# HeriTrack (heritrack.com) - robots.txt
#
# The heritage site (Sthaan), Quest, and Shloka data on this Service is
# proprietary content. Automated scraping, crawling for AI/LLM training,
# and bulk downloading are prohibited under our Terms and Conditions.
# See https://heritrack.com/terms for details.

# --- Known AI / LLM training and content-aggregation crawlers ---
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Meta-ExternalFetcher
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Ai2Bot
Disallow: /

User-agent: img2dataset
Disallow: /

# --- Aggressive SEO / bulk data scrapers ---
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: SerpstatBot
Disallow: /

# --- Everyone else: only the public marketing/legal pages may be indexed.
# All in-app routes (quests, sthaans, shlokas, profile, etc.) are disallowed
# to prevent bulk crawling or scraping of heritage site data. ---
User-agent: *
Allow: /$
Allow: /terms
Allow: /terms.html
Allow: /privacy
Allow: /privacy.html
Allow: /userdeletion
Allow: /userdeletion.html
Disallow: /