# llms.txt for informedclearly.com
site: https://informedclearly.com
owner: Informed Clearly
contact: https://informedclearly.com/contact
last-updated: 2025-09-10
version: 1.0

# Crawl etiquette
crawl-delay: 5s
rate-limit: 1 rps
max-parallel: 2

languages:
  - en
  - nl
  - fr
  - de
  - es
  - pt

# Allowed public content
allow:
  - /                               # root
  - /{lang}/                        # language homes
  - /{lang}/news/{page}/            # listing (pagination)
  - /{lang}/articles/{page}/        # listing (pagination)
  - /{lang}/{category}/             # category landing
  - /{lang}/{category}/{page}/      # category pagination
  - /{lang}/{category}/{id}/{slug}.html  # detail
  - /authors
  - /{lang}/authors/{author-slug}
  - /feed/atom
  - /feed/atom/{lang}
  - /feed/rss
  - /feed/rss/{lang}
  - /sitemap.xml
  - /sitemap-*.xml
  - /sitemap-news.xml
  - /sitemap-categories.xml
  - /sitemap-static.xml
  - /site.webmanifest
  - /robots.txt

# Do NOT crawl or use these for training
disallow:
  - /submit-url
  - /submit-url-status
  - /image_upload
  - /track-page
  - /like/
  - /dislike/
  - /static/news_image/             # no image downloads/rehosting
  # Optional:
  # - /search                        # disallow generic crawling of search

# Category slug normalization
category-slug: lowercase, spaces->hyphens

# Pagination guidance
pagination:
  - path_pattern: /{lang}/news/{page}/
    first_page: /{lang}/news/1/
    rel_links: true
  - path_pattern: /{lang}/articles/{page}/
    first_page: /{lang}/articles/1/
    rel_links: true
  - path_pattern: /{lang}/{category}/{page}/
    first_page: /{lang}/{category}/1/
    rel_links: true

# Canonicals & duplicates
canonicals:
  - detail_pages: /{lang}/{category}/{id}/{slug}.html

# Usage policy for LLMs
usage-policy:
  text:
    - Summarize or quote short passages with attribution to "Informed Clearly".
    - Do not reproduce full articles.
  images:
    - Do not download, store, or rehost images from /static/news_image/.
    - Use alt text or link to the page instead.
  attribution:
    - 'Source: Informed Clearly — {title} ({url})'
  # Optional stricter clauses:
  # training: prohibited
  # retention: cache-only; max-age: 30d

# Freshness
refresh:
  listing_pages: 12h
  detail_pages: 24h

# Query parameters
query-params:
  keep:
    - q
  drop:
    - utm_*
    - ref

# Sitemaps
sitemaps:
  - https://informedclearly.com/sitemap.xml