# ============================================================
# ConfLists - robots.txt
# ============================================================


# ============================================================
# 1. GENERAL CRAWL RULES
# ============================================================

User-agent: *

# ------------------------------------------------------------
# WordPress administration
# ------------------------------------------------------------

Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php


# ------------------------------------------------------------
# Internal WordPress search
# ------------------------------------------------------------

Disallow: /?s=
Disallow: /search/


# ------------------------------------------------------------
# WP Event Manager AJAX / filter endpoints
# ------------------------------------------------------------

Disallow: /jm-ajax/
Disallow: /*?event_search=
Disallow: /*?event_location=
Disallow: /*?event_category=
Disallow: /*?event_type=


# ------------------------------------------------------------
# RSS / Atom feeds and trackbacks
# ------------------------------------------------------------

Disallow: /feed/
Disallow: */feed/
Disallow: */trackback/


# ============================================================
# 2. IMPORTANT PUBLIC CONTENT
# ============================================================

# Main conference/event content

Allow: /international-
Allow: /topic/
Allow: /event/
Allow: /conference/
Allow: /venue/


# ============================================================
# 3. STATIC RESOURCES
# ============================================================

Allow: /*.js
Allow: /*.css
Allow: /wp-content/uploads/


# ============================================================
# 4. PAGINATION CONTROL
# ============================================================

# Allow first and second pages.
# Limit deeper pagination.

Disallow: */page/3/
Disallow: */page/4/
Disallow: */page/5/
Disallow: */page/6/
Disallow: */page/7/
Disallow: */page/8/
Disallow: */page/9/


# ============================================================
# 5. YANDEX CRAWL RATE
# ============================================================

User-agent: Yandex

Crawl-delay: 2


# ============================================================
# 6. LEGITIMATE SEARCH ENGINES
#
# Explicitly allowed.
# ============================================================

User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: Yandex
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Applebot
Allow: /


# ============================================================
# 7. COMMERCIAL SEO / DATA SCRAPERS
#
# These crawlers are intentionally blocked.
# ============================================================

User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: PetalBot
Disallow: /


# ============================================================
# 8. AI / DATA COLLECTION BOTS
#
# These are intentionally blocked.
# ============================================================

User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Diffbot
Disallow: /


# ============================================================
# 9. SITEMAP
# ============================================================

Sitemap: https://www.conferencelists.com/sitemap_index.xml