# robots.txt for eftours.com
# Last updated: 2026-04-22

# Algolia-Crawler-Verif: 90E775AD7ADA5970

# =============================================================================
# DEFAULT RULES (search engines, standard crawlers)
# =============================================================================

User-agent: *
Allow: /
Allow: /educational-tours/search
Allow: /account/login
Allow: /llms.txt

# Internal tools and admin
Disallow: /secure/
Disallow: /sitecore/
Disallow: /api/
Disallow: /forms

# Account and personal
Disallow: /account/
Disallow: /personal/

# Preview and print (duplicate content)
Disallow: /preview-tour*
Disallow: /print-tour/

# Legacy paths (redirect to internal corp domain -- security risk)
Disallow: /ctt_pdf
Disallow: /eliterature/

# Pricing and scheduling
Disallow: /educational-tour/*/detailed-price
Disallow: /appt-scheduling-landing/
Disallow: /appt-scheduling/

# Error pages
Disallow: /error/

# Inactive paths
Disallow: /tour-website

# Review pagination and photos (248+ duplicate URL variations per tour)
Disallow: /educational-tour/*/reviews/photos
Disallow: /educational-tour/*/reviews/more

# Help center search (dynamic params, thin content)
Disallow: /help-center/search-results

# User-specific pages
Disallow: /invite/
Disallow: /referral/
Disallow: /accountrecovery
Disallow: /invalidloginlink

# Search with query parameters (thin/duplicate content)
Disallow: /educational-tours/search?query=

# Sensitive query parameters
Disallow: /*?*reviewId=
Disallow: /*?*accountnumber=
Disallow: /*?*individualid=
Disallow: /*?*__RequestVerificationToken=

# WeShare internal pages
Disallow: /weshare/admin
Disallow: /weshare/serveradmin
Disallow: /weshare/angular_apps
Disallow: /weshare/under-maintenance
Disallow: /weshare/log-in/?targeturl=*
Disallow: /weshare/request-demo
Disallow: /weshare/activation
Disallow: /weshare/repeat-activation
Disallow: /weshare/experience
Disallow: /weshare/story
Disallow: /weshare/teacher

# UTM and tracking parameters (prevent duplicate indexing)
Disallow: /*?*utm_source=
Disallow: /*?*utm_medium=
Disallow: /*?*utm_campaign=
Disallow: /*?*utm_term=
Disallow: /*?*utm_content=
Disallow: /*?*utm_segment=
Disallow: /*?*sourcecode=
Disallow: /*?*utm_group=
Disallow: /*?*utm_season=
Disallow: /*?*url=
Disallow: /*?*source=

# =============================================================================
# AI TRAINING CRAWLERS (blocked)
#
# These crawlers scrape content for AI model training, not search.
# Blocking them protects content from unauthorized training use while
# keeping the site visible in AI-powered search results.
# =============================================================================

User-agent: CCBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: YouBot
Disallow: /

# =============================================================================
# AI SEARCH CRAWLERS (allowed)
#
# GPTBot (ChatGPT search), PerplexityBot (Perplexity search), Bingbot
# (Copilot), and Googlebot (AI Overviews) are NOT blocked. They fall
# under User-agent: * and can crawl public content normally. This ensures
# eftours.com appears in AI-powered search results and gets cited in
# AI responses.
#
# Content usage policy: see https://www.eftours.com/llms.txt
# =============================================================================

Sitemap: https://www.eftours.com/sitemap.xml