# Copied from GitHub https://github.com/ai-robots-txt/ai.robots.txt/blob/main/robots.txt
User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: Amazonbot
User-agent: anthropic-ai
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: Brightbot 1.0
User-agent: Bytespider
User-agent: CCBot
User-agent: ChatGPT-User
User-agent: Claude-Web
User-agent: ClaudeBot
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: Crawlspace
User-agent: Diffbot
User-agent: DuckAssistBot
User-agent: FacebookBot
User-agent: FriendlyCrawler
User-agent: Google-Extended
User-agent: GoogleOther
User-agent: GoogleOther-Image
User-agent: GoogleOther-Video
User-agent: GPTBot
User-agent: iaskspider/2.0
User-agent: ICC-Crawler
User-agent: ImagesiftBot
User-agent: img2dataset
User-agent: imgproxy
User-agent: ISSCyberRiskCrawler
User-agent: Kangaroo Bot
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: NovaAct
User-agent: OAI-SearchBot
User-agent: omgili
User-agent: omgilibot
User-agent: Operator
User-agent: PanguBot
User-agent: Perplexity-User
User-agent: PerplexityBot
User-agent: PetalBot
User-agent: Scrapy
User-agent: SemrushBot-OCOB
User-agent: SemrushBot-SWA
User-agent: Sidetrade indexer bot
User-agent: Timpibot
User-agent: VelenPublicWebCrawler
User-agent: Webzio-Extended
User-agent: YouBot
Disallow: /

# --------------------------------------------------
# ------------- D  I  S  A  L  L  O  W -------------
# --------------------------------------------------

# Bing
User-agent: bingbot
Disallow: /

# Baidu
User-agent: Baidu-YunGuanCe
Disallow: /
User-agent: Baiduspider
Disallow: /
User-agent: Baiduspider-image
Disallow: /
User-agent: Baiduspider-news
Disallow: /
User-agent: Baiduspider-video
Disallow: /

# You.com
User-agent: YouBot
Disallow: /

# Apple
User-agent: Applebot
Disallow: /

# Amazon
User-agent: Amazonbot
Disallow: /

# Perplexity
User-agent: PerplexityBot
Disallow: /

# Anthropic AI
User-agent: anthropic-ai
Disallow: /

# Bytespider
User-agent: Bytespider
Disallow: /

# Omgili
User-agent: omgili
Disallow: /

# Cohere's AI
User-agent: cohere-ai
Disallow: /

# Common Crawl
User-agent: CCBot
Disallow: /

# OpenAI
User-agent: ChatGPT-User
Disallow: /
User-agent: GPTBot
Disallow: /

# Turn It In Plagiarism Checker
User-Agent: TurnitinBot
Disallow: /

# Name Protect
User-Agent: NPBot
Disallow: /

# Sly Search
User-Agent: SlySearch
Disallow: /

# Google
User-agent: Googlebot
Disallow: /
User-agent: ediapartners-Google 
Disallow: /
User-agent: AdsBot-Google
Disallow: /
User-agent: Google-Extended
Disallow: /
User-agent: Feedfetcher-Google
Disallow: /

# Bing
User-agent: AdIdxBot
Disallow: /
User-agent: Bingbot
Disallow: /
User-agent: BingPreview
Disallow: /
User-agent: MicrosoftPreview
Disallow: /

# Facebook
User-agent: Facebot
Disallow: /
User-agent: FacebookBot
Disallow: /
User-agent: Facebook
Disallow: /
User-agent: facebookexternalhit
Disallow: /

# Alexa
User-agent: ia_archiver
Disallow: /

# Diffbot
User-agent: Diffbot
Disallow: /

# --------------------------------------------------
# ---------------- A  L  L  O  W -------------------
# --------------------------------------------------

# RSS readers
User-agent: FreshRSS
Allow: /
User-agent: Feedly
Allow: /
User-agent: inoreader
Allow: /
User-agent: Tiny Tiny RSS
Allow: /
User-agent: Feedbin
Allow: /
User-agent: NewsBlur
Allow: /

# Archive.org
User-agent: archive.org_bot
Allow: /

# Marginalia
User-agent: search.marginalia.nu
Allow: /