# 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.
# use:      how AI systems may consume the content (immediate, reference, or full).

# 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,use=reference
Allow: /

# Training crawlers
User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: MistralAI-Training
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: GoogleOther
Disallow: /

User-agent: Baiduspider
Disallow: /

User-agent: PetalBot
Disallow: /

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

User-agent: Google-CloudVertexBot
Disallow: /

User-agent: QualifiedBot
Disallow: /

User-agent: Cotoyogi
Disallow: /

User-agent: ICC-Crawler
Disallow: /

User-agent: atlassian-bot
Disallow: /

User-agent: FishBot
Disallow: /

User-agent: BorderxBot
Disallow: /

User-agent: NavuBot
Disallow: /

User-agent: SemrushBot-SWA
Disallow: /

User-agent: WARDBot
Disallow: /

User-agent: magpie-crawler
Disallow: /

User-agent: KimiBot
Disallow: /

User-agent: CitibotSiteCrawler
Disallow: /

# END Cloudflare Managed Content

# ======================================================================
# robots.txt — Cleaned & Modernized for Epoxy.com
# Last updated: 2025-11-18
#
# Purpose:
#   - Block junk, internal tooling, temp folders, admin areas
#   - Allow Google to crawl redirects (important!)
#   - Protect performance and security
#   - Avoid over-blocking legacy URLs needed for SEO preservation
# ======================================================================

User-agent: *

# -----------------------------
# INTERNAL / SYSTEM DIRECTORIES
# -----------------------------
Disallow: /awstats/
Disallow: /channel.cdf/
Disallow: /working/
Disallow: /admin/
Disallow: /cgi-bin/

# ASP.NET system folders
Disallow: /App_Code/
Disallow: /App_Data/
Disallow: /App_GlobalResources/
Disallow: /App_Themes/

# -----------------------------
# FRONT PAGE / OLD CMS CRUFT
# -----------------------------
Disallow: /_borders/
Disallow: /_dsn/
Disallow: /_fpclass/
Disallow: /_overlay/
Disallow: /_private/
Disallow: /_resin/
Disallow: /_sharedtemplates/
Disallow: /_themes/
Disallow: /_vti_bin/

# -----------------------------
# LEGACY ARCHIVE DUMP FOLDERS
# -----------------------------
Disallow: /internal/
Disallow: /chipfloors/
Disallow: /exothermic/

# Old dated folder drops
Disallow: /20160331/
Disallow: /20160630/
Disallow: /20151231/
Disallow: /20150930/

# -----------------------------
# INDIVIDUAL FILES TO BLOCK
# (Dangerous, obsolete, test, or noise)
# -----------------------------
Disallow: /orderform.htm
Disallow: /share.aspx
Disallow: /elastomericbu.aspx
Disallow: /calctest.aspx

# ======================================================================
# NOTES / RULES:
#
# 1) DO NOT block .htm or .html globally.
#    Google must be able to crawl old pages to follow 301 redirects.
#
# 2) DO NOT block old product pages that redirect to new .aspx URLs.
#    Blocking = Google cannot see the redirect = loses SEO value.
#
# 3) Blocking folders is safe ONLY when:
#       - There are no redirects inside them that matter
#       - They contain only dead junk, experiments, or old CMS files
#
# 4) The sitemaps already control what you WANT indexed.
#    Robots.txt should only block what MUST NOT be crawled.
#
# 5) Clean structure, no duplicates, no trailing slash on files.
#
# ======================================================================