# ==============================================================================
# Roadways Robots Policy
# Allow legitimate search engines to crawl and index public timetable records.
# Block automated AI scrapers, LLM training bots, and unauthorized data miners.
# ==============================================================================

# Search Engine Crawlers (Allowed)
User-agent: Googlebot
User-agent: Bingbot
User-agent: YandexBot
User-agent: DuckDuckBot
User-agent: Baiduspider
User-agent: Slurp
Allow: /
Disallow: /admin
Disallow: /api/

# OpenAI Crawlers, Search & ChatGPT Scrapers (Blocked)
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: OpenAI
Disallow: /

# Google AI Crawlers (Blocked while keeping Google Search allowed)
User-agent: Google-Extended
User-agent: GoogleOther
Disallow: /

# Apple Intelligence Training Crawler (Blocked while keeping Apple Search allowed)
User-agent: Applebot-Extended
Disallow: /

# Anthropic Claude Crawlers (Blocked)
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: anthropic-ai
Disallow: /

# Common Crawl & Mass Training Scrapers (Blocked)
User-agent: CCBot
Disallow: /

# ByteDance / TikTok AI Scraper (Blocked)
User-agent: Bytespider
Disallow: /

# Meta / Facebook AI Training (Blocked)
User-agent: FacebookBot
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
Disallow: /

# Perplexity AI Scraper (Blocked)
User-agent: PerplexityBot
Disallow: /

# Cohere AI Training (Blocked)
User-agent: cohere-ai
Disallow: /

# Other Commercial AI & Web Scrapers (Blocked)
User-agent: MistralAI-User
User-agent: AI2Bot
User-agent: Diffbot
User-agent: Omgilibot
User-agent: Omgili
User-agent: ImagesiftBot
User-agent: Amazonbot
User-agent: Scrapy
User-agent: Seekport
User-agent: YouBot
User-agent: Timpibot
User-agent: VelenPublicWebCrawler
Disallow: /

# Default Policy for all other compliant search crawlers
User-agent: *
Allow: /
Disallow: /admin
Disallow: /api/

# Master Sitemaps
Sitemap: https://bustime.haryanabusinfo.in/sitemap.xml