guixsd-config

commit 4e7458a97faa669898b9be044747315156cd1940
parent 6aaaa1230f199a2c566806c371321f87693bf231
Author: Vineet Kumar <git@vineetk.net>
Date:   Fri, 22 May 2026 10:07:41 -0400

saklas: block mj12bot in nginx

Diffstat:
M
epistemia/systems/saklas.scm
 | 
2
+-

1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/epistemia/systems/saklas.scm b/epistemia/systems/saklas.scm
@@ -41,7 +41,7 @@
   (plain-file "nginx-badboi.conf"
 	      "\
 set $bad_boi 0;
-if ($http_user_agent ~* \"(AI2Bot|Ai2Bot\\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\\-ai|Applebot|Applebot\\-Extended|bedrockbot|Brightbot\\ 1\\.0|Bytespider|CCBot|ChatGPT\\-User|Claude\\-SearchBot|Claude\\-User|Claude\\-Web|ClaudeBot|cohere\\-ai|cohere\\-training\\-data\\-crawler|Cotoyogi|Crawlspace|Diffbot|DuckAssistBot|FacebookBot|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Google\\-CloudVertexBot|Google\\-Extended|GoogleOther|GoogleOther\\-Image|GoogleOther\\-Video|GPTBot|iaskspider/2\\.0|ICC\\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\\ Bot|meta\\-externalagent|Meta\\-ExternalAgent|meta\\-externalfetcher|Meta\\-ExternalFetcher|MistralAI\\-User/1\\.0|NovaAct|OAI\\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\\.com|Perplexity\\-User|PerplexityBot|PetalBot|PhindBot|QualifiedBot|QuillBot|quillbot\\.com|SBIntuitionsBot|Scrapy|SemrushBot\\-OCOB|SemrushBot\\-SWA|Sidetrade\\ indexer\\ bot|TikTokSpider|Timpibot|VelenPublicWebCrawler|Webzio\\-Extended|wpbot|YandexAdditional|YandexAdditionalBot|YouBot)\") {
+if ($http_user_agent ~* \"(AI2Bot|Ai2Bot\\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\\-ai|Applebot|Applebot\\-Extended|bedrockbot|Brightbot\\ 1\\.0|Bytespider|CCBot|ChatGPT\\-User|Claude\\-SearchBot|Claude\\-User|Claude\\-Web|ClaudeBot|cohere\\-ai|cohere\\-training\\-data\\-crawler|Cotoyogi|Crawlspace|Diffbot|DuckAssistBot|FacebookBot|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Google\\-CloudVertexBot|Google\\-Extended|GoogleOther|GoogleOther\\-Image|GoogleOther\\-Video|GPTBot|iaskspider/2\\.0|ICC\\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\\ Bot|meta\\-externalagent|Meta\\-ExternalAgent|meta\\-externalfetcher|Meta\\-ExternalFetcher|MistralAI\\-User/1\\.0\\|MJ12|NovaAct|OAI\\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\\.com|Perplexity\\-User|PerplexityBot|PetalBot|PhindBot|QualifiedBot|QuillBot|quillbot\\.com|SBIntuitionsBot|Scrapy|SemrushBot\\-OCOB|SemrushBot\\-SWA|Sidetrade\\ indexer\\ bot|TikTokSpider|Timpibot|VelenPublicWebCrawler|Webzio\\-Extended|wpbot|YandexAdditional|YandexAdditionalBot|YouBot)\") {
     set $bad_boi 1;
 }
 if ($request_uri = \"/robots.txt\") {