PDF Downloader and Data Automation

I need a solution that automates the downloading of .pdf files from public websites, sorting, and combining data. The .pdf files contain data tables with reference numbers, which need to be submitted into a different website's drop-down file downloader. There are two types of files: one that contains orders with attached serial numbers and another that lists serial numbers with associated costs.
To explain further, we have a government contract award list via a .pdf, the .pdf contains award ranking. There is no cost/price associated with said award, just a reference number. The reference number needs to be submitted to download another .pdf where the cost information is. We need to then pair that information together preferably in a .pdf or spreadsheet.

Every year, we need to run this query, and it consumes a huge amount of time. If we can automate even half of this, it would be a significant help. I can provide further details if necessary.

Ideal skills and experience:
- Proficient in data extraction and automation
- Experienced in working with .pdf files
- Able to create scripts, software applications, or browser extensions
- Familiar with Python, JavaScript, or Ruby
- Able to handle large datasets (over a hundred files and over a thousand lines of data)