# robots.txt - SEO Optimized # Last updated: 2026-03-24 # # 【泛站群说明】 # Sitemap 使用相对路径(非绝对 URL),因为本系统部署于泛解析站群, # 同一份 robots.txt 服务于数千个不同域名,无法硬编码域名。 # Google/Baidu/Bing 均支持相对路径 Sitemap 声明(以请求域名为基准解析)。 # ======================================== # Sitemap Declaration # ======================================== Sitemap: /sitemap.xml Sitemap: /image-sitemap.xml Sitemap: /google.xml Sitemap: /baidu.xml Sitemap: /bing.xml Sitemap: /sm.xml Sitemap: /sogou.xml Sitemap: /360.xml Sitemap: /rss.xml # ======================================== # Default Rules for All Crawlers # ======================================== User-agent: * Allow: / Allow: /person/ Allow: /actor/ Allow: /director/ Disallow: /data/ Disallow: /cache/ Disallow: /logs/ Disallow: /src/ Disallow: /scripts/ Disallow: /mmss9988/ Disallow: /tongji/ Disallow: /*.php$ Disallow: /lunli/ Crawl-delay: 2 # ======================================== # Google # ======================================== User-agent: Googlebot Allow: / Allow: /person/ Allow: /actor/ Allow: /director/ Disallow: /data/ Disallow: /cache/ Disallow: /logs/ Disallow: /src/ Disallow: /scripts/ Disallow: /mmss9988/ Disallow: /tongji/ Disallow: /*.php$ Disallow: /lunli/ # Google 忽略 Crawl-delay,由 Search Console 控制抓取频率 # ======================================== # Baidu # ======================================== User-agent: Baiduspider Allow: / Allow: /person/ Allow: /actor/ Allow: /director/ Disallow: /data/ Disallow: /cache/ Disallow: /logs/ Disallow: /src/ Disallow: /scripts/ Disallow: /mmss9988/ Disallow: /tongji/ Disallow: /*.php$ Disallow: /lunli/ Crawl-delay: 2 # ======================================== # 神马搜索(sm.cn) # ======================================== User-agent: YisouSpider Allow: / Allow: /person/ Allow: /actor/ Allow: /director/ Disallow: /data/ Disallow: /cache/ Disallow: /logs/ Disallow: /src/ Disallow: /scripts/ Disallow: /mmss9988/ Disallow: /tongji/ Disallow: /*.php$ Disallow: /lunli/ Crawl-delay: 2 # ======================================== # Bing # ======================================== # 2026-07-02/03 两次生产 502/504 风暴均由 bingbot 高并发触发 # (ticket 20260702-001,683 req/min,99% 长尾唯一 URL 缓存天生难命中) # 从 Crawl-delay:1 调至 5,从源头降低并发峰值 User-agent: Bingbot Allow: / Allow: /person/ Allow: /actor/ Allow: /director/ Disallow: /data/ Disallow: /cache/ Disallow: /logs/ Disallow: /src/ Disallow: /scripts/ Disallow: /mmss9988/ Disallow: /tongji/ Disallow: /*.php$ Disallow: /lunli/ Crawl-delay: 5 # ======================================== # 搜狗 # ======================================== User-agent: Sogou web spider Allow: / Allow: /person/ Allow: /actor/ Allow: /director/ Disallow: /data/ Disallow: /cache/ Disallow: /logs/ Disallow: /src/ Disallow: /scripts/ Disallow: /mmss9988/ Disallow: /tongji/ Disallow: /*.php$ Disallow: /lunli/ Crawl-delay: 2 # ======================================== # 360搜索 # ======================================== User-agent: 360Spider Allow: / Allow: /person/ Allow: /actor/ Allow: /director/ Disallow: /data/ Disallow: /cache/ Disallow: /logs/ Disallow: /src/ Disallow: /scripts/ Disallow: /mmss9988/ Disallow: /tongji/ Disallow: /*.php$ Disallow: /lunli/ Crawl-delay: 2 # ======================================== # Yandex # ======================================== # 2026-07-02 第二次 502/504 风暴中 YandexBot 与 bingbot 同时段共同触发, # 从 Crawl-delay:2 调至 5 一并降压 User-agent: Yandex Allow: / Allow: /person/ Allow: /actor/ Allow: /director/ Disallow: /data/ Disallow: /cache/ Disallow: /logs/ Disallow: /src/ Disallow: /scripts/ Disallow: /mmss9988/ Disallow: /tongji/ Disallow: /*.php$ Disallow: /lunli/ Crawl-delay: 5 # ======================================== # 屏蔽 SEO 工具爬虫(消耗带宽无收益) # ======================================== User-agent: AhrefsBot Disallow: / User-agent: SemrushBot Disallow: / User-agent: MJ12bot Disallow: / User-agent: DotBot Disallow: / # ======================================== # 屏蔽 AI 训练爬虫 # ======================================== User-agent: GPTBot Disallow: / User-agent: ChatGPT-User Disallow: / User-agent: OAI-SearchBot Disallow: / User-agent: ClaudeBot Disallow: / User-agent: anthropic-ai Disallow: / User-agent: Google-Extended Disallow: / User-agent: PerplexityBot Disallow: / User-agent: Cohere-AI Disallow: / User-agent: AI2Bot Disallow: / User-agent: CCBot Disallow: / User-agent: Diffbot Disallow: / User-agent: Amazonbot Disallow: / User-agent: Bytespider Disallow: / User-agent: Meta-ExternalAgent Disallow: / User-agent: omgili Disallow: /