import os
import csv
from collections import defaultdict

def find_duplicate_basenames(root_directory, valid_extensions):
    # Dictionary to store basenames and their corresponding file paths
    basenames_to_paths = defaultdict(list)

    # Traverse the directory tree
    for dirpath, dirnames, filenames in os.walk(root_directory):
        for filename in filenames:
            full_path = os.path.join(dirpath, filename)
            basename, extension = os.path.splitext(filename)
            if extension.lower() in valid_extensions:
                basenames_to_paths[basename].append(full_path)

    # Filter basenames with more than one file
    duplicate_basenames = {basename: paths for basename, paths in basenames_to_paths.items() if len(paths) > 1}

    return duplicate_basenames

def export_to_csv(duplicate_files, output_csv):
    with open(output_csv, "w", newline="") as csvfile:
        fieldnames = ["Basename", "File Paths"]
        writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
        writer.writeheader()

        for basename, paths in duplicate_files.items():
            writer.writerow({"Basename": basename, "File Paths": ", ".join(paths)})

if __name__ == "__main__":
    server_directory = r"\\truenas\isolation\videos"  # Replace with your server directory
    video_extensions = {".mp4", ".mkv", ".avi", ".mov"}  # Add more video extensions if needed
    duplicate_files = find_duplicate_basenames(server_directory, video_extensions)

    if duplicate_files:
        output_csv_file = "duplicate_video_files.csv"
        export_to_csv(duplicate_files, output_csv_file)
        print(f"Duplicate video files exported to {output_csv_file}")
    else:
        print("No duplicate video files found.")