         , 'language'  : language
  34.                         }
  35.  
  36.     remove_tags = [
  37.                       dict(name=['meta','link'])
  38.                      ,dict(attrs={'class':'feedflare'})
  39.                   ]
  40.     remove_attributes=['lang','border']
  41.  
  42.  
  43.     feeds = [
  44.               (u'Latest'      , u'http://feeds2.feedburner.com/businessinsider'                          )
  45.              ,(u'Markets'     , u'http://feeds.feedburner.com/TheMoneyGame'                              )
  46.              ,(u'Wall Street' , u'http://feeds.feedburner.com/clusterstock'                              )
  47.              ,(u'Tech'        , u'http://feeds.feedburner.com/typepad/alleyinsider/silicon_alley_insider')
  48.              ,(u'The Wire'    , u'http://feeds.feedburner.com/businessinsider/thewire'                   )
  49.              ,(u'War Room'    , u'http://feeds.feedburner.com/businessinsider/warroom'                   )
  50.              ,(u'Sports'      , u'http://feeds.feedburner.com/businessinsider/sportspage'                )
  51.              ,(u'Tools'       , u'http://feeds.feedburner.com/businessinsider/tools'                     )
  52.              ,(u'Travel'      , u'http://feeds.feedburner.com/businessinsider/travel'                    )
  53.             ]
  54.  
  55.  
  56.     def preprocess_html(self, soup):
  57.         for item in soup.findAll(style=True):
  58.             del item['style']
  59.         for item in soup.findAll('a'):
  60.             if item['href'].startswith('http://feedads'):
  61.                item.extract()
  62.             else:
  63.                 if item.string is not None:
  64.                    tstr = item.string
  65.                    item.replaceWith(tstr)
  66.         for item in soup.findAll('img'):
  67.             if not item.has_key('alt'):
  68.                item['alt'] = 'image'
  69.         return soup
  70.