# 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.

# 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
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# ═══════════════════════════════════════════════════════════════
# AI Search Engine Crawlers - Allow for GEO
# Generative Engine Optimization - 允許 AI 搜索引擎爬蟲索引
# 更新日期：2026-02-05
# ═══════════════════════════════════════════════════════════════

# OpenAI Crawlers (ChatGPT, SearchGPT)
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Anthropic Claude Crawlers
User-agent: ClaudeBot
Allow: /

User-agent: claude-web
Allow: /

# Perplexity AI Crawler
User-agent: PerplexityBot
Allow: /

# Google AI (Gemini, AI Overview)
User-agent: Google-Extended
Allow: /

# Amazon AI (Alexa, Amazon Q)
User-agent: Amazonbot
Allow: /

# Microsoft Copilot
User-agent: Bingbot
Allow: /

# Apple Intelligence
User-agent: Applebot
Allow: /

# Meta AI
User-agent: Meta-ExternalAgent
Allow: /

# ═══════════════════════════════════════════════════════════════
# General Crawler Rules
# ═══════════════════════════════════════════════════════════════

User-agent: *

# Block admin and login
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-login.php

# Block search results
Disallow: /?s=
Disallow: /search/

# Block feeds
Disallow: /*/feed
Disallow: /*/feed/
Disallow: /feed/
Disallow: /comments/feed/

# Block comment reply links
Disallow: /*?replytocom=

# Block tag archives
Disallow: /archives/tag/
Disallow: /en/archives/tag/
Disallow: /zh-cn/archives/tag/

# Block low-SEO-value paths
# Block old blog legacy paths (2026-02-09)
Disallow: /index.php/
Disallow: /2015/
Disallow: /2016/
Disallow: /2017/
Disallow: /2018/
Disallow: /2019/
Disallow: /archives/64/
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /archives/author/
Disallow: /archives/category/*/page/
Disallow: /zh-cn/archives/category/*/page/
Disallow: /en/archives/category/*/page/
Disallow: /*?fbclid=
Disallow: /*?br=

# ═══════════════════════════════════════════════════════════════
# Sitemap
# ═══════════════════════════════════════════════════════════════

Sitemap: https://dustingmat.com/sitemap_index.xml