Want to create a project on Extraction of auto generated subtitles with Java

I want to build a project that extracts auto-generated captions from a YouTube link, and I plan to use Java for this project. I've completed my core Java studies and want to learn additional topics while working on this project. Could you provide a step-by-step guide for successful completion? Also, is this project a good choice, or are there other better project ideas I should consider? Well I have tried to search on net but cannot find any thing Do you guys know any good place where I can study this