From 30fa4cada40453bcf4c6d61ecabe9809c7fa5b74 Mon Sep 17 00:00:00 2001
From: "Evan G." <evan@mail.fbievan.live>
Date: Fri, 24 May 2024 17:39:07 -0500
Subject: [PATCH] Add robots.txt

I copied https://codeberg.org/benjaminhollon/robots.txt-deny-llm/src/branch/main/robots.txt, or the robots.txt from benjaminhollon, to deny LLM's
---
 static/robots.txt | 69 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 69 insertions(+)
 create mode 100644 static/robots.txt

diff --git a/static/robots.txt b/static/robots.txt
new file mode 100644
index 0000000..c2d2be4
--- /dev/null
+++ b/static/robots.txt
@@ -0,0 +1,69 @@
+# from https://neil-clarke.com/block-the-bots-that-feed-ai-models-by-scraping-your-website/
+
+User-agent: CCBot
+Disallow: /
+
+User-agent: ChatGPT-User
+Disallow: /
+
+User-agent: GPTBot
+Disallow: /
+
+User-agent: Google-Extended
+Disallow: /
+
+User-agent: anthropic-ai
+Disallow: /
+
+User-agent: Omgilibot
+Disallow: /
+
+User-agent: Omgili
+Disallow: /
+
+User-agent: FacebookBot
+Disallow: /
+
+User-agent: Bytespider
+Disallow: /
+
+# from https://github.com/healsdata/ai-training-opt-out
+
+# may not work, needs more research (see https://github.com/rom1504/img2dataset/issues/48)
+User-agent: img2dataset
+Disallow: /
+
+User-agent: Claude-Web
+Disallow: /
+
+User-agent: magpie-crawler
+Disallow: /
+
+# AhrefsBot crawls for data for an "SEO Dataset"—one of their "products" based on this dataset is "AI Writing Tools"
+User-agent: AhrefsBot
+Disallow: /
+
+# from https://www.cyberciti.biz/web-developer/block-openai-bard-bing-ai-crawler-bots-using-robots-txt-file/
+User-agent: PerplexityBot
+Disallow: /
+
+# from https://netfuture.ch/2023/07/blocking-ai-crawlers-robots-txt-chatgpt/
+User-agent: cohere-ai
+Disallow: /
+
+# from https://claytonerrington.com/blog/robots-and-ai/
+
+User-agent: Amazonbot
+Disallow: /
+
+# from https://darkvisitors.com/
+
+User-agent: Applebot
+Disallow: /
+
+User-agent: YouBot
+Disallow: /
+
+# from https://imho.alex-kunz.com/2024/01/25/an-update-on-friendly-crawler/
+User-agent: FriendlyCrawler
+Disallow: /