# =========================================================
# ROBOTS.TXT FOR MAXIMUM VISIBILITY & DISCOVERY
# Purpose: Ensure content is easily found by search engines, news aggregators,
#          and research tools used by journalists and publishers.
# =========================================================

# --- ALLOW ALL REPUTABLE CRAWLERS ---
User-agent: *
Allow: /
Disallow: /search

# --- SPECIFIC ALLOWANCES FOR KEY SEARCH ENGINES ---

User-agent: Googlebot
Allow: /
Disallow: /search

User-agent: Googlebot-News
Allow: /

User-agent: Bingbot
Allow: /
Disallow: /search

User-agent: DuckDuckBot
Allow: /
Disallow: /search

User-agent: Applebot
Allow: /
Disallow: /search

# --- AI SEARCH BOTS (Citations & Real-Time Answers) ---

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Claude-User
Allow: /

User-agent: DuckAssistBot
Allow: /

# --- BLOCK AI TRAINING CRAWLERS ---

User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Google-CloudVertexBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Meta-ExternalFetcher
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: MistralAI-User
Disallow: /

User-agent: Novellum AI Crawl
Disallow: /

User-agent: ProRataInc
Disallow: /

# --- BLOCK SEO COMPETITOR SCRAPERS ---

User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

# --- BLOCK INTERNATIONAL SEARCH ENGINES ---

User-agent: Yandex
Disallow: /

User-agent: Baiduspider
Disallow: /

# --- SITEMAP DECLARATION ---

Sitemap: https://www.ggmoitra.com/sitemap.xml
Sitemap: https://www.ggmoitra.com/atom.xml?redirect=false&start-index=1&max-results=500
Sitemap: https://www.ggmoitra.com/atom.xml?redirect=false&start-index=501&max-results=500
Sitemap: https://www.ggmoitra.com/atom.xml?redirect=false&start-index=1001&max-results=500
Sitemap: https://www.ggmoitra.com/atom.xml?redirect=false&start-index=1501&max-results=500
Sitemap: https://www.ggmoitra.com/atom.xml?redirect=false&start-index=2001&max-results=500