The exciting thing is that in this case it doesn't need to be. Segmentation (which is solved) is sufficient to identify semantically separate parts of the page, and then OCR can be used to place the text from the html on the representation of the page.
I expect that to be significantly different from the task of segmenting objects in a photo, because most of the boundaries are not revealed by texture differences, but implicit in the arrangement.
https://arxiv.org/abs/1704.01474
https://arxiv.org/abs/1711.07695
https://arxiv.org/abs/1710.07363
I'm pretty sure I've seen some webpage work too, but I don't have the reference.
Finding the text in a screenshot of a webpage should be easier than doing it for handwritten documents; it's the "decide what is the navigation" part that I'm doubtful about.
You seem to be overestimating how close to practicality neural-network approaches are for most problems. Very much of the potential application space is still firmly within the domain of research. That doesn't mean what you described is completely impossible, just that you could get a PhD for pulling it off.
[1] https://arxiv.org/abs/1609.04938v1 (incidentally, I noticed that the version of the paper that was accepted for ICML 2017 no longer has the HTML part)