# =============================================================
# Lawmadi OS v60 — robots.txt
# https://lawmadi.com/robots.txt
# =============================================================

# --- Googlebot & Bingbot: Public pages only ---
# 순서 주의: Disallow 를 Allow 보다 **먼저** 둔다. Google·Bing 은 최장일치라 순서와
# 무관하나, 순서우선 파서(예: Python robotparser·일부 크롤러)는 'Allow: /' 가 앞서면
# 뒤따르는 Disallow 를 통째로 무시한다(2026-08-12 실측 — /ask·/api/ 가 허용으로 읽혔다).
User-agent: Googlebot
Disallow: /api/
Disallow: /ask
Disallow: /ask-stream
Disallow: /ask-expert
Disallow: /auth/
Disallow: /health
Disallow: /metrics
Disallow: /diagnostics
Disallow: /export-pdf
Disallow: /upload
Disallow: /analyze-document
Disallow: /feedback
Disallow: /suggest-questions
Disallow: /search
Disallow: /trending
Disallow: /plans
Disallow: /generate-document
Disallow: /document-types
Disallow: /dashboard
Disallow: /conversion
Disallow: /retention
Disallow: /cost-estimate
Disallow: /feedback-summary
Allow: /
Allow: /en
Allow: /about
Allow: /about-en
Allow: /leaders
Allow: /leaders-en
Allow: /leader-profile
Allow: /leader-profile-en
Allow: /clevel
Allow: /clevel-en
Allow: /architecture
Allow: /architecture-en
Allow: /exam-essays
Allow: /exam-search
Allow: /exam-search-index.json
Allow: /leader-exam
Allow: /daily
Allow: /strategy
Allow: /tech
Allow: /news
Allow: /bar
Allow: /precedent
Allow: /guide-wrongful-dismissal
Allow: /guide-deposit-return
Allow: /guide-fraud-complaint
Allow: /guide-traffic-accident
Allow: /guide-divorce-property
Allow: /guide-small-claims
Allow: /guide-inheritance
Allow: /guide-unpaid-wages
Allow: /guide-real-estate
Allow: /guide-debt-recovery
Allow: /guide-damages
Allow: /guide-workplace-bullying
Allow: /guide-dui
Allow: /guide-defamation
Allow: /guide-industrial-accident
Allow: /village-lawyer
Allow: /village-lawyer-en
Allow: /pricing
Allow: /pricing-en
Allow: /terms
Allow: /terms-en
Allow: /privacy
Allow: /privacy-en
Allow: /refund
Allow: /refund-en
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /sitemap.xml
Allow: /openapi.json

# 순서 주의: Disallow 를 Allow 보다 **먼저** 둔다. Google·Bing 은 최장일치라 순서와
# 무관하나, 순서우선 파서(예: Python robotparser·일부 크롤러)는 'Allow: /' 가 앞서면
# 뒤따르는 Disallow 를 통째로 무시한다(2026-08-12 실측 — /ask·/api/ 가 허용으로 읽혔다).
User-agent: Bingbot
Disallow: /api/
Disallow: /ask
Disallow: /ask-stream
Disallow: /ask-expert
Disallow: /auth/
Disallow: /health
Disallow: /metrics
Disallow: /diagnostics
Disallow: /export-pdf
Disallow: /upload
Disallow: /analyze-document
Disallow: /feedback
Disallow: /suggest-questions
Disallow: /search
Disallow: /trending
Disallow: /plans
Disallow: /generate-document
Disallow: /document-types
Disallow: /dashboard
Allow: /
Allow: /en
Allow: /about
Allow: /about-en
Allow: /leaders
Allow: /leaders-en
Allow: /architecture
Allow: /architecture-en
Allow: /village-lawyer
Allow: /village-lawyer-en
Allow: /pricing
Allow: /pricing-en
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /sitemap.xml

# --- AI / LLM Crawlers: Welcome ---
# Entry points: /llms.txt (overview) · /llms-full.txt (full technical spec)
#               /content-feed.json (today's verified legal content, full text, free)
# Every LLM crawler listed below is explicitly allowed to fetch both files, plus all
# public pages. Unlisted crawlers fall through to the 'User-agent: *' group at the
# bottom, which allows the same files — no LLM bot is blocked from /llms*.txt.
# Fetching and reading is permitted; the legal content itself stays proprietary
# (see 'AI Usage Policy' in /llms.txt — no training / fine-tuning / RAG ingestion).
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: ClaudeBot
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: Claude-Web
User-agent: anthropic-ai
User-agent: Google-Extended
User-agent: Google-CloudVertexBot
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: Amazonbot
User-agent: meta-externalagent
User-agent: meta-externalfetcher
User-agent: FacebookBot
User-agent: MistralAI-User
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: DuckAssistBot
User-agent: YouBot
User-agent: Bytespider
User-agent: PetalBot
User-agent: Diffbot
User-agent: AI2Bot
User-agent: Timpibot
User-agent: Webzio-Extended
User-agent: Omgilibot
User-agent: ImagesiftBot
User-agent: CCBot
Disallow: /api/
Disallow: /ask
Disallow: /ask-stream
Disallow: /ask-expert
Disallow: /auth/
Disallow: /health
Disallow: /export-pdf
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /content-feed.json
Allow: /sitemap.xml
Allow: /image-sitemap.xml
Allow: /feed.xml
Allow: /openapi.json

# --- Naver (Yeti) ---
# 순서 주의: Disallow 를 Allow 보다 **먼저** 둔다. Google·Bing 은 최장일치라 순서와
# 무관하나, 순서우선 파서(예: Python robotparser·일부 크롤러)는 'Allow: /' 가 앞서면
# 뒤따르는 Disallow 를 통째로 무시한다(2026-08-12 실측 — /ask·/api/ 가 허용으로 읽혔다).
User-agent: Yeti
Disallow: /api/
Disallow: /ask
Disallow: /ask-stream
Disallow: /ask-expert
Disallow: /auth/
Disallow: /health
Disallow: /export-pdf
Allow: /
Allow: /en
Allow: /about
Allow: /about-en
Allow: /leaders
Allow: /leaders-en
Allow: /leader-profile
Allow: /leader-profile-en
Allow: /exam-essays
Allow: /exam-search
Allow: /exam-search-index.json
Allow: /leader-exam
Allow: /daily
Allow: /strategy
Allow: /tech
Allow: /news
Allow: /bar
Allow: /precedent
Allow: /pricing
Allow: /pricing-en
Allow: /guide-wrongful-dismissal
Allow: /guide-deposit-return
Allow: /guide-fraud-complaint
Allow: /guide-traffic-accident
Allow: /guide-divorce-property
Allow: /guide-small-claims
Allow: /guide-inheritance
Allow: /guide-unpaid-wages
Allow: /guide-real-estate
Allow: /guide-debt-recovery
Allow: /guide-damages
Allow: /guide-workplace-bullying
Allow: /guide-dui
Allow: /guide-defamation
Allow: /guide-industrial-accident
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /sitemap.xml

# --- All other bots (includes any LLM crawler not named above) ---
User-agent: *
Disallow: /api/
Disallow: /ask
Disallow: /ask-stream
Disallow: /ask-expert
Disallow: /auth/
Disallow: /health
Disallow: /export-pdf
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /sitemap.xml
Allow: /feed.xml

# --- Discovery ---
Sitemap: https://lawmadi.com/sitemap.xml
Sitemap: https://lawmadi.com/image-sitemap.xml