File size: 1,987 Bytes
908a1ab |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 |
import math
import requests
from tqdm import tqdm
from .misc import sizeof_fmt
def download_file_from_google_drive(file_id, save_path):
"""Download files from google drive.
Ref:
https://stackoverflow.com/questions/25010369/wget-curl-large-file-from-google-drive # noqa E501
Args:
file_id (str): File id.
save_path (str): Save path.
"""
session = requests.Session()
URL = 'https://docs.google.com/uc?export=download'
params = {'id': file_id}
response = session.get(URL, params=params, stream=True)
token = get_confirm_token(response)
if token:
params['confirm'] = token
response = session.get(URL, params=params, stream=True)
# get file size
response_file_size = session.get(URL, params=params, stream=True, headers={'Range': 'bytes=0-2'})
if 'Content-Range' in response_file_size.headers:
file_size = int(response_file_size.headers['Content-Range'].split('/')[1])
else:
file_size = None
save_response_content(response, save_path, file_size)
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, file_size=None, chunk_size=32768):
if file_size is not None:
pbar = tqdm(total=math.ceil(file_size / chunk_size), unit='chunk')
readable_file_size = sizeof_fmt(file_size)
else:
pbar = None
with open(destination, 'wb') as f:
downloaded_size = 0
for chunk in response.iter_content(chunk_size):
downloaded_size += chunk_size
if pbar is not None:
pbar.update(1)
pbar.set_description(f'Download {sizeof_fmt(downloaded_size)} ' f'/ {readable_file_size}')
if chunk: # filter out keep-alive new chunks
f.write(chunk)
if pbar is not None:
pbar.close()
|