download pdf from drive drive that block download

download_pdf_drive.py

import io
import re
import json
import requests
import demjson3
from PIL import Image
import urllib.parse as parse

file = input("file url: ")

file_list = []

with requests.Session() as s:
    s.headers.update({"User-Agent": "Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20100101 Firefox/10.0"})
    html_data = s.get(file).text
    viewerData = re.search("window.viewerData = (.*?);", html_data).group(1)
    viewerData_json = demjson3.decode(viewerData)
    clean_viewerData = [i for i in viewerData_json["itemJson"] if i is not None]
    assert clean_viewerData[3] == "application/pdf"
    url_raw_obj = parse.urlparse(clean_viewerData[2])
    page_info_raw = s.get(clean_viewerData[2]).text.removeprefix(")]}'\n")
    page_info = json.loads(page_info_raw)
    url_qs_dict = parse.parse_qs(url_raw_obj.query)
    for i in url_qs_dict.keys():
        url_qs_dict[i] = url_qs_dict[i][0]
    url_qs_dict["w"] = page_info["maxPageWidth"]
    for page_int in range(0, page_info["pages"]):
        url_qs_dict["page"] = str(page_int)
        qr = parse.urlencode(url_qs_dict)
        datar = s.get(f"https://drive.google.com/viewer2/prod-01/img?{qr}").content
        img_obj = Image.open(io.BytesIO(datar))
        file_list.append(img_obj)
        print("save page", page_int+1, "of", page_info["pages"])

file_list[0].save(clean_viewerData[0], format="pdf", save_all=True, append_images=file_list[1:])
print("done")

requirements.txt

requests
demjson3
pillow