# Digital Silk Route — crawler policy
# Search engines: allowed on public pages, blocked on gated/admin areas.
# AI scrapers & dataset crawlers: blocked site-wide to protect our
# courses, curriculum, marketplace products, and proprietary content.

# ---------- Allowed search engines (public marketing pages only) ----------
User-agent: Googlebot
User-agent: Bingbot
User-agent: DuckDuckBot
User-agent: Slurp
User-agent: Applebot
Allow: /
# Marketplace pagination: only ?page=N is a canonical query variant
# (every page carries rel=canonical / prev / next). Block ad-hoc query
# strings so crawlers don't spend budget on non-canonical duplicates.
Allow: /marketplace$
Allow: /marketplace?page=
Disallow: /marketplace?*&*
Disallow: /marketplace?sort=
Disallow: /marketplace?q=
Disallow: /marketplace?category=
Disallow: /marketplace?tag=
Allow: /sellers/
Disallow: /admin
Disallow: /dashboard
Disallow: /seller
Disallow: /tasks
Disallow: /business-os
Disallow: /login
Disallow: /enroll
Disallow: /academy/*/lesson/
Disallow: /my-learning
Disallow: /download/
Disallow: /api/

# ---------- AI training / dataset / scraper bots — fully blocked ----------
User-agent: GPTBot
Disallow: /
User-agent: ChatGPT-User
Disallow: /
User-agent: OAI-SearchBot
Disallow: /
User-agent: Google-Extended
Disallow: /
User-agent: GoogleOther
Disallow: /
User-agent: ClaudeBot
Disallow: /
User-agent: Claude-Web
Disallow: /
User-agent: anthropic-ai
Disallow: /
User-agent: PerplexityBot
Disallow: /
User-agent: Perplexity-User
Disallow: /
User-agent: cohere-ai
Disallow: /
User-agent: CCBot
Disallow: /
User-agent: Amazonbot
Disallow: /
User-agent: Applebot-Extended
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: ByteDance
Disallow: /
User-agent: TikTokSpider
Disallow: /
User-agent: FacebookBot
Disallow: /
User-agent: Meta-ExternalAgent
Disallow: /
User-agent: meta-externalagent
Disallow: /
User-agent: Diffbot
Disallow: /
User-agent: ImagesiftBot
Disallow: /
User-agent: Omgilibot
Disallow: /
User-agent: Omgili
Disallow: /
User-agent: YouBot
Disallow: /
User-agent: AwarioRssBot
Disallow: /
User-agent: AwarioSmartBot
Disallow: /
User-agent: DataForSeoBot
Disallow: /
User-agent: SemrushBot
Disallow: /
User-agent: AhrefsBot
Disallow: /
User-agent: MJ12bot
Disallow: /
User-agent: PetalBot
Disallow: /
User-agent: Timpibot
Disallow: /
User-agent: ICC-Crawler
Disallow: /
User-agent: VelenPublicWebCrawler
Disallow: /
User-agent: Scrapy
Disallow: /
User-agent: magpie-crawler
Disallow: /
User-agent: news-please
Disallow: /
User-agent: Kangaroo Bot
Disallow: /
User-agent: Sidetrade indexer bot
Disallow: /
User-agent: img2dataset
Disallow: /
User-agent: Webzio-Extended
Disallow: /
User-agent: ZoominfoBot
Disallow: /
User-agent: NewsNow
Disallow: /

# ---------- Catch-all (other generic crawlers) ----------
User-agent: *
Allow: /
Allow: /marketplace$
Allow: /marketplace?page=
Disallow: /marketplace?*&*
Disallow: /marketplace?sort=
Disallow: /marketplace?q=
Disallow: /marketplace?category=
Disallow: /marketplace?tag=
Allow: /sellers/
Disallow: /admin
Disallow: /dashboard
Disallow: /seller
Disallow: /tasks
Disallow: /business-os
Disallow: /login
Disallow: /enroll
Disallow: /academy/*/lesson/
Disallow: /my-learning
Disallow: /download/
Disallow: /api/

# Canonical sitemap (also mirrored at /sitemap.xml via the app server route)
Sitemap: https://www.digitalsilkroute.com/sitemap.xml