From ae8f74c10cec97ec758bf39345ff20717302c665 Mon Sep 17 00:00:00 2001 From: Kyle Buckingham Date: Tue, 1 Apr 2025 15:22:04 -0700 Subject: [PATCH 1/8] Update robots.json --- robots.json | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) diff --git a/robots.json b/robots.json index e907c8b..f711d43 100644 --- a/robots.json +++ b/robots.json @@ -69,13 +69,6 @@ "frequency": "Only when prompted by a user.", "description": "Used by plugins in ChatGPT to answer queries based on user input." }, - "Claude-Web": { - "operator": "[Anthropic](https://www.anthropic.com)", - "respect": "Unclear at this time.", - "function": "Scrapes data to train Anthropic's AI products.", - "frequency": "No information provided.", - "description": "Scrapes data to train LLMs and AI products offered by Anthropic." - }, "ClaudeBot": { "operator": "[Anthropic](https://www.anthropic.com)", "respect": "[Yes](https://support.anthropic.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler)", @@ -83,6 +76,20 @@ "frequency": "No information provided.", "description": "Scrapes data to train LLMs and AI products offered by Anthropic." }, + "Claude-User": { + "operator": "[Anthropic](https://www.anthropic.com)", + "respect": "Unclear at this time.", + "function": "Claude-User supports Claude AI users. When individuals ask questions to Claude, it may access websites using a Claude-User agent.", + "frequency": "No information provided.", + "description": "Claude-User supports Claude AI users. When individuals ask questions to Claude, it may access websites using a Claude-User agent." + }, + "Claude-SearchBot": { + "operator": "[Anthropic](https://www.anthropic.com)", + "respect": "Unclear at this time.", + "function": "Claude-SearchBot navigates the web to improve search result quality for users. It analyzes online content specifically to enhance the relevance and accuracy of search responses.", + "frequency": "No information provided.", + "description": "Claude-SearchBot navigates the web to improve search result quality for users. It analyzes online content specifically to enhance the relevance and accuracy of search responses." + }, "cohere-ai": { "operator": "[Cohere](https://cohere.com)", "respect": "Unclear at this time.", @@ -328,4 +335,4 @@ "frequency": "No information.", "description": "Retrieves data used for You.com web search engine and LLMs." } -} \ No newline at end of file +} From 8dc36aa2e2bbc9b99bde043b593cdc6c9669f401 Mon Sep 17 00:00:00 2001 From: Kyle Buckingham Date: Tue, 1 Apr 2025 15:23:28 -0700 Subject: [PATCH 2/8] Update robots.txt --- robots.txt | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/robots.txt b/robots.txt index 8c79fc2..e19468d 100644 --- a/robots.txt +++ b/robots.txt @@ -8,8 +8,9 @@ User-agent: Brightbot 1.0 User-agent: Bytespider User-agent: CCBot User-agent: ChatGPT-User -User-agent: Claude-Web User-agent: ClaudeBot +User-agent: Claude-User +User-agent: Claude-SearchBot User-agent: cohere-ai User-agent: cohere-training-data-crawler User-agent: Crawlspace From 4a6f37d72718aeb44d1d8cbcccb740ace3fe82d6 Mon Sep 17 00:00:00 2001 From: Kyle Buckingham Date: Wed, 16 Apr 2025 16:42:58 -0700 Subject: [PATCH 3/8] Update robots.json Co-authored-by: Glyn Normington --- robots.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/robots.json b/robots.json index f711d43..ba052ae 100644 --- a/robots.json +++ b/robots.json @@ -78,7 +78,7 @@ }, "Claude-User": { "operator": "[Anthropic](https://www.anthropic.com)", - "respect": "Unclear at this time.", + "respect": "[Yes](https://support.anthropic.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler)", "function": "Claude-User supports Claude AI users. When individuals ask questions to Claude, it may access websites using a Claude-User agent.", "frequency": "No information provided.", "description": "Claude-User supports Claude AI users. When individuals ask questions to Claude, it may access websites using a Claude-User agent." From fd41de8522536a25de71f37310a05e77d71a0792 Mon Sep 17 00:00:00 2001 From: Kyle Buckingham Date: Wed, 16 Apr 2025 16:43:03 -0700 Subject: [PATCH 4/8] Update robots.json Co-authored-by: Glyn Normington --- robots.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/robots.json b/robots.json index ba052ae..ca6fc40 100644 --- a/robots.json +++ b/robots.json @@ -85,7 +85,7 @@ }, "Claude-SearchBot": { "operator": "[Anthropic](https://www.anthropic.com)", - "respect": "Unclear at this time.", + "respect": "[Yes](https://support.anthropic.