import HTMLParser
import urllib
import sys
#定义HTML解析器
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()
#创建HTML解析器的实例
lParser = parseLinks()
#打开HTML文件
lParser.feed(urllib.urlopen( \
"
http://www.python.org/index.html").read())
lParser.close()