# ================================================================= # robots.txt — DataWiper.com # Diperbarui: 2025-06-24 # Panduan lengkap untuk Googlebot & crawler lainnya # ================================================================= # ── SEMUA CRAWLER (default) ─────────────────────────────────────── User-agent: * Allow: / # Halaman admin & sistem — JANGAN di-crawl Disallow: /admin/ Disallow: /wp-admin/ Disallow: /dashboard/ Disallow: /login/ Disallow: /masuk/ Disallow: /register/ Disallow: /daftar/ Disallow: /akun/ Disallow: /profil/ Disallow: /api/ Disallow: /cdn-cgi/ Disallow: /cgi-bin/ Disallow: /tmp/ Disallow: /cache/ Disallow: /assets/private/ # URL dengan parameter yang menghasilkan duplicate content Disallow: /search? Disallow: /*?ref= Disallow: /*?utm_ Disallow: /*?session= Disallow: /*?sort= Disallow: /*?filter= Disallow: /*?lang= Disallow: /*?print= Disallow: /*?preview= Disallow: /*?replytocom= # Feed / API endpoints Disallow: /feed/ Disallow: /rss/ Disallow: /api/ # File non-HTML yang tidak perlu di-index Disallow: /*.json$ Disallow: /*.xml$ Disallow: /*.log$ Disallow: /*.sql$ Disallow: /*.zip$ Disallow: /*.tar$ # Izinkan eksplisit halaman SEO penting Allow: /sitemap.xml Allow: /sitemap-pages.xml Allow: /sitemap-blog.xml # ── GOOGLEBOT — Aturan khusus Google ───────────────────────────── User-agent: Googlebot Allow: / # Izinkan akses ke CSS dan JS untuk rendering penuh Allow: /*.css Allow: /*.js Allow: /assets/ Allow: /images/ # Blokir halaman admin & sistem Disallow: /admin/ Disallow: /api/ Disallow: /tmp/ Disallow: /cache/ # Crawl-delay ringan agar tidak membebani server Crawl-delay: 1 # ── GOOGLEBOT IMAGE — Hanya izinkan folder gambar ──────────────── User-agent: Googlebot-Image Allow: /assets/images/ Allow: /images/ Allow: /uploads/ Disallow: / # ── BINGBOT ─────────────────────────────────────────────────────── User-agent: Bingbot Allow: / Disallow: /admin/ Disallow: /api/ Crawl-delay: 2 # ── YANDEX ──────────────────────────────────────────────────────── User-agent: YandexBot Allow: / Disallow: /admin/ Disallow: /api/ Crawl-delay: 3 # ── BLOKIR SCRAPER & BOT BERBAHAYA ─────────────────────────────── # Bot SEO 3rd party — konsumsi crawl budget tanpa manfaat indexing User-agent: AhrefsBot Disallow: / User-agent: SemrushBot Disallow: / User-agent: MJ12bot Disallow: / User-agent: DotBot Disallow: / User-agent: BLEXBot Disallow: / User-agent: PetalBot Disallow: / User-agent: SeznamBot Disallow: / User-agent: GrapeshotCrawler Disallow: / User-agent: AspiegelBot Disallow: / User-agent: DataForSeoBot Disallow: / # Bot scraper konten User-agent: ia_archiver Disallow: / User-agent: CCBot Disallow: / # ── SITEMAP — WAJIB untuk Google Indexing ──────────────────────── Sitemap: https://www.data-wiper.com/sitemap.xml Sitemap: https://www.data-wiper.com/sitemap-pages.xml Sitemap: https://www.data-wiper.com/sitemap-blog.xml