python解析html的简单实例

#!/usr/bin/python
#
#site: WWW.jb200.com

import urllib
import sys
from sgmllib import SGMLParser
class URLLister(SGMLParser):
    urls = []
    def start_a(self, attrs):
        href = [v for k, v in attrs if k=='href']
        if href:
            self.urls.extend(href)
            print href
if __name__=="__main__":
    opener = urllib.FancyURLopener({})
    f = opener.open("http://www.jb200.com")
    data = f.read()
    html = URLLister()
    html.feed(data)
    html.close()