python模块之HTMLParser解析出URL链接

# -*- coding: utf-8 -*-
#python 27
#xiaodeng
#python模块之HTMLParser解析出URL链接
#http://www.cnblogs.com/mfryf/p/3691563.htmlfrom HTMLParser import HTMLParser
class MyHTMLParser(HTMLParser):
def __init__(self):
HTMLParser.__init__(self) #继承
self.links = []#links 链接 def handle_starttag(self, tag, attrs):
#print "Encountered the beginning of a %s tag" % tag if tag == "a":
if len(attrs) == 0:
pass
else:
for variable, value in attrs:
if variable == "href":
self.links.append(value) if __name__ == "__main__":
#写入一个html长字符串
html_code = """<a href="www.google.com"> google.com</a>
<A Href="www.pythonclub.org"> PythonClub </a>
<A HREF = "www.sina.com.cn"> Sina </a>
"""
hp = MyHTMLParser()
hp.feed(html_code)
hp.close()
#print hp.handle_starttag('a', 'href')
print hp.links #['www.google.com', 'www.pythonclub.org', 'www.sina.com.cn']