This project provides an AI-powered script for automatically answering questions in Bilibili's "Hardcore Member Trial" to earn rewards. It targets Bilibili users who have reached level 6 and wish to automate the daily trial process, saving time and effort.

How It Works

The tool directly interacts with Bilibili's API, bypassing OCR for a more robust solution. It leverages Large Language Models (LLMs) to intelligently answer questions. Users can configure various LLM providers, including DeepSeek, Gemini, and OpenAI-compatible APIs, allowing for flexibility in model choice and cost management. The script handles API calls, user authentication via QR code scanning, and question answering, with configurable delays to mitigate platform risk.

Quick Start & Requirements

• Installation: Download pre-compiled executables from releases (Windows, Mac, Ubuntu) or install from source using pip install -r requirements.txt after cloning the repository.
• Execution: Run the executable or python bili_hardcore/main.py.
• Prerequisites: Python 3.9+, Bilibili account at level 6 or higher.
• Configuration: Requires LLM API keys and potentially custom API endpoints.
• Docs: Project Address

Highlighted Details

• Direct Bilibili API integration, no OCR.
• Supports multiple LLM backends (DeepSeek, Gemini, OpenAI-compatible).
• Handles QR code login and CAPTCHA input.
• Configurable delays for risk mitigation.

Maintenance & Community

The project appears to be actively maintained by Karben233. Community support channels are not explicitly mentioned in the README.

Licensing & Compatibility

The README does not specify a license. Compatibility for commercial use or closed-source linking is not addressed.

Limitations & Caveats

The Gemini model may encounter rate limiting (429 errors) or require IP changes. Some models might fail on questions with sensitive words, necessitating manual intervention. The project is designed for users in mainland China and Hong Kong; users outside these regions may need to use specific nodes for initial setup.