from HTMLParser import HTMLParser
import httplib

# create a subclass and override the handler methods
class MyHTMLParser(HTMLParser):
    def handle_starttag(self, tag, attrs):
        print "Encountered a start tag:", tag
        print ''
    def handle_endtag(self, tag):
        print "Encountered an end tag :", tag
        print ''
    def handle_data(self, data):
        print  data 

# get content
conn = httplib.HTTPConnection("www.python.org")
conn.request("GET", "/index.html")
r1 = conn.getresponse()
print r1.status, r1.reason
data = r1.read()

# process html
parser = MyHTMLParser();
parser.feed(data);