stealth-browser

What This Skill Does

The Stealth Browser skill provides advanced web automation capabilities with a strong focus on undetectable browsing. It leverages multiple layers of anti-detection techniques to mimic human user behavior, making it ideal for tasks where bot detection is a concern. This includes bypassing security measures like Cloudflare challenges, solving CAPTCHAs, maintaining persistent login sessions, and performing operations in a headless (silent) mode. The skill prioritizes a "quiet first" approach, attempting headless operations and only switching to a visible headed mode when necessary, such as during manual login or for CAPTCHA solving. It also includes features for session persistence, allowing you to log in once and reuse that session for future automated tasks, significantly streamlining workflows. For long-running tasks, it supports breakpoint resumption via the task_runner.py script, ensuring progress is saved and retries are handled gracefully. The architecture incorporates anti-detection engines, challenge bypass mechanisms, session management, and proxy integration.

Installation

To install the Stealth Browser skill, use the following command:

clawhub install openclaw/skills/skills/mayuqi-crypto/stealth-browser

Core Dependencies (Manual Installation if needed):

npm install -g puppeteer-extra puppeteer-extra-plugin-stealth
npm install -g playwright
pip install undetected-chromedriver DrissionPage

Optional: CAPTCHA Solvers

For CAPTCHA solving, ensure you have API keys for services like 2Captcha, Anti-Captcha, or CapSolver. Store these keys in ~/.clawdbot/secrets/captcha.json:

{
  "2captcha": "YOUR_2CAPTCHA_KEY",
  "anticaptcha": "YOUR_ANTICAPTCHA_KEY",
  "capsolver": "YOUR_CAPSOLVER_KEY"
}

Optional: Proxy Configuration

While not explicitly detailed in the setup, the skill is designed to integrate with proxy services for rotating IP addresses and enhancing anonymity.

Use Cases

• Automated Web Scraping: Scrape data from websites that employ bot detection or Cloudflare protection.
• Account Management: Automate repetitive tasks like logging into websites, managing profiles, or performing actions that require a persistent session.
• Form Filling: Fill out complex web forms that might have anti-bot measures.
• Testing: Test website security and user flows without triggering alarms.
• Data Collection: Gather information from multiple sources reliably, even from challenging sites.
• Cross-Browser Testing: Emulate different browser environments for testing purposes.

Example Prompts

• "Silently browse to example.com and log in using my saved credentials."
• "Solve the CAPTCHA on this page and continue the automation."
• "Automate the process of checking my account balance on mybank.com, ensuring my session remains active."

Tips & Limitations

• Headed Mode for Login: Remember that initial logins often require headed mode for manual intervention. Once logged in, the session can be saved for future headless use. Use the -s sitename argument to manage sessions for different sites. For example, python scripts/stealth_session.py -u "https://target.com/login" -s sitename --headed.
• Session Management: Sessions are stored in ~/.clawdbot/browser-sessions/<sitename>.json. Ensure these files are kept secure.
• Task Runner: For long tasks, utilize task_runner.py to manage progress and ensure recovery from interruptions. task = TaskRunner('my_task'), task.set_total(100), task.mark_completed(i).
• Timeouts: Be aware of default single-page timeouts (30 seconds) and configure longer timeouts for slower operations if needed.
• CAPTCHA Solving Costs: Utilizing CAPTCHA solving services incurs costs. Ensure your API keys are correctly configured and funded.
• Ethical Use: This tool is powerful and should be used ethically and in compliance with website terms of service.
• Proxy Reliability: The effectiveness of anti-detection heavily relies on the quality and rotation of proxies. Poor proxies can still lead to detection.