# 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.

# BEGIN Cloudflare Managed content

User-Agent: *
Content-signal: search=yes,ai-train=no
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# Basic crawling rules
User-Agent: *
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /cdn-cgi/
Disallow: /cdn-cgi/*
Disallow: /cgi-bin/
Disallow: /wp-content/themes/flatsome/assets/js
Disallow: /wp-content/themes/flatsome/assets/js/*
Disallow: /wp-content/litespeed/js/*
Disallow: /san-pham/  # Chặn thư mục sản phẩm
Disallow: /*?doing_wp_cron
Disallow: /*/ceylonthemes.com

# Core files protection
Disallow: /readme.html
Disallow: /license.txt
Disallow: /index.html

# Feed and navigation
Disallow: /feed/$
Disallow: /feed
Disallow: /atom
Disallow: /tag/
Disallow: /search/
Disallow: /search_user

# E-commerce pages
Disallow: /gio-hang
Disallow: /thanh-toan
Disallow: /tai-khoan/*
Disallow: /user/
Disallow: /quantri
Disallow: /quantri?*

# Search parameters
Disallow: ?
Disallow: ?s=
Disallow: ?p=   # Chặn tham số p
Disallow: &p=
Disallow: ?preview_id
Disallow: *?sp_atk
Disallow: *utm_source

# Search keyword restrictions
Disallow: /search?keyword=.com
Disallow: /search?keyword=.tv
Disallow: /search?keyword=.xyz
Disallow: /search?keyword=ă€â€Com
Disallow: /search?keyword=·COM
Disallow: /search?category=.com
Disallow: /search?category=.tv
Disallow: /search?category=.xyz
Disallow: /search?category=*ă€â€Com
Disallow: /search?category=*·COM

# Media and assets
Disallow: /thumbs/*
Disallow: /wp-content/plugins/table-of-contents-plus/front.min.js
Disallow: /wp-includes/js/jquery/jquery.min.js
Disallow: /wp-content/themes/flatsome/inc/extensions/flatsome-instant-page/flatsome-instant-page.js
Disallow: /wp-content/plugins/wpforms-lite/assets/lib/jquery.validate.min.js

# Trackback
Disallow: */trackback
Disallow: //trackback

# AI and Bot restrictions
User-agent: GPTBot
User-agent: CCBot
User-agent: anthropic-ai
User-agent: Omgilibot
User-agent: Diffbot
User-agent: ImagesiftBot
User-agent: PerplexityBot
User-agent: cohere-ai
User-agent: 008
User-agent: ChatGPT-User
User-agent: Bytespider
User-agent: magpie-crawler
User-agent: PetalBot
User-agent: Claude-Web
User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: AlphaAI
User-agent: FriendlyCrawler
User-agent: iaskspider/2.0
User-agent: ICC-Crawler
User-agent: ISSCyberRiskCrawler
User-agent: img2dataset
User-agent: Kangaroo Bot
User-agent: OAI-SearchBot
User-agent: Scrapy
User-agent: Sidetrade indexer bot
User-agent: Timpibot
User-agent: VelenPublicWebCrawler
User-agent: Webzio-Extended
User-agent: YouBot
User-agent: Wget
User-agent: HTTrack
User-agent: LinkWalker
User-agent: EmailCollector
User-agent: Exabot
Disallow: /

Allow: /wp-admin/admin-ajax.php

# Sitemap
Sitemap: https://truongtotnhat.vn/sitemap_index.xml