From 76514f9f327f8639622a28b26e2cf5ffd806bfcc Mon Sep 17 00:00:00 2001
From: Dryusdan <contact@dryusdan.fr>
Date: Mon, 28 Apr 2025 02:52:08 +0200
Subject: [PATCH] Bump AI-robots.txt rules to version 1.29 (#383)

---
 data/bots/ai-robots-txt.yaml |  4 ++--
 web/static/robots.txt        | 18 ++++++++++++++++--
 2 files changed, 18 insertions(+), 4 deletions(-)

diff --git a/data/bots/ai-robots-txt.yaml b/data/bots/ai-robots-txt.yaml
index ef2790c..5beb090 100644
--- a/data/bots/ai-robots-txt.yaml
+++ b/data/bots/ai-robots-txt.yaml
@@ -1,4 +1,4 @@
 - name: "ai-robots-txt"
   user_agent_regex: >-
-    AI2Bot|Ai2Bot-Dolma|Amazonbot|anthropic-ai|Applebot|Applebot-Extended|Brightbot 1.0|Bytespider|CCBot|ChatGPT-User|Claude-Web|ClaudeBot|cohere-ai|cohere-training-data-crawler|Crawlspace|Diffbot|DuckAssistBot|FacebookBot|FriendlyCrawler|Google-Extended|GoogleOther|GoogleOther-Image|GoogleOther-Video|GPTBot|iaskspider/2.0|ICC-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo Bot|Meta-ExternalAgent|Meta-ExternalFetcher|OAI-SearchBot|omgili|omgilibot|PanguBot|Perplexity-User|PerplexityBot|PetalBot|Scrapy|SemrushBot-OCOB|SemrushBot-SWA|Sidetrade indexer bot|Timpibot|VelenPublicWebCrawler|Webzio-Extended|YouBot
-  action: DENY
\ No newline at end of file
+    AI2Bot|Ai2Bot-Dolma|aiHitBot|Amazonbot|anthropic-ai|Applebot|Applebot-Extended|Brightbot 1.0|Bytespider|CCBot|ChatGPT-User|Claude-Web|ClaudeBot|cohere-ai|cohere-training-data-crawler|Cotoyogi|Crawlspace|Diffbot|DuckAssistBot|FacebookBot|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Google-Extended|GoogleOther|GoogleOther-Image|GoogleOther-Video|GPTBot|iaskspider/2.0|ICC-Crawler|ImagesiftBot|img2dataset|imgproxy|ISSCyberRiskCrawler|Kangaroo Bot|meta-externalagent|Meta-ExternalAgent|meta-externalfetcher|Meta-ExternalFetcher|NovaAct|OAI-SearchBot|omgili|omgilibot|Operator|PanguBot|Perplexity-User|PerplexityBot|PetalBot|Scrapy|SemrushBot-OCOB|SemrushBot-SWA|Sidetrade indexer bot|TikTokSpider|Timpibot|VelenPublicWebCrawler|Webzio-Extended|YouBot
+  action: DENY
diff --git a/web/static/robots.txt b/web/static/robots.txt
index 4d0861c..e9dd073 100644
--- a/web/static/robots.txt
+++ b/web/static/robots.txt
@@ -1,9 +1,11 @@
 User-agent: AI2Bot
 User-agent: Ai2Bot-Dolma
+User-agent: aiHitBot
 User-agent: Amazonbot
 User-agent: anthropic-ai
 User-agent: Applebot
 User-agent: Applebot-Extended
+User-agent: Brightbot 1.0
 User-agent: Bytespider
 User-agent: CCBot
 User-agent: ChatGPT-User
@@ -11,9 +13,13 @@ 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: Diffbot
 User-agent: DuckAssistBot
 User-agent: FacebookBot
+User-agent: Factset_spyderbot
+User-agent: FirecrawlAgent
 User-agent: FriendlyCrawler
 User-agent: Google-Extended
 User-agent: GoogleOther
@@ -24,19 +30,27 @@ User-agent: iaskspider/2.0
 User-agent: ICC-Crawler
 User-agent: ImagesiftBot
 User-agent: img2dataset
+User-agent: imgproxy
 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: NovaAct
 User-agent: OAI-SearchBot
 User-agent: omgili
 User-agent: omgilibot
+User-agent: Operator
 User-agent: PanguBot
+User-agent: Perplexity-User
 User-agent: PerplexityBot
 User-agent: PetalBot
 User-agent: Scrapy
-User-agent: SemrushBot
+User-agent: SemrushBot-OCOB
+User-agent: SemrushBot-SWA
 User-agent: Sidetrade indexer bot
+User-agent: TikTokSpider
 User-agent: Timpibot
 User-agent: VelenPublicWebCrawler
 User-agent: Webzio-Extended
@@ -44,4 +58,4 @@ User-agent: YouBot
 Disallow: /
 
 User-agent: *
-Disallow: /
\ No newline at end of file
+Disallow: /