From 100a6f3d11140953bf5d1843890cac1d9f6efd2c Mon Sep 17 00:00:00 2001
From: Seirdy <seirdy@seirdy.one>
Date: Thu, 26 Sep 2024 10:47:07 -0400
Subject: [PATCH] block another LLM scraper

---
 static/robots.txt | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/static/robots.txt b/static/robots.txt
index 5b1d5aa..94c6a97 100644
--- a/static/robots.txt
+++ b/static/robots.txt
@@ -124,6 +124,11 @@ Disallow: /
 # This one doesn't support robots.txt: https://www.allenai.org/crawler
 # block it with your reverse-proxy or WAF or something.
 
+# See <https://ds.rois.ac.jp/center8/crawler/>
+# Parent page says it builds LLMs in the infographic: <https://ds.rois.ac.jp/center8/>
+User-agent: Cotoyogi 
+Disallow: /
+
 # I'm not blocking CCBot for now. It publishes a free index for anyone to use.
 # Googe used this to train the initial version of Bard (now called Gemini).
 # I allow CCBot since its index is also used for upstart/hobbyist search engines