←back to thread

20 points simonw | 1 comments | | HN request time: 0.208s | source
Show context
simonw ◴[] No.46264196[source]
JustHTML https://github.com/EmilStenstrom/justhtml is a neat new Python library - it implements a compliant HTML5 parser in ~3,000 lines of code that passes the full existing 9,200 test HTML5 conformance suite.

Emil Stenström wrote it with a variety of coding agent tools over the course of a couple of months. It's a really interesting case study in using coding agents to take on a very challenging project, taking advantage of their ability to iterate against existing tests.

I wrote a bit more about it here: https://simonwillison.net/2025/Dec/14/justhtml/

replies(2): >>46265212 #>>46267896 #
EmilStenstrom ◴[] No.46265212[source]
Thanks for sharing simon! Writing a parser is a really good job for a coding agent, because there's a clear right/wrong answer. In this case, the path there is the challenging part. The hours I've spent trying to convince agents to implement adoption agency well... :)
replies(1): >>46270332 #
msephton ◴[] No.46270332[source]
RSS on website is erroring. I'd like to follow!
replies(1): >>46271076 #
1. EmilStenstrom ◴[] No.46271076[source]
Thanks! Now fixed.