# robots.txt — 珠海长先新材料科技股份有限公司
# https://www.changxianchem.com

# --- Search engines -----------------------------------------------------------
User-agent: *
Allow: /

# API endpoints have nothing to index.
Disallow: /api/

# Internal search result pages: thin content, infinite combinations.
Disallow: /search
Disallow: /en/search
Disallow: /*?s=
Disallow: /*?q=

# --- English tree (temporary) -------------------------------------------------
# The English URLs are served, but their content is currently the Chinese
# fallback while the CMS is being populated — the English translations live in
# Strapi and are authored there. Each English page is already emitted with
# `noindex,follow`, and the sitemap omits the English tree, so this block is
# belt-and-braces: it stops crawlers fetching hundreds of URLs that would only
# be discarded as duplicates.
#
# REMOVE THIS BLOCK once the CMS is connected and English content is published.
# See `isUntranslatedFallback()` in src/lib/cms.ts and strapi/README.md.
Disallow: /en/

# --- AI / answer engines ------------------------------------------------------
# We are explicitly open to AI crawlers. Our content is factual and we want
# assistants to be able to answer questions about our products accurately.
# /llms.txt is the curated, machine-readable summary we prefer they start from.
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Bytespider
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: CCBot
Allow: /

# --- Crawl etiquette ----------------------------------------------------------
User-agent: *
Crawl-delay: 1

# --- Discovery ----------------------------------------------------------------
Sitemap: https://www.changxianchem.com/sitemap-index.xml
Sitemap: https://www.changxianchem.com/rss.xml
Sitemap: https://www.changxianchem.com/en/rss.xml

# --- Machine-readable site summary --------------------------------------------
# See: https://llmstxt.org/
# llms.txt is served at https://www.changxianchem.com/llms.txt