A simple HTML parser with HTMLParser module for Python 2.X.

MyHTMLParser.py

from HTMLParser import HTMLParser

class MyHTMLParser(HTMLParser):
	def handle_starttag(self, tag, attrs):
		print("Start tag:", tag)
		for attr in attrs:
			print("	 attr:", attr)
	
	def handle_endtag(self, tag):
		print("End tag  :", tag)
	
	def handle_data(self, data):
		print("Data	 :", data)
	
	def handle_comment(self, data):
		print("Comment  :", data)
	
	def handle_entityref(self, name):
		c = chr(name2codepoint[name])
		print("Named ent:", c)
	
	def handle_charref(self, name):
		if name.startswith('x'):
			c = chr(int(name[1:], 16))
		else:
			c = chr(int(name))
		print("Num ent  :", c)
	
	def handle_decl(self, data):
		print("Decl	 :", data)

parser = MyHTMLParser()

parser.feed('<img src="python-logo.png" alt="The Python logo">')

'''
Command: python MyHTMLParser.py 

Output:
('Start tag:', 'img')
('\t attr:', ('src', 'python-logo.png'))
('\t attr:', ('alt', 'The Python logo'))
'''