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler)", "function": "Claude-SearchBot navigates the web to improve search result quality for users. It analyzes online content specifically to enhance the relevance and accuracy of search responses.", "frequency": "No information provided.", "description": "Claude-SearchBot navigates the web to improve search result quality for users. It analyzes online content specifically to enhance the relevance and accuracy of search responses." From b1d9a60a38c04cac81dd156ad73ddef7eb60b50b Mon Sep 17 00:00:00 2001 From: Cory Dransfeldt Date: Wed, 21 May 2025 11:40:33 -0700 Subject: [PATCH 5/8] chore(robots.json): adds wpbot --- robots.json | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/robots.json b/robots.json index bddefdd..ed7d63d 100644 --- a/robots.json +++ b/robots.json @@ -412,6 +412,13 @@ "frequency": "Unclear at this time.", "description": "Webzio-Extended is a web crawler used by Webz.io to maintain a repository of web crawl data that it sells to other companies, including those using it to train AI models. More info can be found at https://darkvisitors.com/agents/agents/webzio-extended" }, + "wpbot": { + "operator": "[QuantumCloud](https://www.quantumcloud.com)", + "respect": "Unclear at this time; opt out provided via [Google Form](https://forms.gle/ajBaxygz9jSR8p8G9)", + "function": "Live chat support and lead generation.", + "frequency": "Unclear at this time.", + "description": "wpbot is a used to support the functionality of the AI Chatbot for WordPress plugin. It supports the use of customer models, data collection and customer support." + }, "YouBot": { "operator": "[You](https://about.you.com/youchat/)", "respect": "[Yes](https://about.you.com/youbot/)", @@ -419,4 +426,4 @@ "frequency": "No information.", "description": "Retrieves data used for You.com web search engine and LLMs." } -} \ No newline at end of file +} From 7c5389f4a0c5f60745e1a7552e142bd33a587d8f Mon Sep 17 00:00:00 2001 From: "ai.robots.txt" Date: Wed, 21 May 2025 19:00:23 +0000 Subject: [PATCH 6/8] Merge pull request #98 from kylebuckingham/main Updating Claude Bots --- .htaccess | 2 +- Caddyfile | 2 +- haproxy-block-ai-bots.txt | 3 ++- nginx-block-ai-bots.conf | 2 +- table-of-bot-metrics.md | 3 ++- 5 files changed, 7 insertions(+), 5 deletions(-) diff --git a/.htaccess b/.htaccess index cc483c7..2146722 100644 --- a/.htaccess +++ b/.htaccess @@ -1,3 +1,3 @@ RewriteEngine On -RewriteCond %{HTTP_USER_AGENT} (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\-CloudVertexBot|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|MistralAI\-User/1\.0|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Perplexity\-User|PerplexityBot|PetalBot|QualifiedBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|TikTokSpider|Timpibot|VelenPublicWebCrawler|Webzio\-Extended|YouBot) [NC] +RewriteCond %{HTTP_USER_AGENT} (AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|anthropic\-ai|Applebot|Applebot\-Extended|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|ClaudeBot|Claude\-User|Claude\-SearchBot|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|imgproxy|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|QualifiedBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|TikTokSpider|Timpibot|VelenPublicWebCrawler|Webzio\-Extended|YouBot) [NC] RewriteRule !^/?robots\.txt$ - [F,L] diff --git a/Caddyfile b/Caddyfile index 205acbd..879426d 100644 --- a/Caddyfile +++ b/Caddyfile @@ -1,3 +1,3 @@ @aibots { - header_regexp User-Agent "(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\-CloudVertexBot|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|MistralAI\-User/1\.0|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Perplexity\-User|PerplexityBot|PetalBot|QualifiedBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|TikTokSpider|Timpibot|VelenPublicWebCrawler|Webzio\-Extended|YouBot)" + header_regexp User-Agent "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|anthropic\-ai|Applebot|Applebot\-Extended|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|ClaudeBot|Claude\-User|Claude\-SearchBot|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|imgproxy|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|QualifiedBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|TikTokSpider|Timpibot|VelenPublicWebCrawler|Webzio\-Extended|YouBot)" } \ No newline at end of file diff --git a/haproxy-block-ai-bots.txt b/haproxy-block-ai-bots.txt index de5b4fb..8a9ccf9 100644 --- a/haproxy-block-ai-bots.txt +++ b/haproxy-block-ai-bots.txt @@ -9,8 +9,9 @@ Brightbot 1.0 Bytespider CCBot ChatGPT-User -Claude-Web ClaudeBot +Claude-User +Claude-SearchBot cohere-ai cohere-training-data-crawler Cotoyogi diff --git a/nginx-block-ai-bots.conf b/nginx-block-ai-bots.conf index 3274559..5f96718 100644 --- a/nginx-block-ai-bots.conf +++ b/nginx-block-ai-bots.conf @@ -1,3 +1,3 @@ -if ($http_user_agent ~* "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|anthropic\-ai|Applebot|Applebot\-Extended|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Diffbot|DuckAssistBot|FacebookBot|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Google\-CloudVertexBot|Google\-Extended|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|imgproxy|ISSCyberRiskCrawler|Kangaroo\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User/1\.0|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Perplexity\-User|PerplexityBot|PetalBot|QualifiedBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|TikTokSpider|Timpibot|VelenPublicWebCrawler|Webzio\-Extended|YouBot)") { +if ($http_user_agent ~* "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|anthropic\-ai|Applebot|Applebot\-Extended|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|ClaudeBot|Claude\-User|Claude\-SearchBot|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|imgproxy|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|QualifiedBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|TikTokSpider|Timpibot|VelenPublicWebCrawler|Webzio\-Extended|YouBot)") { return 403; } \ No newline at end of file diff --git a/table-of-bot-metrics.md b/table-of-bot-metrics.md index 84c69f5..e6f35a4 100644 --- a/table-of-bot-metrics.md +++ b/table-of-bot-metrics.md @@ -11,8 +11,9 @@ | Bytespider | ByteDance | No | LLM training. | Unclear at this time. | Downloads data to train LLMS, including ChatGPT competitors. | | CCBot | [Common Crawl Foundation](https://commoncrawl.org) | [Yes](https://commoncrawl.org/ccbot) | Provides open crawl dataset, used for many purposes, including Machine Learning/AI. | Monthly at present. | Web archive going back to 2008. [Cited in thousands of research papers per year](https://commoncrawl.org/research-papers). | | ChatGPT\-User | [OpenAI](https://openai.com) | Yes | Takes action based on user prompts. | Only when prompted by a user. | Used by plugins in ChatGPT to answer queries based on user input. | -| Claude\-Web | [Anthropic](https://www.anthropic.com) | Unclear at this time. | Scrapes data to train Anthropic's AI products. | No information provided. | Scrapes data to train LLMs and AI products offered by Anthropic. | | ClaudeBot | [Anthropic](https://www.anthropic.com) | [Yes](https://support.anthropic.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler) | Scrapes data to train Anthropic's AI products. | No information provided. | Scrapes data to train LLMs and AI products offered by Anthropic. | +| Claude\-User | [Anthropic](https://www.anthropic.com) | [Yes](https://support.anthropic.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler) | Claude-User supports Claude AI users. When individuals ask questions to Claude, it may access websites using a Claude-User agent. | No information provided. | Claude-User supports Claude AI users. When individuals ask questions to Claude, it may access websites using a Claude-User agent. | +| Claude\-SearchBot | [Anthropic](https://www.anthropic.com) | [Yes](https://support.anthropic.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler) | Claude-SearchBot navigates the web to improve search result quality for users. It analyzes online content specifically to enhance the relevance and accuracy of search responses. | No information provided. | Claude-SearchBot navigates the web to improve search result quality for users. It analyzes online content specifically to enhance the relevance and accuracy of search responses. | | cohere\-ai | [Cohere](https://cohere.com) | Unclear at this time. | Retrieves data to provide responses to user-initiated prompts. | Takes action based on user prompts. | Retrieves data based on user prompts. | | cohere\-training\-data\-crawler | Cohere to download training data for its LLMs (Large Language Models) that power its enterprise AI products | Unclear at this time. | AI Data Scrapers | Unclear at this time. | cohere-training-data-crawler is a web crawler operated by Cohere to download training data for its LLMs (Large Language Models) that power its enterprise AI products. More info can be found at https://darkvisitors.com/agents/agents/cohere-training-data-crawler | | Cotoyogi | [ROIS](https://ds.rois.ac.jp/en_center8/en_crawler/) | Yes | AI LLM Scraper. | No information provided. | Scrapes data for AI training in Japanese language. | From fedb658cc08225d71a6b0f32c9c2859b7420f0ee Mon Sep 17 00:00:00 2001 From: "ai.robots.txt" Date: Wed, 21 May 2025 21:06:05 +0000 Subject: [PATCH 7/8] Merge pull request #133 from ai-robots-txt/wpbot chore(robots.json): adds wpbot --- .htaccess | 2 +- Caddyfile | 2 +- haproxy-block-ai-bots.txt | 1 + nginx-block-ai-bots.conf | 2 +- robots.txt | 1 + table-of-bot-metrics.md | 1 + 6 files changed, 6 insertions(+), 3 deletions(-) diff --git a/.htaccess b/.htaccess index 2146722..3337284 100644 --- a/.htaccess +++ b/.htaccess @@ -1,3 +1,3 @@ RewriteEngine On -RewriteCond %{HTTP_USER_AGENT} (AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|anthropic\-ai|Applebot|Applebot\-Extended|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|ClaudeBot|Claude\-User|Claude\-SearchBot|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|imgproxy|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|QualifiedBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|TikTokSpider|Timpibot|VelenPublicWebCrawler|Webzio\-Extended|YouBot) [NC] +RewriteCond %{HTTP_USER_AGENT} (AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|anthropic\-ai|Applebot|Applebot\-Extended|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|ClaudeBot|Claude\-User|Claude\-SearchBot|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|imgproxy|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|QualifiedBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|TikTokSpider|Timpibot|VelenPublicWebCrawler|Webzio\-Extended|wpbot|YouBot) [NC] RewriteRule !^/?robots\.txt$ - [F,L] diff --git a/Caddyfile b/Caddyfile index 879426d..2001edc 100644 --- a/Caddyfile +++ b/Caddyfile @@ -1,3 +1,3 @@ @aibots { - header_regexp User-Agent "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|anthropic\-ai|Applebot|Applebot\-Extended|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|ClaudeBot|Claude\-User|Claude\-SearchBot|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|imgproxy|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|QualifiedBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|TikTokSpider|Timpibot|VelenPublicWebCrawler|Webzio\-Extended|YouBot)" + header_regexp User-Agent "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|anthropic\-ai|Applebot|Applebot\-Extended|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|ClaudeBot|Claude\-User|Claude\-SearchBot|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|imgproxy|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|QualifiedBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|TikTokSpider|Timpibot|VelenPublicWebCrawler|Webzio\-Extended|wpbot|YouBot)" } \ No newline at end of file diff --git a/haproxy-block-ai-bots.txt b/haproxy-block-ai-bots.txt index 8a9ccf9..377710b 100644 --- a/haproxy-block-ai-bots.txt +++ b/haproxy-block-ai-bots.txt @@ -58,4 +58,5 @@ TikTokSpider Timpibot VelenPublicWebCrawler Webzio-Extended +wpbot YouBot \ No newline at end of file diff --git a/nginx-block-ai-bots.conf b/nginx-block-ai-bots.conf index 5f96718..ba1f8c6 100644 --- a/nginx-block-ai-bots.conf +++ b/nginx-block-ai-bots.conf @@ -1,3 +1,3 @@ -if ($http_user_agent ~* "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|anthropic\-ai|Applebot|Applebot\-Extended|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|ClaudeBot|Claude\-User|Claude\-SearchBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Diffbot|DuckAssistBot|FacebookBot|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Google\-CloudVertexBot|Google\-Extended|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|imgproxy|ISSCyberRiskCrawler|Kangaroo\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User/1\.0|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Perplexity\-User|PerplexityBot|PetalBot|QualifiedBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|TikTokSpider|Timpibot|VelenPublicWebCrawler|Webzio\-Extended|YouBot)") { +if ($http_user_agent ~* "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|anthropic\-ai|Applebot|Applebot\-Extended|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|ClaudeBot|Claude\-User|Claude\-SearchBot|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|imgproxy|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|QualifiedBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|TikTokSpider|Timpibot|VelenPublicWebCrawler|Webzio\-Extended|wpbot|YouBot)") { return 403; } \ No newline at end of file diff --git a/robots.txt b/robots.txt index 8690e50..92e527b 100644 --- a/robots.txt +++ b/robots.txt @@ -58,5 +58,6 @@ User-agent: TikTokSpider User-agent: Timpibot User-agent: VelenPublicWebCrawler User-agent: Webzio-Extended +User-agent: wpbot User-agent: YouBot Disallow: / diff --git a/table-of-bot-metrics.md b/table-of-bot-metrics.md index e6f35a4..c795559 100644 --- a/table-of-bot-metrics.md +++ b/table-of-bot-metrics.md @@ -60,4 +60,5 @@ | Timpibot | [Timpi](https://timpi.io) | Unclear at this time. | Scrapes data for use in training LLMs. | No information. | Makes data available for training AI models. | | VelenPublicWebCrawler | [Velen Crawler](https://velen.io) | [Yes](https://velen.io) | Scrapes data for business data sets and machine learning models. | No information. | "Our goal with this crawler is to build business datasets and machine learning models to better understand the web." | | Webzio\-Extended | Unclear at this time. | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Webzio-Extended is a web crawler used by Webz.io to maintain a repository of web crawl data that it