Is there a convenient way to extract all the HTML from the text but remove all styling?
I want to pass the HTML to an LLM but there is significant noise in the raw HTML due to excessive styles (from tables, colors, and positioning).
If there can be an API to get the html but remove all the CSS and styling, I would greatly appreciate it
Is there a convenient way to extract all the HTML from the text but remove all styling?
I want to pass the HTML to an LLM but there is significant noise in the raw HTML due to excessive styles (from tables, colors, and positioning).
If there can be an API to get the html but remove all the CSS and styling, I would greatly appreciate it