# ======================================== # ROBOTS.TXT - OPTIMIZED FOR SEO & SECURITY # ======================================== # ======================================== # ALLOWED BOTS - ESSENTIAL FOR SEO # ======================================== # Google Search Bot (MOST IMPORTANT) User-agent: Googlebot Allow: / Crawl-delay: 1 # Google Image Bot User-agent: Googlebot-Image Allow: / Crawl-delay: 1 # Google Mobile Bot User-agent: Googlebot-Mobile Allow: / Crawl-delay: 1 # Bing Search Bot User-agent: Bingbot Allow: / Crawl-delay: 1 # Bing Preview Bot (for social sharing) User-agent: BingPreview Allow: / # Yandex Bot User-agent: Yandex Allow: / Crawl-delay: 2 # DuckDuckGo Bot User-agent: DuckDuckBot Allow: / Crawl-delay: 1 # Baidu Bot User-agent: Baiduspider Allow: / Crawl-delay: 2 # Sogou Bot User-agent: Sogou Allow: / Crawl-delay: 2 # ======================================== # SOCIAL MEDIA BOTS - ALLOW FOR SHARING # ======================================== # Facebook External Hit (for social previews) User-agent: facebookexternalhit Allow: / # Twitter Bot User-agent: Twitterbot Allow: / # LinkedIn Bot User-agent: LinkedInBot Allow: / # Pinterest Bot User-agent: Pinterest Allow: / # ======================================== # ESSENTIAL TOOLS - ALLOW FOR DEVELOPMENT # ======================================== # Google PageSpeed Insights User-agent: Google PageSpeed Insights Allow: / # Google Structured Data Testing Tool User-agent: Google-Structured-Data-Testing-Tool Allow: / # Google Web Preview User-agent: Google Web Preview Allow: / # ======================================== # BLOCK AI TRAINING BOTS # ======================================== # Anthropic AI User-agent: anthropic-ai Disallow: / User-agent: ClaudeBot Disallow: / User-agent: Claude-Web Disallow: / # OpenAI User-agent: GPTBot Disallow: / User-agent: ChatGPT-User Disallow: / User-agent: GPT-4 Disallow: / User-agent: GPT-4o Disallow: / User-agent: GPT-3 Disallow: / User-agent: GPT-3.5 Disallow: / # Google AI User-agent: Google-Extended Disallow: / User-agent: GoogleOther Disallow: / User-agent: Gemini Disallow: / User-agent: GeminiBot Disallow: / # Apple AI User-agent: Applebot-Extended Disallow: / # Perplexity AI User-agent: PerplexityBot Disallow: / User-agent: Perplexity Disallow: / # You.com User-agent: YouBot Disallow: / User-agent: You.com Disallow: / # Meta/Facebook AI User-agent: Meta-ExternalAgent Disallow: / User-agent: FacebookBot Disallow: / # ByteDance/TikTok AI User-agent: Bytespider Disallow: / # Common Crawl User-agent: CCBot Disallow: / # Cohere AI User-agent: cohere-ai Disallow: / # DataForSeoBot User-agent: DataForSeoBot Disallow: / # Diffbot User-agent: Diffbot Disallow: / # Amazon AI User-agent: Amazonbot Disallow: / # Yandex AI User-agent: YandexGPT Disallow: / # ======================================== # BLOCK AGGRESSIVE SEO TOOLS # ======================================== # Ahrefs User-agent: AhrefsBot Disallow: / # SEMrush User-agent: SemrushBot Disallow: / # Screaming Frog User-agent: Screaming Frog SEO Spider Disallow: / # Xenu Link Sleuth User-agent: Xenu Link Sleuth Disallow: / # ======================================== # BLOCK SCRAPERS & CRAWLERS # ======================================== # Scrapy User-agent: Scrapy Disallow: / # PhantomJS User-agent: PhantomJS Disallow: / # Curl User-agent: curl Disallow: / # Wget User-agent: wget Disallow: / # Python Requests User-agent: python-requests Disallow: / User-agent: python-httplib2 Disallow: / User-agent: python-urllib