{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "5a7cc773",
   "metadata": {},
   "source": [
    "# Recursive URL Loader\n",
    "\n",
    "We may want to process load all URLs under a root directory.\n",
    "\n",
    "For example, let's look at the [LangChain JS documentation](https://js.langchain.com/docs/).\n",
    "\n",
    "This has many interesting child pages that we may want to read in bulk.\n",
    "\n",
    "Of course, the `WebBaseLoader` can load a list of pages. \n",
    "\n",
    "But, the challenge is traversing the tree of child pages and actually assembling that list!\n",
    " \n",
    "We do this using the `RecursiveUrlLoader`.\n",
    "\n",
    "This also gives us the flexibility to exclude some children (e.g., the `api` directory with > 800 child pages)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "2e3532b2",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.document_loaders.recursive_url_loader import RecursiveUrlLoader"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6384c057",
   "metadata": {},
   "source": [
    "Let's try a simple example."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "d69e5620",
   "metadata": {},
   "outputs": [],
   "source": [
    "url = \"https://js.langchain.com/docs/modules/memory/examples/\"\n",
    "loader = RecursiveUrlLoader(url=url)\n",
    "docs = loader.load()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "084fb2ce",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "12"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(docs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "89355b7c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'\\n\\n\\n\\n\\nBuffer Window Memory | 🦜️🔗 Langchain\\n\\n\\n\\n\\n\\nSki'"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "docs[0].page_content[:50]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "13bd7e16",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'source': 'https://js.langchain.com/docs/modules/memory/examples/buffer_window_memory',\n",
       " 'title': 'Buffer Window Memory | 🦜️🔗 Langchain',\n",
       " 'description': 'BufferWindowMemory keeps track of the back-and-forths in conversation, and then uses a window of size k to surface the last k back-and-forths to use as memory.',\n",
       " 'language': 'en'}"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "docs[0].metadata"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "40fc13ef",
   "metadata": {},
   "source": [
    "Now, let's try a more extensive example, the `docs` root dir.\n",
    "\n",
    "We will skip everything under `api`.\n",
    "\n",
    "For this, we can `lazy_load`  each page as we crawl the tree, using `WebBaseLoader` to load each as we go."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5c938b9f",
   "metadata": {},
   "outputs": [],
   "source": [
    "url = \"https://js.langchain.com/docs/\"\n",
    "exclude_dirs = [\"https://js.langchain.com/docs/api/\"]\n",
    "loader = RecursiveUrlLoader(url=url, exclude_dirs=exclude_dirs)\n",
    "# Lazy load each\n",
    "docs = [print(doc) or doc for doc in loader.lazy_load()]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "30ff61d3",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load all pages\n",
    "docs = loader.load()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "457e30f3",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "188"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(docs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "bca80b4a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'\\n\\n\\n\\n\\nAgent Simulations | 🦜️🔗 Langchain\\n\\n\\n\\n\\n\\nSkip t'"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "docs[0].page_content[:50]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "df97cf22",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'source': 'https://js.langchain.com/docs/use_cases/agent_simulations/',\n",
       " 'title': 'Agent Simulations | 🦜️🔗 Langchain',\n",
       " 'description': 'Agent simulations involve taking multiple agents and having them interact with each other.',\n",
       " 'language': 'en'}"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "docs[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": "3.9.16"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}