chore(ua-blocker): update robots.json from upstream (#1280)

Co-authored-by: yusukebe <10682+yusukebe@users.noreply.github.com>
pull/1281/head
github-actions[bot] 2025-07-04 18:13:57 +09:00 committed by GitHub
parent 37d1427601
commit 02a703cffa
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 28 additions and 39 deletions

View File

@ -0,0 +1,5 @@
---
'@hono/ua-blocker': patch
---
chore(ua-blocker): sync `robots.json` with upstream

View File

@ -230,6 +230,13 @@
"operator": "Unknown", "operator": "Unknown",
"respect": "[Yes](https://imho.alex-kunz.com/2024/01/25/an-update-on-friendly-crawler)" "respect": "[Yes](https://imho.alex-kunz.com/2024/01/25/an-update-on-friendly-crawler)"
}, },
"Gemini-Deep-Research": {
"operator": "Unclear at this time.",
"respect": "Unclear at this time.",
"function": "AI Assistants",
"frequency": "Unclear at this time.",
"description": "Gemini-Deep-Research is the agent responsible for collecting and scanning resources used in Google Gemini's Deep Research feature, which acts as a personal research assistant. More info can be found at https://darkvisitors.com/agents/agents/gemini-deep-research"
},
"Google-CloudVertexBot": { "Google-CloudVertexBot": {
"operator": "Google", "operator": "Google",
"respect": "[Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers)", "respect": "[Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers)",
@ -363,6 +370,13 @@
"frequency": "Unclear at this time.", "frequency": "Unclear at this time.",
"description": "Operator and data use is unclear at this time." "description": "Operator and data use is unclear at this time."
}, },
"netEstate Imprint Crawler": {
"operator": "netEstate",
"respect": "Unclear at this time.",
"function": "AI Data Scrapers",
"frequency": "Unclear at this time.",
"description": "netEstate Imprint Crawler is an AI data scraper operated by netEstate. If you think this is incorrect or can provide additional detail about its purpose, please contact us. More info can be found at https://darkvisitors.com/agents/agents/netestate-imprint-crawler"
},
"NovaAct": { "NovaAct": {
"operator": "Unclear at this time.", "operator": "Unclear at this time.",
"respect": "Unclear at this time.", "respect": "Unclear at this time.",
@ -489,47 +503,19 @@
"operator": "[Zyte](https://www.zyte.com)", "operator": "[Zyte](https://www.zyte.com)",
"respect": "Unclear at this time." "respect": "Unclear at this time."
}, },
"SemrushBot": {
"operator": "[Semrush](https://www.semrush.com/)",
"respect": "[Yes](https://www.semrush.com/bot/)",
"function": "Crawls your site for ContentShake AI tool.",
"frequency": "Roughly once every 10 seconds.",
"description": "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": {
"operator": "[Semrush](https://www.semrush.com/)",
"respect": "[Yes](https://www.semrush.com/bot/)",
"function": "Crawls your site for ContentShake AI tool.",
"frequency": "Roughly once every 10 seconds.",
"description": "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": {
"operator": "[Semrush](https://www.semrush.com/)",
"respect": "[Yes](https://www.semrush.com/bot/)",
"function": "Crawls your site for ContentShake AI tool.",
"frequency": "Roughly once every 10 seconds.",
"description": "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": { "SemrushBot-OCOB": {
"operator": "[Semrush](https://www.semrush.com/)", "operator": "[Semrush](https://www.semrush.com/)",
"respect": "[Yes](https://www.semrush.com/bot/)", "respect": "[Yes](https://www.semrush.com/bot/)",
"function": "Crawls your site for ContentShake AI tool.", "function": "Crawls your site for ContentShake AI tool.",
"frequency": "Roughly once every 10 seconds.", "frequency": "Roughly once every 10 seconds.",
"description": "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)." "description": "Data collected is used for the ContentShake AI tool reports."
},
"SemrushBot-SI": {
"operator": "[Semrush](https://www.semrush.com/)",
"respect": "[Yes](https://www.semrush.com/bot/)",
"function": "Crawls your site for ContentShake AI tool.",
"frequency": "Roughly once every 10 seconds.",
"description": "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": { "SemrushBot-SWA": {
"operator": "[Semrush](https://www.semrush.com/)", "operator": "[Semrush](https://www.semrush.com/)",
"respect": "[Yes](https://www.semrush.com/bot/)", "respect": "[Yes](https://www.semrush.com/bot/)",
"function": "Checks URLs on your site for SWA tool.", "function": "Checks URLs on your site for SEO Writing Assistant.",
"frequency": "Roughly once every 10 seconds.", "frequency": "Roughly once every 10 seconds.",
"description": "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)." "description": "Data collected is used for the SEO Writing Assistant tool to check if URL is accessible."
}, },
"Sidetrade indexer bot": { "Sidetrade indexer bot": {
"description": "AI product training.", "description": "AI product training.",

