import re


def extract_customer_ids(file_path):
    # Read the file content
    with open(file_path, "r") as file:
        content = file.read()

    # Define regex pattern for Stripe customer IDs
    # Matches 'cus_' followed by exactly 14 alphanumeric characters
    pattern = r"cus_[A-Za-z0-9]{14}"

    # Find all matches in the content
    customer_ids = re.findall(pattern, content)

    return customer_ids


# Example usage:
if __name__ == "__main__":
    file_path = "mozart_50k_stripe_customers_poorly_formatted.txt"
    customer_ids = extract_customer_ids(file_path)

    # Write customer IDs to output file
    output_file = "mozart_stripe_customer_ids.txt"
    with open(output_file, "w") as f:
        for customer_id in customer_ids:
            f.write(f"{customer_id}\n")

    print(f"Wrote {len(customer_ids)} customer IDs to {output_file}")