CopyRandomImages.py

import os
import shutil
import random
import re
import sys

def find_and_copy_jpgs(input_dir, output_dir):
    if not os.path.exists(output_dir):
        os.makedirs(output_dir)

    file_groups = {}

    for root, dirs, files in os.walk(input_dir):
        for file in files:
            if file.lower().endswith('.jpg'):
                base_name = re.sub(r'_\d{3}\.jpg$', '', file)

                if base_name not in file_groups:
                    file_groups[base_name] = []
                file_groups[base_name].append(os.path.join(root, file))

    for group, files in file_groups.items():
        random_file = random.choice(files)

        relative_path = os.path.relpath(os.path.dirname(random_file), input_dir)
        target_folder = os.path.join(output_dir, relative_path)

        if not os.path.exists(target_folder):
            os.makedirs(target_folder)

        shutil.copy(random_file, target_folder)
        print(f'Copying file: {random_file} -> {target_folder}')

if __name__ == "__main__":
    if len(sys.argv) != 3:
        print("Usage: python script.py <input_folder> <output_folder>")
        sys.exit(1)

    input_folder = sys.argv[1]
    output_folder = sys.argv[2]

    find_and_copy_jpgs(input_folder, output_folder)