langchain/docs/modules/indexes/document_loaders/examples/imsdb.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "cc9b809c",
   "metadata": {},
   "source": [
    "# IMSDb\n",
    "\n",
    ">[IMSDb](https://imsdb.com/) is the `Internet Movie Script Database`.\n",
    "\n",
    "This covers how to load `IMSDb` webpages into a document format that we can use downstream."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "9d1f867e",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "from langchain.document_loaders import IMSDbLoader"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "84a32aa1",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "loader = IMSDbLoader(\"https://imsdb.com/scripts/BlacKkKlansman.html\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "8ae5ffe2",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "data = loader.load()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "d41da111",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'\\n\\r\\n\\r\\n\\r\\n\\r\\n                                    BLACKKKLANSMAN\\r\\n                         \\r\\n                         \\r\\n                         \\r\\n                         \\r\\n                                      Written by\\r\\n\\r\\n                          Charlie Wachtel & David Rabinowitz\\r\\n\\r\\n                                         and\\r\\n\\r\\n                              Kevin Willmott & Spike Lee\\r\\n\\r\\n\\r\\n\\r\\n\\r\\n\\r\\n\\r\\n\\r\\n\\r\\n                         FADE IN:\\r\\n                         \\r\\n          SCENE FROM \"GONE WITH'"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data[0].page_content[:500]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "207bc39b",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'source': 'https://imsdb.com/scripts/BlacKkKlansman.html'}"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data[0].metadata"
   ]
  }
 ],
 "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": "3.10.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}