User-agent: *
Crawl-delay: 10

# ---------------------------------------------------------------------
# Block the relative-link crawl trap. Internal links on this site are
# relative, so a crawler following one from an already-deep URL gets it
# re-prepended onto the current path instead of resolved from the site
# root. See E:\geomatic_media\server\python\analyze_ssl_log_traffic.py
# and plantmaps_ssl_log_report_Sep2026.txt - this pattern was 81.6% of
# all requests in the most recent log. The .htaccess draft returns 410
# for these at the server level regardless; this just stops compliant
# crawlers from requesting them in the first place.
# ---------------------------------------------------------------------
# Shape 1: a .php script gets more path segments appended after it,
# e.g. /interactive-texas-heat-zones-map.php/en/clim/f/us/texas/...
Disallow: /*.php/

# Shape 2: the site's own domain shows up as a path segment (a relative
# link missing "https://"), e.g. /www.plantmaps.com/en/us/lf/state/...
Disallow: /www.plantmaps.com/
Disallow: /plantmaps.com/

# Shape 3: the /en/ locale prefix recurs later in the path, chaining two
# different location sections together, e.g.
# /en/clim/c/ca/quebec/saint-raphael/en/ca/ff/province/quebec/...
Disallow: /en/*/en/

# ---------------------------------------------------------------------
# Known aggressive/abusive crawlers seen hammering this site (see the
# Sep 2026 report) - blocked here as a courtesy layer for any of them
# that actually honor robots.txt. The real enforcement is the IP block
# in .htaccess.draft, since bots ignoring rate etiquette often ignore
# robots.txt too.
# ---------------------------------------------------------------------
User-agent: AionBot
Disallow: /

User-agent: ShapBot
Disallow: /


User-agent: GPTBot
Disallow: /

User-agent: Diffbot
Disallow: /

Sitemap: https://www.plantmaps.com/sitemap.xml
Sitemap: https://www.plantmaps.com/us_cities_hardiness_zones_sitemap.xml
Sitemap: https://www.plantmaps.com/us_counties_hardiness_zones_sitemap.xml
Sitemap: https://www.plantmaps.com/record-temps-sitemap.xml
Sitemap: https://www.plantmaps.com/wine_regions_sitemap.xml