from HTMLParser import HTMLParser
import urllib

class MyHTMLParser(HTMLParser):

    def handle_starttag(self, tag, attrs):
        print "Poczatek %s" % tag

    def handle_endtag(self, tag):
        print "Koniec %s tag" % tag

    def handle_data(self, data):
        print "Dane %s" % data

 p = MyHTMLParser()
 input = urllib.urlopen('http://strona.pl/plik.html')
 html = input.read()
 input.close()
 p.feed(html)
 print p.data
 p.close