# 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.
#
# 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.
User-agent: *
Content-Signal: search=yes,ai-input=yes,ai-train=no
Allow: /
# Block training-only crawlers (but allow citation/search crawlers like GPTBot, ClaudeBot)
User-agent: Bytespider
Disallow: /
User-agent: CCBot
Disallow: /
# Next.js
Disallow: /api/
# WordPress core
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-login.php
Disallow: /wp-register.php
Disallow: /xmlrpc.php
Disallow: /readme.html
Disallow: /license.txt
# Spam / hacked URLs
Disallow: /wp-content/public/
Disallow: /*?discovery=
# Search & internal junk
Disallow: /search/
Disallow: /*?s=
Disallow: /*?p=
Disallow: /*&preview=
Disallow: /*?*e-page=
Disallow: /*?*country=
Disallow: /*?*q=
# Feeds
Disallow: /feed/
Disallow: */feed/
Disallow: */comments/feed/
Disallow: /*?feed=
# Taxonomies
Disallow: /tag/
# Tracking & spam parameters
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?gbraid=
Disallow: /*?wbraid=
Disallow: /*?ref=
Disallow: /*?trk=
Disallow: /*?utm_*
# WooCommerce junk
Disallow: /*?add-to-cart=
Disallow: /*?remove_item=
Disallow: /*?orderby=
Disallow: /*?filter=
Disallow: /*?product_orderby=
Disallow: /*?product_count=
# Misc
Disallow: /*?v=
Disallow: /*?share=
Disallow: /*?r=
Disallow: /*?outputType=
Disallow: /*?gad_source=
Sitemap: https://expatsi.com/sitemap.xml