# 这些爬虫常被用于数据采集、撞库、恶意扫描等行为，禁止爬取
User-agent: AhrefsBot
User-agent: ApacheBench
User-agent: AskTbFXTV
User-agent: BLEXBot
User-agent: BUbiNG
User-agent: CoolpadWebkit
User-agent: CrawlDaddy
User-agent: DigExt
User-agent: Digincore
User-agent: DotBot
User-agent: EasouSpider
User-agent: Elefent
User-agent: Exabot
User-agent: Ezooms
User-agent: FeedDemon
User-agent: heritrix
User-agent: huaban
User-agent: HttpClient
User-agent: ichiro
User-agent: jaunty
User-agent: lightDeckReports Bot
User-agent: Microsoft URL Control
User-agent: MJ12bot
User-agent: oBot
User-agent: psbot
User-agent: Python-urllib
User-agent: Scrapy
User-agent: SEOkicks-Robot
User-agent: SiteExplorer
User-agent: spiderman
User-agent: Swiftbot
User-agent: Teleport
User-agent: TeleportPro
User-agent: TurnitinBot
User-agent: UniversalFeedParser
User-agent: WBSearchBot
User-agent: wsAnalyzer
User-agent: YYSpider
User-agent: YunGuanCe
User-agent: ZmEu
User-agent: aiohttp
Disallow: /

# 以下爬虫用于 AI 模型训练，允许爬取
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: Claude-Web
User-agent: ClaudeBot
User-agent: PerplexityBot
User-agent: Applebot-Extended
User-agent: Baiduspider
User-agent: Bytespider
User-agent: ByteSpider
User-agent: 360Spider
User-agent: Yisouspider
User-agent: DeepSeekBot
User-agent: ChatGLM-Spider
User-agent: QwenBot
User-agent: TongyiBot
User-agent: ChatGLM-Spider
User-agent: YiyanBot
User-agent: Kimi-User
User-agent: KimiBot
User-agent: Kimi-Researcher
User-agent: Kimi-SearchBot
User-agent: MoonshotAI
User-agent: MoonshotBot
User-agent: TencentBot
User-agent: TencentTraveler
User-agent: YuanbaoBot
User-agent: HunyuanBot
User-agent: HunyuanAide
User-agent: ERNIEBot
User-agent: ERNIE-Bot
User-agent: Baidu-YiYan
User-agent: BaiduAI
Allow: /

User-agent: Sogou
Allow: /

# 默认规则：允许所有未在上述黑名单中提及的合法爬虫（如 Googlebot, Bingbot）
User-agent: *
Allow: /

# === 合规隐藏 + 后台保护 ===
User-agent: *
Disallow: /doctor.html
Disallow: /product.html
Disallow: /videos.html
Disallow: /videos/
Disallow: /recruit.html
Disallow: /recruit/
Disallow: /kst.html
Disallow: /index/news/add_*
Disallow: /mobile/news/news/add_*
Disallow: /news/education.html
Disallow: /news/beauty.html
Disallow: /news/medicine.html
Disallow: /news/firstaid.html
Allow: /news/*.html

# === 必应显式放行 ===
User-agent: Bingbot
Allow: /

Sitemap: https://www.ruihanzx.com/pc_sitemap.xml
Sitemap: https://m.ruihanzx.com/m_sitemap.xml