# AdvantageBizMarketing — robots.txt
# Maximize discovery + crawl budget for both classical search engines and AI assistants.
# Last updated: 2026-05-25

# === Default policy ===
User-agent: *
Disallow: /wp/wp-admin/
Disallow: /wp/wp-login.php
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /xmlrpc.php
Disallow: /wp-json/wp/v2/users
Disallow: /?author=
Disallow: /search/
Disallow: /?s=
Disallow: /trackback/
Disallow: /*?replytocom=
Allow: /wp/wp-admin/admin-ajax.php
Allow: /wp-admin/admin-ajax.php
Crawl-delay: 0

# === Google ===
User-agent: Googlebot
Allow: /
Disallow: /wp/wp-admin/
Disallow: /wp-admin/

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-News
Allow: /

# === Google AI / Search Generative ===
User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

# === Bing / Microsoft ===
User-agent: Bingbot
Allow: /
Disallow: /wp/wp-admin/

User-agent: msnbot
Allow: /

# === DuckDuckGo ===
User-agent: DuckDuckBot
Allow: /

# === Yandex ===
User-agent: Yandex
Allow: /

# === OpenAI (ChatGPT) ===
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# === Anthropic (Claude) ===
User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: Claude-SearchBot
Allow: /

# === Perplexity ===
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# === Apple ===
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# === Other AI / Research crawlers (allowed because we want citations) ===
User-agent: CCBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: cohere-training-data-crawler
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: YouBot
Allow: /

User-agent: Diffbot
Allow: /

User-agent: TimpiBot
Allow: /

User-agent: ImagesiftBot
Allow: /

User-agent: Bytespider
Allow: /

User-agent: PetalBot
Allow: /

User-agent: Mojeek
Allow: /

User-agent: Kagibot
Allow: /

User-agent: Brightbot
Allow: /

# === SEO research crawlers — limit but don't block ===
# === Scrapy / generic bots ===
User-agent: Scrapy
Disallow: /

# === Sitemaps ===
Sitemap: https://advantagebizmarketing.com/sitemap_index.xml
Sitemap: https://advantagebizmarketing.com/post-sitemap.xml
Sitemap: https://advantagebizmarketing.com/page-sitemap.xml
Sitemap: https://advantagebizmarketing.com/category-sitemap.xml

# LLM directives
LLM-Content-License: cc-by-nc-4.0
LLM-Discovery: https://advantagebizmarketing.com/llms.txt

# ===== SEO tools (explicit allow — needed for site audits + backlink intel) =====
# Ahrefs (Site Audit + Backlinks + Rank Tracker)
User-agent: AhrefsBot
Allow: /

User-agent: AhrefsSiteAudit
Allow: /

# Semrush (Site Audit + Backlink Analytics + Position Tracking)
User-agent: SemrushBot
Allow: /

User-agent: SemrushBot-SA
Allow: /

User-agent: SemrushBot-BA
Allow: /

User-agent: SemrushBot-SI
Allow: /

User-agent: SiteAuditBot
Allow: /

# Majestic
User-agent: MJ12bot
Allow: /

# Moz (Link Explorer + Pro Site Audit)
User-agent: rogerbot
Allow: /

User-agent: DotBot
Allow: /

User-agent: dotbot
Allow: /

# DataForSEO (powers many SEO platforms)
User-agent: DataForSeoBot
Allow: /

# Screaming Frog
User-agent: ScreamingFrogSEOSpider
Allow: /

# Sitebulb
User-agent: SitebulbBot
Allow: /

# BacklinkChecker
User-agent: BLEXBot
Allow: /

# Pinterest (social discovery)
User-agent: Pinterestbot
Allow: /