# ============================================= # OSKeep.com - 操作系统下载站 robots.txt # 最后更新: 2024-01-16 # 模式: 纯Slug模式 # ============================================= User-agent: * # ==== 允许的重要页面和目录 ==== Allow: / Allow: /browse/ Allow: /download/ Allow: /search/ Allow: /about/ Allow: /contact/ Allow: /privacy/ Allow: /sitemap.xml Allow: /sitemap.html Allow: /robots.txt Allow: /favicon.ico # ==== 静态资源允许 ==== Allow: /assets/ Allow: /images/ Allow: /uploads/ Allow: /css/ Allow: /js/ Allow: /fonts/ # ==== 禁止爬取的敏感目录 ==== Disallow: /admin/ Disallow: /config/ Disallow: /includes/ Disallow: /backup/ Disallow: /tmp/ Disallow: /logs/ Disallow: /phpmyadmin/ # ==== 禁止爬取系统文件 ==== Disallow: /*.inc$ Disallow: /*.log$ Disallow: /*.sql$ Disallow: /*.bak$ Disallow: /*.env$ Disallow: /*.htaccess$ # ==== 允许伪静态分页 ==== Allow: /browse/*/page/ Allow: /search/*/page/ # ==== 允许伪静态URL参数(纯Slug模式) ==== Allow: /browse/*/ Allow: /download/*/ Allow: /search/*/ # ==== 禁止传统查询参数URL(避免重复内容) ==== Disallow: /*?id=* Disallow: /*?page=* Disallow: /*?action=* Disallow: /*?ajax=* Disallow: /*?format=* # ==== 禁止特定爬虫敏感路径 ==== Disallow: /composer.json Disallow: /composer.lock Disallow: /package.json Disallow: /.git/ Disallow: /node_modules/ Disallow: /vendor/ # ==== Sitemap 声明 ==== Sitemap: https://oskeep.com/sitemap.xml # ============================================= # 特定搜索引擎优化规则 # ============================================= # ==== Google 优化 ==== User-agent: Googlebot Allow: / Allow: /browse/ Allow: /download/ Allow: /search/ Allow: /sitemap.xml Crawl-delay: 1 User-agent: Googlebot-Image Allow: /assets/images/ Allow: /uploads/ Crawl-delay: 1 # ==== 百度 优化 ==== User-agent: Baiduspider Allow: / Allow: /browse/ Allow: /download/ Allow: /search/ Allow: /sitemap.xml Crawl-delay: 3 User-agent: Baiduspider-image Allow: /assets/images/ Allow: /uploads/ Crawl-delay: 3 # ==== Bing 优化 ==== User-agent: bingbot Allow: / Allow: /browse/ Allow: /download/ Allow: /search/ Allow: /sitemap.xml Crawl-delay: 2 # ==== 国内搜索引擎优化 ==== User-agent: Sogou web spider Allow: / Crawl-delay: 5 User-agent: 360Spider Allow: / Crawl-delay: 5 User-agent: YisouSpider Allow: / Crawl-delay: 5 # ============================================= # 友好爬虫和工具 # ============================================= User-agent: Applebot Allow: / Crawl-delay: 2 User-agent: Twitterbot Allow: / Crawl-delay: 2 User-agent: facebookexternalhit Allow: / Crawl-delay: 2 User-agent: LinkedInBot Allow: / Crawl-delay: 2 User-agent: WeChat Allow: / Crawl-delay: 2 # ============================================= # 限制商业和恶意爬虫 # ============================================= # 商业SEO工具 - 允许但限速 User-agent: AhrefsBot Disallow: /admin/ Disallow: /config/ Crawl-delay: 10 User-agent: MJ12bot Disallow: /admin/ Disallow: /config/ Crawl-delay: 10 User-agent: SemrushBot Disallow: /admin/ Disallow: /config/ Crawl-delay: 10 User-agent: DotBot Disallow: /admin/ Disallow: /config/ Crawl-delay: 10 # AI爬虫 - 允许但限速 User-agent: GPTBot Disallow: /admin/ Crawl-delay: 5 User-agent: CCBot Disallow: /admin/ Crawl-delay: 5 # 数据收集爬虫 - 限制 User-agent: MauiBot Disallow: / Crawl-delay: 10 User-agent: zoominfobot Disallow: / Crawl-delay: 10 # ============================================= # 简化版本(针对其他所有爬虫) # ============================================= # 通用爬取延迟设置 Crawl-delay: 2 Sitemap: https://www.oskeep.com/sitemap.xml