# ============ Shilan Chemical - robots.txt (B-PLAN 2026-07-15) ============
# Default: allow all crawlers
User-agent: *
Allow: /
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/cache/
Disallow: /wp-content/upgrade/
Disallow: /?s=
Disallow: /?p=
Disallow: /*?utm_
Disallow: /*?fbclid
Disallow: /*?gclid
Disallow: /*.bak_*
Disallow: /*.backup

# ---- Search Engines (whitelist crawl-delay) ----
User-agent: Googlebot
Allow: /
Crawl-delay: 1

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

User-agent: DuckDuckBot
Allow: /

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

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

# ---- AI Crawlers (2026 GEO ready - explicit ALLOW) ----
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: Bytespider
Allow: /

User-agent: DeepSeekBot
Allow: /

User-agent: MistralAI-User
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: YouBot
Allow: /

User-agent: Diffbot
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: LinkedInBot
Allow: /

# ---- Bad Bots (block) ----
User-agent: MJ12bot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: DotBot
Disallow: /

# ---- Sitemap ----
Sitemap: https://sdic-tcca.hbkaixuan.cn/sitemap.xml
Sitemap: https://sdic-tcca.hbkaixuan.cn/sitemap-news.xml