Find Entropy of Strings

find-entropy.py

#!/usr/bin/env python

#
# find-entropy.py
#
# A simple Utility to measure entropy of strings.
# Usage should be something like this:
#
# $ strings file.txt | python find-entropy.py
#
# The preset criteria of 3.75 should weed out most non-human created strings
#

import math
import string
import sys

def shannon_entropy(data):
    """
    Adapted from http://blog.dkbza.org/2007/05/scanning-data-for-entropy-anomalies.html
    by way of truffleHog (https://github.com/dxa4481/truffleHog)
    """
    if not data:
        return 0
    entropy = 0
    for x in string.printable:
        p_x = float(data.count(x)) / len(data)
        if p_x > 0:
            entropy += - p_x * math.log(p_x, 2)
    return entropy

for line in sys.stdin:
    entropy = shannon_entropy(line)
    if entropy > 3.75:
        print (line[:-1], entropy)