{
 "cells": [
  {
   "cell_type": "code",
   "id": "a49a961ef9dafc8b",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-06-10T15:26:54.606280Z",
     "start_time": "2025-06-10T15:26:54.499875Z"
    }
   },
   "source": "from langchain_community.document_loaders import UnstructuredExcelLoader",
   "outputs": [],
   "execution_count": 3
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-06-10T15:26:54.806898Z",
     "start_time": "2025-06-10T15:26:54.804638Z"
    }
   },
   "cell_type": "code",
   "source": "file_dir = 'files/7bd855d8-463d-4ed5-93ca-5fe35145f733.xlsx'",
   "id": "7f1454e97563e93",
   "outputs": [],
   "execution_count": 4
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-06-10T15:29:12.643058Z",
     "start_time": "2025-06-10T15:29:12.625239Z"
    }
   },
   "cell_type": "code",
   "source": [
    "\n",
    "loader = UnstructuredExcelLoader(file_dir, mode=\"elements\")\n",
    "docs = loader.load()\n",
    "\n",
    "print(len(docs))\n",
    "\n",
    "# docs"
   ],
   "id": "initial_id",
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1\n"
     ]
    }
   ],
   "execution_count": 7
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-06-10T15:32:40.555855Z",
     "start_time": "2025-06-10T15:32:40.553019Z"
    }
   },
   "cell_type": "code",
   "source": "print(docs[0].metadata['text_as_html'])",
   "id": "6c69b91ca45b0039",
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<table><tr><td>Location</td><td>Burgers</td><td>Hot Dogs</td><td>Salads</td><td>Fries</td><td>Ice Cream</td><td>Soda</td></tr><tr><td>Pinebrook</td><td>1594</td><td>1999</td><td>2002</td><td>2005</td><td>1977</td><td>1980</td></tr><tr><td>Wharvton</td><td>1983</td><td>2008</td><td>2014</td><td>2015</td><td>2017</td><td>2018</td></tr><tr><td>Sagrada</td><td>2019</td><td>2022</td><td>2022</td><td>2023</td><td>2021</td><td>2019</td></tr><tr><td>Algrimand</td><td>1958</td><td>1971</td><td>1982</td><td>1989</td><td>1998</td><td>2009</td></tr><tr><td>Marztep</td><td>2015</td><td>2016</td><td>2018</td><td>2019</td><td>2021</td><td>2022</td></tr><tr><td>San Cecelia</td><td>2011</td><td>2010</td><td>2012</td><td>2013</td><td>2015</td><td>2016</td></tr><tr><td>Pimento</td><td>2017</td><td>1999</td><td>2001</td><td>2003</td><td>1969</td><td>2967</td></tr><tr><td>Tinseles</td><td>1967</td><td>1969</td><td>1982</td><td>1994</td><td>2005</td><td>2006</td></tr><tr><td>Rosdale</td><td>2007</td><td>2009</td><td>2021</td><td>1989</td><td>2005</td><td>2011</td></tr></table>\n"
     ]
    }
   ],
   "execution_count": 11
  },
  {
   "metadata": {},
   "cell_type": "code",
   "outputs": [],
   "execution_count": null,
   "source": "",
   "id": "29d83c36757726aa"
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}