Overview
This node automates browser tasks using Amazon Bedrock AgentCore Browser and Playwright. It supports running custom Playwright scripts on a specified URL, executing browser tasks from natural language instructions, and navigating to a URL to extract data. It is useful for scenarios like web scraping, automated testing, and data extraction from web pages. For example, users can run a script to get the page title, perform searches on e-commerce sites, or extract specific content from web pages.
Use Case Examples
- Run a custom Playwright script to retrieve the page title.
- Navigate to amazon.com, search for wireless headphones, and extract the top 3 product names and prices.
- Navigate to a URL and extract text or HTML content from specified selectors.
Properties
| Name | Meaning |
|---|---|
| Authentication | Selects the authentication method to use, either standard AWS credentials or custom AgentCore Browser API credentials. |
| Browser Tool ARN | The Amazon Resource Name (ARN) of the AgentCore Browser tool to use for the session. |
| Start URL | The URL to navigate to at the start of the browser session. |
| Timeout (ms) | Maximum time in milliseconds to wait for the operation to complete. |
| Script | JavaScript/TypeScript code to execute in the browser context. The 'page' object is available for Playwright commands. |
| Screenshot Mode | Determines when to capture screenshots during script execution: none, final page, or on error only. |
Output
Binary
Screenshot image data in PNG format if screenshots are captured.
JSON
result- The result object returned from the executed Playwright script.sessionInfobrowserId- Identifier of the browser instance used in the session.sessionId- Identifier of the browser session.
screenshot- Binary data of the screenshot image if captured.
Dependencies
- Amazon Bedrock AgentCore Browser service
- Playwright library
Troubleshooting
- Ensure valid AWS or AgentCore Browser API credentials are provided to avoid authentication errors.
- Timeout errors may occur if the page takes too long to load; increase the Timeout (ms) parameter if needed.
- Script errors may occur if the provided JavaScript code is invalid or references unavailable objects; verify the script syntax and usage of the 'page' object.
- Screenshot capture may fail if the page is not fully loaded or if permissions are restricted; adjust screenshot mode or page load conditions.
Links
- Playwright Documentation - Official documentation for Playwright, the browser automation library used in the node.
- Amazon Bedrock AgentCore Browser - Information about the Amazon Bedrock AgentCore Browser service used for browser automation.