# ==============================================================
# robots.txt — 100cuci.io
# Last updated: April 2026
# Purpose: Maximum search engine visibility across all crawlers
# ==============================================================
 
 
# ── Google (main + image + video + news crawlers) ──────────────
User-agent: Googlebot
Allow: /
 
User-agent: Googlebot-Image
Allow: /
 
User-agent: Googlebot-Video
Allow: /
 
User-agent: Googlebot-News
Allow: /
 
 
# ── Bing & Microsoft ───────────────────────────────────────────
User-agent: Bingbot
Allow: /
 
User-agent: msnbot
Allow: /
 
User-agent: msnbot-media
Allow: /
 
User-agent: BingPreview
Allow: /
 
 
# ── Yahoo ──────────────────────────────────────────────────────
User-agent: Slurp
Allow: /
 
 
# ── Yandex ─────────────────────────────────────────────────────
User-agent: YandexBot
Allow: /
 
User-agent: YandexImages
Allow: /
 
 
# ── DuckDuckGo ─────────────────────────────────────────────────
User-agent: DuckDuckBot
Allow: /
 
 
# ── Baidu ──────────────────────────────────────────────────────
User-agent: Baiduspider
Allow: /
 
 
# ── Apple (Spotlight / Siri suggestions) ───────────────────────
User-agent: Applebot
Allow: /
 
 
# ── Facebook / Meta link preview ──────────────────────────────
User-agent: facebookexternalhit
Allow: /
 
 
# ── Twitter / X link preview ──────────────────────────────────
User-agent: Twitterbot
Allow: /
 
 
# ── LinkedIn link preview ─────────────────────────────────────
User-agent: LinkedInBot
Allow: /
 
 
# ── WhatsApp link preview ─────────────────────────────────────
User-agent: WhatsApp
Allow: /
 
 
# ── Telegram link preview ─────────────────────────────────────
User-agent: TelegramBot
Allow: /
 
 
# ── SEO audit tools (keeps your rankings data accurate) ───────
User-agent: AhrefsBot
Allow: /
 
User-agent: SemrushBot
Allow: /
 
User-agent: MJ12bot
Allow: /
 
User-agent: DotBot
Allow: /
 
 
# ── Catchall: allow every other legitimate crawler ────────────
User-agent: *
Allow: /
 
# Block only these private / system paths from ALL bots
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-login.php
Disallow: /wp-register.php
Disallow: /xmlrpc.php
Disallow: /wp-cron.php
Disallow: /wp-json/
Disallow: /feed/
Disallow: /comments/feed/
Disallow: /?s=                  # internal search result pages
Disallow: /*?*replytocom=        # comment reply URLs (duplicate content)
Disallow: /cdn-cgi/              # Cloudflare internal endpoints
 
 
# ── Crawl-delay hint for less aggressive bots ─────────────────
# (Googlebot & Bingbot ignore this — they self-regulate)
Crawl-delay: 5
 
 
# ── Sitemap locations ─────────────────────────────────────────
Sitemap: https://100cuci.io/sitemap.xml
Sitemap: https://100cuci.io/sitemap_index.xml
Sitemap: https://100cuci.io/sitemap-posts.xml
Sitemap: https://100cuci.io/sitemap-pages.xml
Sitemap: https://100cuci.io/sitemap-categories.xml