removing duplicated photos from your hard drive

These last days I've been trying to organize my photo collection. I realized that some of them were in more than one folder, that is, some photos were duplicated or triplicated on my hard drive.

So, I wrote a python script to solve my problem, and here it is:

import os

import sys

import hashlib

def removeDuplicatedImages(dirname):

print "DEBUG: looking for images at "+dirname

list_of_images={}

list_of_images_to_remove=[]

for root, dirs, files in os.walk(dirname):

for file in files:

filename=root+os.sep+file

f=open(filename,'r')

md5sum=hashlib.md5(f.read()).hexdigest()

f.close()

if not list_of_images.has_key(md5sum):

list_of_images[md5sum]=[filename]

else:

print "DEBUG: removing " + filename

os.remove(filename)

return

if __name__ == '__main__':

if len(sys.argv)!=2:

print "Usage " + sys.argv[0] + "dirname"

sys.exit()

dirname=sys.argv[1]

removeDuplicatedImages(dirname)