# Data Compliance China — robots.txt
# DCC is open to crawling. AI-friendly surfaces are explicitly
# advertised below; per-page markdown sources are at
# /posts/<slug>.md and /laws/<slug>.md.

User-agent: *
Allow: /

User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Bytespider
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Diffbot
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: YouBot
Allow: /

User-agent: Cohere-AI
Allow: /

User-agent: cohere-training-data-crawler
Allow: /

# AI-friendly surfaces:
#   https://datacompliancechina.com/llms.txt          — curated index for LLMs
#   https://datacompliancechina.com/llms-full.txt     — full corpus as plain markdown
#   https://datacompliancechina.com/manifest.json     — structured catalog
#   https://datacompliancechina.com/glossary.json     — bilingual glossary as JSON
#   https://datacompliancechina.com/posts/<slug>.md   — raw markdown for any brief
#   https://datacompliancechina.com/laws/<slug>.md    — raw markdown for any law
#   https://datacompliancechina.com/rss.xml           — RSS feed

Sitemap: https://datacompliancechina.com/sitemap-index.xml