# =============================================================
# robots.txt — hmapr.com
# Last updated: 2026-07-30
#
# This file controls two things:
#   1. Traditional search engine crawling (Google, Bing, etc.)
#   2. AI crawler access (chatbots, answer engines, AI training bots)
#
# Review this file whenever:
#   - New site sections/paths are added
#   - Client changes their stance on AI training use of their content
#   - A new major AI crawler enters the market
# =============================================================

# -------------------------------------------------------------
# STANDARD CRAWLERS (Google, Bing, etc.)
# -------------------------------------------------------------
User-agent: *
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /?s=
Disallow: /search/
Allow: /wp-admin/admin-ajax.php
Crawl-delay: 10

# -------------------------------------------------------------
# AI SEARCH / ANSWER ENGINE CROWLERS — ALLOWED
# These bots power AI answer engines and chat assistants that can
# cite/link back to hmapr.com content (visibility, not just training).
# Recommended: keep these open if the goal is AI-driven visibility.
# -------------------------------------------------------------
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Bingbot
Allow: /

# -------------------------------------------------------------
# BULK AI-TRAINING / DATA-SCRAPING BOTS — BLOCKED
# These typically scrape content for model training with no
# direct citation/referral benefit back to the site.
# CLIENT DECISION NEEDED: confirm this stance before publishing.
# Remove/comment out any bot the client wants to allow instead.
# -------------------------------------------------------------
User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

# -------------------------------------------------------------
# REFERENCE FILES
# -------------------------------------------------------------
# LLM-readable site summary (site structure, key pages, team, case studies)
# See: https://hmapr.com/llms.txt

Sitemap: https://hmapr.com/sitemap_index.xml
Sitemap:https://hmapr.com/sitemap.xml