LLPhant Support HTML Parsing

This adds support for HTML parsing.

Jun 14 '24 15:06 amenk

Great idea @amenk

Jun 14 '24 17:06 MaximeThoonsen

@amenk You can try to fix formatting problems with: composer fix-lint Try also

composer refactor && composer test

Jun 29 '24 14:06 f-lombardo

@f-lombardo thanks, currently not working on this

Will hopefully pick up later.

Jul 17 '24 11:07 amenk

@amenk @f-lombardo what about just use WebPageTextGetter class in Tool? To get the text from html should be quite enough no? (even if quite messy ^^)

Oct 11 '24 15:10 MaximeThoonsen

@amenk @f-lombardo what about just use WebPageTextGetter class in Tool? To get the text from html should be quite enough no? (even if quite messy ^^)

Well, it's an option, even if whe should change it a bit in order to parse also HTML coming from a file. Another thing to consider is if LLPhant should handle the parsing of complex HTML pages by itself or it has to delegate that to an external specialized library.

Oct 11 '24 16:10 f-lombardo