# robots.txt – Version 1.7 – 2026-06-18
# Purpose: Control crawler access to sensitive or irrelevant parts of the site
# Changelog:
#   v1.7 (2026-06-18): Disallow /wp-json/ for main crawlers (Google, Bing) to
#         stop crawling REST/oEmbed discovery endpoints (crawl-budget waste);
#         part of AdSense low-value-content remediation.
#   v1.6 (2026-03-11): Added Disallow for all /feed/ URLs across all bots
#         including Googlebot, to prevent RSS feed duplicates from being
#         crawled and indexed (454 duplicate pages identified in GSC
#         kachen.online). Pattern covers /feed/, /*/feed/, /comments/feed/.
#   v1.5 (2025-12-17): Initial comprehensive version with AI crawler blocks.
# Notes:
#   - Validated for Google and AdSense compliance
#   - Includes comprehensive AI crawler disallow rules
#   - Multisite: TaSty, KACHEN, REESEN
#   - AI-training policy: This site disallows AI model training crawlers.
#   - SEO tools: Allowed for competitive analysis
# ------------------------------------------------------------
# General rules for all user agents
# ------------------------------------------------------------
User-agent: *
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /xmlrpc.php
Disallow: /?s=
Disallow: /feed/
Disallow: /comments/feed/
Disallow: /*/feed/
Disallow: /wp-json/
Allow: /wp-admin/admin-ajax.php
Allow: /wp-content/uploads/
# ------------------------------------------------------------
# Google crawlers (explicit allow + feed block)
# ------------------------------------------------------------
User-agent: Googlebot
Allow: /
Disallow: /feed/
Disallow: /comments/feed/
Disallow: /*/feed/
Disallow: /wp-json/
User-agent: Googlebot-Mobile
Allow: /
Disallow: /feed/
Disallow: /*/feed/
Disallow: /wp-json/
User-agent: Googlebot-Image
Allow: /
# ------------------------------------------------------------
# Bing and other search engines
# ------------------------------------------------------------
User-agent: Bingbot
Allow: /
Disallow: /feed/
Disallow: /*/feed/
Disallow: /wp-json/
User-agent: Slurp
Allow: /
User-agent: DuckDuckBot
Allow: /
User-agent: Yandex
Allow: /
# ------------------------------------------------------------
# SEO and analytics tools (allowed)
# ------------------------------------------------------------
User-agent: AhrefsBot
Allow: /
User-agent: SemrushBot
Allow: /
User-agent: MJ12bot
Allow: /
User-agent: DotBot
Allow: /
User-agent: Screaming Frog SEO Spider
Allow: /
# ------------------------------------------------------------
# Pinterest crawler (for Rich Pins and sharing)
# ------------------------------------------------------------
User-agent: Pinterestbot
Allow: /
Crawl-delay: 2
# ------------------------------------------------------------
# AI, LLM, and data-mining crawlers (BLOCKED)
# Updated: 2025-11-25 - Comprehensive list
# ------------------------------------------------------------
User-agent: GPTBot
Disallow: /
User-agent: ChatGPT-User
Disallow: /
User-agent: ClaudeBot
Disallow: /
User-agent: Claude-Web
Disallow: /
User-agent: anthropic-ai
Disallow: /
User-agent: Google-Extended
Disallow: /
User-agent: Applebot-Extended
Disallow: /
User-agent: FacebookBot
Disallow: /
User-agent: meta-externalagent
Disallow: /
User-agent: Amazonbot
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: CCBot
Disallow: /
User-agent: PerplexityBot
Disallow: /
User-agent: cohere-ai
Disallow: /
User-agent: YouBot
Disallow: /
User-agent: Diffbot
Disallow: /
User-agent: PetalBot
Disallow: /
User-agent: SeekportBot
Disallow: /
User-agent: Timpibot
Disallow: /
User-agent: img2dataset
Disallow: /
User-agent: Omgilibot
Disallow: /
# ------------------------------------------------------------
# Sitemaps
# ------------------------------------------------------------
Sitemap: https://tasty.lu/sitemaps.xml
Sitemap: https://kachen.lu/sitemaps.xml
Sitemap: https://reesenmag.lu/sitemaps.xml