How do I search sub-folders and sub-sub-folders in Google Drive?

Question

This is a commonly asked question.

The scenario is:-

folderA____ folderA1____folderA1a
       \\____folderA2____folderA2a
                    \\___fo         


        

Answer 1

Sharing a Python solution to the excellent Alternative 3 by @pinoyyid, above, in case it's useful to anyone. I'm not a developer so it's probably hopelessly un-pythonic... but it works, only makes 2 API calls, and is pretty quick.

1. Get a master list of all the folders in a drive.
2. Test whether the folder-to-search is a parent (ie. it has subfolders).
3. Iterate through subfolders of the folder-to-search testing whether they too are parents.
4. Build a Google Drive file query with one '' in parents segment per subfolder found.

Interestingly, Google Drive seems to have a hard limit of 599 '' in parents segments per query, so if your folder-to-search has more subfolders than this, you need to chunk the list.

FOLDER_TO_SEARCH = '123456789'  # ID of folder to search
DRIVE_ID = '654321'  # ID of shared drive in which it lives
MAX_PARENTS = 500  # Limit set safely below Google max of 599 parents per query.


def get_all_folders_in_drive():
    """
    Return a dictionary of all the folder IDs in a drive mapped to their parent folder IDs (or to the
    drive itself if a top-level folder). That is, flatten the entire folder structure.
    """
    folders_in_drive_dict = {}
    page_token = None
    max_allowed_page_size = 1000
    just_folders = "trashed = false and mimeType = 'application/vnd.google-apps.folder'"
    while True:
        results = drive_api_ref.files().list(
            pageSize=max_allowed_page_size,
            fields="nextPageToken, files(id, name, mimeType, parents)",
            includeItemsFromAllDrives=True, supportsAllDrives=True,
            corpora='drive',
            driveId=DRIVE_ID,
            pageToken=page_token,
            q=just_folders).execute()
        folders = results.get('files', [])
        page_token = results.get('nextPageToken', None)
        for folder in folders:
            folders_in_drive_dict[folder['id']] = folder['parents'][0]
        if page_token is None:
            break
    return folders_in_drive_dict


def get_subfolders_of_folder(folder_to_search, all_folders):
    """
    Yield subfolders of the folder-to-search, and then subsubfolders etc. Must be called by an iterator.
    :param all_folders: The dictionary returned by :meth:`get_all_folders_in-drive`.
    """
    temp_list = [k for k, v in all_folders.items() if v == folder_to_search]  # Get all subfolders
    for sub_folder in temp_list:  # For each subfolder...
        yield sub_folder  # Return it
        yield from get_subfolders_of_folder(sub_folder, all_folders)  # Get subsubfolders etc


def get_relevant_files(self, relevant_folders):
    """
    Get files under the folder-to-search and all its subfolders.
    """
    relevant_files = {}
    chunked_relevant_folders_list = [relevant_folders[i:i + MAX_PARENTS] for i in
                                     range(0, len(relevant_folders), MAX_PARENTS)]
    for folder_list in chunked_relevant_folders_list:
        query_term = ' in parents or '.join('"{0}"'.format(f) for f in folder_list) + ' in parents'
        relevant_files.update(get_all_files_in_folders(query_term))
    return relevant_files


def get_all_files_in_folders(self, parent_folders):
    """
    Return a dictionary of file IDs mapped to file names for the specified parent folders.
    """
    files_under_folder_dict = {}
    page_token = None
    max_allowed_page_size = 1000
    just_files = f"mimeType != 'application/vnd.google-apps.folder' and trashed = false and ({parent_folders})"
    while True:
        results = drive_api_ref.files().list(
            pageSize=max_allowed_page_size,
            fields="nextPageToken, files(id, name, mimeType, parents)",
            includeItemsFromAllDrives=True, supportsAllDrives=True,
            corpora='drive',
            driveId=DRIVE_ID,
            pageToken=page_token,
            q=just_files).execute()
        files = results.get('files', [])
        page_token = results.get('nextPageToken', None)
        for file in files:
            files_under_folder_dict[file['id']] = file['name']
        if page_token is None:
            break
    return files_under_folder_dict


if __name__ == "__main__":
    all_folders_dict = get_all_folders_in_drive()  # Flatten folder structure
    relevant_folders_list = [FOLDER_TO_SEARCH]  # Start with the folder-to-archive
    for folder in get_subfolders_of_folder(FOLDER_TO_SEARCH, all_folders_dict):
        relevant_folders_list.append(folder)  # Recursively search for subfolders
    relevant_files_dict = get_relevant_files(relevant_folders_list)  # Get the files