-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathurllister.py
More file actions
33 lines (27 loc) · 839 Bytes
/
Copy pathurllister.py
File metadata and controls
33 lines (27 loc) · 839 Bytes
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
"""Extract list of URLs in a web page
This program is part of "Dive Into Python", a free Python book for
experienced programmers. Visit http://diveintopython.org/ for the
latest version.
"""
__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.org/")
parser = URLLister()
parser.feed(usock.read())
parser.close()
usock.close()
for url in parser.urls: print url