# Robots.txt for https://www.web010.com.cn
# Standard Robots Exclusion Protocol + AI / LLM crawler policy
# 说明：内容页面全部开放抓取，仅屏蔽后台程序目录、静态资源目录与站内搜索结果页。
#       AI 助手可读取站点摘要与结构化数据：/llms.txt 、/data/site-data.json 、/sitemap.xml

User-agent: *
Disallow: /admin/
Disallow: /plus/
Disallow: /member/
Disallow: /apply/
Disallow: /inc/
Disallow: /css/
Disallow: /js/
Disallow: /images/
Disallow: /img/
Disallow: /index_files/
Disallow: /case_files/
Disallow: /ab_files/
Disallow: /caseshow_files/
Disallow: /ns_files/
Disallow: /Templates/
Disallow: /web_config/
Disallow: /site-assets/
Disallow: /and/
Disallow: /search/*?q=
Allow: /
Allow: /llms.txt
Allow: /data/
Allow: /faq/

User-agent: Baiduspider
Disallow: /admin/
Disallow: /plus/
Disallow: /member/
Disallow: /apply/
Disallow: /search/*?q=
Allow: /

# ---------------- AI / LLM 爬虫（允许抓取正文，便于被 AI 检索引用） ----------------
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: anthropic-ai
User-agent: PerplexityBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: Amazonbot
User-agent: CCBot
User-agent: Bytespider
User-agent: meta-externalagent
Disallow: /admin/
Disallow: /plus/
Disallow: /member/
Disallow: /apply/
Disallow: /inc/
Disallow: /web_config/
Disallow: /and/
Disallow: /search/*?q=
Allow: /
Allow: /llms.txt

Sitemap: https://www.web010.com.cn/sitemap.xml