Scrape CT Images from Scan of the Month Website

get_ct_images.py

import base64
import requests
import os
from io import StringIO

output_path = "output"
default_url = "https://www.scanofthemonth.com/scans/game-boy-compendium"
source = requests.get(default_url)
ujson = set([x.strip().replace('"', "").split("=")[-1] for x in source.text.split("\n") if "data-src=" in x])

for jurl in ujson:
    data = requests.get(jurl)
    data = data.json()
    folder = data["nm"]
    if not os.path.exists(os.path.join(output_path, folder)):
        os.mkdir(os.path.join(output_path, folder))
    for layer, asset in zip(data["layers"], data["assets"]):
        imgname = layer["nm"]
        encodedimg = asset["p"].replace("data:image/png;base64,", "")
        with open(os.path.join(output_path, folder, imgname), "wb") as img:
            base64.decode(StringIO(encodedimg), img)