suimeng
/
honojs-middleware
mirror of https://github.com/honojs/middleware.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

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
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
.changeset/auto-sync-robots.md 100644
View File

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

48
packages/ua-blocker/src/data/robots.json
View File

@ -230,6 +230,13 @@
"operator": "Unknown",
"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": {
"operator": "Google",
"respect": "[Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers)",
@ -363,6 +370,13 @@
"frequency": "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": {
"operator": "Unclear at this time.",
"respect": "Unclear at this time.",
@ -489,47 +503,19 @@
"operator": "[Zyte](https://www.zyte.com)",
"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": {
"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-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)."
"description": "Data collected is used for the ContentShake AI tool reports."
},
"SemrushBot-SWA": {
"operator": "[Semrush](https://www.semrush.com/)",
"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.",
"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": {
"description": "AI product training.",

14
packages/ua-blocker/src/generated.ts
View File

@ -32,6 +32,7 @@ User-agent: facebookexternalhit
User-agent: Factset_spyderbot
User-agent: FirecrawlAgent
User-agent: FriendlyCrawler
User-agent: Gemini-Deep-Research
User-agent: Google-CloudVertexBot
User-agent: Google-Extended
User-agent: GoogleOther
@ -51,6 +52,7 @@ User-agent: Meta-ExternalFetcher
User-agent: MistralAI-User
User-agent: MistralAI-User/1.0
User-agent: MyCentralAIScraperBot
User-agent: netEstate Imprint Crawler
User-agent: NovaAct
User-agent: OAI-SearchBot
User-agent: omgili
@ -69,11 +71,7 @@ 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
@ -87,7 +85,7 @@ User-agent: YandexAdditionalBot
User-agent: YouBot
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 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 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 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 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", "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|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|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)/;