From 8ccc63e3b09f9b2c36aa48089c223d13baee19b2 Mon Sep 17 00:00:00 2001
From: Thilo Maier <git@maier.asia>
Date: Sun, 27 Jul 2025 23:46:19 +0200
Subject: [PATCH 1/2] Disallow AI bots Fixes #971

---
 static/robots.txt | 101 ++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 98 insertions(+), 3 deletions(-)

diff --git a/static/robots.txt b/static/robots.txt
index e9e57dc4..bf19cf19 100644
--- a/static/robots.txt
+++ b/static/robots.txt
@@ -1,3 +1,98 @@
-# https://www.robotstxt.org/robotstxt.html
-User-agent: *
-Disallow:
+User-agent: Googlebot
+User-agent: Bingbot
+User-agent: Slurp
+User-agent: DuckDuckBot
+User-agent: Baiduspider
+User-agent: YandexBot
+Allow: /
+
+User-agent: AI2Bot
+User-agent: Ai2Bot-Dolma
+User-agent: aiHitBot
+User-agent: Amazonbot
+User-agent: Andibot
+User-agent: anthropic-ai
+User-agent: Applebot
+User-agent: Applebot-Extended
+User-agent: Awario
+User-agent: bedrockbot
+User-agent: Brightbot 1.0
+User-agent: Bytespider
+User-agent: CCBot
+User-agent: ChatGPT-User
+User-agent: Claude-SearchBot
+User-agent: Claude-User
+User-agent: Claude-Web
+User-agent: ClaudeBot
+User-agent: cohere-ai
+User-agent: cohere-training-data-crawler
+User-agent: Cotoyogi
+User-agent: Crawlspace
+User-agent: Datenbank Crawler
+User-agent: Devin
+User-agent: Diffbot
+User-agent: DuckAssistBot
+User-agent: Echobot Bot
+User-agent: EchoboxBot
+User-agent: FacebookBot
+User-agent: facebookexternalhit
+User-agent: Factset_spyderbot
+User-agent: FirecrawlAgent
+User-agent: FriendlyCrawler
+User-agent: Gemini-Deep-Research
+User-agent: Google-CloudVertexBot
+User-agent: Google-Extended
+User-agent: GoogleAgent-Mariner
+User-agent: GoogleOther
+User-agent: GoogleOther-Image
+User-agent: GoogleOther-Video
+User-agent: GPTBot
+User-agent: iaskspider/2.0
+User-agent: ICC-Crawler
+User-agent: ImagesiftBot
+User-agent: img2dataset
+User-agent: ISSCyberRiskCrawler
+User-agent: Kangaroo Bot
+User-agent: meta-externalagent
+User-agent: Meta-ExternalAgent
+User-agent: meta-externalfetcher
+User-agent: Meta-ExternalFetcher
+User-agent: MistralAI-User
+User-agent: MistralAI-User/1.0
+User-agent: MyCentralAIScraperBot
+User-agent: netEstate Imprint Crawler
+User-agent: NovaAct
+User-agent: OAI-SearchBot
+User-agent: omgili
+User-agent: omgilibot
+User-agent: Operator
+User-agent: PanguBot
+User-agent: Panscient
+User-agent: panscient.com
+User-agent: Perplexity-User
+User-agent: PerplexityBot
+User-agent: PetalBot
+User-agent: PhindBot
+User-agent: Poseidon Research Crawler
+User-agent: QualifiedBot
+User-agent: QuillBot
+User-agent: quillbot.com
+User-agent: SBIntuitionsBot
+User-agent: Scrapy
+User-agent: SemrushBot-OCOB
+User-agent: SemrushBot-SWA
+User-agent: Sidetrade indexer bot
+User-agent: SummalyBot
+User-agent: Thinkbot
+User-agent: TikTokSpider
+User-agent: Timpibot
+User-agent: VelenPublicWebCrawler
+User-agent: WARDBot
+User-agent: Webzio-Extended
+User-agent: wpbot
+User-agent: YandexAdditional
+User-agent: YandexAdditionalBot
+User-agent: YouBot
+Disallow: /
+
+Sitemap: https://www.maier.tech/sitemap.xml

From fda2a421833797f49571093f1d5f0766437f231c Mon Sep 17 00:00:00 2001
From: Thilo Maier <git@maier.asia>
Date: Sun, 27 Jul 2025 23:52:38 +0200
Subject: [PATCH 2/2] Add comment

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

diff --git a/static/robots.txt b/static/robots.txt
index bf19cf19..eb8a3cb5 100644
--- a/static/robots.txt
+++ b/static/robots.txt
@@ -6,6 +6,7 @@ User-agent: Baiduspider
 User-agent: YandexBot
 Allow: /
 
+# https://github.com/ai-robots-txt/ai.robots.txt
 User-agent: AI2Bot
 User-agent: Ai2Bot-Dolma
 User-agent: aiHitBot