In recent times, with the increased use of the internet and websites, a lot of data is generated. To analyse this data, manually scraping them from websites is often a time-consuming process. With the rapid growth of Artificial Intelligence (AI) and Large Language Models (LLMs), we are able to propose a new and efficient way to tackle web scraping. This paper presents a framework for streamlining web scraping by incorporating LangChain and large language models. The framework facilitates data extraction from websites through the use of LangChain's capabilities and large language models like GPT-4. Key elements include a textual partitioning mechanism and a vector database such as ChromaDB to process and scrutinize web content. The system also features a conversational agent powered by OpenAI for generating responses based on user inquiries and contextual data post scraping. The paper outlines the system's design, incorporating Streamlit for a user-friendly interface. Real-world demonstrations of web scraping operations and interactive conversations showcase the system's capabilities, highlighting its potential for enhancing user engagement and retrieving information from websites.