home *** CD-ROM | disk | FTP | other *** search
/ Chip 2011 November / CHIP_2011_11.iso / Programy / Narzedzia / Calibre / calibre-0.8.18.msi / file_280 / historiaro.recipe < prev    next >
Text File  |  2011-09-09  |  2KB  |  52 lines
  1. # -*- coding: utf-8 -*-
  2. #!/usr/bin/env  python
  3.  
  4. __license__   = 'GPL v3'
  5. __copyright__ = u'2011, Silviu Cotoar\u0103'
  6. '''
  7. historia.ro
  8. '''
  9.  
  10. from calibre.web.feeds.news import BasicNewsRecipe
  11.  
  12. class HistoriaRo(BasicNewsRecipe):
  13.     title                        = u'Historia'
  14.     __author__            = u'Silviu Cotoar\u0103'
  15.     description             = ''
  16.     publisher                = 'Historia'
  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,Istorie'
  23.     encoding              = 'utf-8'
  24.     cover_url   = 'http://www.historia.ro/sites/all/themes/historia/images/historia.png'
  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={'class':'c_antet_title'})
  35.             , dict(name='a', attrs={'class':'overlaybox'})
  36.             , dict(name='div', attrs={'class':'art_content'})
  37.                               ]
  38.  
  39.     remove_tags = [
  40.              dict(name='div', attrs={'class':['fl_left']})
  41.            , dict(name='div', attrs={'id':['article_toolbar']})
  42.            , dict(name='div', attrs={'class':['zoom_cont']})
  43.                           ]
  44.  
  45.  
  46.     feeds          = [
  47.                         (u'Feeds', u'http://www.historia.ro/rss.xml')
  48.                      ]
  49.  
  50.     def preprocess_html(self, soup):
  51.         return self.adeify_images(soup)
  52.