home *** CD-ROM | disk | FTP | other *** search
/ Maximum CD 2011 January / maximum-cd-2011-01.iso / DiscContents / calibre-0.7.26.msi / file_4049 < prev    next >
Encoding:
Text File  |  2010-09-30  |  2.1 KB  |  58 lines
  1. __license__   = 'GPL v3'
  2. __copyright__ = '2008-2010, Darko Miletic <darko.miletic at gmail.com>'
  3. '''
  4. harpers.org
  5. '''
  6. from calibre.web.feeds.news import BasicNewsRecipe
  7.  
  8. class Harpers(BasicNewsRecipe):
  9.     title                 = u"Harper's Magazine"
  10.     __author__            = u'Darko Miletic'
  11.     language              = 'en'
  12.     description           = u"Harper's Magazine: Founded June 1850."
  13.     publisher             = "Harper's Magazine "
  14.     category              = 'news, politics, USA'
  15.     oldest_article        = 30
  16.     max_articles_per_feed = 100
  17.     no_stylesheets        = True
  18.     use_embedded_content  = False
  19.  
  20.     conversion_options = {
  21.                           'comment'   : description
  22.                         , 'tags'      : category
  23.                         , 'publisher' : publisher
  24.                         , 'language'  : language
  25.                         }
  26.  
  27.     extra_css = '''
  28.                 h1{ font-family:georgia ; color:#111111; font-size:large;}
  29.                 .box-of-helpful{ font-family:arial ; font-size:x-small;}
  30.                 p{font-family:georgia ;}
  31.                 .caption{font-family:Verdana,sans-serif;font-size:x-small;color:#666666;}
  32.                 '''
  33.  
  34.     keep_only_tags = [ dict(name='div', attrs={'id':'cached'}) ]
  35.     remove_tags = [
  36.                      dict(name='table', attrs={'class':['rcnt','rcnt topline']})
  37.                     ,dict(name=['link','object','embed','meta','base'])
  38.                   ]
  39.     remove_attributes = ['width','height']
  40.  
  41.     feeds       = [(u"Harper's Magazine", u'http://www.harpers.org/rss/frontpage-rss20.xml')]
  42.  
  43.     def get_cover_url(self):
  44.         cover_url = None
  45.         index = 'http://harpers.org/'
  46.         soup = self.index_to_soup(index)
  47.         link_item = soup.find(name = 'img',attrs= {'class':"cover"})
  48.         if link_item:
  49.            cover_url = 'http://harpers.org' + link_item['src']
  50.         return cover_url
  51.  
  52.     def preprocess_html(self, soup):
  53.         for item in soup.findAll(style=True):
  54.             del item['style']
  55.         for item in soup.findAll(xmlns=True):
  56.             del item['xmlns']
  57.         return soup
  58.