# ============================================================================
# robots.txt for cnglobalsourcing.com
# Last updated: 2026-07-19
# ============================================================================

# ── All crawlers: allow everything except private/admin paths ────────────────
User-agent: *
Allow: /
Disallow: /admin/
Disallow: /private/
Disallow: /cgi-bin/
Disallow: /tmp/

# ── Sitemap references (all major search engines) ─────────────────────────────
Sitemap: https://cnglobalsourcing.com/sitemap.xml

# ── Google / Googlebot ────────────────────────────────────────────────────────
User-agent: Googlebot
Allow: /
Crawl-delay: 0

User-agent: Googlebot-Image
Allow: /
Crawl-delay: 0

User-agent: Googlebot-News
Allow: /
Crawl-delay: 0

User-agent: Googlebot-Video
Allow: /
Crawl-delay: 0

User-agent: Googlebot-Mobile
Allow: /
Crawl-delay: 0

User-agent: AdsBot-Google
Allow: /
Crawl-delay: 0

# ── Baidu / Baiduspider ──────────────────────────────────────────────────────
User-agent: Baiduspider
Allow: /
Crawl-delay: 1

User-agent: Baiduspider-image
Allow: /
Crawl-delay: 1

User-agent: Baiduspider-video
Allow: /
Crawl-delay: 1

User-agent: Baiduspider-mobile
Allow: /
Crawl-delay: 1

# ── Bing / Bingbot ───────────────────────────────────────────────────────────
User-agent: Bingbot
Allow: /
Crawl-delay: 0

User-agent: BingPreview
Allow: /
Crawl-delay: 0

# ── Yandex / YandexBot ───────────────────────────────────────────────────────
User-agent: YandexBot
Allow: /
Crawl-delay: 1

User-agent: YandexImages
Allow: /
Crawl-delay: 1

User-agent: YandexVideo
Allow: /
Crawl-delay: 1

User-agent: YandexMobileBot
Allow: /
Crawl-delay: 1

User-agent: YandexMetrika
Allow: /
Crawl-delay: 1

# ── Naver / Yeti ───────────────────────────────────────────────────────────
User-agent: Yeti
Allow: /
Crawl-delay: 1

User-agent: NaverBot
Allow: /
Crawl-delay: 1

# ── AI Crawlers (used by AI companies for training / search) ──────────────────
# Block only if you don't want AI training; these lines ALLOW AI crawling
# Remove or add Disallow to restrict specific AI crawlers

User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: CCBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Bytespider
Allow: /
Crawl-delay: 1

User-agent: PetalBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Diffbot
Allow: /

User-agent: FacebookBot
Allow: /

# ── Block scrapers that ignore crawl-delay ────────────────────────────────────
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: MJ12bot
Disallow: /

# ── Host directive (mirror guidance for some crawlers) ────────────────────────
# Host: cnglobalsourcing.com