爬虫提取html标签

#coding:gbk
import HTMLParser
import urllib
import sys
class parseLinks(HTMLParser.HTMLParser):
    def handle_starttag(self,tag,attrs):
        if tag=="a":
            for name,value in attrs:
                if name=='href':
                    print value
                    print self.get_starttag_text()
IParser=parseLinks()
IParser.feed(urllib.urlopen("http://automationtesting.xxxxx/").read())
IParser.close()

找到a标签和href标签