# As a condition of accessing this website, you agree to abide by the following # content signals: # (a) If a Content-Signal = yes, you may collect content for the corresponding # use. # (b) If a Content-Signal = no, you may not collect content for the # corresponding use. # (c) If the website operator does not include a Content-Signal for a # corresponding use, the website operator neither grants nor restricts # permission via Content-Signal with respect to the corresponding use. # The content signals and their meanings are: # search: building a search index and providing search results (e.g., returning # hyperlinks and short excerpts from your website's contents). Search does not # include providing AI-generated search summaries. # ai-input: inputting content into one or more AI models (e.g., retrieval # augmented generation, grounding, or other real-time taking of content for # generative AI search answers). # ai-train: training or fine-tuning AI models. # use: how AI systems may consume the content (immediate, reference, or full). # ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF # RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT # AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET. # BEGIN Cloudflare Managed content User-agent: * Content-Signal: search=yes,ai-train=no,use=reference Allow: / # Training crawlers User-agent: Amazonbot Disallow: / User-agent: Applebot-Extended Disallow: / User-agent: Bytespider Disallow: / User-agent: CCBot Disallow: / User-agent: ClaudeBot Disallow: / User-agent: Diffbot Disallow: / User-agent: Google-Extended Disallow: / User-agent: GPTBot Disallow: / User-agent: omgili Disallow: / User-agent: anthropic-ai Disallow: / User-agent: Claude-Web Disallow: / User-agent: cohere-ai Disallow: / User-agent: MistralAI-Training Disallow: / User-agent: meta-externalagent Disallow: / User-agent: GoogleOther Disallow: / User-agent: Baiduspider Disallow: / User-agent: PetalBot Disallow: / User-agent: AwarioSmartBot User-agent: AwarioRssBot Disallow: / User-agent: Google-CloudVertexBot Disallow: / User-agent: QualifiedBot Disallow: / User-agent: Cotoyogi Disallow: / User-agent: ICC-Crawler Disallow: / User-agent: atlassian-bot Disallow: / User-agent: FishBot Disallow: / User-agent: BorderxBot Disallow: / User-agent: NavuBot Disallow: / User-agent: SemrushBot-SWA Disallow: / User-agent: WARDBot Disallow: / User-agent: magpie-crawler Disallow: / User-agent: KimiBot Disallow: / User-agent: CitibotSiteCrawler Disallow: / # END Cloudflare Managed Content # ============================================== # 网站:您的网站名称 # 最后更新:[日期] # 目标:允许搜索引擎和AI抓取,阻止恶意/无用爬虫 # ============================================== # ============================================== # 第1部分:允许主流搜索引擎和AI爬虫 # ============================================== # Google 搜索引擎 User-agent: Googlebot User-agent: Googlebot-Image User-agent: Googlebot-News User-agent: Googlebot-Video Allow: / Disallow: /wp-admin/ Disallow: /wp-login.php Disallow: /wp-login/ Disallow: /xmlrpc.php Disallow: /search/ Crawl-delay: 1 # Bing 搜索引擎 User-agent: Bingbot User-agent: MSNBot User-agent: MSNBot-Media Allow: / Disallow: /wp-admin/ Disallow: /wp-login.php Disallow: /xmlrpc.php Crawl-delay: 1 # OpenAI / ChatGPT User-agent: GPTBot User-agent: ChatGPT-User Allow: / Disallow: /wp-admin/ Disallow: /wp-login.php Disallow: /xmlrpc.php Allow: /wp-json/ # 保留 API 接口抓取 Crawl-delay: 2 # Anthropic (Claude) User-agent: Claude-Web User-agent: ClaudeBot Allow: / Disallow: /wp-admin/ Allow: /wp-json/ Crawl-delay: 2 # Apple (Siri, Spotlight) User-agent: Applebot User-agent: Applebot-Extended Allow: / Crawl-delay: 1 # 百度 (中国用户) User-agent: Baiduspider User-agent: Baiduspider-image User-agent: Baiduspider-video User-agent: Baiduspider-news Allow: / Disallow: /wp-admin/ Disallow: /wp-login.php Disallow: /xmlrpc.php Crawl-delay: 3 # ============================================== # 第2部分:阻止无用/恶意/过度抓取爬虫 # ============================================== # SEO工具 / 高负载爬虫 User-agent: AhrefsBot User-agent: SemrushBot User-agent: MJ12bot User-agent: MauiBot User-agent: Barkrowler User-agent: BLEXBot Disallow: / Crawl-delay: 10 # 内容窃取/聚合爬虫 User-agent: CCBot User-agent: DotBot User-agent: Lipperhey User-agent: SISTRIX Disallow: / # 垃圾邮件/恶意爬虫 User-agent: MegaIndex User-agent: SiteExplorer User-agent: XoviBot Disallow: / # ============================================== # 第3部分:通用规则(其他爬虫) # ============================================== User-agent: * Allow: / # 允许抓取公开内容 Disallow: /wp-admin/ Disallow: /wp-includes/ Disallow: /wp-login.php Disallow: /wp-login/ Disallow: /wp-signup.php Disallow: /xmlrpc.php Disallow: /trackback/ Disallow: /readme.html Disallow: /license.txt Disallow: /wp-config.php Disallow: /wp-config-sample.php Disallow: /error_log Disallow: /debug.log Disallow: /cgi-bin/ Disallow: /private/ Disallow: /admin/ Disallow: /user/ Disallow: /users/ Disallow: /profile/ Disallow: /profiles/ Disallow: /member/ Disallow: /members/ Disallow: /search/ Disallow: /?s= Disallow: /?q= Disallow: /*?* # 避免动态重复抓取 Disallow: /*.php$ # 避免抓取 PHP 文件 Disallow: /wp-content/uploads/*.php Disallow: /wp-content/uploads/*.exe Disallow: /wp-content/uploads/*.js # 保留 Elementor / WooCommerce / WP REST API 接口可抓取 Allow: /wp-json/ # 全局抓取延迟 Crawl-delay: 2