# 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.

# robots.txt — https://twitterscore.io
# TwitterScore: crypto & NFT analytics based on Twitter/X followers.
#
# One policy for every crawler. AI / answer-engine crawlers (GPTBot,
# ClaudeBot, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, …)
# are intentionally NOT given their own groups: a bare "Allow: /" group
# would make them ignore the Disallow rules below and crawl private
# dashboards. They fall back to this "*" group instead, so they are
# welcome on all public content and blocked from app/admin areas — which
# is exactly what we want for AI visibility.

User-agent: *
# Content signals (Cloudflare / cf.link/content-signals-policy): allow AI SEARCH
# indexing + real-time AI answers/citation (we WANT AI-Overview / ChatGPT /
# Perplexity visibility), but RESERVE rights on model TRAINING. Flip ai-train to
# yes to permit training on our data.
Content-Signal: search=yes, ai-input=yes, ai-train=no
#
# NB: intentionally NO "Allow: /" here — everything not Disallowed is
# allowed by default, and an explicit "Allow: /" makes first-match-wins
# parsers (Python robotparser & friends) approve EVERY url before they
# reach the Disallows below. Also no blank lines inside this group —
# strict RFC-1994 parsers treat a blank line as end-of-group and would
# drop the remaining rules as orphaned. Comment separators are safe.
#
# --- Private / app surfaces (no SEO value, waste crawl budget) ---
Disallow: /admin/
Disallow: /admins/
Disallow: /admin-tools/
# /api/prices is the public API-pricing landing page — keep it crawlable.
# Longest-match wins (Google/Bing), so this Allow beats the /api/ Disallow.
Allow: /api/prices
Disallow: /api/
# Paid-ad click-redirect endpoints (own-domain redirect to the advertiser's
# URL). rel="sponsored" is set on the <a> tags in static/js/ads/*.js; this
# Disallow is Google's documented second layer for paid links (block the
# redirect page from crawling) — see Search Essentials "qualify outbound links".
Disallow: /ads/
Disallow: /new/
Disallow: /payments/
Disallow: /stream/
Disallow: /_a/
Disallow: /o/
Disallow: /oauth/
Disallow: /accountsDashboard/
Disallow: /applicationsDashboard/
Disallow: /monitoringDashboard/
Disallow: /coinsDashboard/
Disallow: /adminLogsDashboard/
Disallow: /CoinsNoneTwitterDashboard/
Disallow: /usersEdit/
# /scoring/ itself is the public "Bulk Score Check" tool page (own
# meta robots: index,follow) — keep it crawlable. Its AJAX data endpoints
# stay blocked. NB: the more specific Disallows must come BEFORE the
# general Allow — primitive parsers (no wildcard/anchor support, e.g.
# Python's urllib.robotparser) match literal prefixes in file order,
# first match wins; only Google/Bing do real longest-match.
Disallow: /scoring/ajax/
Disallow: /scoring/v2/ajax/
Allow: /scoring/
Disallow: /settings/
Disallow: /subscription/
Disallow: /watchlist/
Disallow: /profile/
Disallow: /sign-in/
Disallow: /sign-up/
Disallow: /sign-out/
Disallow: /password-change/
Disallow: /password_reset/
Disallow: /activate/
Disallow: /search/
#
# --- AJAX/JSON endpoints (fragments, not pages) ---
Disallow: /*/ajax/
Disallow: /*/ajax
#
# --- Tracking-parameter variants only (canonical handles the rest).
#     NB: do NOT use a blanket "Disallow: /*?" — it also blocks the
#     paginated sitemap sub-files (sitemap-accounts.xml?p=2). ---
Disallow: /*?utm_
Disallow: /*?ref=
Disallow: /*?fbclid=

Sitemap: https://twitterscore.io/sitemap.xml