How to Hash Duplicate Photos and Delete Copies in Python

from pathlib import Path
import hashlib

def file_hash(path, chunk_size=8192):
    hasher = hashlib.sha256()
    with open(path, "rb") as f:
        for chunk in iter(lambda: f.read(chunk_size), b""):
            hasher.update(chunk)
    return hasher.hexdigest()

def delete_duplicate_photos(directory):
    directory = Path(directory)
    seen_hashes = {}
    deleted = []
    
    for photo in directory.glob("*"):
        if not photo.is_file() or photo.suffix.lower() not in {".jpg", ".jpeg", ".png", ".gif", ".bmp"}:
            continue
        digest = file_hash(photo)
        if digest in seen_hashes:
            print(f"Deleting duplicate: {photo.name} (identical to {seen_hashes[digest].name})")
            photo.unlink()
            deleted.append(photo.name)
        else:
            seen_hashes[digest] = photo
    
    return deleted

if __name__ == "__main__":
    # Create test files to demonstrate
    test_dir = Path("test_photos")
    test_dir.mkdir(exist_ok=True)
    original = test_dir / "original.jpg"
    duplicate = test_dir / "copy.jpg"
    original.write_bytes(b"same image data")
    duplicate.write_bytes(b"same image data")
    
    removed = delete_duplicate_photos(test_dir)
    print(f"Removed {len(removed)} duplicate(s): {removed}")
    print(f"Remaining files: {[f.name for f in test_dir.iterdir()]}")