# Glenfield Digital Group - Robots.txt
# Last Updated: December 2025

# Default crawl delay for all bots
User-agent: *
Crawl-delay: 10
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/plugins/

# Allow major search engines for SEO
User-agent: Googlebot
Crawl-delay: 10
Allow: /
Allow: /wp-content/uploads/

User-agent: Bingbot
Crawl-delay: 10
Allow: /
Allow: /wp-content/uploads/

User-agent: Slurp
Crawl-delay: 10
Allow: /

User-agent: Googlebot-Image
Crawl-delay: 5
Allow: /
Allow: /wp-content/uploads/ 

User-agent: MSNBot
Crawl-delay: 5
Allow: /

User-agent: Baiduspider
Crawl-delay: 10
Allow: /

User-agent: DuckDuckBot
Crawl-delay: 10
Allow: /

User-agent: Yandex
Crawl-delay: 10
Allow: /

User-agent: Applebot
Crawl-delay: 10
Allow: /

# Allow ad-related bots (optional for Google Ads performance)

User-agent: AdsBot-Google
Crawl-delay: 10
Allow: /  #

# Social media bots for link previews
User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: WhatsApp
Allow: /

User-agent: TelegramBot
Allow: /

User-agent: facebookexternalhit
Allow: /

# AI Crawlers - Blocked (no content scraping for AI training)

User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: Webzio-Extended
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: img2dataset
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Kangaroo Bot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: Scrapy
Disallow: /

# Aggressive scrapers and bad bots

User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: Nutch
Disallow: /

User-agent: TinEye-bot
Disallow: /

User-agent: ICC-Crawler
Disallow: /

User-agent: trendkite-akashic-crawler
Disallow: /

User-agent: TurnitinBot
Disallow: /

User-agent: R6_CommentReader
Disallow: /

User-agent: iSec_Bot
Disallow: /

User-agent: dataforseo
Disallow: / 

User-agent: SeznamBot
Disallow: / 

User-agent: AdsTxtCrawler
Disallow: / 

User-agent: ia_archiver
Disallow: / 

# Sitemap
Sitemap: https://www.glenfield.net/sitemap.xml