From a74d9d9ca8f51cf8a7a527307a1d6bd48d1cbaaa Mon Sep 17 00:00:00 2001 From: Eric Date: Thu, 1 Oct 2026 01:06:09 +1000 Subject: [PATCH] disallow clanker access to /share, /download, /print does not block search engine bots, just the scrapers that feed the LLM training --- robots.txt | 42 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+) diff --git a/robots.txt b/robots.txt index 9abbfb965..c7fd30d1c 100644 --- a/robots.txt +++ b/robots.txt @@ -2,3 +2,45 @@ User-agent: * Disallow: /edit/ +# AI / LLM training crawlers + +User-agent: GPTBot +Disallow: /share/ +Disallow: /download/ +Disallow: /print/ + +User-agent: ClaudeBot +Disallow: /share/ +Disallow: /download/ +Disallow: /print/ + +User-agent: CCBot +Disallow: /share/ +Disallow: /download/ +Disallow: /print/ + +User-agent: Google-Extended +Disallow: /share/ +Disallow: /download/ +Disallow: /print/ + +User-agent: Bytespider +Disallow: /share/ +Disallow: /download/ +Disallow: /print/ + +User-agent: Applebot-Extended +Disallow: /share/ +Disallow: /download/ +Disallow: /print/ + +User-agent: Meta-ExternalAgent +Disallow: /share/ +Disallow: /download/ +Disallow: /print/ + +User-agent: Amazonbot +Disallow: /share/ +Disallow: /download/ +Disallow: /print/ +