Get lines that appear in one file but not the other, useful for finding missing files when copying/transferring big batches of files.

diff_two_file_lists.py

#!/usr/bin/python

import sys
import os
from sets import Set

def create_file_set(filename, file_extension):
    with open(filename, "r") as in_f:
        result_set = Set()
        for line in in_f:
            result = line.strip().split(file_extension)[0]
            if result not in result_set:
                result_set.add(result)
        return result_set

def main():
    if len(sys.argv) < 4:
        print "Usage: python " + sys.argv[0] + " <file1> <file2> <file extension>"
        exit()

    file1 = sys.argv[1]
    file2 = sys.argv[2]
    file_extension = sys.argv[3]
    
    file1_set = create_file_set(file1, file_extension)
    file2_set = create_file_set(file2, file_extension)

    # get difference between sets
    if len(file1_set) > len(file2_set):
        file_set_diff = file1_set - file2_set
    else:
        file_set_diff = file2_set - file1_set

    for item in file_set_diff:
        print item

    print "Number of items in {}: {}".format(file1, len(file1_set))
    print "Number of items in {}: {}".format(file2, len(file2_set))
    print "Number of items in {}: {}".format("difference set", len(file_set_diff))


if __name__ == "__main__":
    main()