linux 使用python脚本 找出指定目录下重复文件，并作出处理。

#!/usr/bin/python3
#-*- coding: UTF-8 -*-
import hashlib
import sys
import os
import fnmatch
CHUNK_SIZE = 8192

#Find the documents you need.
def find_specific_files(root):
  file_path=[]
  formats=['*.txt','*.bak','*.log','*.py','*.sh']
  for root,dirname,filenames in os.walk(root):
    for extensions in formats:
       for filename in fnmatch.filter(filenames,extensions):
          file_path.append(os.path.join(root,filename))
  return file_path

#Example Obtain the MD5 value of the file.
def get_chunk(filename):
   d=hashlib.md5()
   with open(filename) as f:
     for line in f:
        d.update(line.encode('utf-8'))
   return d.hexdigest()

def main():
  sys.argv.append("")
  directory=sys.argv[1]
  record={}
  if not directory:
    raise SystemExit ("missing directory parameters")
  if not os.path.isdir(directory):
    raise SystemExit ("{0} is not a directory".format(directory))
  for chunk in find_specific_files(directory):
    checksum=get_chunk(chunk)
    if checksum in record:
        print('{0} and {1} contents are always'.format(record[checksum],chunk))
    else:
        record[checksum]=chunk
if __name__ == '__main__':
  main()