# Robots.txt for JSON Align - https://jsonalign.pro/

# Allow all web crawlers to access the site
User-agent: *
Allow: /

# Allow specific major search engine bots
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

# Block access to sensitive or unnecessary files/directories
Disallow: /admin/
Disallow: /private/
Disallow: /temp/
Disallow: /logs/
Disallow: /backup/
Disallow: /config/
Disallow: /node_modules/
Disallow: /.git/
Disallow: /.env
Disallow: /package.json
Disallow: /package-lock.json
Disallow: /yarn.lock
Disallow: /.htaccess
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /cgi-bin/
Disallow: /search?
Disallow: /*?utm_source=*
Disallow: /*?utm_medium=*
Disallow: /*?utm_campaign=*
Disallow: /*?ref=*
Disallow: /*?session=*
Disallow: /*?token=*

# Allow access to important files
Allow: /favicon.ico
Allow: /favicon.svg
Allow: /robots.txt
Allow: /sitemap.xml
Allow: /sitemap.txt
Allow: /*.css
Allow: /*.js
Allow: /*.png
Allow: /*.jpg
Allow: /*.jpeg
Allow: /*.gif
Allow: /*.svg
Allow: /*.webp
Allow: /*.ico
Allow: /*.woff
Allow: /*.woff2
Allow: /*.ttf
Allow: /*.eot

# Crawl-delay for different bots (in seconds)
# Crawl-delay: 1

# Sitemap location
Sitemap: https://jsonalign.pro/sitemap.xml
Sitemap: https://jsonalign.pro/sitemap.txt

# Host directive (specify canonical domain)
Host: jsonalign.pro

# Additional directives for better SEO
# Clean-param: utm_source&utm_medium&utm_campaign&ref&session&token

# Block malicious bots and scrapers
User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: BuiltWith
Disallow: /

User-agent: MegaIndex
Disallow: /

User-agent: SeekportBot
Disallow: /

User-agent: LinkpadBot
Disallow: /

User-agent: spbot
Disallow: /

User-agent: PetalBot
Disallow: /

# Allow access to manifest and service worker files
Allow: /manifest.json
Allow: /site.webmanifest
Allow: /sw.js
Allow: /service-worker.js

# Allow access to API endpoints if you have any
Allow: /api/

# Block access to error pages from being indexed
Disallow: /404
Disallow: /500
Disallow: /*404*
Disallow: /*error*

# Allow access to important landing pages and tools
Allow: /json-beautifier/
Allow: /json-formatter/
Allow: /json-validator/
Allow: /json-minifier/
Allow: /json-converter/
Allow: /json-to-csv/
Allow: /json-to-xml/
Allow: /json-to-yaml/
Allow: /about/
Allow: /help/
Allow: /faq/
Allow: /privacy/
Allow: /terms/
Allow: /contact/

# Performance optimization - avoid crawling duplicate content
Disallow: /*?print=*
Disallow: /*?mobile=*
Disallow: /*?amp=*
Disallow: /*?format=*

# Block access to backup and temporary files
Disallow: /*.bak
Disallow: /*.tmp
Disallow: /*.old
Disallow: /*~
Disallow: /*.backup

# End of robots.txt


# Robots.txt for JSON Align - https://jsonalign.pro/

# Allow all web crawlers to access the site
User-agent: *
Allow: /

# Sitemap location
Sitemap: https://jsonalign.pro/sitemap.xml

# Rest of your robots.txt file remains unchanged