Sampled MD5 Example

md5.py

#!/usr/bin/env python

'''
Calculate an MD5sum from the file, sampling ``read`` bytes within the file from every ``interval``.
'''

import hashlib

PATH = 'path/to/file'

def md5sum(file, start=0, interval=1024**2, read=1024):
    '''Calculate an MD5 sum from blocks from a file read'''


    file.seek(0, 2)
    size = file.tell()
    file.seek(start, 0)
    shift = interval - read
    md5 = hashlib.md5()

    while file.tell() < size:
        file.seek(shift, 1)
        md5.update(file.read(read))

    return md5.digest()


if __name__ == '__main__':
    with open(PATH, 'rb') as f:
        print(md5sum(f))