# ============================================ # ROBOTS.TXT - GROUP BUILDER FORUMS # ============================================ # -------------------------------------------- # SEARCH ENGINES - FULL ACCESS # -------------------------------------------- User-agent: Googlebot Crawl-delay: 1 Allow: / User-agent: Bingbot Crawl-delay: 1 Allow: / User-agent: Slurp Crawl-delay: 2 Allow: / # -------------------------------------------- # SOCIAL MEDIA - ALLOW (for link previews) # -------------------------------------------- User-agent: facebookexternalhit Allow: / User-agent: Twitterbot Allow: / User-agent: LinkedInBot Allow: / # -------------------------------------------- # AI CRAWLERS - THROTTLED (hedge your bets) # -------------------------------------------- User-agent: GPTBot Crawl-delay: 30 Allow: / User-agent: ChatGPT-User Crawl-delay: 30 Allow: / User-agent: ClaudeBot Crawl-delay: 30 Allow: / User-agent: Claude-Web Crawl-delay: 30 Allow: / User-agent: anthropic-ai Crawl-delay: 30 Allow: / User-agent: PerplexityBot Crawl-delay: 30 Allow: / User-agent: OAI-SearchBot Crawl-delay: 30 Allow: / # -------------------------------------------- # AI TRAINING BOTS - BLOCK (no benefit to you) # -------------------------------------------- User-agent: Bytespider Disallow: / User-agent: CCBot Disallow: / User-agent: cohere-ai Disallow: / User-agent: cohere-training-data-crawler Disallow: / User-agent: Diffbot Disallow: / User-agent: ImagesiftBot Disallow: / User-agent: Meta-ExternalAgent Disallow: / User-agent: meta-externalagent Disallow: / User-agent: meta-webindexer Disallow: / User-agent: omgili Disallow: / User-agent: omgilibot Disallow: / User-agent: Quora-Bot Disallow: / User-agent: YouBot Disallow: / User-agent: quillbot.com Disallow: / # -------------------------------------------- # CONTENT SCRAPERS - BLOCK # -------------------------------------------- User-agent: Amazonbot Disallow: / User-agent: AhrefsBot Disallow: / User-agent: AliyunSecBot Disallow: / User-agent: AwarioRssBot Disallow: / User-agent: AwarioSmartBot Disallow: / User-agent: BLEXBot Disallow: / User-agent: DataForSeoBot Disallow: / User-agent: DotBot Disallow: / User-agent: EchoboxBot Disallow: / User-agent: FriendlyCrawler Disallow: / User-agent: MJ12bot Disallow: / User-agent: magpie-crawler Disallow: / User-agent: MyCentralAIScraperBot Disallow: / User-agent: NewsNow Disallow: / User-agent: news-please Disallow: / User-agent: PetalBot Disallow: / User-agent: peer39_crawler Disallow: / User-agent: Scrapy Disallow: / User-agent: SeekrBot Disallow: / User-agent: SeekportBot Disallow: / User-agent: SemrushBot Disallow: / User-agent: SeznamHomepageCrawler Disallow: / User-agent: Timpibot Disallow: / User-agent: TurnitinBot Disallow: / User-agent: YandexBot Disallow: / # -------------------------------------------- # DEFAULT - ALLOW WITH CRAWL DELAY # -------------------------------------------- User-agent: * Crawl-delay: 5 Allow: / # -------------------------------------------- # XENFORO - BLOCK NON-CONTENT PATHS (all bots) # -------------------------------------------- User-agent: * Disallow: /account/ Disallow: /admin.php Disallow: /find-new/ Disallow: /goto/ Disallow: /login/ Disallow: /lost-password/ Disallow: /register/ Disallow: /search/ Disallow: /whats-new/ Disallow: /posts/*/bookmark$ Disallow: /posts/*/react Disallow: /conversations/ Disallow: /*?order= Disallow: /*?direction= Disallow: /*&order= Disallow: /*&direction= # -------------------------------------------- # SITEMAP # -------------------------------------------- Sitemap: /sitemap.xml