# nendoaddicts.be
# Search engines welcome. AI training/assistant crawlers, data scrapers and
# aggressive SEO/marketing bots are disallowed. (Hard enforcement is at the
# Cloudflare edge; this file is the compliant-bot opt-out.)

User-agent: *
Content-Signal: search=yes, ai-train=no, ai-input=no
Allow: /wp-content/uploads/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-admin/
Disallow: /wp-includes/

# --- AI training / AI assistant crawlers ---
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: ClaudeBot
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: anthropic-ai
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: Meta-ExternalAgent
User-agent: meta-externalagent
User-agent: FacebookBot
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: cohere-ai
User-agent: DuckAssistBot
User-agent: YouBot
User-agent: Ai2Bot
User-agent: Ai2Bot-Dolma
User-agent: PanguBot
User-agent: iaskspider
User-agent: iaskspider/2.0
Disallow: /

# --- Data scrapers / extraction / archiving bots ---
User-agent: amazon-kendra
User-agent: Arquivo-web-crawler
User-agent: coccocbot-web
User-agent: bravest
User-agent: BLEXBot
User-agent: Barkrowler
User-agent: Bytespider
User-agent: CCBot
User-agent: Cotoyogi
User-agent: Crawl4AI
User-agent: Crawlspace
User-agent: Diffbot
User-agent: Echobot Bot
User-agent: EchoboxBot
User-agent: FactSet-SpyderBot
User-agent: FirecrawlAgent
User-agent: Firecrawl
User-agent: FriendlyCrawler
User-agent: ICC-Crawler
User-agent: ISSCyberRiskCrawler
User-agent: ImagesiftBot
User-agent: Jenkersbot
User-agent: Kangaroo Bot
User-agent: LivelapBot
User-agent: MauiBot
User-agent: MoodleBot
User-agent: NewsNow
User-agent: NovaAct
User-agent: Poseidon Research Crawler
User-agent: QualifiedBot
User-agent: Scrapy
User-agent: SeekportBot
User-agent: Seekr
User-agent: SeekrBot
User-agent: TaraGroup Intelligent Bot
User-agent: Timpibot
User-agent: Turnitin
User-agent: VelenPublicWebCrawler
User-agent: Webzio-Extended
User-agent: crawler4j
User-agent: hada-news
User-agent: iMediaEthics-org
User-agent: imgproxy
User-agent: magpie-crawler
User-agent: netEstate Imprint Crawler
User-agent: news-please
User-agent: Omgili
User-agent: Omgilibot
User-agent: YaCy
User-agent: yacybot
Disallow: /

# --- SEO / marketing scrapers ---
User-agent: AhrefsBot
User-agent: SemrushBot
User-agent: MJ12bot
User-agent: DotBot
User-agent: rogerbot
User-agent: BLEXBot
User-agent: DataForSeoBot
User-agent: PetalBot
User-agent: MegaIndex
User-agent: SEOkicks
User-agent: Awario
User-agent: AwarioRssBot
User-agent: AwarioSmartBot
Disallow: /

Sitemap: https://nendoaddicts.be/sitemap_index.xml