{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "621c09fe",
   "metadata": {},
   "outputs": [],
   "source": [
    "from bs4 import BeautifulSoup\n",
    "import pandas as pd\n",
    "\n",
    "# Read HTML content from the file\n",
    "with open(\"index.html\", \"r\", encoding=\"utf-8\") as file:\n",
    "    html_content = file.read()\n",
    "\n",
    "# Parse the HTML content\n",
    "soup = BeautifulSoup(html_content, \"html.parser\")\n",
    "\n",
    "# Find the table\n",
    "table = soup.find(\"table\")\n",
    "\n",
    "# Extract table data\n",
    "if table:\n",
    "    rows = table.find_all(\"tr\")\n",
    "    data = []\n",
    "    for row in rows:\n",
    "        columns = row.find_all(\"td\")\n",
    "        if columns:  # Ensure it's not a header row or empty row\n",
    "            row_data = [column.text.strip() for column in columns]\n",
    "            data.append(row_data)\n",
    "    # Create DataFrame\n",
    "    df = pd.DataFrame(data)\n",
    "    \n",
    "    # Extract first part and last word from the first column\n",
    "    df['Name'] = df[0].str.split().str[:-1].str.join(\" \")\n",
    "    df['Ticker'] = df[0].str.split().str[-1]\n",
    "    df[['Name', 'Ticker']].to_csv(\"Company List.csv\")\n",
    "else:\n",
    "    print(\"Table not found in the HTML content.\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "38efd2c9",
   "metadata": {},
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'c' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[1], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[43mc\u001b[49m)\n",
      "\u001b[0;31mNameError\u001b[0m: name 'c' is not defined"
     ]
    }
   ],
   "source": [
    "print(c)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6c185203",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.10.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}