# robots.txt — HeadToHead.dk
# Purpose: keep public content fully crawlable, block only internal/duplicate/no-value URLs

User-agent: *

# --- Allow crawling by default (no blanket disallow) ---

# Block true internal/admin/debug endpoints
Disallow: /admin/
Disallow: /admin-*
Disallow: /simulation-*
Disallow: /restore-*
Disallow: /private/
Disallow: /preview/
Disallow: /draft/
Disallow: /debug/
Disallow: /tmp/
Disallow: /test/
Disallow: /scripts/
Disallow: /internal/
Disallow: /api/            # if public API docs exist elsewhere, keep those indexable
Disallow: /version.json
Disallow: /unsubscribe.html

# Block site search & thin utility pages (use noindex in HTML too)
Disallow: /soeg
Disallow: /search
Disallow: /soeg?
Disallow: /search?

# Block common tracking/duplicate URL parameters to save crawl budget
# (Google does respect wildcards with '?'; safe for other major bots too)
Disallow: /*?*utm_*=*
Disallow: /*?*gclid=*
Disallow: /*?*fbclid=*
Disallow: /*?*ref=*
Disallow: /*?*source=*
Disallow: /*?*session=*
Disallow: /*?*sort=*
Disallow: /*?*page=*

# IMPORTANT: Do NOT block assets needed for rendering (CSS/JS/fonts/images)
# e.g., leave /_next/, /assets/, /static/ open if present

# --- Sitemaps (index + children) ---
Sitemap: https://headtohead.dk/sitemap.xml
Sitemap: https://headtohead.dk/sitemap-static.xml
Sitemap: https://headtohead.dk/sitemap-leagues.xml
Sitemap: https://headtohead.dk/sitemap-matches.xml
Sitemap: https://headtohead.dk/sitemap-articles.xml
Sitemap: https://headtohead.dk/sitemap-profiles.xml
Sitemap: https://headtohead.dk/sitemap-highscore.xml