This project provides a command-line interface (CLI) tool for bypassing various CAPTCHA types, including text, complex text, puzzle, and reCAPTCHA, by leveraging GPT-4o and Selenium. It is designed for developers and researchers interested in automated CAPTCHA solving and testing.

How It Works

The tool automates browser interactions using Selenium and Firefox, capturing CAPTCHA images. These images are then uploaded to Imgur for hosting, and the image URLs are passed to the OpenAI GPT-4o API for analysis and solution generation. The generated solution is then submitted back to the CAPTCHA interface.

Quick Start & Requirements

• Install: pip install -r requirements.txt
• Prerequisites: Python 3.7+, Firefox Browser, Imgur Account, OpenAI Account.
• Setup: Requires creating a .env file with OPENAI_API_KEY and IMGUR_CLIENT_ID. Geckodriver for Firefox must be installed (via webdriver-manager).
• Usage: python main.py [captcha_type] (e.g., python main.py text).
• Documentation: https://github.com/aydinnyunus/gpt4-captcha-bypass

Highlighted Details

• Supports text, complicated text, puzzle, and reCAPTCHA (including slider variations).
• Claims reCAPTCHA and slider bypass in an average of 10 attempts.
• Utilizes GPT-4o for CAPTCHA solving.

Maintenance & Community

No specific community channels or roadmap are mentioned in the README.

Licensing & Compatibility

The repository does not explicitly state a license.

Limitations & Caveats

The project relies on external services (OpenAI API, Imgur) which incur costs and may have rate limits. The effectiveness against evolving CAPTCHA systems is not detailed.