Python ^3.10: Download all xkcd comics and comic data

get_all_xkcd.py

from get_info import save_infos
from get_imgs import save_imgs

if __name__ == '__main__':
    pth = 'xkcd_save'

    save_infos(pth)
    print()
    save_imgs(pth)

get_imgs.py

import requests
from os import path, listdir
from multiprocessing import Pool
import json
import re


def load_infos(save_dir: str) -> list[str]:
    files = listdir(save_dir)
    json_files = []

    for f in files:
        if re.match('.*\.json$', f):
            json_files.append(f)

    return json_files


def save_img(save_dir: str, file_path: str) -> None:
    pth = path.join(save_dir, file_path)

    with open(pth, 'rt') as fp:
        json_data = json.load(fp)
        num = json_data["num"]
        img = json_data["img"]

        save_path = path.join(save_dir, f'{num}.{img.split(".")[-1]}')

        if path.exists(save_path):
            #print('Exists:', num)
            return

        data = requests.get(img, stream=True)

        if not data.ok:
            print('Not OK:', num)
            return

        print('Saving:', num)
        with open(save_path, 'wb') as f:
            for chunk in data.iter_content(chunk_size=128):
                f.write(chunk)
        print('Done:', num)


def save_imgs(save_dir: str) -> None:
    print('Checking Images...')
    imgs_to_save = load_infos(save_dir)

    pool = Pool()

    for img_info in imgs_to_save:
        pool.apply_async(save_img, (save_dir, img_info))

    pool.close()
    pool.join()

if __name__ == '__main__':
    pth = 'xkcd_save'
    save_imgs(pth)

get_info.py

import requests
from os import mkdir, path
from multiprocessing import Pool
import json

BASE_URL = 'https://xkcd.com/'
JSON_URL = 'info.0.json'


def last_comic_num() -> int:
    return json.loads(requests.get(BASE_URL + JSON_URL).content)['num']


def save_info(save_path: str, num: int) -> None:
    pth = path.join(save_path, f'{num}.json')

    if path.exists(pth):
        #print('Exists:', num)
        return

    data = requests.get(f'{BASE_URL}{num}/{JSON_URL}', stream=True)

    if not data.ok:
        print('Not OK:', num)
        return

    print('Saving:', num)
    with open(pth, 'wb') as f:
        for chunk in data.iter_content(chunk_size=128):
            f.write(chunk)
    print('Done:', num)


def save_infos(save_path: str) -> None:
    print('Checking Info...')
    if not path.exists(save_path):
        mkdir(save_path)

    last_num = last_comic_num()
    print('Latest Comic:', last_num)

    pool = Pool()

    for i in range(1, last_num + 1):
        pool.apply_async(save_info, (save_path, i))

    pool.close()
    pool.join()

if __name__ == '__main__':
    pth = 'xkcd_save'

    save_infos(pth)