Merge pull request #143 from ai-robots-txt/panscient

ai.robots.txt · ai.robots.txt · commit 75ea75a95b00 · 2025-06-04T18:04:06.000Z
chore(robots.json): adds Panscient
diff --git a/.htaccess b/.htaccess
@@ -1,3 +1,3 @@
 RewriteEngine On
-RewriteCond %{HTTP_USER_AGENT} (AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|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|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) [NC]
+RewriteCond %{HTTP_USER_AGENT} (AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|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) [NC]
 RewriteRule !^/?robots\.txt$ - [F,L]
diff --git a/Caddyfile b/Caddyfile
@@ -1,3 +1,3 @@
 @aibots {
-        header_regexp User-Agent "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|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|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)"
+        header_regexp User-Agent "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|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)"
 }
diff --git a/haproxy-block-ai-bots.txt b/haproxy-block-ai-bots.txt
@@ -47,6 +47,8 @@ omgili
 omgilibot
 Operator
 PanguBot
+Panscient
+panscient.com
 Perplexity-User
 PerplexityBot
 PetalBot
diff --git a/nginx-block-ai-bots.conf b/nginx-block-ai-bots.conf
@@ -1,3 +1,3 @@
-if ($http_user_agent ~* "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Diffbot|DuckAssistBot|FacebookBot|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Google\-CloudVertexBot|Google\-Extended|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User/1\.0|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|TikTokSpider|Timpibot|VelenPublicWebCrawler|Webzio\-Extended|wpbot|YandexAdditional|YandexAdditionalBot|YouBot)") {
+if ($http_user_agent ~* "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|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)") {
     return 403;
 }
diff --git a/robots.txt b/robots.txt
@@ -47,6 +47,8 @@ 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
diff --git a/table-of-bot-metrics.md b/table-of-bot-metrics.md
@@ -49,6 +49,8 @@
 | omgilibot | [Webz.io](https://webz.io/) | [Yes](https://web.archive.org/web/20170704003301/http://omgili.com/Crawler.html) | Data is sold. | No information. | Legacy user agent initially used for Omgili search engine. Unknown if still used, `omgili` agent still used by Webz.io. |
 | Operator | Unclear at this time. | Unclear at this time. | AI Agents | Unclear at this time. | Operator is an AI agent created by OpenAI that can use a web browser. It can intelligently navigate and interact with websites to complete multi-step tasks on behalf of a human user. More info can be found at https://darkvisitors.com/agents/agents/operator |
 | PanguBot | the Chinese company Huawei | Unclear at this time. | AI Data Scrapers | Unclear at this time. | PanguBot is a web crawler operated by the Chinese company Huawei. It's used to download training data for its multimodal LLM (Large Language Model) called PanGu. More info can be found at https://darkvisitors.com/agents/agents/pangubot |
+| Panscient | [Panscient](https://panscient.com) | [Yes](https://panscient.com/faq.htm) | Data collection and analysis using machine learning and AI. | The Panscient web crawler will request a page at most once every second from the same domain name or the same IP address. | Compiles data on businesses and business professionals that is structured using AI and machine learning. |
+| panscient\.com | [Panscient](https://panscient.com) | [Yes](https://panscient.com/faq.htm) | Data collection and analysis using machine learning and AI. | The Panscient web crawler will request a page at most once every second from the same domain name or the same IP address. | Compiles data on businesses and business professionals that is structured using AI and machine learning. |
 | Perplexity\-User | [Perplexity](https://www.perplexity.ai/) | [No](https://docs.perplexity.ai/guides/bots) | Used to answer queries at the request of users. | Only when prompted by a user. | Visit web pages to help provide an accurate answer and include links to the page in Perplexity response. |
 | PerplexityBot | [Perplexity](https://www.perplexity.ai/) | [Yes](https://docs.perplexity.ai/guides/bots) | Search result generation. | No information. | Crawls sites to surface as results in Perplexity. |
 | PetalBot | [Huawei](https://huawei.com/) | Yes | Used to provide recommendations in Hauwei assistant and AI search services. | No explicit frequency provided. | Operated by Huawei to provide search and AI assistant services. |

Original file line number	Diff line number	Diff line change
`@@ -1,3 +1,3 @@`
`1`	`1`	`@aibots {`
`2`		- header_regexp User-Agent "(AI2Bot\|Ai2Bot\-Dolma\|aiHitBot\|Amazonbot\|Andibot\|anthropic\-ai\|Applebot\|Applebot\-Extended\|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\|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)"
	`2`	+ header_regexp User-Agent "(AI2Bot\|Ai2Bot\-Dolma\|aiHitBot\|Amazonbot\|Andibot\|anthropic\-ai\|Applebot\|Applebot\-Extended\|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)"
`3`	`3`	`}`
Original file line number	Diff line number	Diff line change
`@@ -1,3 +1,3 @@`
`1`		-if ($http_user_agent ~* "(AI2Bot\|Ai2Bot\-Dolma\|aiHitBot\|Amazonbot\|Andibot\|anthropic\-ai\|Applebot\|Applebot\-Extended\|Brightbot\ 1\.0\|Bytespider\|CCBot\|ChatGPT\-User\|Claude\-SearchBot\|Claude\-User\|Claude\-Web\|ClaudeBot\|cohere\-ai\|cohere\-training\-data\-crawler\|Cotoyogi\|Crawlspace\|Diffbot\|DuckAssistBot\|FacebookBot\|Factset_spyderbot\|FirecrawlAgent\|FriendlyCrawler\|Google\-CloudVertexBot\|Google\-Extended\|GoogleOther\|GoogleOther\-Image\|GoogleOther\-Video\|GPTBot\|iaskspider/2\.0\|ICC\-Crawler\|ImagesiftBot\|img2dataset\|ISSCyberRiskCrawler\|Kangaroo\ Bot\|meta\-externalagent\|Meta\-ExternalAgent\|meta\-externalfetcher\|Meta\-ExternalFetcher\|MistralAI\-User/1\.0\|NovaAct\|OAI\-SearchBot\|omgili\|omgilibot\|Operator\|PanguBot\|Perplexity\-User\|PerplexityBot\|PetalBot\|PhindBot\|QualifiedBot\|QuillBot\|quillbot\.com\|SBIntuitionsBot\|Scrapy\|SemrushBot\-OCOB\|SemrushBot\-SWA\|Sidetrade\ indexer\ bot\|TikTokSpider\|Timpibot\|VelenPublicWebCrawler\|Webzio\-Extended\|wpbot\|YandexAdditional\|YandexAdditionalBot\|YouBot)") {
	`1`	+if ($http_user_agent ~* "(AI2Bot\|Ai2Bot\-Dolma\|aiHitBot\|Amazonbot\|Andibot\|anthropic\-ai\|Applebot\|Applebot\-Extended\|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)") {
`2`	`2`	`return 403;`
`3`	`3`	`}`