duplicate_file_finder.py

import os        # work with files and folders
import hashlib   # create hashes (file fingerprints)

# Folder to scan for duplicates
folder_path = os.path.expanduser("~/Downloads")  # change if needed

# Function to calculate a file's hash
# This creates a unique "fingerprint" based on file content
def get_file_hash(file_path):

    hasher = hashlib.md5()  # MD5 is fast and fine for duplicate detection

    # Open file in binary mode (important!)
    with open(file_path, "rb") as file:

        # Read the file in chunks (good for large files)
        while True:
            chunk = file.read(4096)
            if not chunk:
                break
            hasher.update(chunk)

    # Return the final hash value
    return hasher.hexdigest()

# Dictionary to store hashes we've seen
# Format: {hash: file_path}
seen_files = {}

# List to store duplicates
duplicates = []

# Go through all files in the folder
for filename in os.listdir(folder_path):

    file_path = os.path.join(folder_path, filename)

    # Skip folders
    if os.path.isdir(file_path):
        continue

    try:
        # Get the file's hash
        file_hash = get_file_hash(file_path)

        # Check if we've seen this hash before
        if file_hash in seen_files:
            # Duplicate found!
            duplicates.append((file_path, seen_files[file_hash]))
        else:
            # First time seeing this file
            seen_files[file_hash] = file_path

    except Exception as e:
        print(f"Error reading {filename}: {e}")

# Print results
print("\nDuplicate files found:\n")

if not duplicates:
    print("No duplicates found 🎉")
else:
    for duplicate, original in duplicates:
        print(f"Duplicate: {duplicate}")
        print(f"Original:  {original}")
        print("-" * 40)