View File

@ -32,6 +32,7 @@ User-agent: facebookexternalhit
User-agent: Factset_spyderbot User-agent: Factset_spyderbot
User-agent: FirecrawlAgent User-agent: FirecrawlAgent
User-agent: FriendlyCrawler User-agent: FriendlyCrawler
User-agent: Gemini-Deep-Research
User-agent: Google-CloudVertexBot User-agent: Google-CloudVertexBot
User-agent: Google-Extended User-agent: Google-Extended
User-agent: GoogleOther User-agent: GoogleOther
@ -51,6 +52,7 @@ User-agent: Meta-ExternalFetcher
User-agent: MistralAI-User User-agent: MistralAI-User
User-agent: MistralAI-User/1.0 User-agent: MistralAI-User/1.0
User-agent: MyCentralAIScraperBot User-agent: MyCentralAIScraperBot
User-agent: netEstate Imprint Crawler
User-agent: NovaAct User-agent: NovaAct
User-agent: OAI-SearchBot User-agent: OAI-SearchBot
User-agent: omgili User-agent: omgili
@ -69,11 +71,7 @@ User-agent: QuillBot
User-agent: quillbot.com User-agent: quillbot.com
User-agent: SBIntuitionsBot User-agent: SBIntuitionsBot
User-agent: Scrapy User-agent: Scrapy
User-agent: SemrushBot
User-agent: SemrushBot-BA
User-agent: SemrushBot-CT
User-agent: SemrushBot-OCOB User-agent: SemrushBot-OCOB
User-agent: SemrushBot-SI
User-agent: SemrushBot-SWA User-agent: SemrushBot-SWA
User-agent: Sidetrade indexer bot User-agent: Sidetrade indexer bot
User-agent: TikTokSpider User-agent: TikTokSpider
@ -87,7 +85,7 @@ User-agent: YandexAdditionalBot
User-agent: YouBot User-agent: YouBot
Disallow: / Disallow: /
`; `;
export const ALL_BOTS = ["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", "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", "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", "SemrushBot-BA", "SemrushBot-CT", "SemrushBot-OCOB", "SemrushBot-SI", "SemrushBot-SWA", "Sidetrade indexer bot", "TikTokSpider", "Timpibot", "VelenPublicWebCrawler", "WARDBot", "Webzio-Extended", "wpbot", "YandexAdditional", "YandexAdditionalBot", "YouBot"]; export const ALL_BOTS = ["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", "TikTokSpider", "Timpibot", "VelenPublicWebCrawler", "WARDBot", "Webzio-Extended", "wpbot", "YandexAdditional", "YandexAdditionalBot", "YouBot"];
export const NON_RESPECTING_BOTS = ["Andibot", "anthropic-ai", "Applebot", "Awario", "Brightbot 1.0", "Bytespider", "Claude-Web", "cohere-ai", "cohere-training-data-crawler", "Datenbank Crawler", "Devin", "Diffbot", "DuckAssistBot", "Echobot Bot", "EchoboxBot", "facebookexternalhit", "Factset_spyderbot", "iaskspider/2.0", "img2dataset", "ISSCyberRiskCrawler", "Kangaroo Bot", "Meta-ExternalAgent", "meta-externalfetcher", "Meta-ExternalFetcher", "MistralAI-User", "MyCentralAIScraperBot", "NovaAct", "Operator", "PanguBot", "Perplexity-User", "PhindBot", "Poseidon Research Crawler", "QualifiedBot", "QuillBot", "quillbot.com", "Scrapy", "Sidetrade