Machine Learning Data Engineer

The requirement is to build a Data Scrapper - to scan pdf or such files where text and images are to be separated using OCR techniques/ Python / ML and Process (NLP/openAI/ ChatGPT) with a converter/ middleware to make the data ready in xls or such desired format or to take it into the respective database directly. Require to start this development asap, immediate availability is preferred. If you have done such pdf/ Image/ web scraping with ML then please share your availability.