#
# robots.txt
#
# This file is to prevent the crawling and indexing of certain parts
# of your site by web crawlers and spiders run by sites like Yahoo!
# and Google. By telling these "robots" where not to go on your site,
# you save bandwidth and server resources.
#
# This file will be ignored unless it is at the root of your host:
# Used:    http://example.com/robots.txt
# Ignored: http://example.com/site/robots.txt
#
# For more information about the robots.txt standard, see:
# http://www.robotstxt.org/robotstxt.html

User-agent: *
# CSS, JS, Images
Allow: /core/*.css$
Allow: /core/*.css?
Allow: /core/*.js$
Allow: /core/*.js?
Allow: /core/*.avif
Allow: /core/*.gif
Allow: /core/*.jpg
Allow: /core/*.jpeg
Allow: /core/*.png
Allow: /core/*.svg
Allow: /core/*.webp
Allow: /profiles/*.css$
Allow: /profiles/*.css?
Allow: /profiles/*.js$
Allow: /profiles/*.js?
Allow: /profiles/*.avif
Allow: /profiles/*.gif
Allow: /profiles/*.jpg
Allow: /profiles/*.jpeg
Allow: /profiles/*.png
Allow: /profiles/*.svg
Allow: /profiles/*.webp
# Directories
Disallow: /core/
Disallow: /profiles/
# Files
Disallow: /README.md
Disallow: /composer/Metapackage/README.txt
Disallow: /composer/Plugin/ProjectMessage/README.md
Disallow: /composer/Plugin/Scaffold/README.md
Disallow: /composer/Plugin/VendorHardening/README.txt
Disallow: /composer/Template/README.txt
Disallow: /modules/README.txt
Disallow: /sites/README.txt
Disallow: /themes/README.txt
# Paths (clean URLs)
Disallow: /admin/
Disallow: /comment/reply/
Disallow: /filter/tips
Disallow: /node/add/
Disallow: /search/
Disallow: /search?
Disallow: /user/register
Disallow: /user/password
Disallow: /user/login
Disallow: /user/logout
Disallow: /media/oembed
Disallow: /*/media/oembed
# Paths (no clean URLs)
Disallow: /index.php/admin/
Disallow: /index.php/comment/reply/
Disallow: /index.php/filter/tips
Disallow: /index.php/node/add/
Disallow: /index.php/search/
Disallow: /index.php/search?
Disallow: /index.php/user/password
Disallow: /index.php/user/register
Disallow: /index.php/user/login
Disallow: /index.php/user/logout
Disallow: /index.php/media/oembed
Disallow: /index.php/*/media/oembed

# OpenAI: Model Training
# Allowing GPTBot ensures ChatGPT's base model
# accurately represents Axway's products and messaging.
User-agent: GPTBot
Allow: /

# OpenAI: ChatGPT Search Results
User-agent: OAI-SearchBot
Allow: /

# OpenAI: User-Initiated ChatGPT Browsing
User-agent: ChatGPT-User
Allow: /

# Anthropic: Claude Search
User-agent: ClaudeBot
Allow: /

# Perplexity: AI Search Engine
User-agent: PerplexityBot
Allow: /

# Google: AI Overviews / Gemini
User-agent: Google-Extended
Allow: /

# Meta: Social Previews + AI Features
User-agent: facebookexternalhit
Allow: /

User-agent: meta-externalagent
Allow: /


# Common Crawl (open dataset used by multiple LLM trainers)
User-agent: CCBot
Disallow: /

# ByteDance / TikTok
User-agent: Bytespider
Disallow: /

# Diffbot (data extraction service)
User-agent: Diffbot
Disallow: /

# Apple: AI Model Training (separate from Siri/Applebot search)
User-agent: Applebot-Extended
Disallow: /

# Cohere AI Training
User-agent: cohere-ai
Disallow: /

# Webz.io
User-agent: webzio-extended
Disallow: /

# Omgili
User-agent: omgili
Disallow: /

# Timpi
User-agent: Timpibot
Disallow: /

# img2dataset
User-agent: img2dataset
Disallow: /

# Sidetrade
User-agent: Sidetrade indexer bot
Disallow: /

User-agent: AhrefsBot
Crawl-delay: 10

User-agent: AhrefsSiteAudit
Crawl-delay: 10

User-agent: SEMrushBot
Crawl-delay: 1

User-agent: SemrushBot-SA
Crawl-delay: 1

User-agent: MJ12bot
Crawl-delay: 10

User-agent: DotBot
Crawl-delay: 10

User-agent: BLEXBot
Crawl-delay: 10

User-agent: DataForSeoBot
Crawl-delay: 5

User-agent: SerpstatBot
Crawl-delay: 5

User-agent: Amazonbot
Crawl-delay: 5

Sitemap: https://www.axway.com/sitemap.xml
Sitemap: https://www.axway.com/en/sitemap.xml
Sitemap: https://www.axway.com/fr/sitemap.xml
Sitemap: https://www.axway.com/de/sitemap.xml
Sitemap: https://www.axway.com/pt-br/sitemap.xml