Anonymous

#!/usr/bin/env python

import sys, os, os.path,htmllib
from HTMLParser import HTMLParser

class MyParser(HTMLParser):
	def handle_starttag(self,tag,attrs):
		print tag	

dir = sys.argv[1]

html_files = []

def simple_walk(dir):
   for file in os.listdir(dir):
      filename = os.path.join(dir, file)
      if os.path.isfile(filename):
         if os.path.splitext(filename)[1] == ".html":
            html_files.append(filename)
      elif os.path.isdir(filename):
         simple_walk(filename)

def parse(files):
	for file in files:
		try:
			f = open(file, 'r')
			print file, ':'
			data = f.read()
			parser = MyParser()
			parser.feed(data)
		except parser.HTMLParseError, e:
			print "Error", s, "continuine"
			continue
			

simple_walk(dir)
parse(html_files)