"""
Tiré du livre gratuit "Plongez au coeur de Python",
Pour plus d'information.  Visitez http://diveintopython.net/
"""
 
__author__ = "Mark Pilgrim (mark@diveintopython.org)"
__version__ = "$Revision: 1.2 $"
__date__ = "$Date: 2004/05/05 21:57:19 $"
__copyright__ = "Copyright (c) 2001 Mark Pilgrim"
__license__ = "Python"
 
from sgmllib import SGMLParser
 
class URLLister(SGMLParser):
  def reset(self):
    SGMLParser.reset(self)
    self.urls = []
 
  def start_a(self, attrs):
    href = [v for k, v in attrs if k=='href']
    if href:
      self.urls.extend(href)
 
if __name__ == "__main__":
  import urllib
  usock = urllib.urlopen("http://diveintopython.net/")
  parser = URLLister()
  parser.feed(usock.read())
  parser.close()
  usock.close()
  for url in parser.urls:
   print url