calculate md5 hashes of chunks of a file, configurable block size

md5chunks.py

#!/usr/bin/env python

from optparse import OptionParser
from pathlib import Path
import hashlib
import sys

parser = OptionParser()
parser.add_option("-b", "--blocksize", dest="blocksize", type=int, default=1024,
                  help="Specify blocksize", metavar="blocksize")

(options, args) = parser.parse_args()

if len(args) == 0:
    print ("Please specify a filename")
    sys.exit(1)

f = open(args[0], 'rb')
c = 0

file_size = Path(args[0]).stat().st_size

total_blocks = file_size / options.blocksize

while 1:
    block = f.read(options.blocksize)
    if not block:
        print("processed %8.d blocks out of %8.d total progress is 100%%"%(c-1,total_blocks), file=sys.stderr )
        break
    m = hashlib.md5()
    m.update(block)
    md5 = m.hexdigest()
    print ("%d,%s" % (c, md5))
    
    if c % 10240 == 0:
        print("processed %8.d blocks out of %8.d total progress is %.2f%%"%(c,total_blocks, 100*(float(c)/float(total_blocks))), file=sys.stderr )
    
    c += 1