linux 下pyhton 删除指定目录下所有的重复内容的文件

#!/usr/bin/python

import sys
import os
import filecmp

if __name__ == '__main__':
"""Delete the dups files.

"""
if len(sys.argv) != 2:
print 'input the dir'
all_files = []
for a,b,c in os.walk(sys.argv[1]):
for f in c:
if(a.endswith('/')):
all_files.append(a+f)
else:
all_files.append(a+'/'+f)
ret = set()
for i in range(0, len(all_files)-1):
for j in range(i+1, len(all_files)):
if filecmp.cmp(all_files[i], all_files[j]):
ret.add(all_files[j]);
for f in ret:
os.system('rm -rf %s' % f)