# ================================
# /robots.txt  — BeWell Grace Medical
# ================================
# Purpose: Allow full SEO crawling, limit server load, and block AI/data scrapers.

User-agent: *
Disallow: /wp-admin/
Disallow: /?s=
Disallow: /page/*/?s=
Disallow: /search/
Allow: /wp-admin/admin-ajax.php

# Sitemap (auto-managed by Slim SEO)
Sitemap: https://bewellgracemedical.com/sitemap.xml

# Public content is crawlable
Disallow: /?s=
Disallow: /page/*/?s=
Disallow: /search/
Allow: /

# Prevent indexing internal search results
Disallow: /?s=

# Moderate crawl rate for smaller bots (Google ignores Crawl-delay; Bing honors it)
Crawl-delay: 5

# Major search engines (allowed)
User-agent: Googlebot
Disallow: /?s=
Disallow: /page/*/?s=
Disallow: /search/
Allow: /

User-agent: Bingbot
Disallow: /?s=
Disallow: /page/*/?s=
Disallow: /search/
Allow: /
Crawl-delay: 3

# Block known AI/data scrapers & aggressive crawlers
User-agent: GPTBot
Disallow: /
User-agent: ChatGPT-User
Disallow: /
User-agent: CCBot
Disallow: /
User-agent: PerplexityBot
Disallow: /
User-agent: Claude-Web
Disallow: /
User-agent: Amazonbot
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: DataForSeoBot
Disallow: /
User-agent: omgili
Disallow: /
User-agent: Scrapy
Disallow: /
User-agent: MJ12bot
Disallow: /
User-agent: AhrefsBot
Disallow: /
User-agent: SemrushBot
Disallow: /

# Legal / compliance sections remain indexable via sitemap but are lower priority to crawl
User-agent: *
Disallow: /legal-privacy-compliance/
Disallow: /notice-of-availability/
Disallow: /web-and-mobile-privacy-policy/
Disallow: /notice-of-privacy-practices-2/
Disallow: /terms-of-service/
Disallow: /terms-and-conditions/
Disallow: /legal-disclaimer/
Disallow: /legal-notice-of-non-discrimination/
Disallow: /compliance-and-ethics-hotline/
Disallow: /accessibility-statement/
Disallow: /account-deletion-policy/
Disallow: /legal-privacy-practices-employee-information/
Disallow: /legal-privacy-practices-provider-information/
Disallow: /responsible-disclosure/
Disallow: /transparency-reporting/

# Notes:
# - Service and conversion pages are fully crawlable.
# - Legal pages still index via sitemap; this only reduces crawler frequency.
# - No action needed in Search Console; Google reads this file automatically.

Sitemap: https://bewellgracemedical.com/sitemap.xml