# ==============================================
# Durai Rajamanickam — Portfolio
# Search and AI answer engines welcome.
# AI model training is not permitted.
# ==============================================
#
# Search and answer bots read pages to cite and link back to them.
# Training bots copy pages into model training sets, and are disallowed.
# Bots that ignore this file are denied at the edge (middleware.ts):
# training crawlers, SEO crawlers, HTTP libraries, headless browsers,
# and automation frameworks all get a 403.

# Content use policy (https://contentsignals.org)
# search: building a search index and showing links and snippets
# ai-input: using pages to ground or cite an AI answer
# ai-train: training or fine-tuning AI models
Content-Signal: search=yes, ai-input=yes, ai-train=no

User-agent: *
Allow: /

# Search Engine Crawlers
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Applebot
Allow: /

User-agent: YandexBot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Kagibot
Allow: /

# AI Search and Answer Bots (cite and link back)
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# AI Training Bots (disallowed)
# Google-Extended and Applebot-Extended are opt-out tokens only. Blocking them
# does not affect Google Search, AI Overviews, or Apple search results.
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Google-CloudVertexBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: cohere-training-data-crawler
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: AI2Bot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

# SEO and Backlink Crawlers (disallowed)
User-agent: SemrushBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: MegaIndex
Disallow: /

User-agent: serpstatbot
Disallow: /

# Social Preview Bots
User-agent: FacebookExternalHit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: Slackbot
Allow: /

User-agent: WhatsApp
Allow: /

User-agent: TelegramBot
Allow: /

# Sitemap
Sitemap: https://durairajamanickam.com/sitemap.xml