# PROPOSED physical robots.txt for covid19resources.ca
# Place at /var/www/html/robots.txt (a physical file overrides WordPress's virtual robots.txt).
# Preserves the current virtual rules, adds Events Calendar crawl-trap disallows.

User-agent: *
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

# --- The Events Calendar crawl-trap: stop bots walking the infinite date/filter URL space ---
Disallow: /*?*tribe-bar-date=
Disallow: /*?*eventDate=
Disallow: /*?*eventDisplay=past
Disallow: /*?*eventDisplay=list
Disallow: /*?*tribe_eventcategory=
Disallow: /*?*ical=1
Disallow: /*?*outlook-ical=
Disallow: /*?*post_type=tribe_events&*
# FilterBar param space (plugin is active — expands the trap further):
Disallow: /*?*tribe_events_cat=
Disallow: /*?*tribe-bar-*

# WPML language-duplicated calendar paths (translated slugs multiply the trap ~3x):
Disallow: /*?lang=*&*tribe-bar-date=
Disallow: /events/*/past/
Disallow: /evenements/*/past/

Sitemap: https://covid19resources.ca/sitemap.xml
Sitemap: https://covid19resources.ca/sitemap.html

# NOTE: PetalBot / serpstatbot / Scrapy frequently ignore robots.txt.
# robots.txt only helps the well-behaved crawlers (Semrush, DotBot, SERanking).
# The Cloudflare cache rule (see proposed-cloudflare-cache-rule.md) is the real fix.