# robots.txt for catalogoarquitectura.cl

User-agent: *
Allow: /

# Disallow certain paths
Disallow: /cl/colaborador/
Disallow: /ar/
Disallow: /bo/
Disallow: /co/
Disallow: /ec/
Disallow: /en/
Disallow: /mx/
Disallow: /pe/
Disallow: /uy/

# Block specific bots entirely
User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: aiHitBot
User-agent: Amazonbot
User-agent: anthropic-ai
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: Brightbot 1.0
User-agent: Bytespider
User-agent: CCBot
User-agent: ChatGPT-User
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: Cotoyogi
User-agent: Crawlspace
User-agent: Diffbot
User-agent: DuckAssistBot
User-agent: Factset_spyderbot
User-agent: FirecrawlAgent
User-agent: FriendlyCrawler
User-agent: GPTBot
User-agent: iaskspider/2.0
User-agent: ICC-Crawler
User-agent: ImagesiftBot
User-agent: img2dataset
User-agent: imgproxy
User-agent: ISSCyberRiskCrawler
User-agent: Kangaroo Bot
User-agent: MistralAI-User/1.0
User-agent: NovaAct
User-agent: OAI-SearchBot
User-agent: omgili
User-agent: omgilibot
User-agent: Operator
User-agent: PanguBot
User-agent: Perplexity-User
User-agent: PerplexityBot
User-agent: PetalBot
User-agent: QualifiedBot
User-agent: Scrapy
User-agent: SemrushBot-OCOB
User-agent: SemrushBot-SWA
User-agent: Sidetrade indexer bot
User-agent: TikTokSpider
User-agent: Timpibot
User-agent: VelenPublicWebCrawler
User-agent: Webzio-Extended
User-agent: wpbot
User-agent: YouBot
User-agent: BLEXBot
Disallow: /

# Specify the location of your sitemap
Sitemap: https://www.catalogoarquitectura.cl/sitemap.xml.gz