Files
langchain/docs/docs/integrations/document_loaders/xml.ipynb
2024-07-01 13:36:48 -07:00

60 lines
1.2 KiB
Plaintext

{
"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_community.document_loaders import UnstructuredXMLLoader\n",
"\n",
"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
}