# ====================================================
# AI Data Collection Policy
#
# Crawling or use of content from this site for
# AI training, LLM development, or machine learning
# purposes is prohibited without prior written consent.
#
# Contact: https://www.khan.co.kr/help/help_digital.html
# ====================================================

# Block AI Learning Bots & Scrapers
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: anthropic-ai
User-agent: Google-Extended
User-agent: GoogleOther
User-agent: GoogleOther-Image
User-agent: Bytespider
User-agent: TikTokSpider
User-agent: Applebot-Extended
User-agent: CCBot
User-agent: DeepSeekBot
User-agent: cohere-ai
User-agent: meta-externalagent
User-agent: Diffbot
User-agent: Omgilibot
User-agent: Omgili
User-agent: PetalBot
User-agent: PanguBot
User-agent: WRTNBot
User-agent: YouBot
User-agent: FriendlyCrawler
User-agent: ICC-Crawler
User-agent: ImagesiftBot
User-agent: img2dataset
User-agent: Scrapy
User-agent: 01-AI-Bot
User-agent: ChatGLM-Spider
User-agent: TongyiBot
User-agent: YiyanBot
Disallow: /

# Block SEO & Marketing Bots
User-agent: AhrefsBot
User-agent: SemrushBot
User-agent: dotbot
User-agent: DataForSeoBot
Disallow: /

# Allow AI Search Bots - block non-public pages only
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: Operator
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Claude-SearchBot
User-agent: Gemini-Deep-Research
User-agent: GoogleAgent-URLContext
User-agent: MistralAI-User
User-agent: Kimi-User
User-agent: Manus-User
Disallow: /login
Disallow: /SecListData.html
Disallow: /print.html
Disallow: /article/201709021732001
Disallow: /national/national-general/article/201709021732001
Disallow: /article/201609241422011
Disallow: /national/national-general/article/201609241422011

# Default Rules for General Search Engines
User-agent: *
Disallow: /login
Disallow: /SecListData.html
Disallow: /article/201709021732001
Disallow: /national/national-general/article/201709021732001
Disallow: /print.html?art_id=201709021732001&media=khan&type=basic
Disallow: /article/201609241422011
Disallow: /national/national-general/article/201609241422011
Disallow: /print.html?art_id=201609241422011&media=khan&type=basic

# Sitemap and RSS Feed Locations
Sitemap: https://www.khan.co.kr/sitemap.xml
Sitemap: https://www.khan.co.kr/sitemap/latest-articles.xml
Sitemap: https://www.khan.co.kr/sitemap/daily-images.xml
Sitemap: https://www.khan.co.kr/sitemap/daily-videos.xml
Sitemap: https://www.khan.co.kr/sitemap/authors.xml
Sitemap: https://www.khan.co.kr/rss/rssdata/english_news.xml
Sitemap: https://www.khan.co.kr/rss/rssdata/newsletter_news.xml
Sitemap: https://www.khan.co.kr/rss/rssdata/interactive_news.xml
Sitemap: https://www.khan.co.kr/rss/rssdata/video_news.xml

#DaumWebMasterTool:35bc55071cd98ae09fdf97e6c96768225c02c9f6ab5b8fe3c1118aefe5139d74:gbyst4GwRZz3X/sV/51MJQ==