home *** CD-ROM | disk | FTP | other *** search
/ Chip 2011 November / CHIP_2011_11.iso / Programy / Narzedzia / Calibre / calibre-0.8.18.msi / file_280 / unica.recipe < prev    next >
Text File  |  2011-09-09  |  2KB  |  57 lines
  1. # -*- coding: utf-8 -*-
  2. #!/usr/bin/env  python
  3.  
  4. __license__   = 'GPL v3'
  5. __copyright__ = u'2011, Silviu Cotoar\u0103'
  6. '''
  7. unica.ro
  8. '''
  9.  
  10. from calibre.web.feeds.news import BasicNewsRecipe
  11.  
  12. class Unica(BasicNewsRecipe):
  13.     title                     = u'Unica'
  14.     __author__             = u'Silviu Cotoar\u0103'
  15.     description               = 'Asa cum esti tu'
  16.     publisher                 = 'Unica'
  17.     oldest_article            = 5
  18.     language                 = 'ro'
  19.     max_articles_per_feed = 100
  20.     no_stylesheets        = True
  21.     use_embedded_content  = False
  22.     category               = 'Ziare,Reviste,Femei'
  23.     encoding              = 'utf-8'
  24.     cover_url             = 'http://www.unica.ro/fileadmin/images/logo.gif'
  25.  
  26.     conversion_options = {
  27.                              'comments'   : description
  28.                             ,'tags'       : category
  29.                             ,'language'   : language
  30.                             ,'publisher'  : publisher
  31.                          }
  32.  
  33.     keep_only_tags = [
  34.              dict(name='div', attrs={'id':'sticky'})
  35.             , dict(name='p', attrs={'class':'bodytext'})
  36.  
  37.                      ]
  38.  
  39.     remove_tags = [
  40.              dict(name='div', attrs={'class':['top-links']})
  41.            , dict(name='div', attrs={'id':['autor_name']})
  42.            , dict(name='div', attrs={'class':['box-r']})
  43.            , dict(name='div', attrs={'class':['category']})
  44.            , dict(name='div', attrs={'class':['data']})
  45.                   ]
  46.  
  47.     remove_tags_after = [
  48.              dict(name='ul', attrs={'class':'pager'})
  49.             ]
  50.  
  51.     feeds          = [
  52.         (u'Feeds', u'http://www.unica.ro/rss.html')
  53.                      ]
  54.  
  55.     def preprocess_html(self, soup):
  56.         return self.adeify_images(soup)
  57.