# 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
# ----------------------------
# PhoenixFM robots.txt - Optimized for reducing bot load
# ----------------------------
# Block aggressive third-party SEO crawlers
User-agent: AhrefsBot
Disallow: /
User-agent: SemrushBot
Disallow: /
User-agent: MJ12bot
Disallow: /
User-agent: DotBot
Disallow: /
User-agent: BLEXBot
Disallow: /
# Block known media scrapers
User-agent: Yandex
Disallow: /
User-agent: Baiduspider
Disallow: /
# Allow main search engines
User-agent: Googlebot
Disallow:
User-agent: Bingbot
Disallow:
User-agent: Slurp
Disallow:
User-agent: DuckDuckBot
Disallow:
# ----------------------------
# Block AI crawlers
# ----------------------------
# OpenAI
User-agent: GPTBot
Disallow: /
# Anthropic
User-agent: ClaudeBot
Disallow: /
# Perplexity
User-agent: PerplexityBot
Disallow: /
# Copilot / Microsoft Bing Chat (optional — Bingbot still allowed above)
# This one is tricky because Bingbot powers normal search as well.
# If you want to be extra strict, uncomment the next 2 lines:
# User-agent: Bingbot
# Disallow: /
# Google AI crawler (experimental)
User-agent: Google-Extended
Disallow: /
# Common AI data scrapers
User-agent: FacebookBot
Disallow: /
User-agent: Applebot
Disallow: /
User-agent: CCBot
Disallow: /
User-agent: YouBot
Disallow: /
# ----------------------------
# General WordPress rules
# ----------------------------
User-agent: *
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/cache/
Disallow: /wp-content/uploads/wpcf7_captcha/
Allow: /wp-admin/admin-ajax.php
# ----------------------------
# Large media files - block bots from podcasts
# ----------------------------
User-agent: *
Disallow: /podcasts/
# ----------------------------
# Sitemap
# ----------------------------
Sitemap: https://www.phoenixfm.com/sitemap_index.xml
robots.txt