User-agent: *
Disallow: /blog/wp-admin/

# --- Added to stop crawl-budget waste on duplicate/tracking-parameter URLs ---
# These rules only block Googlebot from crawling these specific query-string
# variants. They do NOT block real visitors, campaign clicks, or affiliate
# links, and they do NOT affect the clean canonical version of any page.

# Third-party tracking parameters landing on our URLs (not generated by us,
# picked up from external referring pages / bots probing common param names)
Disallow: /*optimizely_user_id=*
Disallow: /*ampDeviceId=*
Disallow: /*ampSessionId=*

# Internal blog filter/facet combinations (thin, near-duplicate archive views)
Disallow: /*filter-industries=*
Disallow: /*filter-products=*
Disallow: /*filter-countries=*
Disallow: /*&keywords=*
Disallow: /*&categories=*
Disallow: /*&onlycontent=*

# Widget pagination state leaking into the URL (hashed per-widget IDs, e.g.
# 2879f8e3_page=2, 7930de53_page=2). Wildcard covers any hash prefix.
Disallow: /*_page=*

# PartnerStack affiliate tracking parameters — these two showed up directly
# in the "Crawled - currently not indexed" examples pulled from GSC.
# Blocking them from CRAWLING does not touch the affiliate program itself —
# tracking runs off the click and the browser session, not off whether
# Googlebot indexes that exact tagged URL.
Disallow: /*ps_partner_key=*
Disallow: /*ps_xid=*

Allow: /

Sitemap: https://www.invespcro.com/sitemap.xml