Free tools

Robots.txt Examples

Robots.txt file content for theathletic.com.

Robot.txt file for: theathletic.com

      # New York Times content is made available for your personal, non-commercial
# use subject to our Terms of Service here:
# https://help.nytimes.com/hc/en-us/articles/115014893428-Terms-of-Service.
# Use of any device, tool, or process designed to data mine or scrape the content
# using automated means is prohibited without prior written permission from
# The New York Times Company.  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 https://nytlicensing.com/contact/ for assistance.

# General Rules
User-agent: *
User-agent: Googlebot
Disallow: /wp/wp-admin/
Allow: /wp/wp-admin/admin-ajax.php
Disallow: /async-*
Disallow: /search/*
Allow: /search/$
Disallow: /checkout/
Disallow: /checkout?plan_id*
Allow: /checkout/$
Disallow: /checkout2*
Disallow: /login/
Disallow: /login?login_source*
Disallow: /login?ref_page*
Allow: /login/$
Disallow: /login2/
Disallow: /login2?login_source*
Disallow: /login2?ref_page*
Allow: /login2/$
Disallow: /report/
Disallow: /*/discuss/*
Disallow: /register/
Disallow: /register?welcome_redirect*
Disallow: /register2/
Disallow: /register2?welcome_redirect*
Disallow: /betmgm-redirect*
Disallow: /cdn-cgi/
Disallow: /verizon/*
Disallow: /forgot-password/*
Allow: /forgot-password/$
Disallow: /forgot-password2/*
Allow: /forgot-password2/$
Disallow: /amp-social-login*
Disallow: /track-analytics/
Disallow: /amp-auth/
Disallow: /rss-feed/
Disallow: /global-color-test.php
Disallow: /global-font-test.php
Disallow: /graphql*
Disallow: /api*
Disallow: /ip*
Disallow: /call-set-cookie-with-context/*
Disallow: /get-current-user/
Disallow: /pv.json
Disallow: /following-feed-test/*
Disallow: */boxscore/*
Disallow: /feed-test/
Disallow: /migrate/

# misc bots
User-agent: Amazonbot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: AwarioRssBot
User-agent: AwarioSmartBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: magpie-crawler
Disallow: /

User-agent: NewsNow
Disallow: /

User-agent: news-please
Disallow: /

User-agent: omgili
Disallow: /

User-agent: omgilibot
Disallow: /

User-agent: peer39_crawler
User-agent: peer39_crawler/1.0
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Scrapy
Disallow: /

User-agent: TurnitinBot
Disallow: /

# Googlebot Specific Rules
User-agent: Googlebot
Disallow: *adgroupid*
Disallow: *campaignid*
Disallow: *ad_id*
Disallow: *access_token*
Disallow: *amp_reader_id*
Disallow: */?source=*
Disallow: /live-blogs/*embed=1*