LaunchKit · 2026
Back to Skills

playwright-scraper-skill

Playwright-based web scraping OpenClaw Skill with anti-bot protection.

38
17.1k downloads
by @waisimon

Setup & Installation

openclaw skills install @waisimon/playwright-scraper-skill

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install playwright-scraper-skill

What This Skill Does

Playwright-based scraper with three tiers of anti-bot handling. Covers static pages via built-in fetch, JavaScript-rendered pages via standard Playwright, and Cloudflare-protected sites via a stealth mode that masks automation markers and mimics real device behavior.

Playwright Stealth achieved 100% success on Cloudflare-protected sites where Crawlee, standard Puppeteer, and Rust-based alternatives all failed with 0-20% success rates.

When to use it

  • Scraping content from Cloudflare-protected forums
  • Extracting data from JavaScript-rendered e-commerce pages
  • Monitoring dynamic news sites that block standard crawlers
  • Saving HTML snapshots of pages requiring JS execution
  • Collecting structured data from community discussion boards

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: scrape the top posts from https://m.discuss.com.hk/#hot

AGENT
  1. 1Identifies the site uses Cloudflare anti-bot protection
  2. 2Selects playwright-stealth.js as the appropriate script
  3. 3Runs the script with the target URL
  4. 4Script sets a realistic mobile User-Agent, hides webdriver markers, and adds random delays to mimic human behavior
  5. 5Returns JSON with page title and content, saves screenshot.png and page.html locally
OUTPUT

JSON object with url, title, and content fields, plus screenshot and HTML file saved to disk

Requirements

Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.

Playwright Chromium browser (installed via npx playwright install chromium)