# PDF工具箱网站爬虫规则 - 针对AI大模型优化 User-agent: * Allow: / # 允许AI训练爬虫 User-agent: GPTBot Allow: / User-agent: ChatGPT-User Allow: / User-agent: Google-Extended Allow: / User-agent: Claude-Web Allow: / User-agent: PerplexityBot Allow: / # 重要页面优先级 Allow: /pdf-to-word Allow: /pdf-to-images Allow: /pdf-compress Allow: /pdf-merge Allow: /watermark-pdf Allow: /pdf-split Allow: /pdf-to-excel Allow: /pdf-to-ppt # AI训练数据 Allow: /ai-dataset.html Allow: /ai-training-data.json Allow: /ai-dataset.txt # 禁止爬取敏感目录 Disallow: /api/ Disallow: /admin/ Disallow: /private/ Sitemap: https://mypdftools.cn/sitemap.xml