# ============================================================ # BILARNA.COM – robots.txt # API is hosted on api.bilarna.com (separate domain, not here) # Last updated: 2026-06-12 # ============================================================ # ------------------------------------------------------------ # 1. DEFAULT – All crawlers # ------------------------------------------------------------ User-agent: * Allow: / # Explicit allow for AI/agent machine-readable files Allow: /llms.txt Allow: /agent-manifest.json Allow: /.well-known/mcp.json Allow: /provider/*/agent.json Allow: /provider/*/llms.txt Allow: /provider/*/openapi.yaml # API is served from a separate domain (api.bilarna.com) — never crawl the # same-origin proxy path here, it wastes crawl budget and backend capacity. Disallow: /api/ # Throttle default crawl rate — backend runs on a small 2 vCPU host and cannot # sustain unthrottled concurrent crawling of category/provider pages. Crawl-delay: 5 # ------------------------------------------------------------ # 2. SEARCH ENGINES – Standard crawlers # ------------------------------------------------------------ User-agent: Googlebot Allow: / User-agent: Bingbot Allow: / User-agent: Applebot Allow: / # ------------------------------------------------------------ # 3. AI SEARCH & ANSWER ENGINES # (indexing + recommendations, NOT training) # ------------------------------------------------------------ User-agent: GPTBot Allow: / User-agent: OAI-SearchBot Allow: / User-agent: ChatGPT-User Allow: / User-agent: PerplexityBot Allow: / User-agent: Claude-Web Allow: / User-agent: Anthropic-AI Allow: / User-agent: Google-Extended Allow: / User-agent: Grok Allow: / User-agent: xAI-ContentAgent Allow: / User-agent: DeepSeekBot Allow: / User-agent: MistralBot Allow: / User-agent: iaskspider Allow: / User-agent: YouBot Allow: / # ByteDance AI – search/indexing access granted, throttled (known for aggressive crawl rates) User-agent: Bytespider Allow: / Crawl-delay: 20 # Common Crawl – access granted (open web index) User-agent: CCBot Allow: / # ------------------------------------------------------------ # 4. AI TRAINING CRAWLERS – Block (content protection) # ------------------------------------------------------------ User-agent: Applebot-Extended Disallow: / User-agent: AI2Bot-Dolma Disallow: / User-agent: Ai2Bot Disallow: / User-agent: img2dataset Disallow: / User-agent: Webzio-Extended Disallow: / User-agent: VelenPublicWebCrawler Disallow: / User-agent: Timpibot Disallow: / User-agent: magpie-crawler Disallow: / User-agent: * Disallow: /cdn-cgi/ # ------------------------------------------------------------ # 5. SEO TOOLS – Allow (monitoring & analytics), throttled # These are non-search-engine bots crawling aggressively for # backlink/keyword data — throttle hard to protect backend capacity. # ------------------------------------------------------------ User-agent: SemrushBot Allow: / Crawl-delay: 20 User-agent: AhrefsBot Allow: / Crawl-delay: 20 User-agent: DataForSeoBot Allow: / Crawl-delay: 20 User-agent: MJ12bot Disallow: / User-agent: DotBot Disallow: / User-agent: Screaming Frog SEO Spider Disallow: / # ------------------------------------------------------------ # 6. DATA SCRAPERS – Block (no value, crawl budget waste) # ------------------------------------------------------------ User-agent: omgili Disallow: / User-agent: PiplBot Disallow: / User-agent: Nicecrawler Disallow: / # ------------------------------------------------------------ # 7. SOCIAL / OTHER – Case by case # ------------------------------------------------------------ User-agent: FacebookBot Allow: / User-agent: Meta-ExternalAgent Allow: / User-agent: Diffbot Allow: / User-agent: Amazonbot Allow: / User-agent: cohere-ai Allow: / # The content signals User-Agent: * Content-Signal: ai-train=yes, search=yes, ai-input=yes Allow: / # ------------------------------------------------------------ # 8. SITEMAPS # ------------------------------------------------------------ Sitemap: https://bilarna.com/sitemap_index.xml