# 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

# ========================================================
# AJTraining 网站爬虫访问控制策略
# 网站: https://prawnikpabianice.pl/
# 最后更新: 2026年01月08日 (整合版)
# ========================================================

# ==================== 基础访问规则 ====================
# 屏蔽资源文件和系统路径，防止泄露目录结构
User-agent: *
Disallow: /css/
Disallow: /cookies/
Disallow: /files/
Disallow: /video/
Disallow: /images/
Disallow: /js/
Disallow: /assets/
Disallow: /static/
Disallow: /uploads/
Disallow: /fonts/
Disallow: /media/
Disallow: /vendor/
Disallow: /plugins/
Disallow: /temp/
Disallow: /cache/
Disallow: /sors.txt
Disallow: /admin/
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/themes/
Disallow: /config/
Disallow: /backend/
Disallow: /controlpanel/
Disallow: /dashboard/
Disallow: /database/
Disallow: /sql/
Disallow: /private/
Disallow: /secure/
Disallow: /cgi-bin/
Disallow: /tmp/
Disallow: /logs/
Disallow: /backup/
Disallow: /old/
Disallow: /test/
Disallow: /dev/
Disallow: /staging/
Disallow: /api/

# ==================== 安全监控陷阱路径 ====================
# 用于识别恶意扫描器的诱饵路径
Disallow: /honeypot-43-173/
Disallow: /blocked-ip-monitor/
Disallow: /suspicious-access-log/
Disallow: /crawler-trap-2024/
Disallow: /security-monitoring/
Disallow: /bad-bot-detector/
Disallow: /ip-monitoring-log/
Disallow: /malicious-crawler-log/
Disallow: /spider-trap-zone/
Disallow: /honeypot-admin/
Disallow: /fake-wp-login/
Disallow: /dummy-config/
Disallow: /fake-backup-zip/
Disallow: /phpmyadmin/
Disallow: /mysql/
Disallow: /administrator/
Disallow: /joomla/
Disallow: /drupal/
Disallow: /wordpress/
Disallow: /wp-login.php
Disallow: /xmlrpc.php

# ==================== 搜索引擎爬虫设置 ====================
# Google 系列
User-agent: Googlebot
Crawl-delay: 5
Request-rate: 1/5
Allow: /

User-agent: Googlebot-Image
Allow: /

# 其他主流搜索
User-agent: Bingbot
User-agent: YandexBot
User-agent: DuckDuckBot
User-agent: Applebot
Crawl-delay: 10
Allow: /

# 中文搜索
User-agent: Baiduspider
User-agent: 360Spider
User-agent: Sogou
User-agent: Sogou Spider
User-agent: Sogou web spider
User-agent: YisouSpider
Crawl-delay: 10
Allow: /

# ==================== AI/大模型爬虫策略 ====================
# 允许部分知名 AI 用于索引（可根据隐私需求调整）
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: Google-Extended
User-agent: AnthropicBot
User-agent: ClaudeBot
User-agent: CCBot
User-agent: PerplexityBot
Crawl-delay: 10
Allow: /

# ==================== 社交媒体预览 ====================
User-agent: facebookexternalhit
User-agent: Facebot
User-agent: Twitterbot
User-agent: Pinterestbot
User-agent: LinkedInBot
User-agent: WhatsApp
User-agent: TelegramBot
User-agent: Discordbot
Allow: /

# ========================================================
# 严格封禁区 (SEO工具 / 采集类 / 恶意行为)
# ========================================================

# 数据分析 / SEO 工具
User-agent: AhrefsBot
User-agent: SemrushBot
User-agent: MJ12bot
User-agent: DotBot
User-agent: BLEXBot
User-agent: DataForSeoBot
User-agent: SeznamBot
User-agent: ScreamingFrog
User-agent: SiteAuditBot
User-agent: XoviBot
User-agent: MegaIndex
User-agent: Spbot
User-agent: ZoominfoBot
User-agent: ProWebWalker
User-agent: Barkrowler
User-agent: KouContentAnalytics
Disallow: /

# 商城 / 采集 / 开发工具 (UA 伪装常客)
User-agent: Amazonbot
User-agent: AlibabaBot
User-agent: AliyunSecBot
User-agent: ShopBot
User-agent: PriceSpider
User-agent: Crawlera
User-agent: Python-urllib
User-agent: curl
User-agent: wget
User-agent: Scrapy
User-agent: PycURL
Disallow: /

# 垃圾爬虫 / 资源消耗型
User-agent: PetalBot
User-agent: Bytespider
User-agent: Exabot
User-agent: MauiBot
User-agent: SentiBot
User-agent: Trendictionbot
User-agent: Gigabot
User-agent: AspiegelBot
User-agent: BUbiNG
User-agent: CensysInspect
User-agent: GrapeshotCrawler
User-agent: NetcraftSurveyAgent
User-agent: LinkpadBot
User-agent: DomainCrawler
User-agent: Linguee
User-agent: Lipperhey
Disallow: /

# 站点地图
Sitemap: https://prawnikpabianice.pl/sitemap.xml