A well-known company wants to automate the process of filtering their applicants due to the large number of applicants applying each day. The company receives over 150 resumes per day. The resume includes the applicant’s name, previous/current work, previous/current education, and some other information. The company saves these resumes on an S3 bucket in the company’s VPC cloud. The company wants to extract personally identifiable information, locations, organizations, and dates from the resumes. However, the resumes are provided in PDF format not text format. Which combination of services should the company use to extract the information from the PDF resumes?