Scrape directory, OCR contact information and enrich

I need help scraping this directory of Enterprise Agreements (~24K records in total). https://www.fwc.gov.au/document-search?search-ui=agreements&f%5B%5D=agreement-status%3A163803&expiry_date_from=2025-06-09&expiry_date_to= I need you to capture the top-level fields shown on the results page (see attached). PLUS... ...and this is the potentially complicated part... I need you to identify the signatory inside the PDF agreement, including their title. Sometimes this will be straight forward, because the decision maker is clearly stated in the PDF... but other times it might be handwritten OR it could just be their signature. So you'll need an OCR step to look at the hand written text and/or signature... then that should trigger a secondary verification step to ensure the contact has been captured correctly. For instance, if it only includes the signature. It should extract "J Doe", then run a search to see if that matches an employee with that company. If it detects a fuzzy match, e.g. "L Doe", it should correct the text and list the title of that person. Also, there are several names in these documents. we ONLY want the employer representative — so we need the smarts to make sure we're not capturing the wrong information. — Optional Step 2 I also have a second requirement — but this is not essential. Once we have extracted all the companies... regardless of whether we extract a signatory, I want to search for relevant contacts at that company using apollo or similar. I will provide you with a list of title keywords (e.g. any title containing the term "Payroll" with director level or higher), then you will provide the name, title and email address.