# ======================================================
# robots.txt for Branch.io
# ======================================================

# Default policy
User-agent: *
Allow: /

# -----------------------------
# Explicit ALLOW for AI/LLM crawlers
# -----------------------------
User-agent: GPTBot
Allow: /

User-agent: CCBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Applebot-Extended
Allow: /

# -----------------------------
# Crawl hygiene (limit noisy URLs)
# -----------------------------
# Common tracking parameters
Disallow: /*utm_
Disallow: /*gclid=
Disallow: /*fbclid=
Disallow: /*msclkid=
Disallow: /*ref=

# Additional query params / WP patterns
Disallow: /*?currency=
Disallow: /*?page_id=
Disallow: /*?wvideo=
Disallow: /*?p=
Disallow: /*?amp

# WP endpoints - Security: Block REST API discovery
Disallow: /wp-json/

# Deep link/debug parameters that create infinite combinations
Disallow: /*&deeplink_path
Disallow: /*&branch

# Internal assets that don't need indexing
Disallow: /assets/
Disallow: /scripts/

# -----------------------------
# Security: Block sensitive paths
# -----------------------------
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/themes/*/assets/
Disallow: /*.php$
Disallow: /xmlrpc.php
Disallow: /wp-trackback.php
Disallow: /wp-cron.php
Disallow: /readme.html
Disallow: /license.txt

# Allow specific needed paths
Allow: /wp-admin/admin-ajax.php
Allow: /wp-content/uploads/

# -----------------------------
# Sitemaps (production)
# Yoast sitemap index links to all section sitemaps
# -----------------------------
Sitemap: https://www.branch.io/sitemap_index.xml