It may give more transparency if it output the code to do scrapping with playwright.

Then we can review the code before actually running it.

And the reviewed result can be saved for future running.

Well, i guess that with an LLM you kind of hope it will understand you whereas with a regular program you don't have to hope for that, just that it will work without throwing errors (usually with a magnitudes lower error rate).

Okay that’s a pretty good point actually.

I guess I wrongly assume regular API’s are more reliable, but you’re right they’re basically black boxes too…