# robots.txt for math.iisc.ac.in
# Updated: 2026-05-25
#
# Legitimate search engine crawlers are welcome.
# AI training/scraping crawlers are blocked to protect bandwidth and content.

# --- Blocked: ByteDance / TikTok (caught in infinite redirect loop) ---
User-agent: Bytespider
Disallow: /

# --- Blocked: OpenAI crawlers (bulk PDF downloading) ---
User-agent: GPTBot
Disallow: /
User-agent: ChatGPT-User
Disallow: /
User-agent: OAI-SearchBot
Disallow: /

# --- Blocked: Amazon (bulk crawling) ---
User-agent: Amazonbot
Disallow: /

# --- Blocked: Anthropic ---
User-agent: ClaudeBot
Allow: /~arvind/
Disallow: /

User-agent: Claude-User
Allow: /~arvind/
Disallow: /

User-agent: Claude-SearchBot
Allow: /~arvind/
Disallow: /

User-agent: Claude-Web
Allow: /~arvind/
Disallow: /
User-agent: anthropic-ai
Allow: /~arvind/
Disallow: /

# --- Blocked: Meta ---
User-agent: FacebookBot
Disallow: /
User-agent: Meta-ExternalAgent
Disallow: /
User-agent: Meta-ExternalFetcher
Disallow: /

# --- Blocked: Common Crawl (primary AI training data source) ---
User-agent: CCBot
Disallow: /

# --- Blocked: Perplexity ---
User-agent: PerplexityBot
Disallow: /

# --- Blocked: Apple AI training ---
User-agent: Applebot-Extended
Disallow: /

# --- Blocked: Miscellaneous AI/scraper bots seen in logs ---
User-agent: SleepBot
Disallow: /
User-agent: ImagesiftBot
Disallow: /
User-agent: cohere-ai
Disallow: /

# --- Opt out of Google AI training (Bard/Gemini) while keeping search indexing ---
User-agent: Google-Extended
Disallow: /

# --- Allow: Legitimate search engine crawlers ---
User-agent: Googlebot
Allow: /

User-agent: bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

# --- Default: allow all other crawlers, but request a polite crawl rate ---
User-agent: *
Crawl-delay: 5