Created
December 9, 2020 20:31
-
-
Save Miopas/cdd8b3502bd72df7642e7838010e0fb3 to your computer and use it in GitHub Desktop.
Download files from Google Drive in Python
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
import requests | |
import pdb | |
import sys | |
def download_file_from_google_drive(id, destination): | |
URL = "https://docs.google.com/uc?export=download" | |
session = requests.Session() | |
response = session.get(URL, params = { 'id' : id }, stream = True) | |
token = get_confirm_token(response) | |
if token: | |
params = { 'id' : id, 'confirm' : token } | |
response = session.get(URL, params = params, stream = True) | |
print('downloading {}...'.format(destination)) | |
save_response_content(response, destination) | |
def get_confirm_token(response): | |
for key, value in response.cookies.items(): | |
if key.startswith('download_warning'): | |
return value | |
return None | |
def save_response_content(response, destination): | |
CHUNK_SIZE = 32768 | |
with open(destination, "wb") as f: | |
for chunk in response.iter_content(CHUNK_SIZE): | |
if chunk: # filter out keep-alive new chunks | |
f.write(chunk) | |
def get_id(url): | |
arr = url.split('/') | |
return arr[-1] | |
if __name__ == "__main__": | |
# The file id is from the shared link. The file must be publicly accessible. | |
file_id = 'ilk8kp88nidrn1ld4l22jugugm7jk723' | |
destination = './raw/{}'.format('openwebtxt.tar.xz') | |
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