From 7a92c3e95ff57546f50218c2191bc31b94e92bd5 Mon Sep 17 00:00:00 2001 From: Claude Date: Mon, 17 Aug 2026 11:28:16 +0000 Subject: [PATCH] Fix two site-health link-check failures The weekly scheduled site-health run fails at the lychee step on two links, neither of which is actually broken: - PubMed returns 203 Non-Authoritative Information to automated clients. The page exists; NCBI just serves a proxied copy. Add 203 to the accepted status codes alongside the other anti-bot responses we already tolerate. - The Elements of Statistical Learning link points at the legacy web.stanford.edu/~hastie path, which is slow enough to hit lychee's 30s timeout. Point it at the canonical hastie.su.domains URL. Co-Authored-By: Claude Opus 5 Claude-Session: https://claude.ai/code/session_01TGQdxbWZuEieA3pkDjAiss --- learning.md | 2 +- lychee.toml | 4 +++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/learning.md b/learning.md index 86b8a14..6a7af2f 100644 --- a/learning.md +++ b/learning.md @@ -67,7 +67,7 @@ But we're all busy people. What I usually end up recommending to students: There are lots of great references. The current deep learning phase notwithstanding, machine learning is actually a very broad field, and what is old now will eventually be new again. Some references worth checking out: - [An Introduction to Statistical Learning](https://www.statlearning.com) -- [Elements of Statistical Learning](http://web.stanford.edu/~hastie/ElemStatLearn/) (free pdf) +- [Elements of Statistical Learning](https://hastie.su.domains/ElemStatLearn/) (free pdf) - [Pattern Recognition and Machine Learning](https://www.springer.com/us/book/9780387310732) - [Machine Learning: A Probabilistic Perspective](https://probml.github.io/pml-book/) diff --git a/lychee.toml b/lychee.toml index ebe9af0..9b39bcb 100644 --- a/lychee.toml +++ b/lychee.toml @@ -24,13 +24,15 @@ user_agent = "Mozilla/5.0 (compatible; lychee-link-checker; +https://lychee.cli. # - 200/204/206: success # - 202: escholarship.org and some other deferred-fetch repos return # this on a request that will succeed if you retry or wait +# - 203: pubmed.ncbi.nlm.nih.gov returns this to automated clients — the +# page exists, NCBI is just serving a proxied/modified copy # - 401: paywalled but exists # - 403/405/429: bot-protection / rate-limit / method-not-allowed # - 415: some servers (e.g. OJS journal platforms, ccneuro.org PDFs) # reject lychee's request based on the Accept header even though the # resource exists and loads in a browser. # - 999: LinkedIn's bot-detection response -accept = [200, 202, 204, 206, 401, 403, 405, 415, 429, 999] +accept = [200, 202, 203, 204, 206, 401, 403, 405, 415, 429, 999] # Hosts to skip: # - pearsonlab.github.io: this is the site we're building. The sitemap