# As a condition of accessing this website, you agree to abide by the following
# content signals:

# (a)  If a Content-Signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a Content-Signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a Content-Signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via Content-Signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.
# use:      how AI systems may consume the content (immediate, reference, or full).

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

# BEGIN Cloudflare Managed content

User-agent: *
Content-Signal: search=yes,ai-train=no,use=reference
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# robots.txt for healingtrip.site
# Last updated: July 8, 2026

# Default rules for all crawlers
User-agent: *
Allow: /

# Sitemap location
Sitemap: https://healingtrip.site/sitemap.xml

# Disallow access to sensitive areas
Disallow: /admin/
Disallow: /private/
Disallow: /temp/
Disallow: /backup/
Disallow: /api/
Disallow: /config/
Disallow: /.env
Disallow: /.git/

# Allow important pages
Allow: /index.html
Allow: /about.html
Allow: /contact.html
Allow: /privacy-policy.html
Allow: /disclaimer.html

# Crawl-delay for polite crawling
Crawl-delay: 1

# Specific rules for major search engines
User-agent: Googlebot
Allow: /
Crawl-delay: 0

User-agent: Bingbot
Allow: /
Crawl-delay: 1

User-agent: Slurp
Allow: /
Crawl-delay: 1

# Block bad bots
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: MJ12bot
Disallow: /

# Block access to certain file types
User-agent: *
Disallow: /*.pdf$
Disallow: /*.doc$
Disallow: /*.docx$
Disallow: /*.xls$
Disallow: /*.xlsx$
Disallow: /*.ppt$
Disallow: /*.pptx$
Disallow: /*.zip$
Disallow: /*.rar$

# Allow image and CSS files
User-agent: *
Allow: /*.jpg$
Allow: /*.jpeg$
Allow: /*.gif$
Allow: /*.png$
Allow: /*.svg$
Allow: /*.webp$
Allow: /*.css$
Allow: /*.js$

# Block access to query parameters
User-agent: *
Disallow: /*?
Disallow: /*&
Disallow: /*=

# Block access to print versions
User-agent: *
Disallow: /*?print=
Disallow: /*?utm_

# Block access to search results
User-agent: *
Disallow: /search?q=
Disallow: /search?query=

# Block access to tag pages
User-agent: *
Disallow: /tag/
Disallow: /tags/

# Block access to category pages (if not needed for SEO)
User-agent: *
Disallow: /category/
Disallow: /categories/

# Block access to author pages
User-agent: *
Disallow: /author/
Disallow: /authors/

# Block access to date archives (optional, based on preference)
User-agent: *
Disallow: /2020/
Disallow: /2021/
Disallow: /2022/
Disallow: /2023/
Disallow: /2024/
Disallow: /2025/

# Allow current year
User-agent: *
Allow: /2026/

# Block access to pagination beyond page 10
User-agent: *
Disallow: /page/11
Disallow: /page/12
Disallow: /page/13
Disallow: /page/14
Disallow: /page/15

# Block access to feed pages (if not needed)
User-agent: *
Disallow: /feed/
Disallow: /rss/
Disallow: /atom/

# Block access to trackback URLs
User-agent: *
Disallow: /trackback/

# Block access to login and registration pages
User-agent: *
Disallow: /login/
Disallow: /register/
Disallow: /signup/
Disallow: /wp-admin/
Disallow: /wp-login.php

# Block access to cart and checkout (if e-commerce)
User-agent: *
Disallow: /cart/
Disallow: /checkout/
Disallow: /my-account/

# Block access to internal search results
User-agent: *
Disallow: /?s=
Disallow: /search/

# Block access to preview pages
User-agent: *
Disallow: /*?preview=
Disallow: /*&preview=

# Block access to draft pages
User-agent: *
Disallow: /*?draft=
Disallow: /*&draft=

# Block access to password-protected pages
User-agent: *
Disallow: /*?password=
Disallow: /*&password=

# Block access to certain URL parameters
User-agent: *
Disallow: /*?ref=
Disallow: /*?source=
Disallow: /*?medium=
Disallow: /*?campaign=

# Block access to session IDs
User-agent: *
Disallow: /*;jsessionid=
Disallow: /*?jsessionid=

# Block access to certain file extensions
User-agent: *
Disallow: /*.php$
Disallow: /*.asp$
Disallow: /*.aspx$
Disallow: /*.jsp$

# Allow clean URLs
User-agent: *
Allow: /$
Allow: /*.html$

# Block access to certain directories
User-agent: *
Disallow: /includes/
Disallow: /lib/
Disallow: /vendor/
Disallow: /node_modules/
Disallow: /bower_components/

# Block access to cache directories
User-agent: *
Disallow: /cache/
Disallow: /tmp/
Disallow: /logs/

# Block access to upload directories (if needed)
User-agent: *
Disallow: /uploads/temp/
Disallow: /uploads/drafts/

# Allow main upload directory
User-agent: *
Allow: /uploads/

# Block access to certain WordPress paths
User-agent: *
Disallow: /wp-content/plugins/
Disallow: /wp-includes/
Disallow: /wp-content/cache/

# Allow WordPress content
User-agent: *
Allow: /wp-content/themes/
Allow: /wp-content/uploads/

# Block access to XML-RPC
User-agent: *
Disallow: /xmlrpc.php

# Block access to WordPress cron
User-agent: *
Disallow: /wp-cron.php

# Block access to WordPress REST API (if not needed)
User-agent: *
Disallow: /wp-json/

# Block access to certain WordPress parameters
User-agent: *
Disallow: /*?p=
Disallow: /*?page_id=
Disallow: /*?cat=
Disallow: /*?tag=
Disallow: /*?author=

# Block access to attachment pages (optional)
User-agent: *
Disallow: /attachment/

# Block access to certain post formats
User-agent: *
Disallow: /type/

# Block access to certain post types
User-agent: *
Disallow: /portfolio/
Disallow: /product/

# Block access to certain taxonomies
User-agent: *
Disallow: /portfolio_category/
Disallow: /product_category/
Disallow: /product_tag/

# Block access to comment pages
User-agent: *
Disallow: /comment-page-

# Block access to trackback pages
User-agent: *
Disallow: /trackback/

# Block access to pingback
User-agent: *
Disallow: /xmlrpc.php?rsd

# Block access to certain WordPress feeds
User-agent: *
Disallow: /feed/$
Disallow: /comments/feed/$
Disallow: /*/feed/$
Disallow: /*/comments/feed/$

# Block access to certain WordPress embeds
User-agent: *
Disallow: /embed/

# Block access to certain WordPress oEmbed
User-agent: *
Disallow: /wp-json/oembed/

# Block access to certain WordPress REST routes
User-agent: *
Disallow: /wp-json/wp/v2/users

# Block access to certain WordPress admin AJAX
User-agent: *
Disallow: /wp-admin/admin-ajax.php

# End of robots.txt