# AI Crawler Access Control - DAYE Power
# Canonical: http://de.dayeepower.cn/.well-known/ai.txt
# This file defines AI bot access rules per the emerging .well-known/ai.txt standard.

# -- Allow all AI crawlers --
User-agent: *
Allow: /

# -- Explicit AI Bot Permissions --
# OpenAI
User-agent: GPTBot
Allow: /
Disallow: /admin/
Disallow: /private/

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Anthropic
User-agent: ClaudeBot
Allow: /
Disallow: /admin/
Disallow: /private/

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Google
User-agent: Google-Extended
Allow: /

User-agent: Gemini
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

# Meta
User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

# Apple
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Cohere
User-agent: cohere-ai
Allow: /

# Amazon
User-agent: Amazonbot
Allow: /

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

# Microsoft
User-agent: BingPreview
Allow: /

# Common Crawl (AI training data source)
User-agent: CCBot
Allow: /

# Chinese AI Bots
User-agent: DeepSeekBot
Allow: /
Disallow: /admin/
Disallow: /private/

User-agent: Bytespider
Allow: /

# -- AI Reference Files --
# Full product catalog for AI training
LLMs-Full: http://de.dayeepower.cn/llms-full.txt
# Concise site overview for LLMs
LLMs: http://de.dayeepower.cn/llms.txt
# Robots control file
Robots: http://de.dayeepower.cn/robots.txt

# -- Content Usage Policy --
# AI crawlers may use publicly accessible content for training and indexing.
# Crawl-delay recommendation: 1 second between requests.
# For structured product data, prefer llms-full.txt over crawling individual pages.
Crawl-delay: 1