#
# robots.txt - Control de acceso para crawlers
# Actualizado: Agosto 2025
#


User-agent: *
Allow: /
Disallow: /300x250_1/
Disallow: /300x250_2/
Disallow: /300x250_3/
Disallow: /300x250_4/
Disallow: /layer/
Disallow: /Skyscrapper/
Disallow: /bottom/
Disallow: /footer/
Disallow: /skin/
Disallow: /top/
Disallow: /customer-preview/

# Bots que consumen muchos recursos sin beneficio SEO
User-agent: HTTrack
Disallow: /

User-agent: WebZIP
Disallow: /

User-agent: WebCopier
Disallow: /

User-agent: Teleport
Disallow: /

User-agent: TeleportPro
Disallow: /

User-agent: Offline Explorer
Disallow: /

User-agent: SiteSnagger
Disallow: /

User-agent: WebStripper
Disallow: /

User-agent: WebReaper
Disallow: /

User-agent: wget
Disallow: /

User-agent: larbin
Disallow: /

User-agent: libwww
Disallow: /


User-agent: grapeshot
Disallow: 

User-agent: PetalBot
Allow: /

User-agent: facebookexternalhit
Allow: /

Sitemap: https://www.publinews.gt/arc/outboundfeeds/google-news-feed/?outputType=xml
Sitemap: https://www.publinews.gt/arc/outboundfeeds/sitemap-index/?outputType=xml
Sitemap: https://www.publinews.gt/arc/outboundfeeds/sitemap/latest/?outputType=xml
Sitemap: https://www.publinews.gt/arc/outboundfeeds/news/deportes/?outputType=xml
Sitemap: https://www.publinews.gt/arc/outboundfeeds/news/entretenimiento/?outputType=xml
Sitemap: https://www.publinews.gt/arc/outboundfeeds/news/noticias/?outputType=xml