From 9dcde94cd32db622ede0bbc203fcaa6b01e327ee Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E7=8E=8B=E4=B8=80=E8=B5=AB?= Date: Thu, 11 Jun 2026 14:43:28 +0800 Subject: [PATCH] ci: add linkcheck_ignore for CI-blocked external links (#6, Category 4) Several external links return HTTP 403 (or similar) to the linkcheck bot on CI runners even though they resolve fine in a browser. linkcheck is advisory, but ignoring these known bot-blockers keeps the report focused on genuinely broken links. Only the consistently-blocking domains are ignored. Genuine breakage is left visible on purpose: - the missing worksheet .ods (tracked in guidebook#263) - the Deloitte 404 - the Stack Overflow text-fragment anchor Refs #6. --- conf.py | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/conf.py b/conf.py index ee9946f..a3eaee5 100644 --- a/conf.py +++ b/conf.py @@ -30,6 +30,25 @@ myst_enable_extensions = ["colon_fence", "tasklist"] myst_heading_anchors = 3 +# Sites that reject the linkcheck bot with HTTP 403 (and similar) in CI even +# though the URLs resolve fine in a browser. linkcheck is advisory, but these +# patterns keep the report focused on genuinely broken links. Genuine 404s and +# anchor problems are intentionally NOT listed here so they stay visible. +linkcheck_ignore = [ + r"https://www\.bls\.gov/", + r"https://www\.nytimes\.com/", + r"https://www\.unwomen\.org/", + r"https://www\.weforum\.org/", + r"https://academic\.oup\.com/", + r"https://.*\.wiley\.com/", + r"https://www\.huffpost\.com/", + r"https://www\.managers\.org\.uk/", + r"https://www\.mayoclinic\.org/", + r"https://www\.teamblind\.com/", + r"https://www\.theburnoutproject\.com\.au/", + r"https://www\.opavote\.com/", +] + language = "en" guidebook_languages = [ {"code": "en", "build_dir": "en", "label": "English", "aliases": []},