Untitled

token.py

#!/usr/bin/python
import nltk
import re

if __name__ == '__main__':
    f = open("a.html","r")
    s = f.read()
    s = re.sub('<.*?>', '', s)
    s = re.sub('\s+', ' ', s)
    print s

Output

praveen@praveen-desktop:~/Desktop$ python token.py
Traceback (most recent call last):
  File "token.py", line 2, in <module>
    import nltk
  File "/usr/lib/python2.5/site-packages/nltk/__init__.py", line 60, in <module>
    from utilities import *
  File "/usr/lib/python2.5/site-packages/nltk/utilities.py", line 8, in <module>
    import locale, re, types, textwrap, pydoc
  File "/usr/lib/python2.5/pydoc.py", line 55, in <module>
    import sys, imp, os, re, types, inspect, __builtin__, pkgutil
  File "/usr/lib/python2.5/inspect.py", line 31, in <module>
    import sys, os, types, string, re, dis, imp, tokenize, linecache
  File "/usr/lib/python2.5/tokenize.py", line 38, in <module>
    COMMENT = N_TOKENS
NameError: name 'N_TOKENS' is not defined