# ==================================================
# FD.nl Robots.txt (FD-optimized v2.1)
# ==================================================

# AI & TDM OPT-OUT
# Machine-readable policy:
# https://fd.nl/.well-known/ai-policy
# https://fd.nl/.well-known/tdm-policy.json
# Alternate path (W3C TDMRep standard):
# https://fd.nl/.well-known/tdmrep.json

# All use of FD content is subject to the Terms & Conditions and Copyright
# Policy outlined on FD.nl.
#
# Scraping, harvesting, or any other form of data or text mining, machine learning,
# or artificial intelligence purposes — including the training or development of AI
# technologies or machine learning language models using FD content — is expressly
# prohibited.
#
# Prohibited uses include but are not limited to:
# (1) text and data mining activities under Art. 4 of the EU Directive on Copyright in
# the Digital Single Market;
# (2) the development of any software, machine learning, artificial intelligence (AI),
# and/or large language models (LLMs);
# (3) creating or providing archived or cached data sets containing our content to others; and/or
# (4) any commercial purposes.
# Contact zakelijk@fd.nl for assistance.
#
# Visit https://fdmg.nl/content/uploads/2021/06/AV_Abonnementen.pdf for our Terms and Conditions.
# Visit https://fd.nl/copyright for our Copyright Policy.
# For any licensing queries, please contact zakelijk@fd.nl.

##########################################
# A. GENERAL RULES FOR ALL BOTS
##########################################

User-agent: *
Crawl-Delay: 1

# Query / facet / sort combinations
Disallow: /search?*

# Logged-in / personalized areas & auth flows
Disallow: /mijn-nieuws
Disallow: /login
Disallow: /logout
Disallow: /mijn-fd
Disallow: /registreren
Disallow: /register*
# Filetypes
Disallow: /*.pdf$

##########################################
# B. SEARCH / NEWS SPECIALS
##########################################
User-agent: Googlebot-Image
Allow: /image/
##########################################
# C. AI / LLM / TRAINING / GENERATIVE
##########################################
User-agent: GPTBot
Disallow: /
User-agent: ChatGPT-User
Disallow: /
User-agent: OAI-SearchBot
Disallow: /
User-agent: anthropic-ai
Disallow: /
User-agent: Claude-Web
Disallow: /
User-agent: ClaudeBot
Disallow: /
User-agent: Claude-SearchBot
Disallow: /
User-agent: Claude-User
Disallow: /
User-agent: Google-Extended
Disallow: /
User-agent: GoogleOther
Disallow: /
User-agent: Applebot-Extended
Disallow: /
User-agent: Amazonbot
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: cohere-ai
Disallow: /
User-agent: cohere-training-data-crawler
Disallow: /
User-agent: DuckAssistBot
Disallow: /
User-agent: MistralAI-User
Disallow: /
User-agent: AI2Bot
Disallow: /
User-agent: Gemini-Deep-Research
Disallow: /
User-agent: Webzio-Extended
Disallow: /
User-agent: MyCentralAIScraperBot
Disallow: /
User-agent: PerplexityBot
Disallow: /
User-agent: Perplexity-User
Disallow: /
User-agent: Scrapy
Disallow: /
# Common dataset crawlers
User-agent: CCBot
Disallow: /
##########################################
# D. AD MANAGER / ADSENSE CRAWLER ACCESS
##########################################
User-agent: Mediapartners-Google
Crawl-Delay: 1
Allow: /

##########################################
# E. META / FACEBOOK SCRAPING & AI
##########################################
User-agent: facebookbot
Disallow: /
User-agent: FacebookBot
Disallow: /
User-agent: Meta-ExternalAgent
Disallow: /
User-agent: meta-externalagent
Disallow: /
User-agent: Meta-ExternalFetcher
Disallow: /
User-agent: meta-externalfetcher
Disallow: /
##########################################
# F. DATA / MEDIA INTELLIGENCE / AGGREGATORS
##########################################
User-agent: Meltwater
Disallow: /
User-agent: TweetmemeBot
Disallow: /
User-agent: linkfluence
Disallow: /
User-agent: Cision
Disallow: /
User-agent: LexisNexis
Disallow: /
User-agent: Talkwater
Disallow: /
User-agent: Jetbot
Disallow: /
User-agent: Newzbin
Disallow: /
User-agent: flipboard
Disallow: /
User-agent: NewsNow
Disallow: /
User-agent: Diffbot
Disallow: /
User-agent: magpie-crawler
Disallow: /
User-agent: omgili
Disallow: /
User-agent: omgilibot
Disallow: /
User-agent: archive.org_bot
Disallow: /
User-agent: ia_archiver
Disallow: /
##########################################
# SITEMAPS
##########################################

Sitemap: https://fd.nl/sitemap/sitemap_index.xml
Sitemap: https://fd.nl/sitemap/sitemap_google_news.xml
Sitemap: https://fd.nl/sitemap/sitemap-journalist.xml
Sitemap: https://fd.nl/sitemap/sitemap-tags.xml
