{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "import subprocess\n",
    "from pathlib import Path\n",
    "import re\n",
    "\n",
    "from tqdm import tqdm\n",
    "\n",
    "import pipeline.videos as videos"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 1/1 [00:02<00:00,  2.37s/it]\n"
     ]
    }
   ],
   "source": [
    "VIDEO_DIR = Path(\"videos\")\n",
    "VIDEO_DIR.mkdir(exist_ok=True)\n",
    "(VIDEO_DIR / \".gitingore\").write_text(\"**\")\n",
    "\n",
    "video_urls = [\"https://www.youtube.com/watch?v=frYIj2FGmMA&foo=bar\"]\n",
    "\n",
    "\n",
    "def get_id(url: str) -> str:\n",
    "    return re.search(r\"(?<=v=)[^&]+\", url).group(0)\n",
    "\n",
    "\n",
    "for video_url in tqdm(video_urls):\n",
    "    video_id = get_id(video_url)\n",
    "    video_path = VIDEO_DIR / f\"{video_id}.mp4\"\n",
    "    if video_path.exists():\n",
    "        print(f\"Skipping {video_path} because it already exists\")\n",
    "        continue\n",
    "    subprocess.run([\"yt-dlp\", \"--quiet\", \"-f\", \"133\", \"-o\", str(video_path), video_url])\n",
    "\n",
    "# get_id(video_urls[0])\n",
    "# # !yt-dlp -f 133 -o \"buster.mp4\" {video_url}\n",
    "# def download_video(video_url: str) -> None:\n",
    "#     subprocess.run(['yt-dlp', '-f', '133', '-o', 'buster.mp4', video_url])"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "semvideo-hackathon-230523",
   "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": "3.9.16"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}