# Google Search Engine Robot
# ==========================
User-agent: Googlebot

Allow: /*?s=
Allow: /*?t=
Allow: /*?ref_src=
Allow: /hashtag/*?src=
Allow: /i/api/
# Same length as the /*/likes and /*/media rules; RFC 9309 breaks the tie in
# favor of Allow, so /i/api/ fetches stay crawlable.
Allow: /i/api/*
Disallow: /*?lang=en-ss
Allow: /*?lang=
Disallow: /search?q=
Disallow: /search/realtime
Disallow: /search/users
Disallow: /search/*/grid

Disallow: /*/analytics
Disallow: /*/followers
Disallow: /*/following
Disallow: /*/verified_followers

Disallow: /account/deactivated
Disallow: /settings/deactivated

# Only `*` and `$` are metacharacters here (RFC 9309); regex classes match
# literally. /photo is anchored so /status/*/photo/1 media pages stay open.
Disallow: /*/status/*/likes
Disallow: /*/status/*/retweets
Disallow: /*/likes
Disallow: /*/likes?
Disallow: /*/media
Disallow: /*/media?
Disallow: /*/photo$
Disallow: /*/photo?
Allow: /*?

User-agent: Bingbot

Allow: /*?s=
Allow: /*?t=
Allow: /*?ref_src=
Allow: /hashtag/*?src=
Allow: /i/api/
Allow: /i/api/*
Disallow: /*?lang=en-ss
Allow: /*?lang=
Disallow: /search?q=
Disallow: /search/realtime
Disallow: /search/users
Disallow: /search/*/grid

Disallow: /*/analytics
Disallow: /*/followers
Disallow: /*/following
Disallow: /*/verified_followers

Disallow: /account/deactivated
Disallow: /settings/deactivated

Disallow: /*/status/*/likes
Disallow: /*/status/*/retweets
Disallow: /*/likes
Disallow: /*/likes?
Disallow: /*/media
Disallow: /*/media?
Disallow: /*/photo$
Disallow: /*/photo?
Allow: /*?

User-agent: facebookexternalhit

Allow: /*?lang=
Allow: /*?s=
Allow: /*?t=
Allow: /*?ref_src=
Allow: /hashtag/*?src=
Allow: /search?*cashtagRestId=
Allow: /i/api/
Allow: /i/api/*
Disallow: /search?q=
Disallow: /search/realtime
Disallow: /search/users
Disallow: /search/*/grid

Disallow: /*?
Disallow: /*/followers
Disallow: /*/following
Disallow: /*/verified_followers

Disallow: /account/deactivated
Disallow: /settings/deactivated

Disallow: /*/status/*/likes
Disallow: /*/status/*/retweets
Disallow: /*/likes
Disallow: /*/likes?
Disallow: /*/media
Disallow: /*/media?
Disallow: /*/photo$
Disallow: /*/photo?

User-Agent: Google-Extended
Disallow: *

User-Agent: FacebookBot
Disallow: *

User-agent: Discordbot
Disallow: *

# Every bot that might possibly read and respect this file
# ========================================================
User-agent: *
Disallow: /


# WHAT-4882 - Keep notification-email links (/i/u) out of search results.
# Named crawlers stay un-blocked on purpose: they must crawl /i/u to see its
# X-Robots-Tag noindex (the robots.txt Noindex directive died in 2019).
Disallow: /i/u

# Wait 1 second between successive requests. See ONBOARD-2698 for details.
Crawl-delay: 1

# Independent of user agent. Links in the sitemap are full URLs using https://
# and need to match the protocol of the sitemap.
Sitemap: https://x.com/sitemap.xml