User-agent: * Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /wp-content/uploads/wpo-plugins-tables-list.json Sitemap: https://theaugustapress.com/sitemap_index.xml # ========================================== # AI / LLM training & answer engines (BLOCK) # ========================================== User-agent: GPTBot Disallow: / User-agent: ChatGPT-User Disallow: / User-agent: OAI-SearchBot Disallow: / User-agent: CCBot Disallow: / User-agent: ClaudeBot Disallow: / User-agent: anthropic-ai Disallow: / User-agent: Google-Extended Disallow: / User-agent: Amazonbot Disallow: / User-agent: Applebot-Extended Disallow: / User-agent: Meta-ExternalAgent Disallow: / User-agent: Meta-ExternalFetcher Disallow: / User-agent: PerplexityBot Disallow: / User-agent: YouBot Disallow: / User-agent: AI2Bot Disallow: / User-agent: Bytespider Disallow: / # ========================================== # SEO intelligence & competitive crawlers # ========================================== User-agent: AhrefsBot Disallow: / User-agent: MJ12bot Disallow: / User-agent: DotBot Disallow: / User-agent: BLEXBot Disallow: / User-agent: SeobilityBot Disallow: / User-agent: SerpstatBot Disallow: / User-agent: DataForSeoBot Disallow: / # ========================================== # Archivers, downloaders & scrapers # ========================================== User-agent: ia_archiver Disallow: / User-agent: HTTrack Disallow: / User-agent: SiteSucker Disallow: / User-agent: Teleport Disallow: / User-agent: WebCopier Disallow: / User-agent: wget Disallow: / User-agent: curl Disallow: / # ========================================== # China-based search & scraping bots (BLOCK) # ========================================== User-agent: Sogou web spider Disallow: / User-agent: Sogou Disallow: / User-agent: Baiduspider Disallow: / # ========================================== # ALLOWED: Major search engines # ========================================== User-agent: Googlebot Allow: / User-agent: Bingbot Allow: / User-agent: DuckDuckBot Allow: / User-agent: Applebot Allow: /