mirror of
https://github.com/hwchase17/langchain
synced 2024-10-29 17:07:25 +00:00
e4cfaa5680
### Summary
This PR introduces a `SeleniumURLLoader` which, similar to
`UnstructuredURLLoader`, loads data from URLs. However, it utilizes
`selenium` to fetch page content, enabling it to work with
JavaScript-rendered pages. The `unstructured` library is also employed
for loading the HTML content.
### Testing
```bash
pip install selenium
pip install unstructured
```
```python
from langchain.document_loaders import SeleniumURLLoader
urls = [
"https://www.youtube.com/watch?v=dQw4w9WgXcQ",
"https://goo.gl/maps/NDSHwePEyaHMFGwh8"
]
loader = SeleniumURLLoader(urls=urls)
data = loader.load()
```
139 lines
2.9 KiB
Plaintext
139 lines
2.9 KiB
Plaintext
{
|
|
"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()"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"id": "f3afa135",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Selenium URL Loader\n",
|
|
"\n",
|
|
"This covers how to load HTML documents from a list of URLs using the `SeleniumURLLoader`.\n",
|
|
"\n",
|
|
"Using selenium allows us to load pages that require JavaScript to render.\n",
|
|
"\n",
|
|
"## Setup\n",
|
|
"\n",
|
|
"To use the `SeleniumURLLoader`, you will need to install `selenium` and `unstructured`.\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "5fc50835",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.document_loaders import SeleniumURLLoader"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "24e896ce",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"urls = [\n",
|
|
" \"https://www.youtube.com/watch?v=dQw4w9WgXcQ\",\n",
|
|
" \"https://goo.gl/maps/NDSHwePEyaHMFGwh8\"\n",
|
|
"]"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "60a29397",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"loader = SeleniumURLLoader(urls=urls)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "0090cd57",
|
|
"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
|
|
}
|