A script to extract images from .zip, .docx, .xlsx, and .pptx

image_mod.py

#!/usr/bin/python3

import os
import shutil
import logging
import zipfile
import argparse
import tempfile
from pathlib import Path

def extract_images(filepath, destination):

    temp_path = tempfile.gettempdir()
    logging.info('The default path for temporary directories and files is {}'.format(temp_path))
    destination_path = Path(destination)
    file_count = 0
    overall_size = 0
    data = []

    # Extracts the images from the file to temporary directory
    if zipfile.is_zipfile(filepath):
        
        # Creates a temporary directory to work with
        with tempfile.TemporaryDirectory() as working_dir:
            working_dir_name = Path(working_dir).name
            logging.info('Created temporal directory "{}"'.format(working_dir_name))
            shutil.copy(filepath, working_dir)
            logging.info('Copied {} to {}'.format(filepath.name, working_dir_name))
            file = Path(working_dir) / filepath.name

            # Makes a list of all images
            image_list = []
            for x in zipfile.ZipFile(file).namelist():
                if x.endswith('.png') or x.endswith('.jpeg'):
                    image_list.append(x)

            # Extracts images and moves them out of the temp directory
            for x in image_list:
                zipfile.ZipFile(file).extract(x)
                logging.info('Extracted {}'.format(x))
            logging.info('Extracted all image files')
            for x in image_list:
                shutil.copy(x, destination_path)
                logging.info('Copied {}'.format(x))
            logging.info('Copied all image files to {}'.format(destination_path.resolve()))

            for x in image_list:
                overall_size = overall_size + zipfile.ZipFile(file).getinfo(x).file_size
            file_count = len(image_list)

        data.append(file_count)
        data.append(overall_size)

        return data

    else:
        logging.info('File is a {}'.format(filepath.suffix))
        logging.error('File cannot be accessed, must have the following extensions: zip, docx, xlsx, pptx')

        data.append(filepath.suffix)

        return data

def main():
    parser = argparse.ArgumentParser(prog = 'image_mod.py', description = 'Extracts images from zip, docx, xlsx, and pptx files')
    parser.add_argument('filepath')
    parser.add_argument('-d', '--destination', default = '.')
    args = parser.parse_args()

    if args.destination:
        if Path(args.filepath).is_file() and Path(args.destination).is_dir():
            process = extract_images(Path(args.filepath), Path(args.destination))
            if len(process) == 2:
                print('Operation completed successfully. {} images were extracted ({:,.2f}KB total)'.format(process[0], process[1] / 1024))
                logging.info('Operation successful')
            else:
                print('Operation failed. File type {} not supported.'.format(process[0]))
                logging.info('Operation failed')
        else:
            print('Operation failed. Either the file you provided or the destination directory doesn\'t exist.')
            logging.info('Filename or destination directory doesn\'t exist')
            logging.error('File: {}; Directory: {}'.format(Path(args.filepath).exists(), Path(args.destination).exists()))

if __name__ == "__main__":
    logging.basicConfig(filename = 'common_tasks.log', level = logging.DEBUG, format = '%(asctime)s - %(name)s - %(levelname)s: %(message)s')
    main()