python htmllib.HTMLParser处理A标签

#!/usr/bin/python 
#encoding='utf-8' 
import htmllib,urllib,formatter,string 
'''''
import chardet,sys
type = sys.getdefaultencoding()
''' 
class GetLinks(htmllib.HTMLParser): 
    def __init__(self):
        self.links = {}
        f = formatter.NullFormatter()
        htmllib.HTMLParser.__init__(self, f) 
 
    def anchor_bgn(self, href, name, type): 
        self.save_bgn() 
        self.link = href 
 
    def anchor_end(self):
        text = string.strip(self.save_end())
        if self.link and text: 
            self.links[text] = self.link#self.links.get(text, []) + [self.link] 
            #print self.links 
            #exit() 
fp = urllib.urlopen("http://www.baidu.com")
data = fp.read() 
fp.close() 
 
linkdemo = GetLinks()
linkdemo.feed(data)
linkdemo.close() 
 
for href, link in linkdemo.links.items():
    print href, "=>", link