indexes all images from an instagram thread

threaddump.py

from selenium import webdriver
import requests
import figa
from redis import Redis
from pprint import pp


@figa.config
class Config:
    default = "config.json"


def get_instagram_session():
    opts = webdriver.ChromeOptions()
    opts.add_argument("headless")
    opts.add_argument('window-size=1280x720')

    driver = webdriver.Chrome()  # chrome_options=opts)
    driver.implicitly_wait(3)

    driver.get("https://instagram.com/")

    input("Press enter when logged in.")

    session = requests.Session()
    for cookie in driver.get_cookies():
        session.cookies.set(cookie["name"], cookie["value"])

    session.headers.update({
        "referer": "https://www.instagram.com/direct/inbox",
        "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.40"
                      "44.138 Safari/537.36 OPR/68.0.3618.173",

    })

    driver.quit()

    return session


if __name__ == "__main__":
    cfg = Config("default")

    db = Redis(cfg.redis.host, cfg.redis.port, password=cfg.redis.password, decode_responses=True)

    session = get_instagram_session()

    session.headers.update({
        "x-ig-app-id": cfg.app_id,
        "x-ig-www-claim": "hmac.AR2Fmty-ITmxPw22Wm2U2sYqm92w3eYApVAlxSj2beCUI8xM",
        "x-requested-with": "XMLHttpRequest"
    })

    threads = session.get(
        "https://www.instagram.com/direct_v2/web/inbox/?persistentBadging=true&folder=&limit=10&thread_message_limit=10"
    )

    thread = None
    for t in threads.json()["inbox"]["threads"]:
        if t["thread_id"] == cfg.thread_id:
            thread = t
            break

    if thread is None:
        raise KeyError("Thread not found")

    cursor = thread["newest_cursor"]
    while True:
        resp = session.get("https://www.instagram.com/direct_v2/web/threads/{}/".format(cfg.thread_id),
                           params={"cursor": cursor}).json()

        for message in resp["thread"]["items"]:
            if message["item_type"] == "media":
                if "image_versions2" in message["media"]:
                    versions = sorted(message["media"]["image_versions2"]["candidates"],
                                      key=lambda c: c["width"] * c["height"])
                    largest = versions[-1]

                    db.set("images:{}".format(message["media"]["id"]), largest["url"])
                else:
                    pp(message["media"])

        cursor = resp["thread"]["prev_cursor"]