indexer bot", "TikTokSpider", "Timpibot", "WARDBot", "Webzio-Extended", "wpbot"]; export const NON_RESPECTING_BOTS = ["Andibot", "anthropic-ai", "Applebot", "Awario", "Brightbot 1.0", "Bytespider", "Claude-Web", "cohere-ai", "cohere-training-data-crawler", "Datenbank Crawler", "Devin", "Diffbot", "DuckAssistBot", "Echobot Bot", "EchoboxBot", "facebookexternalhit", "Factset_spyderbot", "Gemini-Deep-Research", "iaskspider/2.0", "img2dataset", "ISSCyberRiskCrawler", "Kangaroo Bot", "Meta-ExternalAgent", "meta-externalfetcher", "Meta-ExternalFetcher", "MistralAI-User", "MyCentralAIScraperBot", "netEstate Imprint Crawler", "NovaAct", "Operator", "PanguBot", "Perplexity-User", "PhindBot", "Poseidon Research Crawler", "QualifiedBot", "QuillBot", "quillbot.com", "Scrapy", "Sidetrade indexer bot", "TikTokSpider", "Timpibot", "WARDBot", "Webzio-Extended", "wpbot"];
export const ALL_BOTS_REGEX = /(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|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|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|SEMRUSHBOT-BA|SEMRUSHBOT-CT|SEMRUSHBOT-OCOB|SEMRUSHBOT-SI|SEMRUSHBOT-SWA|SIDETRADE INDEXER BOT|TIKTOKSPIDER|TIMPIBOT|VELENPUBLICWEBCRAWLER|WARDBOT|WEBZIO-EXTENDED|WPBOT|YANDEXADDITIONAL|YANDEXADDITIONALBOT|YOUBOT)/; export const ALL_BOTS_REGEX = /(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|TIKTOKSPIDER|TIMPIBOT|VELENPUBLICWEBCRAWLER|WARDBOT|WEBZIO-EXTENDED|WPBOT|YANDEXADDITIONAL|YANDEXADDITIONALBOT|YOUBOT)/;
export const NON_RESPECTING_BOTS_REGEX = /(ANDIBOT|ANTHROPIC-AI|APPLEBOT|AWARIO|BRIGHTBOT 1.0|BYTESPIDER|CLAUDE-WEB|COHERE-AI|COHERE-TRAINING-DATA-CRAWLER|DATENBANK CRAWLER|DEVIN|DIFFBOT|DUCKASSISTBOT|ECHOBOT BOT|ECHOBOXBOT|FACEBOOKEXTERNALHIT|FACTSET_SPYDERBOT|IASKSPIDER\/2.0|IMG2DATASET|ISSCYBERRISKCRAWLER|KANGAROO BOT|META-EXTERNALAGENT|META-EXTERNALFETCHER|META-EXTERNALFETCHER|MISTRALAI-USER|MYCENTRALAISCRAPERBOT|NOVAACT|OPERATOR|PANGUBOT|PERPLEXITY-USER|PHINDBOT|POSEIDON RESEARCH CRAWLER|QUALIFIEDBOT|QUILLBOT|QUILLBOT.COM|SCRAPY|SIDETRADE INDEXER BOT|TIKTOKSPIDER|TIMPIBOT|WARDBOT|WEBZIO-EXTENDED|WPBOT)/; export const NON_RESPECTING_BOTS_REGEX = /(ANDIBOT|ANTHROPIC-AI|APPLEBOT|AWARIO|BRIGHTBOT 1.0|BYTESPIDER|CLAUDE-WEB|COHERE-AI|COHERE-TRAINING-DATA-CRAWLER|DATENBANK CRAWLER|DEVIN|DIFFBOT|DUCKASSISTBOT|ECHOBOT BOT|ECHOBOXBOT|FACEBOOKEXTERNALHIT|FACTSET_SPYDERBOT|GEMINI-DEEP-RESEARCH|IASKSPIDER\/2.0|IMG2DATASET|ISSCYBERRISKCRAWLER|KANGAROO BOT|META-EXTERNALAGENT|META-EXTERNALFETCHER|META-EXTERNALFETCHER|MISTRALAI-USER|MYCENTRALAISCRAPERBOT|NETESTATE IMPRINT CRAWLER|NOVAACT|OPERATOR|PANGUBOT|PERPLEXITY-USER|PHINDBOT|POSEIDON RESEARCH CRAWLER|QUALIFIEDBOT|QUILLBOT|QUILLBOT.COM|SCRAPY|SIDETRADE INDEXER BOT|TIKTOKSPIDER|TIMPIBOT|WARDBOT|WEBZIO-EXTENDED|WPBOT)/;