# Managed by Prosomo. Updated 2026-08-27.
# Real search engines (Googlebot, Bingbot, etc.) keep full access via the
# default block. Live AI-search / user-fetch crawlers (ChatGPT Search,
# Perplexity, Claude) are allowed with the SAME path restrictions as regular
# search engines, so the site can appear in AI-powered search results.
# AI training-only scrapers and aggressive SEO crawlers are disallowed.

# --- AI search / user-fetch crawlers — ALLOWED (same limits as default) ---
# These serve live answers to users; they are not bulk training crawlers.
# OAI-SearchBot   = ChatGPT Search index
# ChatGPT-User    = ChatGPT fetching a page for a user
# Claude-SearchBot= Claude search index
# Claude-User     = Claude fetching a page for a user
# PerplexityBot   = Perplexity search index
# Perplexity-User = Perplexity fetching a page for a user
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /xmlrpc.php
Disallow: /?s=
Disallow: /search/
Disallow: /wp-content/uploads/cfdb7_uploads/
Allow: /wp-admin/admin-ajax.php

# --- AI training-only scrapers — DISALLOWED ---
# ClaudeBot and GPTBot are the training crawlers (unlike the search/user
# agents above). Claude-Web and anthropic-ai are legacy Anthropic names,
# kept blocked for completeness.
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: anthropic-ai
User-agent: CCBot
User-agent: Bytespider
User-agent: ByteDance
User-agent: Amazonbot
User-agent: Applebot-Extended
User-agent: Google-Extended
User-agent: cohere-ai
User-agent: Diffbot
User-agent: Omgilibot
User-agent: Omgili
User-agent: FacebookBot
User-agent: meta-externalagent
Disallow: /

# --- SEO / backlink crawlers (heavy + low value) ---
User-agent: AhrefsBot
User-agent: SemrushBot
User-agent: SemrushBot-SA
User-agent: MJ12bot
User-agent: DotBot
User-agent: BLEXBot
User-agent: DataForSeoBot
User-agent: SERankingBacklinksBot
User-agent: Barkrowler
User-agent: SiteAuditBot
Disallow: /

# --- Other crawlers seen generating heavy load on this site ---
User-agent: IbouBot
User-agent: PetalBot
User-agent: YandexBot
Disallow: /

# --- Default for everyone else (Googlebot, Bingbot, etc.) ---
User-agent: *
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /xmlrpc.php
Disallow: /?s=
Disallow: /search/
Disallow: /wp-content/uploads/cfdb7_uploads/
Allow: /wp-admin/admin-ajax.php

Sitemap: https://rydelroofing.ca/sitemap.xml