Generating file structure from filenames using Google Drive API and Python

I have a bunch of files sat in a Google Drive folder whose filenames contains information regarding the desired folder/subfolder structure:

[folder~subfolder] MyFile.ext

Some files simply read:

[folder] MyOtherFile.ext

I am looking for a way to sort the files into the desired file structure using thr Google Drive API, creating the folders/subfolders if they do not already exist.

This is what I have so far:

import os
from google.oauth2.credentials import Credentials
from googleapiclient.discovery import build
from googleapiclient.errors import HttpError
# Set up the Drive API credentials
creds = Credentials.from_authorized_user_file(r"CREDENTIALS_PATH", ['https://www.googleapis.com/auth/drive'])
# Define the name of the Google Drive folder
folder_name = 'FOLDER_CONTAINING_FILES'
# Create a Drive API client
service = build('drive', 'v3', credentials=creds)
# Define the function to parse the subdirectories and sub-subdirectories
def parse_directory(filename):
# Split the filename by '] '
parts = filename.split('] ')
subdirs = []
for part in parts:
# Check if the part is a subdirectory
if '[' in part:
subdir = part[1:]
subdirs.append(subdir)
return subdirs
# Get the list of files in the Google Drive folder
try:
query = "mimeType='application/vnd.google-apps.folder' and trashed = false and name='" + folder_name + "'"
folder = service.files().list(q=query).execute().get('files')[0]
folder_id = folder.get('id')
query = "'" + folder_id + "' in parents and trashed = false and mimeType != 'application/vnd.google-apps.folder'"
files = service.files().list(q=query).execute().get('files')
except HttpError as error:
print(f'An error occurred: {error}')
files = []
# Create dictionaries to store the subdirectories and sub-subdirectories
subdirs_dict = {}
subsubdirs_dict = {}
# Loop through the files and create the subdirectories and sub-subdirectories if necessary
for file in files:
filename = file.get('name')
subdirs = parse_directory(filename)
if len(subdirs) == 0:
continue
parent_id = folder_id
for i in range(len(subdirs)):
subdir = subdirs[i]
if i == len(subdirs) - 1:
subsubdir = ''
else:
subsubdir = subdirs[i+1]
if subdir not in subdirs_dict:
# Create the subdirectory if it doesn't exist
metadata = {'name': subdir, 'parents': [parent_id], 'mimeType': 'application/vnd.google-apps.folder'}
subdir_file = service.files().create(body=metadata, fields='id').execute()
subdirs_dict[subdir] = subdir_file.get('id')
parent_id = subdirs_dict[subdir]
if subsubdir != '':
if subsubdir not in subsubdirs_dict:
# Create the sub-subdirectory if it doesn't exist
metadata = {'name': subsubdir, 'parents': [parent_id], 'mimeType': 'application/vnd.google-apps.folder'}
subsubdir_file = service.files().create(body=metadata, fields='id').execute()
subsubdirs_dict[subsubdir] = subsubdir_file.get('id')
parent_id = subsubdirs_dict[subsubdir]
# Loop through the files and move them to the appropriate subdirectory or sub-subdirectory
for file in files:
filename = file.get('name')
subdirs = parse_directory(filename)
if len(subdirs) == 0:
continue
parent_id = folder_id
for i in range(len(subdirs)):
subdir = subdirs[i]
if i == len(subdirs) - 1:
subsubdir = ''
else:
subsubdir = subdirs[i+1]
if subdir in subdirs_dict:
parent_id = subdirs_dict[subdir]
if subsubdir != '' and subsubdir in subsubdirs_dict:
parent_id = subsubdirs_dict[subsubdir]
metadata = {'name': filename, 'parents': [parent_id]}
service.files().update(fileId=file.get('id'), body=metadata).execute()

At present, my code produces (almost) the correct folders but they are not nested properly. For example, for these input files:

[0_diss] good_journals.txt
[0_diss~historic_disses] Zhang (2020) - NAV premia.pdf
[0_diss~literature] A Guide to Writing the Literature Review.pdf

The script produces the following folders:

0_diss
0_diss~historic_disses
0_diss~literature

What I want is for folders entitled '0_diss', 'historic_disses', and 'literature' to be created (if they do not already exist) and for 'historic_disses' and 'literature' to be a subfolder of '0_diss'. I hope this makes more sense.

Would really appreciate some help on this one, I'm not an experienced programmer and am trying my best to learn Python. Thanks.

This answer assumes there can only be one ~ because that's the data and examples you provided. You can parse directories like this:

from typing import Optional
import re
def parse_directories(filename: str) -> Optional[dict]:
dirs = {}
# Make sure we have a supported file name, match anything not ]~ into group 1
# Then optionally match anything not ] after ~ into group 2 
match = re.search('^\[([^\]~]+)~?([^\]]+)?\]', filename)
# If anything was matched, assign always available parent, else return null
if (not match):
return None
dirs['parent'] = match.group(1)
# If child was found, assign it too
if (match.group(2)):
dirs['child'] = match.group(2)
return dirs

Then use just one loop to create new directories and move the files into them:

for filename in filenames:
newdirs = parse_directories(filename)
if newdirs:
if 'child' in newdirs:
# Create your child folder
# To verify if it's been already made simply store paths as a list
else:
# Create newdirs['parent'] if needed
# Move the file to the new/already existing folder, you don't need a 2nd loop

This should get you on the right track.