# Robots.txt for kangyihuang.dev - Optimized for Global and Chinese Search Engines

User-agent: *
Allow: /

# Sitemap locations
Sitemap: https://kangyihuang.dev/sitemap.xml
Sitemap: https://kangyihuang.dev/api/sitemap

# Crawl-delay for respectful crawling
Crawl-delay: 1

# Allow all major global search engines
User-agent: Googlebot
Allow: /
Crawl-delay: 1

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

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

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

# Chinese search engines
User-agent: Baiduspider
Allow: /
Crawl-delay: 1

User-agent: Sogou web spider
Allow: /
Crawl-delay: 1

User-agent: Sogou News Spider
Allow: /
Crawl-delay: 1

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

User-agent: 360Spider
Allow: /
Crawl-delay: 1

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

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

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

# Block AI training crawlers (optional)
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

# Block common spam bots
User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MegaIndex
Disallow: /

# Special directives for Chinese search engines
User-agent: Baiduspider
Disallow: /api/
Disallow: /_next/
Allow: /images/
Allow: /?lang=zh

User-agent: Sogou web spider
Disallow: /api/
Disallow: /_next/
Allow: /images/
Allow: /?lang=zh