google drive cleanup.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# !pip install tqdm pydrive joblib"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pydrive.auth import GoogleAuth\n",
    "from pydrive.drive import GoogleDrive\n",
    "from google.colab import auth\n",
    "from oauth2client.client import GoogleCredentials\n",
    "\n",
    "from tqdm import tqdm\n",
    "\n",
    "#For local usage\n",
    "gauth = GoogleAuth()\n",
    "gauth.LocalWebserverAuth() # client_secrets.json need to be in the same directory as the script\n",
    "drive = GoogleDrive(gauth)\n",
    "\n",
    "#For google colab usage\n",
    "# auth.authenticate_user()\n",
    "# gauth = GoogleAuth()\n",
    "# gauth.credentials = GoogleCredentials.get_application_default()\n",
    "# drive = GoogleDrive(gauth)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Get files by filter logic"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# https://developers.google.com/drive/api/v2/search-files#python\n",
    "fileList = drive.ListFile({'q': \"title contains '.pkl' and trashed=false\"}).GetList()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(len(fileList))\n",
    "fileList[0]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Unparallel"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "for file in tqdm(fileList):\n",
    "    file.Delete() # Permanently delete the file."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Parallel"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from joblib import Parallel, delayed\n",
    "\n",
    "def delete_file(file):\n",
    "    file.Delete() \n",
    "\n",
    "Parallel(n_jobs=4)(delayed(delete_file)(i) for i in fileList)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}