diff --git a/.htaccess b/.htaccess index cc483c7..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|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|wpbot|YouBot) [NC] RewriteRule !^/?robots\.txt$ - [F,L] diff --git a/Caddyfile b/Caddyfile index 205acbd..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|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|wpbot|YouBot)" } \ No newline at end of file diff --git a/haproxy-block-ai-bots.txt b/haproxy-block-ai-bots.txt index de5b4fb..377710b 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 @@ -57,4 +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 3274559..ba1f8c6 100644 --- a/nginx-block-ai-bots.conf +++ b/nginx-block-ai-bots.conf @@ -1,3 +1,3 @@ -if ($http_user_agent ~* "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|anthropic\-ai|Applebot|Applebot\-Extended|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Diffbot|DuckAssistBot|FacebookBot|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Google\-CloudVertexBot|Google\-Extended|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|imgproxy|ISSCyberRiskCrawler|Kangaroo\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User/1\.0|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Perplexity\-User|PerplexityBot|PetalBot|QualifiedBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|TikTokSpider|Timpibot|VelenPublicWebCrawler|Webzio\-Extended|YouBot)") { +if ($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|wpbot|YouBot)") { return 403; } \ No newline at end of file diff --git a/robots.json b/robots.json index bddefdd..06187ae 100644 --- a/robots.json +++ b/robots.json @@ -76,12 +76,26 @@ "frequency": "Only when prompted by a user.", "description": "Used by plugins in ChatGPT to answer queries based on user input." }, - "Claude-Web": { + "Claude-SearchBot": { "operator": "[Anthropic](https://www.anthropic.com)", - "respect": "Unclear at this time.", - "function": "Scrapes data to train Anthropic's AI products.", + "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": "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)", + "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." + }, + "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)", @@ -280,11 +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.", @@ -412,6 +426,13 @@ "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/)", diff --git a/robots.txt b/robots.txt index b3e16f8..92e527b 100644 --- a/robots.txt +++ b/robots.txt @@ -9,8 +9,9 @@ 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: Cotoyogi @@ -57,5 +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 84c69f5..c795559 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. | @@ -59,4 +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. |