Academic calendar scraper, parser, and uploader #88
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Scrape academic calendars from Box. The links come from https://www.utdallas.edu/academics/calendar/ and a special Box download URL is used to get the PDF based on its file ID.
Parse the PDFs with Gemini. Pull the first page of text out of the PDF (works better than sending the actual file) and send it with a prompt describing the schema. It's been mistake free since I started sending it the PDF text instead of the PDF file. It costs about $0.13 to parse all the academic calendars but I'm hashing the prompts and storing the results in cloud storage so nothing should ever be re-parsed unless the PDF changes. 8 new environment variables are required. 4 for Gemini and 4 for the Nebula API for cloud storage caching.
Upload is very similar to the other uploaders.
There's a lot of
go.mod
changes that may not be entirely necessary. They were just made automatically so I could work on reverting them.I haven't yet set this up to run automatically but I can after merge. Unsure if we'd want it daily or weekly.