# As a condition of accessing this website, you agree to abide by the following
# content signals:

# (a)  If a Content-Signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a Content-Signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a Content-Signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via Content-Signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.
# use:      how AI systems may consume the content (immediate, reference, or full).

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

# BEGIN Cloudflare Managed content

User-agent: *
Content-Signal: search=yes,ai-train=no,use=reference
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# ============================================================
# RakitWeb — robots.txt
# https://rakitweb.site
# ============================================================

# ── Default: izinkan search engine utama ────────────────────
User-agent: *
Allow: /
Disallow: /login
Disallow: /signup
Disallow: /api/
Disallow: /_nuxt/
Disallow: /cdn-cgi/
Crawl-delay: 10

# ── Google (prioritas utama) ────────────────────────────────
User-agent: Googlebot
Allow: /
Allow: /docs/
Allow: /blog/
Allow: /pricing
Allow: /team
Allow: /changelog
Crawl-delay: 2

User-agent: Googlebot-Image
Allow: /

User-agent: AdsBot-Google
Allow: /

User-agent: Google-InspectionTool
Allow: /

# ── Bing ────────────────────────────────────────────────────
User-agent: Bingbot
Allow: /
Crawl-delay: 5

User-agent: msnbot
Allow: /
Crawl-delay: 5

# ── Baidu ───────────────────────────────────────────────────
User-agent: Baiduspider
Allow: /
Crawl-delay: 10

# ── DuckDuckGo ──────────────────────────────────────────────
User-agent: DuckDuckBot
Allow: /

# ── Yahoo ───────────────────────────────────────────────────
User-agent: Slurp
Allow: /
Crawl-delay: 10

# ── Web Archive ─────────────────────────────────────────────
User-agent: ia_archiver
Allow: /
Crawl-delay: 30

# ── Social Media (hanya OG preview, bukan scraper) ──────────
User-agent: Twitterbot
Allow: /
Crawl-delay: 30

User-agent: facebookexternalhit
Allow: /
Crawl-delay: 30

User-agent: LinkedInBot
Allow: /
Crawl-delay: 30

User-agent: WhatsApp
Allow: /

User-agent: TelegramBot
Allow: /

# ── Apple ───────────────────────────────────────────────────
User-agent: Applebot
Allow: /
Crawl-delay: 10

# ================================================================
# AI CRAWLERS — DIBLOKIR TOTAL
# Alasan: hammering edge requests, tidak ada nilai SEO,
#         hanya digunakan untuk training dataset AI model besar.
# ================================================================

# OpenAI / ChatGPT
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

# Anthropic / Claude
User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

# Common Crawl (sumber utama dataset training LLM)
User-agent: CCBot
Disallow: /

# ByteDance / TikTok
User-agent: Bytespider
Disallow: /

# DeepSeek
User-agent: DeepSeek
Disallow: /

User-agent: DeepSeekBot
Disallow: /

# Perplexity
User-agent: PerplexityBot
Disallow: /

# You.com
User-agent: YouBot
Disallow: /

# Cohere
User-agent: cohere-ai
Disallow: /

# Meta AI
User-agent: FacebookBot
Disallow: /

# Huawei
User-agent: PetalBot
Disallow: /

# AI2 / Semantic Scholar
User-agent: Semanticscholar
Disallow: /

# Diffbot (AI content extraction)
User-agent: Diffbot
Disallow: /

# img2dataset (dataset scraper)
User-agent: img2dataset
Disallow: /

# ── Blokir SEO scrapers komersial ───────────────────────────
User-agent: SemrushBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

# ── Blokir tech-detection bots ──────────────────────────────
User-agent: Wappalyzer
Disallow: /

User-agent: BuiltWith
Disallow: /

User-agent: WhatCMS
Disallow: /

User-agent: SimilarTech
Disallow: /

User-agent: Netcraft
Disallow: /

User-agent: W3Techs
Disallow: /

User-agent: TechnographyScraper
Disallow: /

# ── Sitemap ──────────────────────────────────────────────────
Sitemap: https://rakitweb.site/sitemap.xml
Sitemap: https://rakitweb.site/sitemap-blog.xml