# 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.
# BEGIN Cloudflare Managed content
User-agent: *
Content-Signal: search=yes,ai-train=no
Allow: /
User-agent: Amazonbot
Disallow: /
User-agent: Applebot-Extended
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: CCBot
Disallow: /
User-agent: ClaudeBot
Disallow: /
User-agent: CloudflareBrowserRenderingCrawler
Disallow: /
User-agent: Google-Extended
Disallow: /
User-agent: GPTBot
Disallow: /
User-agent: meta-externalagent
Disallow: /
# END Cloudflare Managed Content
User-agent: *
Crawl-delay: 5
User-agent: Mediapartners-Google
Allow: /
User-agent: Mozilla/5.0 (compatible; PaperLiBot/2.1; http://support.paper.li/entries/20023257-what-is-paper-li)
Disallow: /
User-agent: PaperLiBot
Disallow: /
User-Agent: AhrefsBot
Disallow: /
User-agent: MJ12bot
Disallow: /
User-agent: MegaIndex.ru/2.0
Disallow: /
User-agent: SentiBot
Disallow: /
User-agent: BLEXBot
Disallow: /
# http://www.opensiteexplorer.org/dotbot
User-agent: dotbot
Disallow: /
# http://openlinkprofiler.org/bot
User-agent: spbot
Disallow: /
# http://www.crazywebcrawler.com/
User-agent: CrazyWebCrawler-Spider
Disallow: /
# https://ranksonic.com/ranksonic_bot.html
User-agent: RankSonicBot
Disallow: /
# http://www.seokicks.de/robot.html
User-agent: SEOkicks-Robot
Disallow: /
# These fools don't even respect robots.txt
User-agent: QuerySeekerSpider
Disallow: /
# http://www.picsearch.com/bot.html
User-agent: psbot
Disallow: /
User-agent: SemrushBot
Disallow: /
User-agent: Flamingo_SearchEngine
Disallow: /
# domainreanimator.com
User-agent: Domain Re-Animator Bot
Disallow: /
# Mozilla/5.0+(compatible;+MegaIndex.ru/2.0;++http://megaindex.com/crawler)
# http://megaindex.com/crawler
User-agent: MegaIndex
Disallow: /
# Sitemap URL
Sitemap: https://www.spaceweatherlive.com/sitemap.php