Takeda-adhs.de - SEO Check

Meta Tags

Medienliste

Überschriftenstruktur

Gefundene Links auf dieser Seite

HTTP-Header

Links von Wikipedia

• Lisdexamfetamin

Robots.txt

#
# robots.txt
#
# This file is to prevent the crawling and indexing of certain parts
# of your site by web crawlers and spiders run by sites like Yahoo!
# and Google. By telling these "robots" where not to go on your site,
# you save bandwidth and server resources.
#
# This file will be ignored unless it is at the root of your host:
# Used:    http://example.com/robots.txt
# Ignored: http://example.com/site/robots.txt
#
# For more information about the robots.txt standard, see:
# http://www.robotstxt.org/robotstxt.html

User-agent: *
# CSS, JS, Images
Allow: /core/*.css$
Allow: /core/*.css?
Allow: /core/*.js$
Allow: /core/*.js?
Allow: /core/*.avif
Allow: /core/*.gif
Allow: /core/*.jpg
Allow: /core/*.jpeg
Allow: /core/*.png
Allow: /core/*.svg
Allow: /core/*.webp
Allow: /profiles/*.css$
Allow: /profiles/*.css?
Allow: /profiles/*.js$
Allow: /profiles/*.js?
Allow: /profiles/*.avif
Allow: /profiles/*.gif
Allow: /profiles/*.jpg
Allow: /profiles/*.jpeg
Allow: /profiles/*.png
Allow: /profiles/*.svg
Allow: /profiles/*.webp
# Directories
Disallow: /core/
Disallow: /profiles/
# Files
Disallow: /README.md
Disallow: /composer/Metapackage/README.txt
Disallow: /composer/Plugin/ProjectMessage/README.md
Disallow: /composer/Plugin/Scaffold/README.md
Disallow: /composer/Plugin/VendorHardening/README.txt
Disallow: /composer/Template/README.txt
Disallow: /modules/README.txt
Disallow: /sites/README.txt
Disallow: /themes/README.txt
# Paths (clean URLs)
Disallow: /admin/
Disallow: /comment/reply/
Disallow: /filter/tips
Disallow: /node/add/
Disallow: /search/
Disallow: /search?
Disallow: /user/register
Disallow: /user/password
Disallow: /user/login
Disallow: /user/logout
Disallow: /media/oembed
Disallow: /*/media/oembed
# Paths (no clean URLs)
Disallow: /index.php/admin/
Disallow: /index.php/comment/reply/
Disallow: /index.php/filter/tips
Disallow: /index.php/node/add/
Disallow: /index.php/search/
Disallow: /index.php/search?
Disallow: /index.php/user/password
Disallow: /index.php/user/register
Disallow: /index.php/user/login
Disallow: /index.php/user/logout
Disallow: /index.php/media/oembed
Disallow: /index.php/*/media/oembed

# ===================================================
# 1. BLOCK PURE TRAINING BOTS (No model training)
# ===================================================
 
# OpenAI (ChatGPT training)
User-agent: GPTBot
Disallow: /
 
# Anthropic (Claude training)
User-agent: ClaudeBot
Disallow: /
 
# Google Gemini training
# Blocks AI training, not Google Search.
User-agent: Google-Extended
Disallow: /
 
# Meta (Llama training)
User-agent: Meta-ExternalAgent
Disallow: /
 
# Apple Intelligence training
User-agent: Applebot-Extended
Disallow: /
 
# Amazon Web Services AI training
User-agent: Amazonbot
Disallow: /
 
# Grok / xAI training
User-agent: xai-crawler
Disallow: /
 
# ByteDance / TikTok AI training
User-agent: Bytespider
Disallow: /
 
# Cohere enterprise AI models
User-agent: cohere-ai
Disallow: /
 
# Large-scale training datasets (Common Crawl & LAION)
User-agent: CCBot
Disallow: /
 
User-agent: OAI-SearchBot-WD
Disallow: /
 
# Other aggressive AI scrapers, e.g. Diffbot / Images_AI
User-agent: Diffbot
Disallow: /
 
User-agent: Image2Dataset
Disallow: /
 
 
# ===================================================
# 2. ALLOW SEARCH, RAG AND USER-TRIGGERED RETRIEVAL BOTS
# ===================================================
 
# OpenAI ChatGPT Search and live user requests
User-agent: OAI-SearchBot
Allow: /
 
User-agent: ChatGPT-User
Allow: /
 
# Perplexity AI search engine / search indexing blocked
User-agent: PerplexityBot
Disallow: /
 
# Perplexity user-triggered retrieval allowed
User-agent: Perplexity-User
Allow: /
 
# Meta AI web search and live citations
User-agent: Meta-WebIndexer
Allow: /
 
User-agent: Meta-ExternalFetcher
Allow: /
 
# Anthropic Claude live search / user retrieval
User-agent: Claude-SearchBot
Allow: /
 
User-agent: Claude-User
Allow: /
 
# You.com search engine
User-agent: YouBot
Allow: /
 
 
# ===================================================
# 3. CLASSIC SEARCH ENGINES (Google & Bing)
# ===================================================
 
User-agent: Googlebot
Allow: /
 
User-agent: Bingbot
Allow: /

# ===================================================
# ADD SITEMAP
# ===================================================
Sitemap: https://www.takeda-adhs.de/sitemap.xml

Suchvorschau