diff options
| author | Vineet Kumar <git@vineetk.net> | 2026-05-22 10:07:41 -0400 |
|---|---|---|
| committer | Vineet Kumar <git@vineetk.net> | 2026-05-22 10:07:41 -0400 |
| commit | 4e7458a97faa669898b9be044747315156cd1940 (patch) | |
| tree | 134f7585c2f235d71b32f653d96fe6754c22141f | |
| parent | 6aaaa1230f199a2c566806c371321f87693bf231 (diff) | |
saklas: block mj12bot in nginx
| -rw-r--r-- | epistemia/systems/saklas.scm | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/epistemia/systems/saklas.scm b/epistemia/systems/saklas.scm index 59c23b4..00d2594 100644 --- a/epistemia/systems/saklas.scm +++ b/epistemia/systems/saklas.scm | |||
| @@ -41,7 +41,7 @@ | |||
| 41 | (plain-file "nginx-badboi.conf" | 41 | (plain-file "nginx-badboi.conf" |
| 42 | "\ | 42 | "\ |
| 43 | set $bad_boi 0; | 43 | set $bad_boi 0; |
| 44 | if ($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)\") { | 44 | 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)\") { |
| 45 | set $bad_boi 1; | 45 | set $bad_boi 1; |
| 46 | } | 46 | } |
| 47 | if ($request_uri = \"/robots.txt\") { | 47 | if ($request_uri = \"/robots.txt\") { |