This project is a Python-based tool designed for efficient web content extraction and interaction with AI models. It fetches webpage data, processes HTML elements, and integrates with locally hosted AI models for advanced content analysis.
- Automated Web Scraping: Uses BeautifulSoup and requests to extract text and links from websites.
- AI-Powered Analysis: Integrates with OpenAI's API and locally hosted AI models like
llama3.2. - Structured Data Extraction: Implements a Website class for efficient content parsing.
- Error Handling & API Key Management: Ensures secure API usage with environment-based configuration.
- Python
- BeautifulSoup
- Requests
- OpenAI API
- Local AI Models (Llama3.2)
-
Clone the repository:
git clone https://github.com/GarlicDeveloper/Ollama-WebScrapper.git -
Install dependencies:
https://ollama.com/ -
Just Install Ollama in your local machine and Run Below Line in powershell
ollama run llama3.2 -
Run the script:
Just Shift+Enter all the lines in Jupyter lab
Feel free to contribute by submitting issues or pull requests!
🚀