# robots.txt for https://fernandojlopez.com (The Lopez Law Group)
# Updated 2026-07-13
# Goals: keep crawl focused on real content, welcome AI answer engines (AEO/GEO/AIO),
# and stop wasting crawl on parameter/duplicate URLs.

# =========================================================
# Default rules for all standard crawlers (Googlebot, Bingbot, etc.)
# =========================================================
User-agent: *
Allow: /

# WordPress admin (keep out of crawl; admin-ajax must stay allowed for the site to work)
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

# Trashed / staging leftovers
Disallow: /*__trashed/
Disallow: /practice-areas__trashed/

# Plugin internals: block only the 403 directory URLs, leave every asset file crawlable
Disallow: /wp-content/plugins/*/$

# Non-content query strings (crawl waste, never the canonical URL)
Disallow: /*?adSubId=
Disallow: /*?nonamp=
Disallow: /*?page_id=
Disallow: /*?s=
Disallow: /*?replytocom=
Disallow: /*?creating_cache=
Disallow: /*/amp/

# NOTE on UTM/GBP parameter URLs (e.g. /?utm_source=google...gbp-weslaco):
# These are intentionally NOT blocked here. Each already has a canonical tag pointing
# to the clean URL, so Google consolidates them correctly. Blocking them in robots.txt
# would stop Google from reading that canonical. The correct fix is to set the Google
# Business Profile website link to the clean URL https://fernandojlopez.com/ .

# (Removed the old "Disallow: /wp-includes/js/wp-emoji-release.min.js" line. Blocking a
#  single JS file only created a "Blocked by robots.txt" report entry with no benefit.)

# =========================================================
# AI / LLM crawlers - explicitly WELCOME
# The firm wants its content read and cited by AI answer engines
# (ChatGPT, Claude, Perplexity, Google AI Overview / Gemini, Copilot, Grok, etc.).
# Each named bot ignores the "*" block above, so we allow the whole site to each.
# =========================================================
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: Claude-SearchBot
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: Amazonbot
Allow: /

User-agent: Bytespider
Allow: /

User-agent: CCBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

# =========================================================
# Sitemaps
# sitemap_index.xml already references the page, post and video sitemaps.
# =========================================================
Sitemap: https://fernandojlopez.com/sitemap_index.xml

# AI content guide for this site: https://fernandojlopez.com/llms.txt