# robots.txt for morganlegalny.com — Morgan Legal Group, P.C.
# v3 (2026-08-21): carried over from the WordPress site during the React rebuild.
# The AI-crawler allowances and scraper blocks below are deliberate — do not let
# a framework default overwrite this file.
# Goal: maximize visibility in Claude / ChatGPT / Perplexity / Microsoft Copilot

# ============================================================================
# AI crawlers — EXPLICITLY ALLOWED
# ============================================================================
# OpenAI / ChatGPT
User-agent: GPTBot
Allow: /
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

User-agent: OAI-SearchBot
Allow: /
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

User-agent: ChatGPT-User
Allow: /

# Anthropic / Claude
User-agent: Anthropic-ai
Allow: /
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

User-agent: anthropic-ai
Allow: /
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

User-agent: Claude-Web
Allow: /

User-agent: ClaudeBot
Allow: /
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

# Perplexity
User-agent: PerplexityBot
Allow: /
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

User-agent: Perplexity-User
Allow: /

# Microsoft Bing / Copilot (Copilot is grounded on Bing index)
User-agent: Bingbot
Allow: /
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

User-agent: BingPreview
Allow: /

# Google Gemini / Bard training
User-agent: Google-Extended
Allow: /
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

# Apple Intelligence
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# DuckDuckGo AI assist
User-agent: DuckAssistBot
Allow: /

# Mistral
User-agent: MistralAI-User
Allow: /

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

User-agent: FacebookBot
Allow: /

# ============================================================================
# Abusive / low-value scrapers — BLOCKED
# ============================================================================
User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: AspiegelBot
Disallow: /

User-agent: SeznamBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

# ============================================================================
# Default — all other crawlers
# ============================================================================
User-agent: *
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-content/plugins/
Disallow: /wp-includes/
Disallow: /xmlrpc.php
Disallow: /readme.html
Disallow: /license.txt
Disallow: /wp-config.php
Disallow: /?s=
Disallow: /search/
Disallow: /*?replytocom

# ============================================================================
# Sitemaps + LLM citation file
# ============================================================================
# sitemap.xml is a sitemap INDEX and it is now SELF-SUFFICIENT: it lists only
# files we generate ourselves — sitemap-pages.xml plus sitemap-articles-1..6.xml,
# covering all 5,482 indexable static pages. It no longer points at Yoast's
# post-sitemap*.xml, which will disappear together with WordPress.
# 05.09.2026 — движок снят, и вместе с ним снята строка Yoast-индекса.
# sitemap_index.xml с этого дня отдаёт 404, а Google был на него направлен: строка
# пережила снятие движка на несколько дней и превратилась в ошибку в Search Console.
# Второе условие той же заметки выполнено раньше: /blog/ — наша страница, отвечает 200.
# Отставшую строку теперь ловит verify-deployed-sitemap.mjs: каждая Sitemap: из этого
# файла обязана отдавать 200, иначе проверка краснеет.
Sitemap: https://www.morganlegalny.com/sitemap.xml

# LLM citation file (authoritative facts for AI engines):
# https://www.morganlegalny.com/llms.txt