binary2image.py

"""Binary to Image Converter."""
import os
from argparse import ArgumentParser
from PIL import Image
from tqdm import tqdm


def get_binary_data(filename):
    """Extract byte values from binary executable file and store them in list.

    :param file: executable file
    :return: byte value list
    """
    binary_values = []
    with open(filename, "rb") as file:
        while byte := file.read(1):
            binary_values.append(ord(byte))

    return binary_values


def get_size(data_length):
    """Obtain image size.

    Source: Malware images: visualization and automatic classification.
    :param data_length: Number of bytes in file
    :return: size as integer tuple
    """
    size = data_length
    kib = 2**10

    if size < 10 * kib:
        width = 32
    elif size < 30 * kib:
        width = 64
    elif size < 60 * kib:
        width = 128
    elif size < 100 * kib:
        width = 256
    elif size < 200 * kib:
        width = 384
    elif size < 500 * kib:
        width = 512
    elif size < 1000 * kib:
        width = 768
    else:
        width = 1024

    height = size // width + 1

    return (width, height)


def save_file(folder, filename, data, size):
    """Save PIL image to disk.

    :param folder: folder where images will be saved
    :param filename: binary filename
    :param data: grayscale image
    :param size: image size
    """
    image = Image.new("L", size)
    image.putdata(data)

    name, _ = os.path.splitext(filename)
    name = os.path.basename(name)
    imagename = os.path.join(folder, name + ".png")

    image.save(imagename)


if __name__ == "__main__":

    parser = ArgumentParser(
        description="Transform all files in a folder into PNG images"
    )
    parser.add_argument("input_folder", help="Folder with the original files")
    parser.add_argument(
        "output_folder", help="Folder where the images will be saved"
    )
    args = parser.parse_args()

    files = [
        os.path.join(args.input_folder, bin_file)
        for bin_file in os.listdir(args.input_folder)
    ]
    os.makedirs(args.output_folder, exist_ok=True)
    for bin_file in tqdm(files):
        greyscale_data = get_binary_data(bin_file)
        bin_size = get_size(len(greyscale_data))
        save_file(args.output_folder, bin_file, greyscale_data, bin_size)