From 2cc6baa43f941782c21ef6ceeedc8e07c123af2b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Asger=20Geel=20Weirs=C3=B8e?= Date: Mon, 5 Oct 2026 21:30:00 +0200 Subject: [PATCH] Keep crawlers off the tarball archives, not the tarball index SEO crawlers were downloading the release archives (up to about 2 GB each) even though they are served noindex. Disallow only *.tar.zst and *.zip under /tarballz/; the index page and the PKGBUILDs stay crawlable. Repeated in every group, because a crawler with its own group ignores User-agent: *. Claude-Session: https://claude.ai/code/session_01GGe7kUhooMFuzY6GaDb2w9 --- public/robots.txt | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/public/robots.txt b/public/robots.txt index 48f4f64..46b143c 100644 --- a/public/robots.txt +++ b/public/robots.txt @@ -1,43 +1,72 @@ # Asger Weirsøe — asger.weirsoe.dk # Alle crawlere er velkomne, inkl. AI/LLM-crawlere (vi vil gerne findes og citeres). +# Undtagelse: selve arkivfilerne under /tarballz/ (op til ~2 GB stykket). Indeks og +# PKGBUILD'er må gerne crawles. Står i hver gruppe, fordi en crawler med sin egen +# gruppe ignorerer User-agent: *. User-agent: * Allow: / +Disallow: /tarballz/*.tar.zst +Disallow: /tarballz/*.zip # Eksplicit velkomst til AI/LLM-crawlere User-agent: GPTBot Allow: / +Disallow: /tarballz/*.tar.zst +Disallow: /tarballz/*.zip User-agent: OAI-SearchBot Allow: / +Disallow: /tarballz/*.tar.zst +Disallow: /tarballz/*.zip User-agent: ChatGPT-User Allow: / +Disallow: /tarballz/*.tar.zst +Disallow: /tarballz/*.zip User-agent: ClaudeBot Allow: / +Disallow: /tarballz/*.tar.zst +Disallow: /tarballz/*.zip User-agent: Claude-Web Allow: / +Disallow: /tarballz/*.tar.zst +Disallow: /tarballz/*.zip User-agent: anthropic-ai Allow: / +Disallow: /tarballz/*.tar.zst +Disallow: /tarballz/*.zip User-agent: PerplexityBot Allow: / +Disallow: /tarballz/*.tar.zst +Disallow: /tarballz/*.zip User-agent: Perplexity-User Allow: / +Disallow: /tarballz/*.tar.zst +Disallow: /tarballz/*.zip User-agent: Google-Extended Allow: / +Disallow: /tarballz/*.tar.zst +Disallow: /tarballz/*.zip User-agent: Applebot-Extended Allow: / +Disallow: /tarballz/*.tar.zst +Disallow: /tarballz/*.zip User-agent: CCBot Allow: / +Disallow: /tarballz/*.tar.zst +Disallow: /tarballz/*.zip User-agent: cohere-ai Allow: / +Disallow: /tarballz/*.tar.zst +Disallow: /tarballz/*.zip Sitemap: https://asger.xn--weirse-fya.dk/sitemap-index.xml