langchain/docs/extras/modules/data_connection/document_loaders/integrations/xml.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "22a849cc",
   "metadata": {},
   "source": [
    "# XML\n",
    "\n",
    "The `UnstructuredXMLLoader` is used to load `XML` files. The loader works with `.xml` files. The page content will be the text extracted from the XML tags."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "e6616e3a",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.document_loaders import UnstructuredXMLLoader"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "a654e4d9",
   "metadata": {},
   "outputs": [
    {
      "data": {
        "text/plain": [
          "Document(page_content='United States\\n\\nWashington, DC\\n\\nJoe Biden\\n\\nBaseball\\n\\nCanada\\n\\nOttawa\\n\\nJustin Trudeau\\n\\nHockey\\n\\nFrance\\n\\nParis\\n\\nEmmanuel Macron\\n\\nSoccer\\n\\nTrinidad & Tobado\\n\\nPort of Spain\\n\\nKeith Rowley\\n\\nTrack & Field', metadata={'source': 'example_data/factbook.xml'})"
        ]
      },
      "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
    }
   ],
   "source": [
    "loader = UnstructuredXMLLoader(\n",
    "    \"example_data/factbook.xml\",\n",
    ")\n",
    "docs = loader.load()\n",
    "docs[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a54342bb",
   "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": "3.8.15"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}