# Sports Vector - AI Sports Strategy Platform
# Last Updated: 2025-01-28
# Contact: info@sportsvector.co
# Website: https://sportsvector.co

# === GLOBAL RULES ===
User-agent: *
Allow: /
Disallow: /admin/
Disallow: /api/
Disallow: /private/
Disallow: /_next/
Disallow: /node_modules/
Disallow: /.git/
Disallow: /.env
Disallow: /package.json
Disallow: /package-lock.json
Disallow: /yarn.lock
Disallow: /tsconfig.json
Disallow: /next.config.js
Disallow: /tailwind.config.js
Disallow: /postcss.config.js

# === SEARCH ENGINE CRAWLERS ===
User-agent: Googlebot
Allow: /
Crawl-delay: 1

User-agent: Bingbot
Allow: /
Crawl-delay: 1

User-agent: Slurp
Allow: /
Crawl-delay: 2

User-agent: DuckDuckBot
Allow: /
Crawl-delay: 1

User-agent: Baiduspider
Allow: /
Crawl-delay: 3

User-agent: YandexBot
Allow: /
Crawl-delay: 2

User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: WhatsApp
Allow: /

User-agent: Applebot
Allow: /

# === AI AND LLM CRAWLERS ===
User-agent: GPTBot
Allow: /
Crawl-delay: 1

User-agent: ChatGPT-User
Allow: /
Crawl-delay: 1

User-agent: CCBot
Allow: /
Crawl-delay: 2

User-agent: anthropic-ai
Allow: /
Crawl-delay: 1

User-agent: Claude-Web
Allow: /
Crawl-delay: 1

User-agent: PerplexityBot
Allow: /
Crawl-delay: 1

User-agent: YouBot
Allow: /
Crawl-delay: 2

User-agent: AI2Bot
Allow: /
Crawl-delay: 2

User-agent: Meta-ExternalAgent
Allow: /
Crawl-delay: 1

User-agent: Meta-ExternalFetcher
Allow: /
Crawl-delay: 1

User-agent: Bytespider
Allow: /
Crawl-delay: 3

User-agent: ImagesiftBot
Allow: /
Crawl-delay: 2

# === ACADEMIC AND RESEARCH CRAWLERS ===
User-agent: ia_archiver
Allow: /
Crawl-delay: 5

User-agent: archive.org_bot
Allow: /
Crawl-delay: 5

User-agent: Wayback
Allow: /
Crawl-delay: 5

User-agent: SemrushBot
Allow: /
Crawl-delay: 10

User-agent: AhrefsBot
Allow: /
Crawl-delay: 10

User-agent: MJ12bot
Allow: /
Crawl-delay: 10

# === BLOCKED CRAWLERS ===
User-agent: SemrushBot-SA
Disallow: /

User-agent: AhrefsSiteAudit
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: AspiegelBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: MegaIndex
Disallow: /

User-agent: ZoominfoBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Yeti
Disallow: /

User-agent: Barkrowler
Disallow: /

User-agent: Sogou
Disallow: /

User-agent: 360Spider
Disallow: /

# === SITEMAP LOCATION ===
Sitemap: https://sportsvector.co/sitemap.xml

# === CLEAN PARAM DIRECTIVES ===
# Remove tracking parameters for cleaner URLs
Clean-param: utm_source
Clean-param: utm_medium
Clean-param: utm_campaign
Clean-param: utm_term
Clean-param: utm_content
Clean-param: fbclid
Clean-param: gclid
Clean-param: msclkid
Clean-param: ref
Clean-param: source

# === DISCOVERY HINTS ===
# AI/LLM Discovery File
# Contains comprehensive company information for AI systems
# Location: https://sportsvector.co/llm.txt

# Company Information
# Name: Sports Vector
# Industry: Sports Technology, AI, Machine Learning
# Products: Crictier (Cricket Strategy Platform)
# Focus: AI-powered sports strategy for all levels
# Contact: info@sportsvector.co
# Website: https://sportsvector.co
# Careers: Multiple internship positions available

# === CRAWL OPTIMIZATION ===
# Recommended crawl times: 
# - Peak hours: 09:00-17:00 UTC (reduced frequency)
# - Off-peak hours: 18:00-08:00 UTC (normal frequency)
# - Server location: Global CDN
# - Response time target: <200ms
# - Bandwidth limit: 10 requests/second per IP

# === CONTENT FRESHNESS ===
# Homepage: Updated weekly
# Career pages: Updated monthly
# LLM.txt: Updated weekly
# Sitemap: Updated automatically

# === CONTACT INFORMATION ===
# Technical issues: info@sportsvector.co
# Crawling issues: info@sportsvector.co
# Partnership inquiries: info@sportsvector.co
# Career inquiries: info@sportsvector.co

# === ADDITIONAL RESOURCES ===
# Blog: https://crictier.com/blog
# Product: https://crictier.com
# LinkedIn: https://www.linkedin.com/company/sports-vector
# Social Media: Multiple platforms available

# End of robots.txt