Disallow: / # ======================================== # BLOCK MONITORING BOTS (OPTIONAL) # ======================================== # Pingdom User-agent: Pingdom Disallow: / # UptimeRobot User-agent: UptimeRobot Disallow: / # StatusCake User-agent: StatusCake Disallow: / # ======================================== # BLOCK OTHER UNWANTED BOTS # ======================================== # Archive.org (if you don't want archiving) User-agent: ia_archiver Disallow: / # Common Crawl User-agent: CCBot Disallow: / # ======================================== # BLOCK CLOUD & HOSTING PROVIDER BOTS # ======================================== # Google Cloud User-agent: Google-Cloud Disallow: / User-agent: GoogleCloud Disallow: / User-agent: Google-private-cloud Disallow: / User-agent: GoogleProxy Disallow: / User-agent: Google Proxy Disallow: / # Microsoft Corporation User-agent: MicrosoftURLControl Disallow: / User-agent: Microsoft Office Protocol Discovery Disallow: / User-agent: Microsoft-WebDAV-MiniRedir Disallow: / # OVH SAS User-agent: OVH Disallow: / User-agent: OVH SAS Disallow: / # DigitalOcean User-agent: DigitalOcean Disallow: / # Huawei Clouds User-agent: HuaweiClouds Disallow: / User-agent: HuaweiCloud Disallow: / User-agent: Huawei Disallow: / # Facebook (chặn toàn bộ bot Facebook ngoài bot social sharing) User-agent: Facebook Disallow: / User-agent: Facebot Disallow: / # Amazon.com User-agent: Amazonbot Disallow: / User-agent: Amazon-Route53-Health-Check-Service Disallow: / User-agent: AWS Disallow: / User-agent: Amazon Disallow: / # Omonia d.o.o. User-agent: Omonia Disallow: / User-agent: Omonia d.o.o. Disallow: / # ColoCrossing User-agent: ColoCrossing Disallow: / # ======================================== # BLOCK CLICK FRAUD, FAKE TRAFFIC, ANALYTIC SPAM BOTS # ======================================== User-agent: Clickagy Disallow: / User-agent: ClickCease Disallow: / User-agent: ClickGuard Disallow: / User-agent: Clixtell Disallow: / User-agent: AdbeatBot Disallow: / User-agent: AdMuncher Disallow: / User-agent: AdRecon Disallow: / User-agent: AdScanner Disallow: / User-agent: AdSpider Disallow: / User-agent: Semalt Disallow: / User-agent: Darodar Disallow: / User-agent: Buttons-for-website Disallow: / User-agent: SimplePie Disallow: / User-agent: BLEXBot Disallow: / User-agent: MegaIndex.ru Disallow: / User-agent: RankActiveLinkBot Disallow: / User-agent: RankFlex Disallow: / User-agent: RankSonicSiteAuditor Disallow: / User-agent: SeznamBot Disallow: / User-agent: spbot Disallow: / User-agent: SputnikBot Disallow: / User-agent: YandexImages Disallow: / User-agent: YandexMetrika Disallow: / User-agent: Sogou web spider Disallow: / User-agent: Sogou inst spider Disallow: / User-agent: Sogou spider2 Disallow: / User-agent: Sogou blog Disallow: / User-agent: Sogou News Spider Disallow: / User-agent: Sogou Orion spider Disallow: / User-agent: MJ12bot Disallow: / User-agent: DotBot Disallow: / User-agent: Exabot Disallow: / User-agent: Barkrowler Disallow: / User-agent: ZoominfoBot Disallow: / User-agent: MauiBot Disallow: / User-agent: Seekport Crawler Disallow: / User-agent: SeekportBot Disallow: / User-agent: NetcraftSurveyAgent Disallow: / User-agent: NetEstate NE Crawler Disallow: / User-agent: SISTRIX Crawler Disallow: / User-agent: SISTRIX Disallow: / User-agent: magpie-crawler Disallow: / User-agent: PetalBot Disallow: / User-agent: KagiBot Disallow: / User-agent: KagiSearch Disallow: / User-agent: GigaBot Disallow: / User-agent: CensysInspect Disallow: /