Runs through a list of files and finds any that have duplicate md5 hashes

filehash.py

import md5
import datetime

def output_line(line):
    timestamp = datetime.datetime.today().strftime("%Y-%d-%m %H:%M:%S")
    print(timestamp + ': ' + line)

output_line("Starting program...")
list_file = open('mp3_list.txt','r')
counter = 0
hash_dict = {}
for line in list_file:
    mp3_name = line.strip()
    mp3_file = open(mp3_name,'r')
    m = md5.new()
    m.update(mp3_file.read())
    mp3_file.close()
    digest = m.hexdigest()
    if digest not in hash_dict:
        hash_dict[digest] = []
    hash_dict[digest].append(mp3_name)
    counter += 1
    if counter % 100 == 0:
        output_line(str(counter) + " files inspected, " + str(len(hash_dict)) + 
                    " hashes found...")
list_file.close()
output_line("Writing duplicates.txt...")
dupe_file = open('duplicates.txt','w')
for hash in hash_dict:
    if len(hash_dict[hash]) > 1:
        dupe_file.write(' OR '.join(asset_list) + "\n")
dupe_file.close()
output_line("Finished.")