Counting files of a given extension in a given directory and all subdirectories

count-files.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Total number of .pdf files: 8798\n"
     ]
    }
   ],
   "source": [
    "import os\n",
    "import time\n",
    "from IPython.display import clear_output\n",
    "\n",
    "def count_files(dir, extension=None, verbose=True):\n",
    "    total_files = 0\n",
    "    iteration = 0\n",
    "    for root, dirs, files in os.walk(dir):\n",
    "        iteration += 1\n",
    "        if extension:\n",
    "            filtered_files = [f for f in files if f.lower().endswith(extension.lower())]\n",
    "            if verbose and len(filtered_files)>0:\n",
    "                if iteration % 10 == 0:\n",
    "                    clear_output(wait=True) \n",
    "                print(f\"{len(filtered_files)} {extension} files in {root}\")\n",
    "            total_files += len(filtered_files)\n",
    "        else:\n",
    "            if verbose: print(f\"{len(files)} files in {root}\")\n",
    "            total_files += len(files)\n",
    "\n",
    "    return total_files\n",
    "\n",
    "extension = '.pdf'\n",
    "dir='C:/'\n",
    "total_files = count_files(dir=dir, extension=extension, verbose=True)\n",
    "\n",
    "clear_output(wait=True)\n",
    "time.sleep(1)\n",
    "print(f\"Total number of {extension} files: {total_files}\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "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": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}