Last active
August 6, 2020 21:37
-
-
Save lelogrott/84102f9e4d655bd92a45ab024a13bc90 to your computer and use it in GitHub Desktop.
downloads all files in a google drive folder keeping the folder structure.
This file contains hidden or 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
from __future__ import print_function | |
import pickle | |
import io | |
import argparse | |
import sys | |
import os.path | |
from pathlib import Path | |
from googleapiclient.discovery import build | |
from google_auth_oauthlib.flow import InstalledAppFlow | |
from google.auth.transport.requests import Request | |
from apiclient.http import MediaIoBaseDownload | |
class GoogleDriveService: | |
# If modifying these scopes, delete the file token.pickle. | |
SCOPES = ['https://www.googleapis.com/auth/drive'] | |
def __init__(self): | |
self.load_creds() | |
self.client = build('drive', 'v3', credentials=self.creds) | |
def load_creds(self): | |
self.creds = None | |
# The file token.pickle stores the user's access and refresh tokens, and is | |
# created automatically when the authorization flow completes for the first | |
# time. | |
if os.path.exists('token.pickle'): | |
with open('token.pickle', 'rb') as token: | |
self.creds = pickle.load(token) | |
# If there are no (valid) credentials available, let the user log in. | |
if not self.creds or not self.creds.valid: | |
if self.creds and self.creds.expired and self.creds.refresh_token: | |
self.creds.refresh(Request()) | |
else: | |
flow = InstalledAppFlow.from_client_secrets_file( | |
'./../credentials.json', GoogleDriveService.SCOPES) | |
if REMOTE_RUN: | |
self.creds = flow.run_console() | |
else: | |
self.creds = flow.run_local_server(port=0) | |
# Save the credentials for the next run | |
with open('./../token.pickle', 'wb') as token: | |
pickle.dump(self.creds, token) | |
def download_file(self, file_id, file_name, file_path='./', verbose=False): | |
request = self.client.files().get_media(fileId=file_id) | |
fh = io.FileIO((file_path + file_name), 'wb') | |
downloader = MediaIoBaseDownload(fh, request) | |
done = False | |
while done is False: | |
status, done = downloader.next_chunk() | |
if verbose: | |
print("%s%s - Download %d%%." % (file_path, file_name, int(status.progress() * 100))) | |
def download_all_files_in_folder(self, folder_id, file_path='./'): | |
# creates path if does not exist | |
if not os.path.exists(file_path): | |
os.makedirs(file_path) | |
page_token = None | |
while(True): | |
# Call the Drive v3 API | |
results = self.client.files().list( | |
q=("'%s' in parents" % folder_id), | |
fields="nextPageToken, files(id, name, mimeType, parents)", pageToken=page_token | |
).execute() | |
items = results.get('files', []) | |
if not items: | |
print('No files found in %s' % file_path) | |
else: | |
for item in items: | |
if item['mimeType'] == 'application/vnd.google-apps.folder': | |
# continue | |
new_path = ('%s%s/' % (file_path, item['name'].replace('/','\/'))) | |
self.download_all_files_in_folder(item['id'], new_path) | |
else: | |
download_name = item['name'].replace('/','-') | |
# handle avatar files without extension | |
if (item['mimeType'] == 'image/jpeg') and not ('.jpeg' in download_name): | |
download_name += '.jpeg' | |
full_path_file_name = file_path + download_name | |
if os.path.exists(full_path_file_name): | |
print("%s - already exists." % (full_path_file_name)) | |
else: | |
try: | |
self.download_file(item['id'], download_name, file_path, verbose=True) | |
except: | |
e = sys.exc_info()[0] | |
error_file = open('./../download_errors.txt', 'a+') | |
error_file.write("Couldn't download %s%s (%s) - Error: %s\n" % (file_path, download_name, item['id'], e)) | |
error_file.close() | |
page_token = results.get('nextPageToken', None) | |
if page_token is None: | |
break | |
def main(): | |
gdrive_service = GoogleDriveService() | |
# uncomment line below for debugging | |
# import code; code.interact(local=dict(globals(), **locals())) | |
gdrive_service.download_all_files_in_folder(PARENT_FOLDER_ID) | |
if __name__ == '__main__': | |
parser = argparse.ArgumentParser(description='Download files stored in Google Drive.') | |
parser.add_argument('--folder_id', dest='folder_id', help='parent folder id. If none given, all files are downloaded') | |
parser.add_argument('--remote', dest='remote', default=False, help='set to true if running remotely. Eg via SSH. default: false') | |
args = parser.parse_args() | |
PARENT_FOLDER_ID = args.folder_id | |
REMOTE_RUN = bool(args.remote) | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
before running it you should enable the Google Drive API, generate and save the
credentials.json
file and install dependencies.You can find more information on steps 1 and 2 of this Quickstart document