diff --git a/.htaccess b/.htaccess index 74b4e5b..a6c8fea 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|EchoboxBot|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|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|EchoboxBot|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|SemrushBot\-BA|SemrushBot\-CT|SemrushBot\-OCOB|SemrushBot\-SI|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 9ca050b..7ed7e03 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|EchoboxBot|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|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|EchoboxBot|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|SemrushBot\-BA|SemrushBot\-CT|SemrushBot\-OCOB|SemrushBot\-SI|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 dc9f851..fe6c362 100644 --- a/haproxy-block-ai-bots.txt +++ b/haproxy-block-ai-bots.txt @@ -60,7 +60,11 @@ QuillBot quillbot.com SBIntuitionsBot Scrapy +SemrushBot +SemrushBot-BA +SemrushBot-CT SemrushBot-OCOB +SemrushBot-SI SemrushBot-SWA Sidetrade indexer bot TikTokSpider diff --git a/nginx-block-ai-bots.conf b/nginx-block-ai-bots.conf index 4fd7a29..13aac72 100644 --- a/nginx-block-ai-bots.conf +++ b/nginx-block-ai-bots.conf @@ -1,3 +1,3 @@ -if ($http_user_agent ~* "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|bedrockbot|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|Claude\-SearchBot|Claude\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Cotoyogi|Crawlspace|Diffbot|DuckAssistBot|EchoboxBot|FacebookBot|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Google\-CloudVertexBot|Google\-Extended|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|meta\-externalagent|Meta\-ExternalAgent|meta\-externalfetcher|Meta\-ExternalFetcher|MistralAI\-User/1\.0|NovaAct|OAI\-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient\.com|Perplexity\-User|PerplexityBot|PetalBot|PhindBot|QualifiedBot|QuillBot|quillbot\.com|SBIntuitionsBot|Scrapy|SemrushBot\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|TikTokSpider|Timpibot|VelenPublicWebCrawler|Webzio\-Extended|wpbot|YandexAdditional|YandexAdditionalBot|YouBot)") { +if ($http_user_agent ~* "(AI2Bot|Ai2Bot\-Dolma|aiHitBot|Amazonbot|Andibot|anthropic\-ai|Applebot|Applebot\-Extended|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|EchoboxBot|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|SemrushBot\-BA|SemrushBot\-CT|SemrushBot\-OCOB|SemrushBot\-SI|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.txt b/robots.txt index 8964626..b130083 100644 --- a/robots.txt +++ b/robots.txt @@ -60,7 +60,11 @@ User-agent: QuillBot User-agent: quillbot.com User-agent: SBIntuitionsBot User-agent: Scrapy +User-agent: SemrushBot +User-agent: SemrushBot-BA +User-agent: SemrushBot-CT User-agent: SemrushBot-OCOB +User-agent: SemrushBot-SI User-agent: SemrushBot-SWA User-agent: Sidetrade indexer bot User-agent: TikTokSpider diff --git a/table-of-bot-metrics.md b/table-of-bot-metrics.md index b596540..a834382 100644 --- a/table-of-bot-metrics.md +++ b/table-of-bot-metrics.md @@ -62,7 +62,11 @@ | quillbot\.com | [Quillbot](https://quillbot.com) | Unclear at this time. | Company offers AI detection, writing tools and other services. | No explicit frequency provided. | Operated by QuillBot as part of their suite of AI product offerings. | | SBIntuitionsBot | [SB Intuitions](https://www.sbintuitions.co.jp/en/) | [Yes](https://www.sbintuitions.co.jp/en/bot/) | Uses data gathered in AI development and information analysis. | No information. | AI development and information analysis | | Scrapy | [Zyte](https://www.zyte.com) | Unclear at this time. | Scrapes data for a variety of uses including training AI. | No information. | "AI and machine learning applications often need large amounts of quality data, and web data extraction is a fast, efficient way to build structured data sets." | +| SemrushBot | [Semrush](https://www.semrush.com/) | [Yes](https://www.semrush.com/bot/) | Crawls your site for ContentShake AI tool. | Roughly once every 10 seconds. | You enter one text (on-demand) and we will make suggestions on it (the tool uses AI but we are not actively crawling the web, you need to manually enter one text/URL). | +| SemrushBot\-BA | [Semrush](https://www.semrush.com/) | [Yes](https://www.semrush.com/bot/) | Crawls your site for ContentShake AI tool. | Roughly once every 10 seconds. | You enter one text (on-demand) and we will make suggestions on it (the tool uses AI but we are not actively crawling the web, you need to manually enter one text/URL). | +| SemrushBot\-CT | [Semrush](https://www.semrush.com/) | [Yes](https://www.semrush.com/bot/) | Crawls your site for ContentShake AI tool. | Roughly once every 10 seconds. | You enter one text (on-demand) and we will make suggestions on it (the tool uses AI but we are not actively crawling the web, you need to manually enter one text/URL). | | SemrushBot\-OCOB | [Semrush](https://www.semrush.com/) | [Yes](https://www.semrush.com/bot/) | Crawls your site for ContentShake AI tool. | Roughly once every 10 seconds. | You enter one text (on-demand) and we will make suggestions on it (the tool uses AI but we are not actively crawling the web, you need to manually enter one text/URL). | +| SemrushBot\-SI | [Semrush](https://www.semrush.com/) | [Yes](https://www.semrush.com/bot/) | Crawls your site for ContentShake AI tool. | Roughly once every 10 seconds. | You enter one text (on-demand) and we will make suggestions on it (the tool uses AI but we are not actively crawling the web, you need to manually enter one text/URL). | | SemrushBot\-SWA | [Semrush](https://www.semrush.com/) | [Yes](https://www.semrush.com/bot/) | Checks URLs on your site for SWA tool. | Roughly once every 10 seconds. | You enter one text (on-demand) and we will make suggestions on it (the tool uses AI but we are not actively crawling the web, you need to manually enter one text/URL). | | 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. | | TikTokSpider | ByteDance | Unclear at this time. | LLM training. | Unclear at this time. | Downloads data to train LLMS, as per Bytespider. |