From 3c42dc23bd1295c5186a6d4ca1382d248c12bbc3 Mon Sep 17 00:00:00 2001 From: Juraj Roka <95219754+jr-rk@users.noreply.github.com> Date: Fri, 11 Sep 2026 14:46:04 +0200 Subject: [PATCH] fix(robots): disallow scoped search and facet links Backport of the src/robots.txt.ejs change from mendelu 29b88bf36b (#1402): block /collections/*/search, /communities/*/search and any Discovery facet link (/*?f., /*&f.) that was saturating SSR (HTTP 504). Co-Authored-By: Claude Opus 4.8 --- src/robots.txt.ejs | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/src/robots.txt.ejs b/src/robots.txt.ejs index f6dc7fa5cb5..64d93747026 100644 --- a/src/robots.txt.ejs +++ b/src/robots.txt.ejs @@ -18,6 +18,19 @@ Disallow: /profile Disallow: /workflowitems # Crawlers should be able to access entity pages, but not the facet search links present on entity pages Disallow: /entities/*?f +# Scoped search inside a community or collection, and every facet link. +# "Disallow: /search" above only matches paths that START with /search, so +# /collections//search and /communities//search stayed crawlable. +# Crawlers enumerating those facet combinations saturated SSR on 2026-07-22 +# (HTTP 504 for everyone); see the comment in config/config.yml. +Disallow: /collections/*/search +Disallow: /communities/*/search +# The two rules below cover any URL carrying a Discovery facet filter +# (f.author, f.subject, f.dateIssued.min, ...), wherever it appears. Two of +# them because the facet can be the first query parameter (?f.) or a later +# one (&f.), and robots.txt has no way to express "either". +Disallow: /*?f. +Disallow: /*&f. # Optionally uncomment the following line ONLY if sitemaps are working # and you have verified that your site is being indexed correctly.