# ============================================================ # 跨境合规资料文库 - robots.txt # 站点:https://sxdthf.com.cn/ # 更新:2026-07-01 # ============================================================ # ---------- 通用规则(所有爬虫) ---------- User-agent: * Disallow: /admin/ Disallow: /cache/ Disallow: /includes/ Disallow: /database/ Disallow: /deploy/ Disallow: /uploads/ Disallow: /cli_crawl.php Disallow: /bulk_crawl.php Disallow: /crawl_preview.php Disallow: /router.php Disallow: /*.json Disallow: /*.log Disallow: /*.sql Disallow: /*.sqlite Disallow: /*.bak Crawl-delay: 5 Sitemap: https://sxdthf.com.cn/sitemap.xml # ---------- 百度蜘蛛 ---------- User-agent: Baiduspider Disallow: /admin/ Disallow: /cache/ Disallow: /includes/ Disallow: /database/ Disallow: /deploy/ Disallow: /uploads/ Disallow: /cli_crawl.php Disallow: /bulk_crawl.php Disallow: /crawl_preview.php Disallow: /router.php Disallow: /*.json Disallow: /*.log Disallow: /*.sql Disallow: /*.sqlite Disallow: /*.bak Crawl-delay: 2 # ---------- 百度移动蜘蛛 ---------- User-agent: Baiduspider-mobile Disallow: /admin/ Disallow: /cache/ Disallow: /includes/ Disallow: /database/ Disallow: /deploy/ Disallow: /uploads/ Disallow: /cli_crawl.php Disallow: /bulk_crawl.php Disallow: /crawl_preview.php Disallow: /router.php Disallow: /*.json Disallow: /*.log Disallow: /*.sql Disallow: /*.sqlite Disallow: /*.bak Crawl-delay: 2 # ---------- 百度图片蜘蛛 ---------- User-agent: Baiduspider-image Disallow: /admin/ Disallow: /cache/ Disallow: /includes/ Disallow: /database/ Disallow: /deploy/ Disallow: /uploads/ Crawl-delay: 2 # ---------- 谷歌机器人 ---------- User-agent: Googlebot Disallow: /admin/ Disallow: /cache/ Disallow: /includes/ Disallow: /database/ Disallow: /deploy/ Disallow: /uploads/ Disallow: /cli_crawl.php Disallow: /bulk_crawl.php Disallow: /crawl_preview.php Disallow: /router.php Disallow: /*.json Disallow: /*.log Disallow: /*.sql Disallow: /*.sqlite Disallow: /*.bak Crawl-delay: 1 # ---------- 谷歌图片 ---------- User-agent: Googlebot-Image Disallow: /admin/ Disallow: /cache/ Disallow: /includes/ Disallow: /database/ Disallow: /deploy/ Disallow: /uploads/ Crawl-delay: 1 # ---------- Bing 必应 ---------- User-agent: bingbot Disallow: /admin/ Disallow: /cache/ Disallow: /includes/ Disallow: /database/ Disallow: /deploy/ Disallow: /uploads/ Disallow: /cli_crawl.php Disallow: /bulk_crawl.php Disallow: /crawl_preview.php Disallow: /router.php Disallow: /*.json Disallow: /*.log Disallow: /*.sql Disallow: /*.sqlite Disallow: /*.bak Crawl-delay: 3 # ---------- 搜狗蜘蛛 ---------- User-agent: Sogou web spider Disallow: /admin/ Disallow: /cache/ Disallow: /includes/ Disallow: /database/ Disallow: /deploy/ Disallow: /uploads/ Disallow: /cli_crawl.php Disallow: /bulk_crawl.php Disallow: /crawl_preview.php Disallow: /router.php Disallow: /*.json Disallow: /*.log Disallow: /*.sql Disallow: /*.sqlite Disallow: /*.bak Crawl-delay: 3 # ---------- 360 蜘蛛 ---------- User-agent: 360Spider Disallow: /admin/ Disallow: /cache/ Disallow: /includes/ Disallow: /database/ Disallow: /deploy/ Disallow: /uploads/ Disallow: /cli_crawl.php Disallow: /bulk_crawl.php Disallow: /crawl_preview.php Disallow: /router.php Disallow: /*.json Disallow: /*.log Disallow: /*.sql Disallow: /*.sqlite Disallow: /*.bak Crawl-delay: 3 # ---------- 字节跳动/头条蜘蛛 ---------- User-agent: Bytespider Disallow: /admin/ Disallow: /cache/ Disallow: /includes/ Disallow: /database/ Disallow: /deploy/ Disallow: /uploads/ Disallow: /cli_crawl.php Disallow: /bulk_crawl.php Disallow: /crawl_preview.php Disallow: /router.php Disallow: /*.json Disallow: /*.log Disallow: /*.sql Disallow: /*.sqlite Disallow: /*.bak Crawl-delay: 5 # ---------- 神马蜘蛛(UC/夸克) ---------- User-agent: YisouSpider Disallow: /admin/ Disallow: /cache/ Disallow: /includes/ Disallow: /database/ Disallow: /deploy/ Disallow: /uploads/ Disallow: /cli_crawl.php Disallow: /bulk_crawl.php Disallow: /crawl_preview.php Disallow: /router.php Disallow: /*.json Disallow: /*.log Disallow: /*.sql Disallow: /*.sqlite Disallow: /*.bak Crawl-delay: 3 # ---------- AI 爬虫(训练数据用,禁止抓取) ---------- User-agent: GPTBot Disallow: / User-agent: CCBot Disallow: / User-agent: anthropic-ai Disallow: / User-agent: Claude-Web Disallow: / User-agent: cohere-ai Disallow: / User-agent: PerplexityBot Disallow: / User-agent: Applebot-Extended Disallow: / User-agent: FacebookBot Disallow: /admin/ Disallow: /cache/ Disallow: /includes/ Disallow: /database/ Disallow: /deploy/ Disallow: /uploads/