Infrastructure

# Kompas.com content is made available for your personal, non-commercial
# use subject to our Terms of Service here:
# https://inside.kompas.com/term-of-use.
# 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 Cyber Media.  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.
# Contact https://inside.kompas.com/about-us#meet for assistance.

# ===== GOOGLE & SEARCH BOTS =====
User-agent: *
Disallow: /search/
Disallow: /komentar/
Disallow: /copy/
Disallow: /*?jxrecoid=*
Disallow: /*?utm_source=*

# ===== X Image Crawl =====
User-agent: Twitterbot
Allow: /

User-agent: Twitterbot/1.0
Allow: /

User-agent: Xbot
Allow: /

User-agent: X-Twitter-Image-Crawler
Allow: /

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

# ---------------------------------------------
# AI TRAINING BOTS Block All
# ---------------------------------------------
User-agent: Amazonbot
User-agent: GPTBot
User-agent: OpenAI
User-agent: ChatGPT-User
User-agent: CCBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-Agent: PerplexityBot
User-agent: Applebot-Extended
User-agent: AudigentAdBot
User-agent: AwarioRssBot
User-agent: AwarioSmartBot
User-agent: BLEXBot
User-agent: Bytespider
User-agent: ClaudeBot
User-agent: cohere-ai
User-agent: DataForSeoBot
User-agent: Diffbot
User-agent: DuckAssistBot
User-agent: EchoboxBot
User-agent: FacebookBot
User-agent: FriendlyCrawler
User-agent: ImagesiftBot
User-agent: Jetslide
User-agent: magpie-crawler
User-agent: Meta-ExternalAgent
User-agent: meta-externalagent
User-agent: Meta-ExternalFetcher
User-agent: meta-externalfetcher
User-agent: Meta-WebIndexer
User-agent: MistralAI-User
User-agent: MyCentralAIScraperBot
User-agent: NewsNow
User-agent: news-please
User-agent: OAI-SearchBot
User-agent: omgili
User-agent: omgilibot
User-agent: peer39_crawler
User-agent: peer39_crawler/1.0
User-agent: Poseidon Research Crawler
User-agent: quillbot.com
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: YouBot
User-agent: newspaper
User-agent: Perplexity-User
User-agent: docomo
User-agent: yisouspider
User-agent: trendictionbot
User-agent: tin_eye
User-agent: metaexternalagent
User-agent: chatgpt_user
User-agent: meta-externalagent
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: ias-va
User-agent: ias-or
User-agent: ias-ir
User-agent: ias-jp
User-agent: ias-sg
User-agent: ias-au
User-agent: ias_crawler
User-agent: admantx
User-agent: Webz.io
User-agent: ICC-Crawler
User-agent: you.com.
User-agent: ChatGPT’s agent Operator.
User-agent: Bing’s Copilot chat.
User-agent: Grok.

# Block Baidu spiders
User-agent: Baiduspider
User-agent: baiduspider
User-agent: Baiduspider-image
User-agent: Baiduspider-video
User-agent: Baiduspider 
Disallow: /