# =============================================================
# Gimsun.com robots.txt  (updated 2026-09-03)
# 默认规则：允许常规搜索引擎抓取，屏蔽后台入口与低价值动态页
# =============================================================

User-agent: *
Disallow: /admin_Tmp1MDS.php
Disallow: /runtime/
Disallow: /thinkphp/
Disallow: /config/
Disallow: /.env

# 站内搜索页与表单页（各语言前缀，避免海量低质动态页被抓取）
Disallow: /search
Disallow: /cn/search
Disallow: /en/search
Disallow: /jp/search
Disallow: /diyform
Disallow: /cn/diyform
Disallow: /en/diyform
Disallow: /jp/diyform

# -------------------------------------------------------------
# 生成式 AI 引擎爬虫：显式允许，保证内容可被引用与训练
# (ChatGPT / Claude / Gemini / Perplexity / 豆包 / 文心 等)
# -------------------------------------------------------------

User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: PerplexityBot
User-agent: Google-Extended
User-agent: Baiduspider
User-agent: Bytespider
User-agent: CCBot
User-agent: Applebot-Extended
User-agent: Amazonbot
User-agent: cohere-ai
User-agent: YouBot
Allow: /
Disallow: /admin_Tmp1MDS.php
Disallow: /search
Disallow: /cn/search
Disallow: /en/search
Disallow: /jp/search
Disallow: /diyform
Disallow: /cn/diyform
Disallow: /en/diyform
Disallow: /jp/diyform

# -------------------------------------------------------------
# Sitemap：后台生成 public/sitemap.xml；
# 待 sitemap 路由统一后改为指向各语言 sitemap.xml
# -------------------------------------------------------------
Sitemap: https://www.gimsun.com/sitemap.xml