sells to other companies, including those using it to train AI models. More info can be found at https://darkvisitors.com/agents/agents/webzio-extended | +| wpbot | [QuantumCloud](https://www.quantumcloud.com) | Unclear at this time; opt out provided via [Google Form](https://forms.gle/ajBaxygz9jSR8p8G9) | Live chat support and lead generation. | Unclear at this time. | wpbot is a used to support the functionality of the AI Chatbot for WordPress plugin. It supports the use of customer models, data collection and customer support. | | YouBot | [You](https://about.you.com/youchat/) | [Yes](https://about.you.com/youbot/) | Scrapes data for search engine and LLMs. | No information. | Retrieves data used for You.com web search engine and LLMs. | From 7bf7f9164d55a58e0d6080dff52eea3ed5d3584e Mon Sep 17 00:00:00 2001 From: dark-visitors Date: Thu, 22 May 2025 00:58:45 +0000 Subject: [PATCH 8/8] Update from Dark Visitors --- robots.json | 31 +++++++++++++++++++------------ 1 file changed, 19 insertions(+), 12 deletions(-) diff --git a/robots.json b/robots.json index 9dce781..06187ae 100644 --- a/robots.json +++ b/robots.json @@ -76,12 +76,12 @@ "frequency": "Only when prompted by a user.", "description": "Used by plugins in ChatGPT to answer queries based on user input." }, - "ClaudeBot": { + "Claude-SearchBot": { "operator": "[Anthropic](https://www.anthropic.com)", "respect": "[Yes](https://support.anthropic.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler)", - "function": "Scrapes data to train Anthropic's AI products.", + "function": "Claude-SearchBot navigates the web to improve search result quality for users. It analyzes online content specifically to enhance the relevance and accuracy of search responses.", "frequency": "No information provided.", - "description": "Scrapes data to train LLMs and AI products offered by Anthropic." + "description": "Claude-SearchBot navigates the web to improve search result quality for users. It analyzes online content specifically to enhance the relevance and accuracy of search responses." }, "Claude-User": { "operator": "[Anthropic](https://www.anthropic.com)", @@ -90,12 +90,19 @@ "frequency": "No information provided.", "description": "Claude-User supports Claude AI users. When individuals ask questions to Claude, it may access websites using a Claude-User agent." }, - "Claude-SearchBot": { + "Claude-Web": { + "operator": "Anthropic", + "respect": "Unclear at this time.", + "function": "Undocumented AI Agents", + "frequency": "Unclear at this time.", + "description": "Claude-Web is an AI-related agent operated by Anthropic. It's currently unclear exactly what it's used for, since there's no official documentation. If you can provide more detail, please contact us. More info can be found at https://darkvisitors.com/agents/agents/claude-web" + }, + "ClaudeBot": { "operator": "[Anthropic](https://www.anthropic.com)", "respect": "[Yes](https://support.anthropic.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler)", - "function": "Claude-SearchBot navigates the web to improve search result quality for users. It analyzes online content specifically to enhance the relevance and accuracy of search responses.", + "function": "Scrapes data to train Anthropic's AI products.", "frequency": "No information provided.", - "description": "Claude-SearchBot navigates the web to improve search result quality for users. It analyzes online content specifically to enhance the relevance and accuracy of search responses." + "description": "Scrapes data to train LLMs and AI products offered by Anthropic." }, "cohere-ai": { "operator": "[Cohere](https://cohere.com)", @@ -287,11 +294,11 @@ "description": "Meta-ExternalFetcher is dispatched by Meta AI products in response to user prompts, when they need to fetch an individual links. More info can be found at https://darkvisitors.com/agents/agents/meta-externalfetcher" }, "MistralAI-User/1.0": { - "operator": "Mistral AI", - "function": "Takes action based on user prompts.", - "frequency": "Only when prompted by a user.", - "description": "MistralAI-User is for user actions in LeChat. When users ask LeChat a question, it may visit a web page to help answer and include a link to the source in its response.", - "respect": "Yes" + "operator": "Mistral AI", + "function": "Takes action based on user prompts.", + "frequency": "Only when prompted by a user.", + "description": "MistralAI-User is for user actions in LeChat. When users ask LeChat a question, it may visit a web page to help answer and include a link to the source in its response.", + "respect": "Yes" }, "NovaAct": { "operator": "Unclear at this time.", @@ -433,4 +440,4 @@ "frequency": "No information.", "description": "Retrieves data used for You.com web search engine and LLMs." } -} +} \ No newline at end of file