Compares md5 hashes for files in two directories recursively. It will compare using one dir as base (the left one) against the other one (the right one).

compare_files_in_dir.py

import argparse
import hashlib
import os


def get_checksum(f):
    md5 = hashlib.md5()
    md5.update(open(f).read())
    return md5.hexdigest()


def compare_files_recursively(left_dir, right_dir, debug):
    diff = {}
    for (dirpath, dirnames, filenames) in os.walk(left_dir):
        for filename in filenames:
            left_filename = os.path.join(dirpath, filename)
            left_file_md5 = get_checksum(left_filename)

            right_filename = left_filename.replace(left_dir, right_dir)
            try:
              right_file_md5 = get_checksum(right_filename)
            except IOError:
              print 'File does not exist: ' + right_filename
              diff[right_filename] = 'Missing right'
              continue
            if left_file_md5 != right_file_md5 or debug is True:
                print '-----------------------------------'
                print 'Left filename: ' + left_filename
                print 'Right filename: ' + right_filename
                print 'Left hash: ' + left_file_md5
                print 'Right hash: ' + right_file_md5
                print 'Hashes equal?: ' + left_file_md5 == right_file_md5
    print 'Diff: {}'.format(diff)

if __name__ == '__main__':
    parser = argparse.ArgumentParser(description=('Compare files in a folder (left) against files in other folder (right).'
                                                  'Kind of like left merging!'))
    parser.add_argument('--left',
                        dest='left_dir',
                        help='Path to base directory used for the comparison',
                        default='./before')
    parser.add_argument('--right',
                        dest='right_dir',
                        help='Path to directory to compare against',
                        default='./after')
    parser.add_argument('-d', '--debug',
                        dest='debug', action='store_true',
                        help='Debug mode, print all comparisons, else only failed')

    args = parser.parse_args()
    compare_files_recursively(args.left_dir, args.right_dir, args.debug)