#!/usr/bin/env python3 # Copyright (c) 2008-11 Qtrac Ltd. All rights reserved. # This program or module is free software: you can redistribute it and/or # modify it under the terms of the GNU General Public License as published # by the Free Software Foundation, either version 3 of the License, or # (at your option) any later version. It is provided for educational # purposes and is distributed in the hope that it will be useful, but # WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU # General Public License for more details. import string import sys words = {} strip = string.whitespace + string.punctuation + string.digits + "\"'" for filename in sys.argv[1:]: with open(filename) as file: for line in file: for word in line.lower().split(): word = word.strip(strip) if len(word) > 2: words[word] = words.get(word, 0) + 1 for word in sorted(words): print("'{0}' occurs {1} times".format(word, words[word]))