get_duplicate_md5

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# Filename: get_duplicate_md5.py
# Version: 1.0.0
# Author: Jeoi Reqi

"""
Description:
    This script finds duplicate files within the current working directory based on their MD5 hashes.

Expected Output:
-------------------------------------------------------------------------------
    Duplicate files with MD5 hash: 098f6bcd4621d373cade4e832627b4f6

    C:\\Users\\pytho\\OneDrive\\Desktop\\MyScripts\\New PY Scripts\\test.txt
    C:\\Users\\pytho\\OneDrive\\Desktop\\MyScripts\\New PY Scripts\\test_new_name.txt

    You can safely delete the duplicate file(s).

    Program has completed without errors.    GoodBye!
-------------------------------------------------------------------------------

Usage:
    - The script prints the paths of duplicate files along with their MD5 hash.
    - To use this script, simply run it. It will search for duplicate files within the current working directory.

Additional Notes:
    - This script only searches for duplicate files within the current working directory.
    - It calculates the MD5 hash of each file to identify duplicates.
"""

import os
import hashlib
from collections import defaultdict

# Function to calculate the MD5 hash of a file
def get_md5_hex(file_path):
    with open(file_path, "rb") as f:
        md5 = hashlib.md5()
        for chunk in iter(lambda: f.read(4096), b""):
            md5.update(chunk)
    return md5.hexdigest()

# Function to find duplicate files in the current working directory
def find_duplicate_files():
    md5_hashes_seen = defaultdict(list)

    cwd = os.getcwd()  # Get the current working directory
    for root, _, files in os.walk(cwd):
        for file in files:
            file_path = os.path.join(root, file)
            md5_hash = get_md5_hex(file_path)
            md5_hashes_seen[md5_hash].append(file_path)

    for md5_hash, files in md5_hashes_seen.items():
        if len(files) > 1:
            print("\nDuplicate files with MD5 hash:", md5_hash, "\n")
            for file_path in files:
                print(file_path)
            print(
                "\n\tYou can safely delete the duplicate file(s).\n\nProgram has completed without errors.\tGoodBye!\n"
            )

# Main function
def main():
    find_duplicate_files()

if __name__ == "__main__":
    main()