Can doc understanding read .html type file?

Lets say it’s an html full of text with a few images. Would it just do image recognition or does it actually read the HTML? Thank you

Yes, it works through OCR so it can read the HTML.@david_Hernandez2

Hi,

Do you mean if DocumentUnderstanding can handle html file?
I don’t think it suit for that process because layout of html may be changed depending redering environment.

How about using UiAutaomtion such as TableExtraction and/or GetText with string manipulation etc?

Regards,