# As a condition of accessing this website, you agree to abide by the
# following content signals:
# (a) If a content-signal = yes, you may collect content for the
# corresponding use.
# (b) If a content-signal = no, you may not collect content for the
# corresponding use.
# (c) If the website operator does not include a content signal for a
# corresponding use, the website operator neither grants nor restricts
# permission via content signal with respect to the corresponding use.
# The content signals and their meanings are:
# search: building a search index and providing search results (e.g., returning
# hyperlinks and short excerpts from your website's contents). Search
# does not include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
# augmented generation, grounding, or other real-time taking of
# content for generative AI search answers).
# ai-train: training or fine-tuning AI models.
# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.
# Sitemap
Sitemap: https://www.worldhistory.org/sitemap.xml
# Default Bots
User-agent: *
Content-signal: search=yes, ai-train=no, ai-input=yes
Allow: /
Disallow: /admin/
Disallow: /include/
Disallow: /logout/
Disallow: /moderate/
Disallow: /cdn-cgi/
Disallow: /xres/add/
Disallow: /related/
Disallow: /trans/x/
Disallow: /sponsoranalytics/
Disallow: /analytics/
Allow: /search/$
Disallow: /search/?*
Allow: /map/$
Disallow: /map/*/*
Allow: /interestemails/
Disallow: /interestemails/?*
# Specific Bots
User-agent: PerplexityBot
User-agent: Perplexity‑User
User-agent: ProRataInc
Content-signal: search=yes, ai-train=yes, ai-input=yes
Allow: /
Disallow: /books/*/
# Advertising Bots
User-agent: AdsBot-Google
Allow: /
User-agent: AmazonAdBot
Allow: /
User-agent: Bidswitchbot
Allow: /
User-agent: CriteoBot
Allow: /
User-agent: DoubleVerifyBot
Allow: /
User-agent: DVBot
Allow: /
User-agent: Grapeshot
Allow: /
User-agent: Gumgum
Allow: /
User-agent: IAS_admantx
Allow: /
User-agent: IAS_crawler
Allow: /
User-agent: IAS_wombles
Allow: /
User-agent: Leikibot
Allow: /
User-agent: Mediapartners-Google
Allow: /
User-agent: Opebot-v
Allow: /
User-agent: Peer39_crawler
Allow: /
User-agent: Proximic
Allow: /
User-agent: PubMatic Crawler Bot
Allow: /
User-agent: SinceraSyntheticUser
Allow: /
User-agent: SlickBot
Allow: /
User-agent: TTD-Content
Allow: /
robots.txt