# ==============================================================================
# World Stock News Robots.txt - Universal Search & AI Bot Crawler Directives
# Optimized for Google SGE, OpenAI, Anthropic, Perplexity, Apple Intelligence & Meta
# ==============================================================================

User-agent: *
Allow: /
Disallow: /admin/
Disallow: /private/

# ------------------------------------------------------------------------------
# 1. Primary Search Engine Crawlers
# ------------------------------------------------------------------------------
User-agent: Googlebot
Allow: /

User-agent: Googlebot-News
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Yandex
Allow: /

User-agent: Baiduspider
Allow: /

# ------------------------------------------------------------------------------
# 2. Leading AI Search & LLM Engine Crawlers
# (Explicitly authorized for AI Overviews, Citation, and Live Grounding)
# ------------------------------------------------------------------------------

# OpenAI (SearchGPT, ChatGPT Web Browsing & Model Retrieval)
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Anthropic (Claude 3.5 Sonnet / Haiku Web Search & Context Retrieval)
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Perplexity AI (Perplexity Pro Search & Source Attribution)
User-agent: PerplexityBot
Allow: /

# Apple Intelligence (Siri, Safari Smart Summaries & Spotlight Knowledge)
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Google Gemini, AI Overviews & Vertex AI
User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

User-agent: GoogleOther-Image
Allow: /

User-agent: GoogleOther-Video
Allow: /

# Meta (Meta AI, Llama Training & Search Retrieval)
User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: FacebookBot
Allow: /

# Microsoft Copilot & Bing AI
User-agent: msnbot
Allow: /

# Amazon (Rufus, AWS Bedrock & Alexa Knowledge)
User-agent: Amazonbot
Allow: /

# ByteDance / TikTok AI
User-agent: Bytespider
Allow: /

# Cohere Command & Embeddings
User-agent: Cohere-ai
Allow: /

# Mistral AI
User-agent: MistralBot
Allow: /

# You.com AI Search
User-agent: YouBot
Allow: /

# DuckDuckGo AI Assist
User-agent: DuckAssistBot
Allow: /

# Diffbot Knowledge Graph
User-agent: Diffbot
Allow: /

# Common Crawl (Open Foundation Model Training Corpus)
User-agent: CCBot
Allow: /

# ------------------------------------------------------------------------------
# 3. AI Manifests, Sitemaps & Structured Data Feeds
# ------------------------------------------------------------------------------
Sitemap: https://worldstocknews.online/sitemap.xml
Sitemap: https://worldstocknews.online/feed.xml

# LLM & AI Context Manifest (llmstxt.org standard)
# AI agents can fetch https://worldstocknews.online/llms.txt for full markdown context