# Robots.txt for DC P&E, Inc.
# https://dcpande.com
# Last Updated: 2026-08-13
#
# POLICY: AI *training* crawlers are blocked. AI *search / retrieval*
# crawlers are ALLOWED so DC P&E can be found and cited when customers
# ask an AI assistant for plumbing or electrical supply in Dickson,
# Waverly, Dickson County or Humphreys County, TN.

# ===========================================
# STANDARD SEARCH ENGINES - ALLOWED
# ===========================================
User-agent: *
Allow: /
Disallow: /cgi-bin/
Disallow: /tmp/
Disallow: /private/
Disallow: /error_log
Disallow: /*-orig.php$
Disallow: /*.bak$
Disallow: /*.sql$
Disallow: /*.log$
Disallow: /*.docx$

User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Applebot
Allow: /

# ===========================================
# AI SEARCH / RETRIEVAL CRAWLERS - ALLOWED
# These answer live user questions and cite sources.
# Blocking them removes DC P&E from AI search results.
# ===========================================
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: MistralAI-User
Allow: /

# ===========================================
# AI TRAINING CRAWLERS - DISALLOWED
# ===========================================
User-agent: GPTBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: cohere-training-data-crawler
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: TikTokSpider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: AI2Bot
Disallow: /

User-agent: Ai2Bot-Dolma
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: img2dataset
Disallow: /

User-agent: Scrapy
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: Webzio-Extended
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: VelenPublicWebCrawler
Disallow: /

# ===========================================
# SITEMAPS
# ===========================================
Sitemap: https://dcpande.com/sitemap-index.xml
Sitemap: https://dcpande.com/sitemap.xml