# The Main - Montreal's City Magazine
# robots.txt

# Global rules
User-agent: *
Allow: /
Allow: /directory/
Allow: /guide/
Allow: /articles/
Allow: /place/
Allow: /llms.txt
Allow: /llms-full.txt

# Next.js static assets - allow CSS/media for rendering, block JSON/manifests for crawl budget
Allow: /_next/static/css/
Allow: /_next/static/media/
Allow: /_next/static/chunks/
# Article and guide images are served through the image optimizer; Google
# requires image URLs to be crawlable for Images and Discover.
Allow: /_next/image
Disallow: /_next/
Disallow: /*.json$

Disallow: /*?ref=*
Disallow: /api/
Disallow: /admin/
Disallow: /private/
Disallow: /*preview=true
Disallow: /*draft=true
Disallow: /account/
Disallow: /auth/
Disallow: /awards/
Disallow: /fr/awards/
Disallow: /studio/
Disallow: /events/
Disallow: /event/
Disallow: /fr/events/
Disallow: /fr/event/

# AI answer engines fetch a page when someone asks a question and link back
# to it in the answer. Allowed, with no crawl delay, so we can be cited.
# A bot that matches a named group ignores the * group, so the private paths
# are repeated here.
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
Disallow: /_next/
Disallow: /api/
Disallow: /admin/
Disallow: /private/
Disallow: /account/
Disallow: /auth/
Disallow: /studio/
Disallow: /awards/
Disallow: /fr/awards/
Disallow: /events/
Disallow: /event/
Disallow: /fr/events/
Disallow: /fr/event/
Disallow: /*?ref=*
Disallow: /*preview=true
Disallow: /*draft=true
Disallow: /directory/*/*?businesstype=*
Disallow: /directory/*/2
Disallow: /directory/*/3
Disallow: /directory/*/4
Disallow: /directory/*/5
Disallow: /directory/*/6
Disallow: /directory/*/7
Disallow: /directory/*/8
Disallow: /directory/*/9
Disallow: /directory/*/10
Allow: /

# AI training crawlers copy pages to train models and send no readers back.
# Blocked. This does not affect Google Search or Google's AI Overviews, which
# use Googlebot, nor the answer engines above.
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: CCBot
User-agent: Bytespider
User-agent: meta-externalagent
User-agent: cohere-training-data-crawler
Disallow: /

User-agent: Applebot
Allow: /articles/
Allow: /fr/articles/
Allow: /guide/
Allow: /fr/guide/
Allow: /apple-news-feed.xml
Disallow: /api/
Disallow: /admin/
Disallow: /account/
Disallow: /studio/

User-agent: AwarioRssBot
Disallow: /

User-agent: AwarioSmartBot
Disallow: /

# Crawl-delay directive (default for all other bots)
Crawl-delay: 1

# Google News Crawler - Explicit permissions for news content
User-agent: Googlebot-News
Allow: /articles/
Allow: /fr/articles/
Allow: /bulletin/
Allow: /fr/bulletin/
Allow: /guide/
Allow: /fr/guide/
Disallow: /directory/
Disallow: /api/
Disallow: /admin/
Disallow: /account/
Disallow: /studio/

# Sitemap URLs - Standard sitemap for general crawling
Sitemap: https://www.themain.com/sitemap.xml

# Google News Sitemap - Dedicated news content feed
Sitemap: https://www.themain.com/news-sitemap.xml

# Apple News Feed - Optimized RSS for Apple News Publisher
# See: https://www.themain.com/apple-news-feed.xml

# LLMs.txt - AI content documentation
# See: https://www.themain.com/llms.txt