langchain/docs/docs/how_to/document_loader_html.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "0c6c50fc-15e1-4767-925a-53a37c430b9b",
   "metadata": {},
   "source": [
    "# How to load HTML\n",
    "\n",
    "The HyperText Markup Language or [HTML](https://en.wikipedia.org/wiki/HTML) is the standard markup language for documents designed to be displayed in a web browser.\n",
    "\n",
    "This covers how to load `HTML` documents into a LangChain [Document](https://python.langchain.com/api_reference/core/documents/langchain_core.documents.base.Document.html#langchain_core.documents.base.Document) objects that we can use downstream.\n",
    "\n",
    "Parsing HTML files often requires specialized tools. Here we demonstrate parsing via [Unstructured](https://unstructured-io.github.io/unstructured/) and [BeautifulSoup4](https://beautiful-soup-4.readthedocs.io/en/latest/), which can be installed via pip. Head over to the integrations page to find integrations with additional services, such as [Azure AI Document Intelligence](/docs/integrations/document_loaders/azure_document_intelligence) or [FireCrawl](/docs/integrations/document_loaders/firecrawl).\n",
    "\n",
    "## Loading HTML with Unstructured"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "617a5e2b-1e92-4bdd-bd04-95a4d2379410",
   "metadata": {},
   "outputs": [],
   "source": [
    "%pip install unstructured"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "7d167ca3-c7c7-4ef0-b509-080629f0f482",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[Document(page_content='My First Heading\\n\\nMy first paragraph.', metadata={'source': '../../docs/integrations/document_loaders/example_data/fake-content.html'})]\n"
     ]
    }
   ],
   "source": [
    "from langchain_community.document_loaders import UnstructuredHTMLLoader\n",
    "\n",
    "file_path = \"../../docs/integrations/document_loaders/example_data/fake-content.html\"\n",
    "\n",
    "loader = UnstructuredHTMLLoader(file_path)\n",
    "data = loader.load()\n",
    "\n",
    "print(data)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cc85f7e8-f62e-49bc-910e-d0b151c9d651",
   "metadata": {},
   "source": [
    "## Loading HTML with BeautifulSoup4\n",
    "\n",
    "We can also use `BeautifulSoup4` to load HTML documents using the `BSHTMLLoader`.  This will extract the text from the HTML into `page_content`, and the page title as `title` into `metadata`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "06a5e555-8e1f-44a7-b921-4dd8aedd3bca",
   "metadata": {},
   "outputs": [],
   "source": [
    "%pip install bs4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "0a2050a8-6df6-4696-9889-ba367d6f9caa",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[Document(page_content='\\nTest Title\\n\\n\\nMy First Heading\\nMy first paragraph.\\n\\n\\n', metadata={'source': '../../docs/integrations/document_loaders/example_data/fake-content.html', 'title': 'Test Title'})]\n"
     ]
    }
   ],
   "source": [
    "from langchain_community.document_loaders import BSHTMLLoader\n",
    "\n",
    "loader = BSHTMLLoader(file_path)\n",
    "data = loader.load()\n",
    "\n",
    "print(data)"
   ]
  }
 ],
 "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": "3.10.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}