# Allow legitimate search engines and social media
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: LinkedInBot
Allow: /

# Allow AI Search Crawlers (AIEO Optimization)
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Anthropic-AI
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: cohere-ai
Allow: /

# AI Crawler Information Files
# For structured business data, AI crawlers can access:
# https://heardmarketing.io/llms.txt - Structured business info for LLMs
# https://heardmarketing.io/sitemap.xml - Full site structure

# AI-Specific Guidance
# This website is optimized for AI search engines and answer engines.
# Key content areas: /services/, /booked-reviewed/, /blog/, /about/
# Business focus: Digital marketing for local service businesses

# Block common bad bots and scrapers
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: YandexBot
Disallow: /

User-agent: Baiduspider
Disallow: /

User-agent: SeznamBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

# Block Chinese search engines and crawlers
User-agent: 360Spider
Disallow: /

User-agent: Sosospider
Disallow: /

User-agent: Sogou
Disallow: /

User-agent: YodaoBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: EasouSpider
Disallow: /

# Block aggressive crawlers and scrapers
User-agent: MegaIndex
Disallow: /

User-agent: Scrapy
Disallow: /

User-agent: python-requests
Disallow: /

User-agent: curl
Disallow: /

User-agent: wget
Disallow: /

User-agent: HTTrack
Disallow: /

User-agent: ia_archiver
Disallow: /

User-agent: EmailCollector
Disallow: /

User-agent: EmailSiphon
Disallow: /

User-agent: WebBandit
Disallow: /

# Allow good bots
User-agent: *
Allow: /

# Block admin and private areas
Disallow: /admin/
Disallow: /private/

# Sitemap
Sitemap: https://heardmarketing.io/sitemap.xml

# Crawl delay
Crawl-delay: 1