ClawdBot Browser Automation

Give your AI eyes on the web. Automated browsing, scraping, and testing with Puppeteer.

๐ŸŒ Browser Automation Overview

ClawdBot integrates with Puppeteer to control Chrome/Chromium browsers programmatically.

What You Can Do

  • โœ… Browse websites and extract information
  • โœ… Take screenshots and PDFs
  • โœ… Fill forms and submit data
  • โœ… Automate repetitive web tasks
  • โœ… Test web applications
  • โœ… Monitor websites for changes

๐Ÿ”ง Setup

Enable Browser Automation

# In config.yaml
browser:
  enabled: true
  headless: true  # Run without GUI
  
  # Chrome/Chromium path (auto-detected usually)
  executablePath: null
  
  # Launch options
  args:
    - '--no-sandbox'
    - '--disable-setuid-sandbox'

Install Dependencies

# Puppeteer is included with ClawdBot
# But you may need Chrome/Chromium

# macOS
brew install chromium

# Ubuntu/Debian
sudo apt install chromium-browser

# Or let Puppeteer download Chrome
clawdbot browser install-chrome

๐Ÿ’ก Usage Examples

Basic Browsing

You: Go to example.com and tell me what you see
Bot: [Opens browser, navigates, reads content]
Bot: The page shows "Example Domain" with...

Take Screenshot

You: Screenshot github.com
Bot: [Takes screenshot]
Bot: Here's the screenshot: [image]

Extract Information

You: Go to news.ycombinator.com and get top 5 headlines
Bot: [Scrapes page]
Bot: Top stories:
1. New AI breakthrough...
2. Tech company announces...
...

Fill Forms

You: Go to example.com/contact and fill the form with:
Name: John Doe
Email: john@example.com
Message: Hello!

Bot: [Fills form]
Bot: Form filled. Should I submit?

๐Ÿ•ท๏ธ Web Scraping

Scrape Product Prices

You: Check price of iPhone 15 on amazon.com
Bot: [Navigates to Amazon, searches, extracts price]
Bot: iPhone 15 Pro: $999

Monitor Website Changes

# In config.yaml
browser:
  monitors:
    - url: "https://example.com/products"
      selector: ".price"
      interval: 3600  # Check hourly
      notify: true

# ClawdBot will alert you when price changes

Extract Structured Data

You: Go to example.com/products and extract all product names and prices
Bot: [Scrapes page]
Bot: Found 25 products:
- Product A: $29.99
- Product B: $39.99
...

๐Ÿงช Automated Testing

Test Login Flow

You: Test login on myapp.com with test@example.com / password123
Bot: [Navigates, fills form, submits]
Bot: โœ… Login successful
Bot: Redirected to dashboard
Bot: Screenshot: [image]

Check for Broken Links

You: Check all links on example.com
Bot: [Crawls site, tests links]
Bot: Found 3 broken links:
- /old-page (404)
- /missing (404)
- /external-dead (timeout)

Performance Testing

You: Measure page load time for example.com
Bot: [Loads page, measures metrics]
Bot: Load time: 1.2s
Bot: Time to Interactive: 2.1s
Bot: Largest Contentful Paint: 1.8s

โ“ Browser FAQ

Does browser automation work headless?
Yes! Headless mode is default. Set headless: false to see the browser.
Can ClawdBot bypass CAPTCHAs?
No. CAPTCHAs are designed to prevent automation. Some sites may block headless browsers.
Is web scraping legal?
It depends. Check website's robots.txt and terms of service. Respect rate limits.

๐Ÿ“š Related Guides