Lösung für Forumsfrage: http://forum.ubuntuusers.de/topic/md5-dateiliste-nach-doppelten-pruefsummen-eint/

Data.txt

23498239482938492384078789789789  bla/blub/datei1.dat
d41d8cd98f00b204e9800998ecf8427e  ga/bla2345.txt
b9dd393b05195aa2288bd1611d7fc361  bluber/bla4325.txt
d41d8cd98f00b204e9800998ecf8427e  data/ghghg/mfdfdf.dat
57dd7f249a99923eea234e62895dc03f  test.txt
d41d8cd98f00b204e9800998ecf8427e  data/anderer_name_als_mfdfdf.dat

doubles.py

#!/usr/bin/env python
# coding: utf-8

import argparse
from contextlib import closing
from collections import defaultdict
from pprint import pprint


def find_doubles(rows):  
    doubles = defaultdict(list)
    entries = defaultdict(list)
    for index, row in enumerate(rows):
        md5sum, path = row.strip().split()
        entries[md5sum].append((path, index))
    for key, value in entries.iteritems():
        if len(value) > 1:
            doubles[key] = value
    return doubles
    

def main():
    parser = argparse.ArgumentParser(description='Find MD5 doubles.')
    parser.add_argument('--input', type=argparse.FileType('r'), default='-')

    args = parser.parse_args()
    
    with closing(args.input) as infile:
        doubles = find_doubles(infile)
    
    for key, values in doubles.iteritems():
        print u"{} Einträge:".format(len(values))
        print u"\n".join("{}: {} {}".format(line, key, path) 
                            for path, line in values)
        print

if __name__ == "__main__":
    main()

Output

> python doubles.py --input data.txt

3 Einträge:
1: d41d8cd98f00b204e9800998ecf8427e ga/bla2345.txt
3: d41d8cd98f00b204e9800998ecf8427e data/ghghg/mfdfdf.dat
5: d41d8cd98f00b204e9800998ecf8427e data/anderer_name_als_mfdfdf.dat