home *** CD-ROM | disk | FTP | other *** search
/ Chip 2011 November / CHIP_2011_11.iso / Programy / Narzedzia / Calibre / calibre-0.8.18.msi / file_280 / fe_india.recipe < prev    next >
Encoding:
Text File  |  2011-09-09  |  1.7 KB  |  47 lines
  1. __license__   = 'GPL v3'
  2. __copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
  3. '''
  4. financialexpress.com
  5. '''
  6.  
  7. from calibre.web.feeds.news import BasicNewsRecipe
  8.  
  9. class FE_India(BasicNewsRecipe):
  10.     title                 = 'The Financial Express'
  11.     __author__            = 'Darko Miletic'
  12.     description           = 'Financial news from India'
  13.     publisher             = 'The Indian Express Limited'
  14.     category              = 'news, politics, finances, India'
  15.     oldest_article        = 30
  16.     max_articles_per_feed = 200
  17.     no_stylesheets        = True
  18.     encoding              = 'cp1252'
  19.     use_embedded_content  = False
  20.     language              = 'en_IN'
  21.     remove_empty_feeds    = True
  22.     masthead_url          = 'http://static.expressindia.com/frontend/fe/images/fe_logo.jpg'
  23.     publication_type      = 'magazine'
  24.     extra_css             = ' body{font-family: Arial,Helvetica,sans-serif } '
  25.  
  26.     conversion_options = {
  27.                           'comment'   : description
  28.                         , 'tags'      : category
  29.                         , 'publisher' : publisher
  30.                         , 'language'  : language
  31.                         }
  32.  
  33.     keep_only_tags = [dict(attrs={'class':'txt'})]
  34.     remove_attributes = ['width','height']
  35.  
  36.     feeds = [(u'Articles', u'http://www.expressindia.com/syndications/fe.xml')]
  37.  
  38.     def print_version(self, url):
  39.         article_raw = url.rpartition('/')[0]
  40.         article_id = article_raw.rpartition('/')[2]
  41.         return 'http://www.financialexpress.com/printer/news/' + article_id + '/'
  42.  
  43.     def preprocess_html(self, soup):
  44.         for item in soup.findAll(style=True):
  45.             del item['style']
  46.         return soup
  47.