diff --git a/.htaccess b/.htaccess index 7df1c4d..83ef73a 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|Awario|bedrockbot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|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|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|SummalyBot|TikTokSpider|Thinkbot|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YandexAdditional|YandexAdditionalBot|YouBot) [NC] +RewriteCond %{HTTP_USER_AGENT} (AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|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|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|SummalyBot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YandexAdditional|YandexAdditionalBot|YouBot) [NC] RewriteRule !^/?robots\.txt$ - [F] diff --git a/Caddyfile b/Caddyfile index a317541..0f73ac1 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|Awario|bedrockbot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|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|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|SummalyBot|TikTokSpider|Thinkbot|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YandexAdditional|YandexAdditionalBot|YouBot)" + header_regexp User-Agent "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|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|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|SummalyBot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|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 9d4bd10..734d3d5 100644 --- a/haproxy-block-ai-bots.txt +++ b/haproxy-block-ai-bots.txt @@ -74,8 +74,8 @@ SemrushBot-OCOB SemrushBot-SWA Sidetrade indexer bot SummalyBot -TikTokSpider Thinkbot +TikTokSpider Timpibot VelenPublicWebCrawler WARDBot diff --git a/nginx-block-ai-bots.conf b/nginx-block-ai-bots.conf index f4293ce..b967a01 100644 --- a/nginx-block-ai-bots.conf +++ b/nginx-block-ai-bots.conf @@ -1,3 +1,3 @@ -if ($http_user_agent ~* "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|Google\-CloudVertexBot|Google\-Extended|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|SummalyBot|TikTokSpider|Thinkbot|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YandexAdditional|YandexAdditionalBot|YouBot)") { +if ($http_user_agent ~* "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|Awario|bedrockbot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Datenbank\ Crawler|Devin|Diffbot|DuckAssistBot|Echobot\ Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini\-Deep\-Research|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|MistralAI\-User/1\.0|MyCentralAIScraperBot|netEstate\ Imprint\ Crawler|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|Poseidon\ Research\ Crawler|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|SummalyBot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio\-Extended|wpbot|YandexAdditional|YandexAdditionalBot|YouBot)") { return 403; } \ No newline at end of file diff --git a/robots.txt b/robots.txt index 558e6c9..584fd19 100644 --- a/robots.txt +++ b/robots.txt @@ -74,8 +74,8 @@ User-agent: SemrushBot-OCOB User-agent: SemrushBot-SWA User-agent: Sidetrade indexer bot User-agent: SummalyBot -User-agent: TikTokSpider User-agent: Thinkbot +User-agent: TikTokSpider User-agent: Timpibot User-agent: VelenPublicWebCrawler User-agent: WARDBot diff --git a/table-of-bot-metrics.md b/table-of-bot-metrics.md index 9ac6ddc..9971d49 100644 --- a/table-of-bot-metrics.md +++ b/table-of-bot-metrics.md @@ -76,8 +76,8 @@ | SemrushBot\-SWA | [Semrush](https://www.semrush.com/) | [Yes](https://www.semrush.com/bot/) | Checks URLs on your site for SEO Writing Assistant. | Roughly once every 10 seconds. | Data collected is used for the SEO Writing Assistant tool to check if URL is accessible. | | Sidetrade indexer bot | [Sidetrade](https://www.sidetrade.com) | Unclear at this time. | Extracts data for a variety of uses including training AI. | No information. | AI product training. | | SummalyBot | Unclear at this time. | Unclear at this time. | Extracts data to provide summaries for user; additional usages unclear. | No information. | AI input summarization. | -| TikTokSpider | ByteDance | Unclear at this time. | LLM training. | Unclear at this time. | Downloads data to train LLMS, as per Bytespider. | | Thinkbot | [Thinkbot](https://www.thinkbot.agency) | No | Insights on AI integration and automation. | Unclear at this time. | Collects data for analysis on AI usage and automation. | +| TikTokSpider | ByteDance | Unclear at this time. | LLM training. | Unclear at this time. | Downloads data to train LLMS, as per Bytespider. | | 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." | | WARDBot | WEBSPARK | Unclear at this time. | AI Data Scrapers | Unclear at this time. | WARDBot is an AI data scraper operated by WEBSPARK. It's not currently known to be artificially intelligent or AI-related. If you think that's incorrect or can provide more detail about its purpose, please contact us. More info can be found at https://darkvisitors.com/agents/agents/wardbot |