# robots.txt for file.tocwave.com
# NOTE: This is a SEPARATE robots.txt from tocwave.com/robots.txt.
# Subdomains do NOT inherit the main domain's robots.txt - this file
# must be uploaded to file.tocwave.com/robots.txt directly.

# BEGIN AI crawler blocking (same policy as main domain)

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END AI crawler blocking

# --- General crawl rules for file.tocwave.com ---
User-agent: *
Allow: /

# Block direct .apk file crawling/indexing.
# IMPORTANT: this only stops Google from trying to index the raw binary
# (which it can't read anyway - hence the Soft 404 / "crawled not indexed"
# issues in your report). It does NOT stop users from downloading the file.
# Once you build HTML landing pages per app/version (recommended next step),
# point Disallow at the raw file path only, and let the landing page be crawled.
Disallow: /*.apk$

# Block the duplicate query-string mirror variants seen in Search Console
# (these were creating "Duplicate without user-selected canonical" issues)
Disallow: /*?ND
Disallow: /*?MA
Disallow: /*?SA
Disallow: /*?NA