mirror of
https://github.com/hwchase17/langchain
synced 2024-10-31 15:20:26 +00:00
82 lines
2.4 KiB
Plaintext
82 lines
2.4 KiB
Plaintext
|
{
|
||
|
|
"cells": [
|
||
|
|
{
|
||
|
|
"attachments": {},
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"# Browserless"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 1,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"from langchain.document_loaders import BrowserlessLoader"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": null,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"BROWSERLESS_API_TOKEN = \"YOUR_API_TOKEN\""
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 2,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"<!DOCTYPE html><html class=\"client-js vector-feature-language-in-header-enabled vector-feature-language-in-main-page-header-disabled vector-feature-sticky-header-disabled vector-feature-page-tools-pinned-disabled vector-feature-toc-pinned-enabled vector-feature-main-menu-pinned-disabled vector-feature-limited-width-enabled vector-feature-limited-width-content-enabled vector-feature-zebra-design-disabled\" lang=\"en\" dir=\"ltr\"><head>\n",
|
||
|
|
"<meta charset=\"UTF-8\">\n",
|
||
|
|
"<title>Document classification - Wikipedia</title>\n",
|
||
|
|
"<script>document.documentElement.className=\"client-js vector-feature-language-in-header-enabled vector-feature-language-in-main-page-header-disabled vector-feature-sticky-header-disabled vector-feature-page-tools-pinned-disabled vector-feature-toc-pinned-enabled vector-feature-main-menu-pinned-disabled vector-feature-limited-width-enabled vector-feature-limited-width-content-enabled vector-feature-zebra-design-disabled\";(function(){var cookie=document.cookie.match(/(?:^|; )enwikimwclien\n"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"loader = BrowserlessLoader(\n",
|
||
|
|
" api_token=BROWSERLESS_API_TOKEN,\n",
|
||
|
|
" urls=[\n",
|
||
|
|
" \"https://en.wikipedia.org/wiki/Document_classification\",\n",
|
||
|
|
" ],\n",
|
||
|
|
")\n",
|
||
|
|
"\n",
|
||
|
|
"documents = loader.load()\n",
|
||
|
|
"\n",
|
||
|
|
"print(documents[0].page_content[:1000])"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"kernelspec": {
|
||
|
|
"display_name": "venv",
|
||
|
|
"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": "3.11.1"
|
||
|
|
},
|
||
|
|
"orig_nbformat": 4
|
||
|
|
},
|
||
|
|
"nbformat": 4,
|
||
|
|
"nbformat_minor": 2
|
||
|
|
}
|