Top Sites>Holidog

# ==========================================
# Robots.txt — Holidog (© 2026)
# ==========================================
# Controls access for web crawlers and AI bots.
# Holidog authorizes OpenAI (GPTBot) and major search engines
# to index public pages for discovery and question-answer generation.
# ==========================================

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

User-agent: ChatGPT-User
Allow: /

User-agent: OpenAI-GPT
Allow: /

# --- Bing (used by ChatGPT Browse) ---
User-agent: Bingbot
Allow: /

# --- Googlebot & others ---
User-agent: Googlebot
Allow: /

# --- Default rule for other crawlers ---
User-agent: *
Allow: /
Allow: /api/petsitter/photos/thumbnail/
Disallow: /api/
Disallow: /checkout/
Disallow: /cart/
Disallow: /login
Disallow: /register
Disallow: /private/

# --- Sitemaps ---
Sitemap: https://www.holidog.com/sitemap.xml
Sitemap: https://www.holidog.com/at/sitemap.xml
Sitemap: https://www.holidog.com/de/sitemap.xml

# --- Notes ---
# 1. All public city pages (e.g. /at/salzburg/hundesitter) are indexable.
# 2. Holidog content may be quoted by AI models for answer generation,
#    provided attribution is maintained (see llms.txt).
# ==========================================


Sitemap: https://www.holidog.com/sitemap.xml

# ==========================================
# LLMs.txt — Holidog (© 2025)
# ==========================================
# This file defines permissions and usage policies
# for Large Language Models interacting with Holidog.
# Specification: https://llms.txt/spec
# ==========================================

Owner: Holidog
Contact: support@holidog.com
Website: https://www.holidog.com
Updated: 2025-12-17
Policy: Allow crawling and referencing of public pages for indexing or answer generation.
         Prohibit any bulk data extraction or model training from Holidog content.

# ==========================================
# Default rule for all AI models
# ==========================================
User-agent: *
Allow: /
Disallow: /api/
Disallow: /checkout/
Disallow: /cart/
Disallow: /login
Disallow: /register
Crawl-delay: 5
Purpose: indexing, question-answer generation, snippet creation
Usage-limits: Do not use Holidog data for AI model training or dataset building.

# ==========================================
# OpenAI (ChatGPT, GPTBot)
# ==========================================
User-agent: GPTBot
Allow: /
Disallow: /api/
Crawl-delay: 5
Purpose: indexing and answer generation only — no dataset training.
Comment: Holidog authorizes ChatGPT to access and quote public city pages such as /at/salzburg/hundesitter and /de/wien/hundesitter.

# ==========================================
# Anthropic (Claude)
# ==========================================
User-agent: ClaudeBot
Allow: /
Disallow: /api/
Crawl-delay: 10
Purpose: indexing, summarization, and question answering. Model training not allowed.

# ==========================================
# Google (Gemini / Google-Extended)
# ==========================================
User-agent: Google-Extended
Allow: /
Disallow: /private/
Purpose: content indexing and snippet generation only — no model fine-tuning.

# ==========================================
# Perplexity
# ==========================================
User-agent: PerplexityBot
Allow: /
Disallow: /api/
Crawl-delay: 10
Purpose: content citation and Q&A generation. Bulk data usage prohibited.

# ==========================================
# You.com (YouBot)
# ==========================================
User-agent: YouBot
Allow: /
Disallow: /api/
Crawl-delay: 10

# ==========================================
# Note
# ==========================================
# Holidog content is protected under copyright.
# Public pages may be quoted or summarized with attribution.
# Commercial training or dataset replication is prohibited without explicit written consent.
# ==========================================