[HF Course] Format Gradio URLs

format_spaces_urls.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "089e4a3f-d26a-4a9f-9813-607dac123d97",
   "metadata": {},
   "outputs": [],
   "source": [
    "import re\n",
    "from tqdm.auto import tqdm\n",
    "import glob"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "418bba43-f18e-4725-961e-24d4d7e95f83",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "3669579ab57544d883a6477590416840",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/629 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "paths = list(glob.glob(\"chapters/**/**/*.mdx\"))\n",
    "\n",
    "for path in tqdm(paths):\n",
    "    with open(path, \"r\") as f:\n",
    "        data = f.read()\n",
    "\n",
    "    for line in data.split(\"\\n\"):\n",
    "        # Skip URLs for images\n",
    "        if \"resolve\" not in line and \"src=\" in line and \"course-demos\" in line:\n",
    "            # Extract Space URLs\n",
    "            old_url = re.findall(r\"(?=src)src=\\\"(?P<src>[^\\\"]+)\", line)\n",
    "            # Skip formatted URLs\n",
    "            if old_url[0].endswith(\".hf.space\"):\n",
    "                continue\n",
    "            old_url_parts = old_url[0].strip(\"/+\").split(\"/\")\n",
    "            # URLs cannot have underscores\n",
    "            space_name = old_url_parts[-1].replace(\"_\", \"-\")\n",
    "            new_url = f\"https://course-demos-{space_name}.hf.space\"\n",
    "            data = data.replace(old_url[0], new_url)\n",
    "\n",
    "    with open(path, \"wt\") as f:\n",
    "        f.write(data)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "hf",
   "language": "python",
   "name": "hf"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}

The new_url can't really be guessed from the Space ID, so a more rigorous approach is to ping

https://huggingface.co/api/spaces/course-demos/{space_id}/host

and extract the real URL from there. For now, I've left the code untouched since the required fixes were easy to handle manually.