# robots.txt for onda.me
# Generated for SEO & LLM optimization
# Last updated: 2026-08-19

# Default rule: Allow all crawlers
User-agent: *
Allow: /
Crawl-delay: 0
# Content Signals (draft-romm-aipref-contentsignals / contentsignals.org)
# ai-train=no  → AI 모델 학습 데이터 사용 금지 (콘텐츠 자산 보호)
# search=yes   → 검색 엔진 인덱싱 허용 (Google/Bing/Naver SEO)
# ai-input=yes → AI 답변 생성 시 컨텍스트 인용 허용 (Perplexity, ChatGPT Search 등 노출)
Content-Signal: ai-train=no, search=yes, ai-input=yes

# Block unnecessary paths for all crawlers
Disallow: /api/
Disallow: /_next/
Disallow: /admin/
Disallow: /private/
Disallow: /debug/
Disallow: /test/
Disallow: *.json$
Disallow: *.xml$

# Allow important files
Allow: /sitemap.xml
Allow: /sitemap-*.xml
Allow: /*.json-ld
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /humans.txt
# RSS feeds & AI discovery manifests (override the *.xml$ / *.json$ Disallow above)
Allow: /rss.xml
Allow: /rss-*.xml
Allow: /.well-known/*.json

# Search Engine Bots
User-agent: Googlebot
Allow: /
Crawl-delay: 0

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

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

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

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

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

# AI/LLM Crawlers - Explicitly allow for better AI understanding
User-agent: GPTBot
Allow: /
Crawl-delay: 0

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

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

User-agent: anthropic-ai
Allow: /
Crawl-delay: 0

User-agent: Claude-Web
Allow: /
Crawl-delay: 0

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

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

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

# Social Media Bots
User-agent: facebookexternalhit
Allow: /
Crawl-delay: 0

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

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

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

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

# Block bad bots
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: MJ12bot
Disallow: /

# Sitemap locations
# sitemap.xml   — 정적 페이지 전체 (ko/en/ja/zh-Hans/zh-Hant, app/sitemap.ts 가 라우트 스캔으로 생성)
# sitemap-blog.xml — 블로그·뉴스·채용 포스트 (Supabase 에서 빌드 시 생성)
Sitemap: https://onda.me/sitemap.xml
Sitemap: https://onda.me/sitemap-blog.xml

# Cross-promotion — ONDA Plus 미니사이트 (별도 운영, onda.me/showcase 가 cross-link 가이드)
Sitemap: https://site.onda.me/sitemap.xml
Sitemap: https://booking.pension.onda.me/sitemap.xml

# RSS feeds (per locale)
# https://onda.me/rss.xml
# https://onda.me/rss-ko.xml
# https://onda.me/rss-en.xml
# https://onda.me/rss-ja.xml
# https://onda.me/rss-zh-Hans.xml
# https://onda.me/rss-zh-Hant.xml

# Additional directives
Host: onda.me

# LLM.txt location (llmstxt.org standard)
LLMS-Txt: https://onda.me/llms.txt