Infrastructure

#
# robots.txt
#


User-agent: Orthogaffe
Disallow: /

# Crawlers that are kind enough to obey, but which we'd rather not have
# unless they're feeding search engines.
User-agent: UbiCrawler
Disallow: /

User-agent: DOC
Disallow: /

User-agent: Zao
Disallow: /

User-agent: gsa-crawler
Disallow: /

# Some bots are known to be trouble, particularly those designed to copy
# entire sites. Please obey robots.txt.
User-agent: sitecheck.internetseer.com
Disallow: /

User-agent: Zealbot
Disallow: /

User-agent: AmazonAdBot
Disallow:

User-agent: MSIECrawler
Disallow: /

User-agent: SiteSnagger
Disallow: /

User-agent: WebStripper
Disallow: /

User-agent: WebCopier
Disallow: /

User-agent: Fetch
Disallow: /

User-agent: Offline Explorer
Disallow: /

User-agent: Teleport
Disallow: /

User-agent: TeleportPro
Disallow: /

User-agent: WebZIP
Disallow: /

User-agent: linko
Disallow: /

User-agent: HTTrack
Disallow: /

User-agent: Microsoft.URL.Control
Disallow: /

User-agent: Xenu
Disallow: /

User-agent: larbin
Disallow: /

User-agent: libwww
Disallow: /

User-agent: ZyBORG
Disallow: /

User-agent: Download Ninja
Disallow: /

# Sorry, wget in its recursive mode is a frequent problem.
# Please read the man page and use it properly; there is a
# --wait option you can use to set the delay between hits,
# for instance.
#
User-agent: wget
Disallow: /

#
# The 'grub' distributed client has been *very* poorly behaved.
#
User-agent: grub-client
Disallow: /

#
# Doesn't follow robots.txt anyway, but...
#
User-agent: k2spider
Disallow: /

#
# Hits many times per second, not acceptable
# http://www.nameprotect.com/botinfo.html
User-agent: NPBot
Disallow: /

# A capture bot, downloads gazillions of pages with no public benefit
# http://www.webreaper.net/
User-agent: WebReaper
Disallow: /

User-agent: CNCDialer
Disallow: /

User-agent: Maxthon
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: Slurp
Disallow: /


User-agent: *

Disallow: /wp-content/
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wpi/
Disallow: /trackback/
Disallow: /*/*/*/feed.xml
Allow: /retro/*
Disallow: /retro
Disallow: /login.php/
Disallow: /frontend.php/
Disallow: /api/1.0/migration
Disallow: /server
Disallow: /queue
Disallow: /mobile.php/
Disallow: /app.php/
Disallow: /main.php/
#Disallow: /redirect
Disallow: /approve
Disallow: /duplicate
Disallow: /1018282
Disallow: /api/
Disallow: /c/
Disallow: /morepostcomments
Disallow: /offtopic
Disallow: /pda
Disallow: /preview-main/*
Disallow: /tracker
Disallow: /clubcampusparty
Disallow: /entraenatrix
Disallow: /espaciohpultrabook
Disallow: /espaciohtcone
Disallow: /espaciohuawei
Disallow: /espaciolgseriex
Disallow: /espaciolumia
Disallow: /espacionokia
Disallow: /espaciotecnologiasford
Disallow: /espaciotoshiba
Disallow: /lgmobile
Disallow: /espaciovisa
Disallow: /movistartv
Disallow: /mundogalaxy
Disallow: /nuevoestilodeti
Disallow: /philipssmarttv
Disallow: /tecnologiakia
Disallow: /vivephilipstv
Disallow: /vodafoneadslafondo
Disallow: /wishlistpremiosxataka
Disallow: /.well-known/amphtml/apikey.pub
Disallow: /expertos/respuestas/*
Disallow: /usuario/*
Disallow: /busqueda?
Disallow: /search?q=
Disallow: /frontend_dev.php/
# Disallow: /la-cacharreria/search*?*


Sitemap: https://www.xataka.com/sitemap_news.xml
Sitemap: https://www.xataka.com/club/sitemap.xml
Sitemap: https://www.xataka.com/sitemap_index.xml

# ==========================================
# BLOCK LLM & SCRAPERS
# ==========================================

User-agent: AI2Bot
Disallow: /

User-agent: ChatGLM
Disallow: /

User-agent: ChatGLM-Spider
Disallow: /

User-agent: cohere-training-data-crawler
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: OmigiliBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: YouBot
Disallow: /

# ==========================================
# NOTA INTERNA: BOTS AUTORIZADOS (NO BLOQUEADOS)
# Según la tabla de directrices, tienen acceso permitido:
# Applebot-Extended, Bytespider, CCBot, ClaudeBot, GPTBot, 
# Meta-ExternalAgent, ChatGPT-User, Claude-SearchBot, 
# Claude-User, OAI-SearchBot, Perplexity-User, PerplexityBot.
# (ChatGLM aparece duplicado en origen; se ha bloqueado por seguridad).
# ==========================================