# Kompas.id content is made available for your personal, non-commercial
# use subject to our Terms of Service here:
# https://www.kompas.id/syarat-dan-ketentuan
# Use of any device, tool, or process designed to data mine or scrape the content
# using automated means is prohibited without prior written permission from
# PT. Kompas Media Nusantara.  Prohibited uses include but are not limited to:
# (1) text and data mining activities;
# (2) the development of any software, machine learning, artificial intelligence (AI),
# and/or large language models (LLMs);
# (3) creating or providing archived or cached data sets containing our content to others; and/or
# (4) any commercial purposes.


# ========================
# General Search Engine Rules
# ========================

User-agent: *
Disallow: */search
Disallow: *?open_from=
 
# ========================
# Allow Social Media Previews
# ========================

User-agent: Twitterbot
Allow: /
User-agent: FacebookBot
Allow: /
User-agent: LinkedInBot
Allow: /
User-agent: WhatsApp
Allow: /
User-agent: Slackbot
Allow: /
User-agent: TelegramBot
Allow: /
 
# ========================
# Block AI Bots (Training/Indexing)
# ========================

User-agent: OpenAI
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: CCBot

Disallow: /
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: claude-user
User-agent: ClaudeBot
Disallow: /
 
User-agent: PerplexityBot
Disallow: /
User-agent: cohere-ai
Disallow: /
 
User-agent: DuckAssistBot
Disallow: /
 
User-agent: quillbot.com
Disallow: /
 
User-agent: YouBot
Disallow: /
 
User-agent: Amazonbot
Disallow: /
 
User-agent: Applebot-Extended
Disallow: /
 
User-agent: AliyunSecBot
Disallow: /
 
User-agent: Meta-ExternalAgent
User-agent: meta-externalagent
User-agent: Meta-ExternalFetcher
User-agent: meta-externalfetcher
Disallow: /
 
# ========================
# Block Scrapers and Other AI-Adjacent Bots
# ========================

User-agent: AwarioRssBot
User-agent: AwarioSmartBot
User-agent: AudigentAdBot
User-agent: BLEXBot
User-agent: Bytespider
User-agent: DataForSeoBot
User-agent: Diffbot
User-agent: EchoboxBot
User-agent: FriendlyCrawler
User-agent: ImagesiftBot
User-agent: Jetslide
User-agent: magpie-crawler
User-agent: NewsNow
User-agent: news-please
User-agent: omgili
User-agent: omgilibot
User-agent: peer39_crawler
User-agent: peer39_crawler/1.0
User-agent: Poseidon Research Crawler
User-agent: Quora-Bot
User-agent: Scrapy
User-agent: SeekrBot
User-agent: SeznamHomepageCrawler
User-agent: TaraGroup Intelligent Bot
User-agent: Timpibot
User-agent: TurnitinBot
User-agent: ViennaTinyBot
User-agent: MyCentralAIScraperBot
User-agent: OAI-SearchBot
Disallow: /
 
# ========================
# Sitemap for SEO
# ========================

Sitemap: https://www.kompas.id/sitemap.xml