This project is a CLI tool for testing various types of captchas including puzzle, text, complicated text, and reCAPTCHA using Python and Selenium. The tool also uses OpenAI GPT-4 to help solve the captchas.
- Python 3.7+
- Firefox Browser
- Imgur Account for uploading images
- OpenAI Account for GPT-4 API
-
Clone the repository:
git clone https://github.com/aydinnyunus/gpt4-captcha-bypass cd gpt4-captcha-bypass
-
Install the required Python packages:
pip install -r requirements.txt
-
Create a
.env
file in the root directory of your project and add your Imgur Client ID and OpenAI API Key:echo "OPENAI_API_KEY=sk-your-openai-api-key" > .env echo "IMGUR_CLIENT_ID=your-imgur-client-id" >> .env
-
Make sure you have the
geckodriver
for Firefox installed. You can install it usingwebdriver-manager
:pip install webdriver-manager
Run the CLI tool with the desired captcha type:
python main.py [captcha_type]
where [captcha_type]
can be one of: puzzle
, text
, complicated_text
, recaptcha
.
Example:
python main.py text
text
: Tests simple text captchas.complicated_text
: Tests complicated text captchas.recaptcha
: Tests Google's reCAPTCHA.puzzle
: Tests puzzle captchas.
Recaptcha and Slider may be bypassed in average 10 attempts.