scrape.py

import requests
from hashlib import md5
from pathlib import Path

image_hashes = set()
out_path = Path("./images")
out_path.mkdir(exist_ok=True, parents=True)
# Wouldn't it be nice to do this in an async way :/
while len(image_hashes) < 100:
    r = requests.get("https://dog.ceo/api/breeds/image/random")
    resp_url = r.json()["message"]
    image_data = requests.get(resp_url).content
    image_hash = md5(image_data).hexdigest()
    img_name = resp_url.split("/")[-1]
    if image_hash not in image_hashes:
        with open(f"{(out_path/img_name).absolute()}", "wb") as outfile:
            outfile.write(image_data)
        image_hashes.add(image_hash)
        print(len(image_hashes))