Dump video in Google Drive folder

dump_gdrive_video.py

import json
from urllib.parse import parse_qs

import requests as r
from bs4 import BeautifulSoup as Soup

import concurrent.futures

HEADERS = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/114.0"}

def get_video_info(title, docid, filetype, target_fmt="22"):
    res = r.get("https://drive.google.com/get_video_info", params={"docid": docid}, headers=HEADERS)
    
    cookie_drive_stream = res.cookies["DRIVE_STREAM"]
    for stream in parse_qs(res.text)["url_encoded_fmt_stream_map"][0].split(","):
        stream = parse_qs(stream)
        fmt, url = stream["itag"][0], stream["url"][0]

        if fmt == target_fmt:
            return (url, cookie_drive_stream, f"{title}.{filetype.split('/')[1]}")


TITLE = 2
DOCID = 0
FILETYPE = 3

folder = ""

res = r.get(f"https://drive.google.com/drive/folders/{folder}", headers=HEADERS)
soup = Soup(res.text, features="html.parser")

for script in soup.select("script"):
    if script.get_text().startswith("window['_DRIVE_ivd']"):
        break

data = json.loads(eval(script.get_text()[len("window['_DRIVE_ivd'] = "):-len(";if (window['_DRIVE_ivdc']) {window['_DRIVE_ivdc']();}")]))

with concurrent.futures.ThreadPoolExecutor() as executor:
    futures = []

    for file in data[0]:
        title, docid, filetype = file[TITLE], file[DOCID], file[FILETYPE]

        if not filetype.startswith("video/"):
            continue

        futures.append(executor.submit(get_video_info, title, docid, filetype))

    for result in concurrent.futures.as_completed(futures):
        url, cookie_drive_stream, filename = result.result()
        # generate script for aria2c
        print("\n  ".join((url, f'header=Cookie:DRIVE_STREAM={cookie_drive_stream}', f"out=out/{filename}")))