Remove all duplicated files in the CWD by checking each file hash

duplicate_files_removal.py

import subprocess
from pathlib import Path
from typing import List


def get_file_hashes() -> List[str]:
    try:
        file_hashes: str = subprocess.check_output('find . -type f -exec sha256sum {} \\;', text=True, shell=True)
    except subprocess.CalledProcessError:
        return []

    return file_hashes.strip().split('\n')


duplicate_hashes = get_file_hashes()
groups = {}

for dup in duplicate_hashes:
    sha256hash, file_path = dup.split('  ', 1)
    if sha256hash not in groups:
        groups[sha256hash] = []
    groups[sha256hash].append(file_path)

duplicated_files_count = 0
for files in groups.values():
    if len(files) > 1:
        duplicated_files_count += len(files)

print(f'{duplicated_files_count} duplicated items found.')

if duplicated_files_count == 0:
    exit(0)


action = input('Press "c" to continue and remove duplicated files: ').strip()
if action != 'c':
    print('Aborting duplicate files removal.')
    exit(0)


for files in groups.values():
    if len(files) > 1:
        for duplicated_file in files[1:]:
            print(f'Removing {duplicated_file}')
            Path(duplicated_file).unlink()