mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-05 21:12:48 +00:00
feat: adds UnstructuredURLLoader
for loading data from urls (#979)
### Summary Adds a `UnstructuredURLLoader` that supports loading data from a list of URLs. ### Testing ```python from langchain.document_loaders import UnstructuredURLLoader urls = [ "https://www.understandingwar.org/backgrounder/russian-offensive-campaign-assessment-february-8-2023", "https://www.understandingwar.org/backgrounder/russian-offensive-campaign-assessment-february-9-2023" ] loader = UnstructuredURLLoader(urls=urls) raw_documents = loader.load() ```
This commit is contained in:
78
docs/modules/document_loaders/examples/url.ipynb
Normal file
78
docs/modules/document_loaders/examples/url.ipynb
Normal file
@@ -0,0 +1,78 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "2dfc4698",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# URL\n",
|
||||
"\n",
|
||||
"This covers how to load HTML documents from a list of URLs into a document format that we can use downstream."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "16c3699e",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
" from langchain.document_loaders import UnstructuredURLLoader"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "836fbac1",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"urls = [\n",
|
||||
" \"https://www.understandingwar.org/backgrounder/russian-offensive-campaign-assessment-february-8-2023\",\n",
|
||||
" \"https://www.understandingwar.org/backgrounder/russian-offensive-campaign-assessment-february-9-2023\"\n",
|
||||
"]\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "00f46fda",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"loader = UnstructuredURLLoader(urls=urls)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "b68a26b3",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"data = loader.load()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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": "3.8.13"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
Reference in New Issue
Block a user