This study presents a data-driven approach to automating the extraction of structured legal profiles from the websites of the top 500 U.S. law firms. The research addresses the inefficiencies of manual data collection in legal talent acquisition by developing a scalable, AI-assisted web scraping system capable of retrieving and structuring large volumes of unstructured data. Given the variability in website architectures and the presence of anti-scraping mechanisms, a multi-layered web scraping pipeline was designed, incorporating requests, Cloudscraper, Playwright, and Selenium to ensure robust and adaptable content retrieval. Extracted HTML data was processed using AI models, leveraging structured prompt engineering techniques to optimize model performance.