Google Drive download all my items and those that are shared with me

google-drive-backup.py

import os
import re
import io
from googleapiclient.discovery import build
from googleapiclient.http import MediaIoBaseDownload
from google_auth_oauthlib.flow import InstalledAppFlow
from google.auth.transport.requests import Request
from google.oauth2.credentials import Credentials


# Define the scope for the Google Drive API
SCOPES = ['https://www.googleapis.com/auth/drive.readonly']


def sanitize_filename(name):
    """Sanitizes a filename by removing or replacing invalid characters.

    Args:
        name (str): The original filename.

    Returns:
        str: The sanitized filename.
    """
    return re.sub(r'[\\/*?:"<>|]', '_', name)


def download_file(service, file_id, file_path, mime_type):
    """Downloads a file from Google Drive.

    This function downloads a file based on its MIME type. For Google Docs,
    Sheets, and Slides, it converts them to their corresponding Microsoft
    Office formats before downloading.

    Args:
        service: The Google Drive API service instance.
        file_id (str): The ID of the file to download.
        file_path (str): The local path to save the file to.
        mime_type (str): The MIME type of the file.
    """
    if os.path.exists(file_path):
        print(f"File {file_path} already exists, skipping.")
        return

    try:
        print(f"Downloading {file_path}...")
        if mime_type.startswith('application/vnd.google-apps.'):
            if mime_type == 'application/vnd.google-apps.document':
                request = service.files().export_media(fileId=file_id, mimeType='application/vnd.openxmlformats-officedocument.wordprocessingml.document')
                file_path += '.docx'
            elif mime_type == 'application/vnd.google-apps.spreadsheet':
                request = service.files().export_media(fileId=file_id, mimeType='application/vnd.openxmlformats-officedocument.spreadsheetml.sheet')
                file_path += '.xlsx'
            elif mime_type == 'application/vnd.google-apps.presentation':
                request = service.files().export_media(fileId=file_id, mimeType='application/vnd.openxmlformats-officedocument.presentationml.presentation')
                file_path += '.pptx'
        else:
            request = service.files().get_media(fileId=file_id)

        fh = io.FileIO(file_path, 'wb')
        downloader = MediaIoBaseDownload(fh, request)
        done = False
        while not done:
            status, done = downloader.next_chunk()
            print(f"Download {int(status.progress() * 100)}%.")
    except Exception as e:
        print(f"An error occurred: {e}")


def download_folder(service, folder_id, folder_path):
    """Recursively downloads the contents of a folder from Google Drive.

    This function downloads all files in the specified folder, and recursively
    downloads the contents of any subfolders.

    Args:
        service: The Google Drive API service instance.
        folder_id (str): The ID of the folder to download.
        folder_path (str): The local path to save the contents of the folder to.
    """
    if not os.path.exists(folder_path):
        os.makedirs(folder_path)

    response = service.files().list(q=f"'{folder_id}' in parents",
                                    spaces='drive',
                                    fields='nextPageToken, files(id, name, mimeType)').execute()

    for file in response.get('files', []):
        file_name = sanitize_filename(file.get('name'))
        file_id = file.get('id')
        file_path = os.path.join(folder_path, file_name)

        if file.get('mimeType') == 'application/vnd.google-apps.folder':
            download_folder(service, file_id, file_path)
        else:
            download_file(service, file_id, file_path, file.get('mimeType'))


def main():
    """Main function to authenticate and initiate the file download process."""
    creds = None
    if os.path.exists('token.json'):
        creds = Credentials.from_authorized_user_file('token.json', SCOPES)
    if not creds or not creds.valid:
        if creds and creds.expired and creds.refresh_token:
            creds.refresh(Request())
        else:
            flow = InstalledAppFlow.from_client_secrets_file('credentials.json', SCOPES)
            creds = flow.run_local_server(port=0)
        with open('token.json', 'w') as token:
            token.write(creds.to_json())

    service = build('drive', 'v3', credentials=creds)

    page_token = None
    while True:
        response = service.files().list(
            q="'me' in owners",
            spaces='drive',
            fields='nextPageToken, files(id, name, mimeType)',
            pageToken=page_token).execute()

        for file in response.get('files', []):
            filename = os.path.join('backup/', sanitize_filename(file.get('name')))
            if file.get('mimeType') == 'application/vnd.google-apps.folder':
                download_folder(service, file.get('id'), filename)
            else:
                download_file(service, file.get('id'), filename, file.get('mimeType'))

        page_token = response.get('nextPageToken', None)
        if page_token is None:
            break


if __name__ == '__main__':
    main()

Dependencies:

python = "^3.11"
google-api-python-client = "^2.115.0"
google-auth-httplib2 = "^0.2.0"
google-auth-oauthlib = "^1.2.0"

Notes:

• All items are downloaded to backup/*
• Folders are recursively downloaded, keeping their directory structure
• Files already downloaded will be skipped (interrupt protection)
• Google Docs, Spreadsheets, and presentations are exported to openxml formats
• Special characters are replaced in names that might be problematic for MacOS