# Blog robots.txt for blog

# Allow all user agents
User-agent: *
Allow: /
Disallow: /posts/*/upvotes

# Sitemap location
Sitemap: https://blog.pagecord.com/sitemap.xml


# Block AI training crawlers and data scrapers. AI search indexers
# (OAI-SearchBot, PerplexityBot) and user-triggered fetchers
# (ChatGPT-User, Claude-User) remain allowed so posts stay citable
# in AI answers.
# User-agent references:
# - https://github.com/ai-robots-txt/ai.robots.txt
# - https://darkvisitors.com/
User-agent: AgentTimes
User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: aiHitBot
User-agent: AIWebIndex
User-agent: Amazonbot
User-agent: anthropic-ai
User-agent: ApifyBot
User-agent: ApifyWebsiteContentCrawler
User-agent: Applebot-Extended
User-agent: Awario
User-agent: bedrockbot
User-agent: Brightbot
User-agent: Bytespider
User-agent: CCBot
User-agent: ChatGLM-Spider
User-agent: Claude-Web
User-agent: ClaudeBot
User-agent: CloudVertexBot
User-agent: cohere-training-data-crawler
User-agent: Cotoyogi
User-agent: CragCrawler
User-agent: Crawlspace
User-agent: Datenbank Crawler
User-agent: DeepSeekBot
User-agent: Diffbot
User-agent: Echobot Bot
User-agent: EchoboxBot
User-agent: ExaBot
User-agent: FacebookBot
User-agent: Factset_spyderbot
User-agent: FirecrawlAgent
User-agent: FriendlyCrawler
User-agent: Google-CloudVertexBot
User-agent: Google-Extended
User-agent: Google-Firebase
User-agent: GoogleOther
User-agent: GoogleOther-Image
User-agent: GoogleOther-Video
User-agent: GPTBot
User-agent: HenkBot
User-agent: ICC-Crawler
User-agent: ImagesiftBot
User-agent: imageSpider
User-agent: img2dataset
User-agent: ISSCyberRiskCrawler
User-agent: Kangaroo Bot
User-agent: laion-huggingface-processor
User-agent: LAIONDownloader
User-agent: LCC
User-agent: Linguee Bot
User-agent: Meta-ExternalAgent
User-agent: Mozilla-Tabstack
User-agent: MyCentralAIScraperBot
User-agent: NagetBot
User-agent: netEstate Imprint Crawler
User-agent: newsai
User-agent: omgili
User-agent: omgilibot
User-agent: PanguBot
User-agent: Panscient
User-agent: panscient.com
User-agent: Poseidon Research Crawler
User-agent: Querit-SearchBot
User-agent: QueritBot
User-agent: QuillBot
User-agent: quillbot.com
User-agent: SBIntuitionsBot
User-agent: Scrapy
User-agent: ShapBot
User-agent: Sidetrade indexer bot
User-agent: Spider
User-agent: Terra Cotta
User-agent: TerraCotta
User-agent: Thinkbot
User-agent: TikTokSpider
User-agent: Timpibot
User-agent: VelenPublicWebCrawler
User-agent: WARDBot
User-agent: Webzio-Extended
User-agent: YaK
User-agent: YandexAdditional
User-agent: YandexAdditionalBot
User-agent: YouBot
Disallow: /