Get a List of URLs from a Web Page 0

 1"""Extract list of URLs in a web page
 2
 3This program is part of "Dive Into Python", a free Python book for
 4experienced programmers.  Visit http://diveintopython.org/ for the
 5latest version.
 6"""
 7
 8__author__ = "Mark Pilgrim (mark@diveintopython.org)"
 9__version__ = "$Revision: 1.2 $"
10__date__ = "$Date: 2004/05/05 21:57:19 $"
11__copyright__ = "Copyright (c) 2001 Mark Pilgrim"
12__license__ = "Python"
13
14from sgmllib import SGMLParser
15
16class URLLister(SGMLParser):
17	def reset(self):
18		SGMLParser.reset(self)
19		self.urls = []
20
21	def start_a(self, attrs):
22		href = [v for k, v in attrs if k=='href']
23		if href:
24			self.urls.extend(href)
25
26if __name__ == "__main__":
27	import urllib
28	usock = urllib.urlopen("http://diveintopython.org/")
29	parser = URLLister()
30	parser.feed(usock.read())
31	parser.close()
32	usock.close()
33	for url in parser.urls: print url