User-agent: *
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
DisallowAITraining: /

Sitemap: https://social.emucafe.org/sitemap.xml
Sitemap: https://social.emucafe.org/sitemap-news.xml

Disallow: /*/feed
Disallow: /*/feed$
Allow: /feed
Allow: /feed/atom
Allow: /feed/json
Allow: /feed/twtxt
Allow: /feed/mf2
Allow: /feed/jf2
Allow: /feed/as1
Allow: /feed/as2

# Agents
User-agent: Manus-User
User-agent: TwinAgent
Disallow: /

# Assistants
User-agent: AI2Bot-DeepResearchEval
User-agent: bigsur.ai
User-agent: GeistHaus-PageFetcher
User-agent: PhindBot
Disallow: /

# Data Providers
User-agent: ApifyBot
User-agent: ApifyWebsiteContentCrawler
User-agent: Brightbot
User-agent: CragCrawler
User-agent: Crawlspace
User-agent: Diffbot
User-agent: ExaBot
User-agent: FirecrawlAgent
User-agent: HenkBot
User-agent: Querit
User-agent: Querit-SearchBot
User-agent: ShapBot
User-agent: TavilyBot
User-agent: Terra Cotta
User-agent: TerraCotta
User-agent: YouBot
Disallow: /

# AI Data Scrapers
User-agent: AI2Bot
User-agent: AI2Bot-Dolma
User-agent: AmazonBot
User-agent: bedrockbot
User-agent: Bytespider
User-agent: ChatGLM-Spider
User-agent: ClaudeBot
User-agent: cohere-training-data-crawler
User-agent: CohereBot
User-agent: Cotoyogi
User-agent: Datenbank Crawler
User-agent: DeepSeekBot
User-agent: Doubaobot
User-agent: ERNIEBot
User-agent: FacebookBot
User-agent: ICC-Crawler
User-agent: imageSpider
User-agent: Kangaroo Bot
User-agent: KimiBot
User-agent: KimiCrawler
User-agent: laion-huggingface-processor
User-agent: meta-externalagent
User-agent: micro-crawl
User-agent: MistralBot
User-agent: MoonshotBot
User-agent: MoonSpider
User-agent: omgili
User-agent: PanguBot
User-agent: ReflectionBot
User-agent: SalamandraVLM
User-agent: SBIntuitionsBot
User-agent: Spider
User-agent: TimpiBot
User-agent: VelenPublicWebCrawler
User-agent: webzio-extended
Disallow: /

# AI Search
User-agent: AIWebIndex
User-agent: AIWebIndex-Agents
Disallow: /

# Automated Agents
User-agent: Amazon Bedrock AgentCore Browser
Disallow: /

# Fetchers
User-agent: TikTokSpider
Disallow: /

# Intelligence Gatherers
User-agent: Amazing-SearchBot
User-agent: AmazingTest-SearchBot
User-agent: Awario
User-agent: AwarioBot
User-agent: AwarioSmartBot
User-agent: YaK
Disallow: /

# Scrapers
User-agent: Nutch
User-agent: Scrapy
User-agent: Thinkbot
User-agent: ZoominfoBot
Disallow: /

# SEO
User-agent: Barkrowler
User-agent: DataForSEO
User-agent: DataForSEO Bot
User-agent: DataForSEOBot
Disallow: /

# Misc
User-agent: AionBot
User-agent: BriskBot
User-agent: CodeMMPretrainCrawler
User-agent: HaloBot
User-agent: Jetfuel-Public-Dataset-Acquisition
User-agent: MathPicDatasetCrawler
User-agent: NavCrawl
User-agent: QlyzeBot
User-agent: RSSAmplifierBot
User-agent: Somethinggbot
User-agent: supjav
User-agent: ZeroBot
Disallow: /

## Extra
User-agent: Applebot-Extended
User-agent: Google-Extended
Disallow: /

## Crawl Delay 30

User-agent: Ahrefs
User-agent: Buck
User-agent: DotBot
User-agent: MJ12bot
User-agent: rogerbot
User-agent: SemrushBot
User-agent: SemrushBot-BA
User-agent: SERankingBacklinksBot
User-agent: siteexplorer
Crawl-delay: 30

## Specific Crawler Rules

User-agent: Amzn-SearchBot
Disallow: /feed/
Disallow: /category/
Disallow: /page/
Disallow: /tag/
Disallow: /wp-content/
Disallow: /wp-json/
Disallow: /2020/
Disallow: /2021/
Disallow: /2022/
Disallow: /2023/
Disallow: /2024/
Disallow: /2025/
Disallow: /2026/