# ============================================================
# robots.txt – Optimized for WordPress
# Last updated: 2025
# ============================================================


# ============================================================
# GLOBAL BASE RULES
# ============================================================
User-agent: *

# WordPress System Files & Admin
Disallow: /wp-admin/
Allow:    /wp-admin/admin-ajax.php
Disallow: /wp-includes/
Disallow: /wp-login.php
Disallow: /wp-register.php
Disallow: /xmlrpc.php
Disallow: /readme.html
Disallow: /license.txt
Disallow: /wp-config.php
Disallow: /wp-cron.php
Disallow: /wp-mail.php
Disallow: /wp-trackback.php

# WordPress Upload Exploits
Disallow: /wp-content/uploads/wpo-plugins-tables-list.json

# Author Archives (User Enumeration Prevention)
Disallow: /author/
Disallow: /?author=
Disallow: /*?author=

# Search & Pagination
Disallow: /?s=
Disallow: /*?s=
Disallow: /search/
Disallow: /page/
Disallow: /*?paged=
Disallow: /*?page=

# Noisy Query Parameters
Disallow: /*?p=
Disallow: /*&p=
Disallow: /*?preview=
Disallow: /*?attachment_id=
Disallow: /*?filtering=
Disallow: /*?replytocom=
Disallow: /*/disclaimer/

# Feeds (optional – remove if you want feeds indexed)
Disallow: /feed/
Disallow: /*/feed/
Disallow: /comments/feed/

# Allow Static Assets (CSS, JS, Images)
Allow: /*.css$
Allow: /*.js$
Allow: /*.jpg$
Allow: /*.jpeg$
Allow: /*.png$
Allow: /*.gif$
Allow: /*.webp$
Allow: /*.svg$
Allow: /*.ico$
Allow: /*.bmp$
Allow: /*.woff$
Allow: /*.woff2$

# Allow Ads & App Ads
Allow: /ads.txt
Allow: /app-ads.txt


# ============================================================
# MAJOR SEARCH ENGINES – Full Access
# ============================================================
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: Yandex
Allow: /

User-agent: Sogou
Allow: /

User-agent: Exabot
Allow: /


# ============================================================
# AI BOTS – Full Access (Explicitly Allowed)
# ============================================================

# OpenAI / ChatGPT
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

# Anthropic / Claude
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Google AI
User-agent: Google-Extended
Allow: /

# Meta AI
User-agent: Meta-ExternalAgent
Allow: /

User-agent: FacebookBot
Allow: /

# Apple
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Amazon / Alexa
User-agent: Amazonbot
Allow: /

# Microsoft / Copilot
User-agent: Bingbot
Allow: /

# You.com
User-agent: YouBot
Allow: /

# Phind
User-agent: PhindBot
Allow: /

# AI2 / Allen Institute
User-agent: AI2Bot
Allow: /

# Cohere
User-agent: cohere-ai
Allow: /

# Diffbot
User-agent: Diffbot
Allow: /

# Common Crawl (used by many AI training datasets)
User-agent: CCBot
Allow: /

# Bytedance
User-agent: Bytespider
Allow: /


# ============================================================
# SCRAPER & GENERIC BOT PROTECTION
# ============================================================
User-agent: python-requests
Allow: /

User-agent: curl
Allow: /

User-agent: wget
Allow: /

User-agent: libwww-perl
Allow: /

User-agent: Go-http-client
Allow: /

User-agent: Apache-HttpClient
Allow: /

User-agent: Scrapy
Allow: /

User-agent: Java
Allow: /

User-agent: MJ12bot
Allow: /

User-agent: DotBot
Allow: /

User-agent: AhrefsBot
Allow: /

User-agent: SemrushBot
Allow: /

User-agent: MajesticSEO
Allow: /

User-agent: BLEXBot
Allow: /


# ============================================================
# SITEMAP
# ============================================================
Sitemap: https://workdigital.de/sitemap_index.xml