Search

Matched domain: html.design
`robots.txt`

# html.design - robots.txt
# Maintained from: code/static-root/build_robots.py
# Privacy block is identical across all named user-agents because
# the robots.txt spec does not inherit rules from `*`.

Sitemap: https://html.design/sitemap.xml
Sitemap: https://html.design/post-sitemap.xml
Sitemap: https://html.design/page-sitemap.xml
Sitemap: https://html.design/blog-sitemap.xml

# -------------------------------------------------------------
# Catch-all rules for bots not named below
# -------------------------------------------------------------
User-agent: *
Allow: /
Allow: /ai-website-editor$
Disallow: /admin/
Disallow: /adminjack/
Disallow: /api/
Disallow: /storage/
Disallow: /preview?
Disallow: /client/
Crawl-delay: 1

# -------------------------------------------------------------
# AhrefsBot - SEO crawler
# -------------------------------------------------------------
User-agent: AhrefsBot
Allow: /
Allow: /ai-website-editor$
Crawl-delay: 10
Disallow: /admin/
Disallow: /adminjack/
Disallow: /api/
Disallow: /storage/
Disallow: /preview?
Disallow: /client/

# -------------------------------------------------------------
# SemrushBot - SEO crawler
# -------------------------------------------------------------
User-agent: SemrushBot
Allow: /
Allow: /ai-website-editor$
Crawl-delay: 10
Disallow: /admin/
Disallow: /adminjack/
Disallow: /api/
Disallow: /storage/
Disallow: /preview?
Disallow: /client/

# -------------------------------------------------------------
# MJ12bot - SEO crawler (Majestic)
# -------------------------------------------------------------
User-agent: MJ12bot
Allow: /
Allow: /ai-website-editor$
Crawl-delay: 30
Disallow: /admin/
Disallow: /adminjack/
Disallow: /api/
Disallow: /storage/
Disallow: /preview?
Disallow: /client/

# -------------------------------------------------------------
# GPTBot - OpenAI training crawler
# -------------------------------------------------------------
User-agent: GPTBot
Allow: /
Allow: /ai-website-editor$
Disallow: /admin/
Disallow: /adminjack/
Disallow: /api/
Disallow: /storage/
Disallow: /preview?
Disallow: /client/

# -------------------------------------------------------------
# ChatGPT-User - ChatGPT in-chat browsing
# -------------------------------------------------------------
User-agent: ChatGPT-User
Allow: /
Allow: /ai-website-editor$
Disallow: /admin/
Disallow: /adminjack/
Disallow: /api/
Disallow: /storage/
Disallow: /preview?
Disallow: /client/

# -------------------------------------------------------------
# OAI-SearchBot - ChatGPT web search
# -------------------------------------------------------------
User-agent: OAI-SearchBot
Allow: /
Allow: /ai-website-editor$
Disallow: /admin/
Disallow: /adminjack/
Disallow: /api/
Disallow: /storage/
Disallow: /preview?
Disallow: /client/

# -------------------------------------------------------------
# Google-Extended - Google Gemini training (separate from Googlebot search)
# -------------------------------------------------------------
User-agent: Google-Extended
Allow: /
Allow: /ai-website-editor$
Disallow: /admin/
Disallow: /adminjack/
Disallow: /api/
Disallow: /storage/
Disallow: /preview?
Disallow: /client/

# -------------------------------------------------------------
# PerplexityBot - Perplexity AI search
# -------------------------------------------------------------
User-agent: PerplexityBot
Allow: /
Allow: /ai-website-editor$
Disallow: /admin/
Disallow: /adminjack/
Disallow: /api/
Disallow: /storage/
Disallow: /preview?
Disallow: /client/

# -------------------------------------------------------------
# ClaudeBot - Anthropic Claude web features
# -------------------------------------------------------------
User-agent: ClaudeBot
Allow: /
Allow: /ai-website-editor$
Disallow: /admin/
Disallow: /adminjack/
Disallow: /api/
Disallow: /storage/
Disallow: /preview?
Disallow: /client/

# -------------------------------------------------------------
# anthropic-ai - Anthropic training crawler
# -------------------------------------------------------------
User-agent: anthropic-ai
Allow: /
Allow: /ai-website-editor$
Disallow: /admin/
Disallow: /adminjack/
Disallow: /api/
Disallow: /storage/
Disallow: /preview?
Disallow: /client/

# -------------------------------------------------------------
# Applebot-Extended - Apple Intelligence training
# -------------------------------------------------------------
User-agent: Applebot-Extended
Allow: /
Allow: /ai-website-editor$
Disallow: /admin/
Disallow: /adminjack/
Disallow: /api/
Disallow: /storage/
Disallow: /preview?
Disallow: /client/

# -------------------------------------------------------------
# Amazonbot - Amazon Alexa / Rufus / Amazon AI
# -------------------------------------------------------------
User-agent: Amazonbot
Allow: /
Allow: /ai-website-editor$
Disallow: /admin/
Disallow: /adminjack/
Disallow: /api/
Disallow: /storage/
Disallow: /preview?
Disallow: /client/

# -------------------------------------------------------------
# Meta-ExternalAgent - Meta AI training
# -------------------------------------------------------------
User-agent: Meta-ExternalAgent
Allow: /
Allow: /ai-website-editor$
Disallow: /admin/
Disallow: /adminjack/
Disallow: /api/
Disallow: /storage/
Disallow: /preview?
Disallow: /client/

# -------------------------------------------------------------
# Bytespider - ByteDance / TikTok AI
# -------------------------------------------------------------
User-agent: Bytespider
Allow: /
Allow: /ai-website-editor$
Disallow: /admin/
Disallow: /adminjack/
Disallow: /api/
Disallow: /storage/
Disallow: /preview?
Disallow: /client/

# -------------------------------------------------------------
# CCBot - Common Crawl (training corpus for many open-source LLMs)
# -------------------------------------------------------------
User-agent: CCBot
Allow: /
Allow: /ai-website-editor$
Disallow: /admin/
Disallow: /adminjack/
Disallow: /api/
Disallow: /storage/
Disallow: /preview?
Disallow: /client/

# -------------------------------------------------------------
# Timpibot - BLOCKED - Decentralized-search / AI-dataset crawler - 14 req/s abuse observed 2026-05-19
# -------------------------------------------------------------
User-agent: Timpibot
Disallow: /
Look up this url in the url tool https://html.design/.well-known/acme-challenge: 404 text/html
https://html.design/.well-known/csvm: 404 text/html; charset=UTF-8
https://html.design/.well-known/nostr.json: 404 text/html; charset=UTF-8
https://html.design/.well-known/security.txt: 404 text/html; charset=UTF-8
https://html.design/.well-known/traffic-advice: 404 text/html; charset=UTF-8