利用文件哈希值进行排重的Python脚本

import re, sys, os, hashlib

folder = 'C:\\XXX\\';
dicFile = {}
n = 0;
for filename in sorted(os.listdir(folder)):
  path = folder + filename;
  sig = hashlib.sha256(open(path, 'rb').read()).hexdigest()
  if(sig not in dicFile):
    dicFile[sig] = filename;
  else:
    print(filename + " is dupe with " + dicFile[sig]);
    os.remove(path);
    n = n + 1;
print("total deleted: " + str(n));