[chore] Update robots.txt with more AI bots (#3634)

This commit is contained in:
Daenney 2025-01-03 12:46:59 +01:00 committed by GitHub
parent 29da5b35a5
commit 77f1e79532
No known key found for this signature in database
GPG key ID: B5690EEEBB952194

View file

@ -33,9 +33,9 @@
# https://github.com/ai-robots-txt/ai.robots.txt/ # https://github.com/ai-robots-txt/ai.robots.txt/
User-agent: AI2Bot User-agent: AI2Bot
User-agent: Ai2Bot-Dolma User-agent: Ai2Bot-Dolma
User-agent: AdsBot-Google
User-agent: Amazonbot User-agent: Amazonbot
User-agent: anthropic-ai User-agent: anthropic-ai
User-agent: Applebot
User-agent: Applebot-Extended User-agent: Applebot-Extended
User-agent: Bytespider User-agent: Bytespider
User-agent: CCBot User-agent: CCBot
@ -43,9 +43,10 @@
User-agent: ClaudeBot User-agent: ClaudeBot
User-agent: Claude-Web User-agent: Claude-Web
User-agent: cohere-ai User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: Diffbot User-agent: Diffbot
User-agent: DuckAssistBot
User-agent: FacebookBot User-agent: FacebookBot
User-agent: facebookexternalhit
User-agent: FriendlyCrawler User-agent: FriendlyCrawler
User-agent: Google-Extended User-agent: Google-Extended
User-agent: GoogleOther User-agent: GoogleOther
@ -56,14 +57,18 @@
User-agent: ICC-Crawler User-agent: ICC-Crawler
User-agent: ImagesiftBot User-agent: ImagesiftBot
User-agent: img2dataset User-agent: img2dataset
User-agent: ISSCyberRiskCrawler
User-agent: Kangaroo Bot
User-agent: Meta-ExternalAgent User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher User-agent: Meta-ExternalFetcher
User-agent: OAI-SearchBot User-agent: OAI-SearchBot
User-agent: omgili User-agent: omgili
User-agent: omgilibot User-agent: omgilibot
User-agent: PanguBot
User-agent: PerplexityBot User-agent: PerplexityBot
User-agent: PetalBot User-agent: PetalBot
User-agent: Scrapy User-agent: Scrapy
User-agent: Sidetrade indexer bot
User-agent: Timpibot User-agent: Timpibot
User-agent: VelenPublicWebCrawler User-agent: VelenPublicWebCrawler
User-agent: Webzio-Extended User-agent: Webzio-Extended