From 5b4d53e8efca88ccc89ee10af3fdc0066efe1afb Mon Sep 17 00:00:00 2001
From: Jasper <37783831+jagilley@users.noreply.github.com>
Date: Mon, 17 Jul 2023 17:02:19 -0700
Subject: [PATCH] Add text_content kwarg to BrowserlessLoader (#7856)
Added keyword argument to toggle between getting the text content of a
site versus its HTML when using the `BrowserlessLoader`
---
.../integrations/browserless.ipynb | 43 ++++++++++----
langchain/document_loaders/browserless.py | 58 ++++++++++++++-----
2 files changed, 75 insertions(+), 26 deletions(-)
diff --git a/docs/extras/modules/data_connection/document_loaders/integrations/browserless.ipynb b/docs/extras/modules/data_connection/document_loaders/integrations/browserless.ipynb
index dc90b998a42..382a60533cd 100644
--- a/docs/extras/modules/data_connection/document_loaders/integrations/browserless.ipynb
+++ b/docs/extras/modules/data_connection/document_loaders/integrations/browserless.ipynb
@@ -5,12 +5,16 @@
"cell_type": "markdown",
"metadata": {},
"source": [
- "# Browserless"
+ "# Browserless\n",
+ "\n",
+ "Browserless is a service that allows you to run headless Chrome instances in the cloud. It's a great way to run browser-based automation at scale without having to worry about managing your own infrastructure.\n",
+ "\n",
+ "To use Browserless as a document loader, initialize a `BrowserlessLoader` instance as shown in this notebook. Note that by default, `BrowserlessLoader` returns the `innerText` of the page's `body` element. To disable this and get the raw HTML, set `text_content` to `False`."
]
},
{
"cell_type": "code",
- "execution_count": 1,
+ "execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
@@ -19,26 +23,44 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
- "BROWSERLESS_API_TOKEN = \"YOUR_API_TOKEN\""
+ "BROWSERLESS_API_TOKEN = \"YOUR_BROWSERLESS_API_TOKEN\""
]
},
{
"cell_type": "code",
- "execution_count": 2,
+ "execution_count": 14,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "\n",
- "\n",
- "Document classification - Wikipedia\n",
- "