diff --git a/.htaccess b/.htaccess index dbbde1e..5fefc69 100644 --- 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|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) [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 index 08b2fd3..5caa249 100644 --- a/Caddyfile +++ b/Caddyfile @@ -1,3 +1,3 @@ @aibots { - header_regexp 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)" + 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)" } \ No newline at end of file diff --git a/haproxy-block-ai-bots.txt b/haproxy-block-ai-bots.txt index cdaeecd..fe153c8 100644 --- a/haproxy-block-ai-bots.txt +++ b/haproxy-block-ai-bots.txt @@ -6,7 +6,6 @@ Andibot anthropic-ai Applebot Applebot-Extended -bedrockbot Brightbot 1.0 Bytespider CCBot diff --git a/nginx-block-ai-bots.conf b/nginx-block-ai-bots.conf index 542ac65..e5d660b 100644 --- a/nginx-block-ai-bots.conf +++ b/nginx-block-ai-bots.conf @@ -1,3 +1,3 @@ -if ($http_user_agent ~* "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|bedrockbot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Diffbot|DuckAssistBot|FacebookBot|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Google\-CloudVertexBot|Google\-Extended|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User/1\.0|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|TikTokSpider|Timpibot|VelenPublicWebCrawler|Webzio\-Extended|wpbot|YandexAdditional|YandexAdditionalBot|YouBot)") { +if ($http_user_agent ~* "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|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; } \ No newline at end of file diff --git a/robots.json b/robots.json index 8f5dadd..6df5084 100644 --- a/robots.json +++ b/robots.json @@ -55,13 +55,6 @@ "frequency": "Unclear at this time.", "description": "Apple has a secondary user agent, Applebot-Extended ... [that is] used to train Apple's foundation models powering generative AI features across Apple products, including Apple Intelligence, Services, and Developer Tools." }, - "bedrockbot": { - "operator": "[Amazon](https://amazon.com)", - "respect": "[Yes](https://docs.aws.amazon.com/bedrock/latest/userguide/webcrawl-data-source-connector.html#configuration-webcrawl-connector)", - "function": "Data scraping for custom AI applications.", - "frequency": "Unclear at this time.", - "description": "Connects to and crawls URLs that have been selected for use in a user's AWS bedrock application." - }, "Brightbot 1.0": { "operator": "Browsing.ai", "respect": "Unclear at this time.", @@ -503,4 +496,4 @@ "frequency": "No information.", "description": "Retrieves data used for You.com web search engine and LLMs." } -} +} \ No newline at end of file diff --git a/robots.txt b/robots.txt index a8dc655..26a9d78 100644 --- a/robots.txt +++ b/robots.txt @@ -6,7 +6,6 @@ User-agent: Andibot User-agent: anthropic-ai User-agent: Applebot User-agent: Applebot-Extended -User-agent: bedrockbot User-agent: Brightbot 1.0 User-agent: Bytespider User-agent: CCBot diff --git a/table-of-bot-metrics.md b/table-of-bot-metrics.md index ee324f7..69b9ec2 100644 --- a/table-of-bot-metrics.md +++ b/table-of-bot-metrics.md @@ -8,7 +8,6 @@ | anthropic\-ai | [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. | | Applebot | Unclear at this time. | Unclear at this time. | AI Search Crawlers | Unclear at this time. | Applebot is a web crawler used by Apple to index search results that allow the Siri AI Assistant to answer user questions. Siri's answers normally contain references to the website. More info can be found at https://darkvisitors.com/agents/agents/applebot | | Applebot\-Extended | [Apple](https://support.apple.com/en-us/119829#datausage) | Yes | Powers features in Siri, Spotlight, Safari, Apple Intelligence, and others. | Unclear at this time. | Apple has a secondary user agent, Applebot-Extended ... [that is] used to train Apple's foundation models powering generative AI features across Apple products, including Apple Intelligence, Services, and Developer Tools. | -| bedrockbot | [Amazon](https://amazon.com) | [Yes](https://docs.aws.amazon.com/bedrock/latest/userguide/webcrawl-data-source-connector.html#configuration-webcrawl-connector) | Data scraping for custom AI applications. | Unclear at this time. | Connects to and crawls URLs that have been selected for use in a user's AWS bedrock application. | | Brightbot 1\.0 | Browsing.ai | Unclear at this time. | LLM/AI training. | Unclear at this time. | Scrapes data to train LLMs and AI products focused on website customer support. | | 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). |