-
-
Save grimpy/7dd579059d7c4c42d0528e4676edffaf to your computer and use it in GitHub Desktop.
Google Drive file downloader for Python, with progress bar with tqdm. Based on this SO answer https://stackoverflow.com/a/39225039/3175094
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
import requests | |
import sys | |
import os | |
from tqdm import tqdm | |
def download_file_from_google_drive(id, destination=None): | |
URL = "https://docs.google.com/uc?export=download" | |
session = requests.Session() | |
viewresp = session.get(URL, params={"id": id}, stream=True) | |
token = None | |
for key, value in viewresp.cookies.items(): | |
if key.startswith("download_warning"): | |
token = value | |
break | |
else: | |
print("Could not find token for url") | |
#sys.exit(1) | |
params = {"id": id, "confirm": token} | |
response = session.get(URL, params=params, stream=True, headers={'Range': 'bytes=0-'}) | |
CHUNK_SIZE = 32 * 1024 | |
total_size = int(response.headers.get("content-length", 0)) | |
if total_size == 0: | |
# attempt to get it out of Content-Range | |
range = response.headers.get('Content-Range', None) | |
if range: | |
total_size = int(range.split('/')[-1]) | |
if destination is None or os.path.isdir(destination): | |
for segment in response.headers.get('Content-Disposition').split(';'): | |
if segment.startswith('filename='): | |
filename = segment.split('=', 1)[-1].strip('"') | |
break | |
else: | |
print("Could not find destination file") | |
sys.exit(1) | |
if destination is not None: | |
destination = os.path.join(destination, filename) | |
else: | |
destination = filename | |
partfile = destination + ".part" | |
stat = None | |
initial = 0 | |
if os.path.exists(partfile): | |
stat = os.stat(partfile) | |
response.close() | |
response = session.get(URL, params=params, stream=True, headers={'Range': 'bytes={}-'.format(stat.st_size)}) | |
initial = stat.st_size | |
range = response.headers.get('Content-Range', None) | |
with tqdm(desc=destination, total=total_size, initial=initial, unit="B", unit_scale=True) as pbar: | |
with open(partfile, "ab") as f: | |
f.seek(initial) | |
for chunk in response.iter_content(CHUNK_SIZE): | |
if chunk: | |
pbar.update(CHUNK_SIZE) | |
f.write(chunk) | |
os.rename(partfile, destination) | |
if __name__ == "__main__": | |
import argparse | |
from urllib import parse | |
parser = argparse.ArgumentParser() | |
parser.add_argument("-url", dest="url", required=True) | |
parser.add_argument("-dest", dest="dest") | |
options = parser.parse_args() | |
# TAKE ID FROM SHAREABLE LINK | |
if options.url.startswith("https://"): | |
parsedurl = parse.urlparse(options.url) | |
query = parse.parse_qs(parsedurl.query) | |
if "id" not in query: | |
print("Link does not contain fileid") | |
sys.exit(1) | |
file_id = query["id"][0] | |
else: | |
file_id = options.url | |
destination = options.dest | |
download_file_from_google_drive(file_id, destination) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment