37a6b01598
- Remove all web scraping services, blog articles, locations, tools pages - Remove fake author profiles and old categories - Add 6 new AI automation blog articles targeting legal/consultancy firms - Rewrite blog index with new AI automation content - Update robots.txt with correct ukaiautomation.co.uk domain - Update sitemap.xml with current pages only
72 lines
1.3 KiB
Plaintext
72 lines
1.3 KiB
Plaintext
# UK AI Automation - robots.txt
|
|
# https://ukaiautomation.co.uk
|
|
|
|
User-agent: *
|
|
Allow: /
|
|
|
|
# Block sensitive directories and files
|
|
Disallow: /includes/
|
|
Disallow: /assets/
|
|
Disallow: /admin/
|
|
Disallow: /logs/
|
|
Disallow: /vendor/
|
|
Disallow: /config/
|
|
Disallow: /database/
|
|
Disallow: /docker/
|
|
|
|
# Block configuration and handler files
|
|
Disallow: /*-handler.php
|
|
Disallow: /*.log$
|
|
Disallow: /*.inc$
|
|
Disallow: /*.sql$
|
|
Disallow: /*.sh$
|
|
Disallow: /*.bak$
|
|
Disallow: /db-config.php
|
|
Disallow: /.email-config.php
|
|
Disallow: /.recaptcha-config.php
|
|
|
|
# Block query string URLs to prevent duplicate content
|
|
Disallow: /*?*
|
|
|
|
# Allow important static assets for rendering
|
|
Allow: /assets/css/*.css
|
|
Allow: /assets/js/*.js
|
|
Allow: /assets/images/*.webp
|
|
Allow: /assets/images/*.png
|
|
Allow: /assets/images/*.jpg
|
|
Allow: /assets/images/*.svg
|
|
|
|
# Sitemaps
|
|
Sitemap: https://ukaiautomation.co.uk/sitemap.xml
|
|
|
|
# Crawl-delay for respectful crawling
|
|
Crawl-delay: 1
|
|
|
|
# Specific instructions for major search engines
|
|
User-agent: Googlebot
|
|
Allow: /
|
|
Crawl-delay: 0
|
|
|
|
User-agent: Bingbot
|
|
Allow: /
|
|
Crawl-delay: 1
|
|
|
|
# AI crawlers - explicitly allowed for citation
|
|
User-agent: GPTBot
|
|
Allow: /
|
|
|
|
User-agent: ChatGPT-User
|
|
Allow: /
|
|
|
|
User-agent: ClaudeBot
|
|
Allow: /
|
|
|
|
User-agent: anthropic-ai
|
|
Allow: /
|
|
|
|
User-agent: PerplexityBot
|
|
Allow: /
|
|
|
|
User-agent: Google-Extended
|
|
Allow: /
|