I'm a big fan of local myself, but unfortunately the local models aren't there yet. Even of the closed-source models, many surprisingly struggle with relatively simple requests in this domain.

Don't get me wrong, there are a lot more iterations of tool + prompt + agent flow updates we can and will do to make things even better, and the models will keep getting better themselves, but the task is non-trivial. If you download the raw HTML of a webpage, it's a messy jungle, and frankly impressive that the models are capable of doing anything useful with it