#!/usr/bin/env python3 # -*- coding: utf-8 -*- from html.parser import HTMLParser from html.entities import name2codepoint class MyHTMLParser(HTMLParser): def handle_starttag(self, tag, attrs): print('<%s>' % tag) def handle_endtag(self, tag): print('' % tag) def handle_startendtag(self, tag, attrs): print('<%s/>' % tag) def handle_data(self, data): print(data) def handle_comment(self, data): print('') def handle_entityref(self, name): print('&%s;' % name) def handle_charref(self, name): print('&#%s;' % name) parser = MyHTMLParser() parser.feed('''

Some html HTML tutorial...
END

''')