You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

24 lines
358 B
Python

#/bin/env python
from hashlib import md5
import os
# remove duplicates
filedict = dict()
for root, dirs, files in os.walk('.'):
for f in files:
path = os.path.join(root, f)
fo = open(path)
content = fo.read()
fo.close()
h = md5(content).hexdigest()
if filedict.get(h, None):
os.remove(path)
else:
filedict[h] = path
print filedict