Playwright Stealth Scraper for Openclaw

A high-performance MCP skill for Openclaw Skills that bypasses sophisticated anti-bot measures using Playwright Extra and the Stealth plugin.

3coco3
v1.0.0
Mar 6, 2026
1
6.4k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install playwright-scraper

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install playwright-scraper using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is Playwright Stealth Scraper?

The Playwright Stealth Scraper is a specialized MCP skill designed to empower AI agents with the ability to navigate and extract data from the modern web. Built for the Openclaw Skills ecosystem, it utilizes Playwright Extra and the puppeteer-extra-plugin-stealth to effectively mimic human browser behavior, allowing agents to access content that is typically protected by anti-scraping technologies.

This skill is particularly effective for scraping Single Page Applications (SPAs) and React-based websites that require full JavaScript execution to display content. By masking the automated nature of the browser, it ensures reliable data retrieval for complex research and automation tasks.

Playwright Stealth Scraper Use Cases

  • Accessing and scraping data from websites protected by Cloudflare or other advanced bot detection systems.
  • Extracting content from dynamic, JavaScript-rendered web applications like React, Vue, or Angular sites.
  • Automating market intelligence and competitor data collection within the Openclaw Skills framework.
  • Conducting deep-web research where standard HTTP requests are blocked or restricted.

How Playwright Stealth Scraper Works

  1. The AI agent triggers the stealth_scrape tool by providing a target website URL.
  2. The skill launches a Chromium instance managed by Playwright Extra.
  3. The Stealth plugin is applied to the browser instance to spoof fingerprints and hide automation signals.
  4. The browser navigates to the URL, executing all necessary JavaScript to render the page fully.
  5. The rendered HTML content is captured and returned to the Openclaw Skills environment for analysis.

Playwright Stealth Scraper Setup

To install and configure this skill, ensure you have Playwright and Chromium installed in your local skill directory:

# Install dependencies
npm install playwright-extra puppeteer-extra-plugin-stealth

# Install the Chromium browser
npx playwright install chromium

Playwright Stealth Scraper Data Schema & Taxonomy

The skill returns data in a structured format suitable for AI consumption:

Property Description Type
url The target URL that was processed String
content The full rendered HTML or text content of the page String
status Success or failure indicator of the scrape operation Boolean

Playwright Stealth Scraper Advanced Features

  • Stealth Mode: Leverages puppeteer-extra-plugin-stealth to bypass common bot detection hurdles.
  • Dynamic Content Support: Full JavaScript execution ensures data from modern web frameworks is captured.
  • User-Agent Spoofing: Automatically rotates or mimics standard browser User-Agents for better anonymity.
  • Custom Viewport: Ability to configure window dimensions to emulate various device types within Openclaw Skills.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*