User-agent: * Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ sitemap: https://legaltegrity.com/page-sitemap.xml # ----------------------------------------------- # Suchmaschinen - explizit erlaubt # ----------------------------------------------- # Google User-agent: Googlebot Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ User-agent: AdsBot-Google-Mobile Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ User-agent: Googlebot-Image Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ User-agent: Googlebot-News Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ User-agent: Google-Video Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ # Bing / Microsoft User-agent: Bingbot Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ User-agent: BingPreview Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ User-agent: MSNBot-Media Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ User-agent: msnbot Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ # DuckDuckGo User-agent: DuckDuckBot Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ # Ecosia User-agent: Ecosiabot Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ # Internet Archive (Wayback Machine) User-agent: ia_archiver Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ # ----------------------------------------------- # Social Media - explizit erlaubt (Link-Previews) # ----------------------------------------------- User-agent: Twitterbot Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ User-agent: LinkedInBot Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ User-agent: Slackbot Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ User-agent: WhatsApp Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ # ----------------------------------------------- # KI-Crawler - explizit erlaubt # ----------------------------------------------- # Anthropic (Claude) User-agent: Claude-User Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ User-agent: ClaudeBot Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ User-agent: Claude-Web Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ User-agent: anthropic-ai Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ User-agent: AnthropicCrawler Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ # OpenAI (ChatGPT) User-agent: GPTBot Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ User-agent: ChatGPT-User Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ User-agent: OAI-SearchBot Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ # Google (Gemini/Bard) User-agent: Google-Extended Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ User-agent: Googlebot-Extended Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ # Perplexity AI User-agent: PerplexityBot Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ # Meta (Llama) User-agent: FacebookBot Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ User-agent: Meta-ExternalAgent Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ # Apple (Siri/Spotlight) User-agent: Applebot-Extended Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ # ByteDance (TikTok) User-agent: Bytespider Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ # Cohere User-agent: cohere-ai Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ # Common Crawl (Training) User-agent: CCBot Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ # Diffbot User-agent: Diffbot Allow: / Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /*?e-page-* Disallow: /wp-json/ Disallow: /en/wp-json/ # ----------------------------------------------- # SEO-Scraper / Wettbewerbs-Tools - gesperrt # ----------------------------------------------- User-agent: AhrefsBot Disallow: / User-agent: SemrushBot Disallow: / User-agent: MJ12bot Disallow: / User-agent: DotBot Disallow: / User-agent: BLEXBot Disallow: / User-agent: RogerBot Disallow: / User-agent: linkdexbot Disallow: / User-agent: Exabot Disallow: / User-agent: meanpathbot Disallow: / User-agent: Cliqzbot Disallow: / User-agent: sistrix Disallow: / User-agent: serpstatbot Disallow: / User-agent: DataForSeoBot Disallow: / User-agent: seoscannerbot Disallow: / User-agent: Screaming Frog SEO Spider Disallow: / User-agent: SiteAuditBot Disallow: / # ----------------------------------------------- # Scraper / Content-Diebstahl - gesperrt # ----------------------------------------------- User-agent: SiteExplorer Disallow: / User-agent: spbot Disallow: / User-agent: zgrab Disallow: / User-agent: MegaIndex Disallow: / User-agent: Scrapy Disallow: / User-agent: HTTrack Disallow: / User-agent: WebCopier Disallow: / User-agent: SurveyBot Disallow: / User-agent: Nutch Disallow: / User-agent: sogou Disallow: / User-agent: Mail.Ru Disallow: / User-agent: grapeshot Disallow: / User-agent: TurnitinBot Disallow: / # ----------------------------------------------- # Preisvergleich / Shopping-Scraper - gesperrt # ----------------------------------------------- User-agent: PriceSpider Disallow: / User-agent: Shopbot Disallow: / User-agent: Pricerunner Disallow: / # ----------------------------------------------- # Unerwuenschte KI-Training-Scraper - gesperrt # ----------------------------------------------- User-agent: omgili Disallow: / User-agent: omgilibot Disallow: / User-agent: peer39_crawler Disallow: / User-agent: Proximic Disallow: / # ----------------------------------------------- # Spam / Malicious - gesperrt # ----------------------------------------------- User-agent: EmailCollector Disallow: / User-agent: EmailSiphon Disallow: / User-agent: WebBandit Disallow: / User-agent: EmailWolf Disallow: / User-agent: ExtractorPro Disallow: / User-agent: CopyRightCheck Disallow: / User-agent: Meltwater Disallow: / User-agent: newspaper Disallow: /