# robots.txt hermanodeleche.com
# IPS 4.7 + HestiaCP
# Actualizado: 2026-04

User-Agent: *

# === Acciones/formularios sin contenido único ===
Disallow: /startTopic/
Disallow: /markallread/
Disallow: /*?do=add
Disallow: /*?do=submit
Disallow: /*?do=email
Disallow: /*?do=findComment
Disallow: /*?do=getLastComment
Disallow: /*?do=getNewComment
Disallow: /*?do=reportComment
Disallow: /*?do=embed
Disallow: /*?advancedSearchForm=

# === URLs legacy de IPS que generan redirects 301 (11.5% del crawl budget) ===
Disallow: /*?app=core&do=find
Disallow: /*&do=find
Disallow: /*?app=core&module=system&controller=content

# === Paginación y filtros (duplicate content) ===
Disallow: /*?sortby=
Disallow: /*?filter=
Disallow: /*?tab=comments

# === Áreas internas sin valor SEO ===
Disallow: /staff/
Disallow: /online/
Disallow: /leaderboard/
Disallow: /discover/
Disallow: /search/
Disallow: /messenger/
Disallow: /notifications/
Disallow: /modcp/
Disallow: /admin/
Disallow: /applications/
Disallow: /cgi-bin/

# === URLs con extensión .xml residuales ===
Disallow: /*.xml/

# === NO BLOQUEAR todavía (esperar meta noindex + desindexación) ===
# Estas se activarán después de 8-12 semanas con noindex aplicado:
# Disallow: /profile/
# Disallow: /login/
# Disallow: /register/
# Disallow: /lostpassword/

# === Assets estáticos - permitir ===
Allow: /uploads/
Allow: /*.css$
Allow: /*.js$
Allow: /*.jpg$
Allow: /*.jpeg$
Allow: /*.png$
Allow: /*.gif$
Allow: /*.webp$
Allow: /*.svg$

# === Sitemap ===
Sitemap: https://hermanodeleche.com/sitemap.php

# === Bloqueo de scrapers conocidos (preservado de versión anterior) ===
User-agent: UbiCrawler
Disallow: /
User-agent: DOC
Disallow: /
User-agent: Zao
Disallow: /
User-agent: sitecheck.internetseer.com
Disallow: /
User-agent: Zealbot
Disallow: /
User-agent: MSIECrawler
Disallow: /
User-agent: SiteSnagger
Disallow: /
User-agent: WebStripper
Disallow: /
User-agent: WebCopier
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: /
User-agent: wget
Disallow: /
User-agent: grub-client
Disallow: /
User-agent: k2spider
Disallow: /
User-agent: NPBot
Disallow: /
User-agent: WebReaper
Disallow: /