# robots.txt for AVSOPS
# https://avsops.com/
# Generated: 2026-07-20


# PRODUCTION SITE - Welcome legitimate crawlers!

# ================================================
# ALLOWED: Major Search Engines (explicit allow)
# ================================================
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-News
Allow: /

User-agent: Googlebot-Video
Allow: /

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

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

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

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

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

User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: Applebot
Allow: /

# ================================================
# BLOCKED: AI Training Bots & LLM Crawlers
# ================================================
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Amazonbot
Disallow: /

# ================================================
# BLOCKED: Known Bad Bots & Scrapers
# ================================================
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: serpstatbot
Disallow: /

User-agent: MegaIndex
Disallow: /

User-agent: Seekport
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: ZoominfoBot
Disallow: /

User-agent: BomboraBot
Disallow: /

User-agent: proximic
Disallow: /

User-agent: Sogou
Disallow: /

User-agent: Exabot
Disallow: /

User-agent: Nutch
Disallow: /

User-agent: linkdexbot
Disallow: /

User-agent: archive.org_bot
Disallow: /

User-agent: ia_archiver
Disallow: /

User-agent: rogerbot
Disallow: /

User-agent: Screaming Frog SEO Spider
Disallow: /

User-agent: MauiBot
Disallow: /

User-agent: SeznamBot
Disallow: /

User-agent: YisouSpider
Disallow: /

User-agent: Cliqzbot
Disallow: /

User-agent: Buck
Disallow: /

User-agent: Riddler
Disallow: /

User-agent: ltx71
Disallow: /

User-agent: CriteoBot
Disallow: /

# ================================================
# DEFAULT: All other bots - limited access
# ================================================
User-agent: *
Allow: /
Crawl-delay: 10

# Disallow admin and private paths for all
Disallow: /admin/
Disallow: /private/
Disallow: /*.json$

# Sitemap location - essential for SEO
Sitemap: https://avsops.com/sitemap.xml

# Additional sitemaps (if using sitemap index)
# Sitemap: https://avsops.com/sitemap-pages.xml
# Sitemap: https://avsops.com/sitemap-organizations.xml
# Sitemap: https://avsops.com/sitemap-locations.xml