Sitemap: https://www.executivegroupfl.com/sitemap-index.xml # ========================================================= # DEFAULT: deny everything not explicitly allowed below. # Any crawler not named in this file — known or unknown, # AI or otherwise — is blocked by default. # ========================================================= User-agent: * Disallow: / # ========================================================= # SEARCH ENGINES — drive organic search traffic # ========================================================= User-agent: Googlebot Disallow: /index.php?advanced=1 Disallow: /index.php?quick=1 Disallow: /emails_kvarea/ Disallow: /mobilefirst/ Disallow: /private_kvarea/ Disallow: /wp-admin/ Disallow: /wp-includes/ Disallow: /admin/ Allow: /sell Allow: /areas Allow: /pages Allow: /resources Allow: /index.php?showagency=1 Allow: /index.php?showagent=1 Allow: / User-agent: Googlebot-Image Allow: / User-agent: Googlebot-Mobile Allow: / Crawl-delay: 10 User-agent: bingbot Allow: / Crawl-delay: 120 # ========================================================= # GOOGLE ADS — required for marketing team's Google Ads # campaigns (landing page checks, ad quality/relevance scoring) # ========================================================= User-agent: AdsBot-Google Allow: / User-agent: AdsBot-Google-Mobile Allow: / User-agent: AdsBot-Google-Mobile-Apps Allow: / # ========================================================= # SOCIAL PREVIEW BOTS — generate link previews when listings # or pages are shared, driving click-through traffic # ========================================================= User-agent: Twitterbot Allow: / User-agent: facebookexternalhit Allow: / # ========================================================= # AI ANSWER / REAL-TIME SEARCH CRAWLERS — fetch content live # to answer user questions, can cite/link back as a lead source # ========================================================= User-agent: ChatGPT-User User-agent: OAI-SearchBot User-agent: PerplexityBot User-agent: ClaudeBot User-agent: Claude-Web User-agent: Amazonbot Allow: / # ========================================================= # SEO / SITE-AUDIT TOOLS — kept from the original file for # internal SEO/QA use, not a direct traffic/lead source # ========================================================= User-agent: PowerMapper Allow: / Crawl-delay: 5 User-agent: Screaming Frog SEO Spider Allow: / User-agent: SemrushBot Allow: / # ========================================================= # COOKIE / PRIVACY COMPLIANCE SCANNERS — kept from the original # file so consent-banner services can keep scanning the live site # ========================================================= User-agent: TermlyBot Allow: / User-agent: CookieYesbot Allow: / User-agent: Osano Privacy Compliance Scanner Allow: / # ========================================================= # EXCLUDED (falls under the default Disallow: / above) # Kept here only as a record of what was deliberately left out # and why, so it isn't mistaken for an oversight later: # # AI training / bulk-scraping crawlers (no traffic back): # GPTBot, CCBot, Bytespider, Google-Extended, anthropic-ai, # Applebot-Extended, Diffbot, Omgilibot, Omgili, YouBot # # Ad-serving crawler (AdSense revenue, not campaign traffic — # different from AdsBot-Google above, which is allowed): # Mediapartners-Google # # Deprecated/inactive: # Slurp (Yahoo), msnbot # =========================================================