deletes duplicate files

dupes-delete.py

from collections import defaultdict
import subprocess

basedir = "/Users/user/Desktop/files"

dict1 = defaultdict(list)
dict2 = {}
count = 0

output = subprocess.check_output(['find', basedir, '-type', 'f'], text=True)

# Makes a dictonary of all files and their md5 checksums
for line in output.splitlines():
    md5 = subprocess.check_output(['md5', '-q', line], text=True)
    dict1[md5.strip()].append(line)

# Looks for checksums associated to 2 or more files and creates a dictionary of them
for value in dict1.values():
    if len(value) > 1:
        dict2[count] = value
        count = count + 1

# Deletes every copy of those file less the first occurance and moves the remaining copy to an originals folder
subprocess.check_output(['mkdir', '-p', basedir + "/originals"], text=True)
for k, v in dict2.items():
    index = range(len(v)-1)
    for s in index:
        subprocess.check_output(['rm', '-f', v[s]], text=True)
        print(f"deleting duplicate file {v[s]}")
    print(f'Original copy moved from {v[len(v)-1]} to {basedir + "/originals/"}')    
    subprocess.check_output(['mv', v[len(v)-1], basedir + "/originals/."], text=True)