How to Diagnose Why Google Is Not Indexing Your Pages

Published Read 7 min read

On this page

“Not indexed” is a symptom, not a diagnosis, and the methodology that actually resolves it is to read which Page indexing state a URL is in before doing anything, because the states sit at different points in the discover-to-crawl-to-index pipeline and each one fails for a different reason with a different fix. The pivotal distinction is between “Discovered – currently not indexed,” which means Google knows the URL exists but has not crawled it, a crawl-priority problem, and “Crawled – currently not indexed,” which means Google crawled the page and decided it was not worth indexing, a value problem.

These two look identical on the surface and share the same surface complaint, but the first is fixed with internal linking and architecture and the second is fixed with content. Conflating them is why months of “various fixes” change nothing.

This post owns the diagnostic method and the coverage-state reference: how to read one page’s state and act on it. The systemic question of why Google deliberately skips a fraction of pages on a large site, and the crawl-budget economics behind that, is a separate scale question and is not covered here.

The pipeline: each stage fails independently

Indexing is a sequence: Google discovers a URL, crawls it, decides whether to index it, and only then can it rank. A page can stall at any stage, and the Page indexing report tells you which stage it stalled at. That is the whole point of reading the state first. “Not indexed” with no further detail is useless; “Discovered – currently not indexed” versus “Crawled – currently not indexed” versus “Excluded by noindex tag” each points at a completely different lever. Note that the report is called Page indexing in current Search Console; the older “Coverage” name refers to the same family of states but is no longer the report’s name.

The pivotal split: Discovered versus Crawled

Read this distinction carefully, because it determines your entire course of action.

“Discovered – currently not indexed” means Google found the URL, usually via a sitemap or a link, but has not crawled it yet. The page never got fetched, so its content played no part in the decision. This is a crawl-priority problem: Google has decided this URL is not worth its limited crawl attention right now.

The causes are structural. Weak internal linking leaves the page poorly connected, so Google sees little signal that it matters. High click depth, a page buried many clicks from the homepage, signals low importance. Crawl waste elsewhere on the site, sprawling parameter URLs or thin templated pages, spends the crawl budget that this page needed. And a URL known only from the sitemap has the weakest possible discovery signal, because a sitemap entry alone, with no internal links pointing at it, tells Google almost nothing about the page’s importance. The fix is architectural: link to the page from relevant, well-crawled pages, reduce its click depth, and cut the crawl waste competing with it.

“Crawled – currently not indexed” means the opposite: Google did fetch the page, evaluated it, and chose not to index it. The content was the input to a “no” decision. This is a value problem, not a discovery one, and no amount of internal linking forces it in. The page is thin, duplicative, or carries no unique signal that distinguishes it from what Google already indexes. The fix is to make the page genuinely worth indexing: add firsthand value, resolve duplication through consolidation or canonicalization, and sharpen it to fully satisfy a real query rather than restating what hundreds of other pages already say.

The trap is treating these the same. Building internal links to a “Crawled – currently not indexed” page does nothing if the page is thin, and rewriting the content of a “Discovered – currently not indexed” page does nothing if Google never crawls it to see the rewrite. Read the state, then act on its actual cause.

The first-five-minutes checks

For any single non-indexed URL, three checks establish ground truth fast.

URL Inspection reads the exact current state straight from Google’s index, so you start from fact rather than guesswork about which of the states applies. Then run Test Live URL on the same page; this fetches and renders the page as Googlebot would right now, catching rendering failures, content that depends on JavaScript Google is not executing, or a resource block that leaves the rendered page effectively empty. A page that looks full in your browser but renders blank to Googlebot will sit in a not-indexed state no matter what else you do. Finally, scan robots.txt for a forgotten Disallow covering the URL’s path, a frequent and silent cause that blocks crawling entirely.

A coverage-state reference for routing

Each Page indexing state routes to a fix direction. The current strings, verify them against your own report since wording is what you act on, and what each implies:

State What it means Fix direction
Discovered – currently not indexed Known, not yet crawled Internal links, reduce click depth, cut crawl waste
Crawled – currently not indexed Crawled, judged not worth indexing Content value and uniqueness, or consolidate
Duplicate without user-selected canonical Near-duplicate, you set no canonical Set a canonical to the clean URL
Alternate page with proper canonical tag Google is obeying your canonical Usually intended; only worry if you wanted this page indexed
Excluded by noindex tag Your own noindex told Google to stay out Find and remove the noindex source
Blocked by robots.txt Crawling is blocked Decide whether the block is intended
Page with redirect Redirecting URL, destination indexed Usually intended; cut old-URL sources if it grows
Soft 404 Looks empty or error-like to Google Add real content or return a proper status
Not found (404) URL returns 404 Restore or redirect if it should exist

The states owning their own dedicated GSC string fixes (the canonical, robots, noindex, and redirect statuses) each have a deeper treatment of their own; this table is the routing layer, telling you which direction a given non-indexed page belongs in.

Diagnosing each side in practice

For a “Discovered” page, sample the affected URLs and check how they are linked. Are they reachable from the main navigation or a hub page, or only from the sitemap? Count clicks from the homepage. If they are deep and weakly linked, the architecture is the cause, and adding contextual internal links from strong pages plus flattening depth is the fix.

For a “Crawled – currently not indexed” page, compare the thin survivors against your indexed peers. Take a page that did get indexed in the same template or topic and ask what it has that the rejected one lacks: genuine unique content, firsthand detail, a real reason to exist separately. The gap is your fix. If the honest answer is that the page duplicates another or adds nothing, consolidation or removal is the correct move, not a forced re-index.

The strategic reality

Not every page deserves to be indexed, and chasing 100% indexation on a site with thin or duplicative pages is the wrong goal. “Request indexing” in URL Inspection triggers a crawl, not an index decision; it asks Google to look again, but Google still applies the same value judgment. For an unchanged thin page, requesting indexing mostly just confirms the rejection faster. Use it for pages you have genuinely improved or for a small number of high-priority URLs, and let natural recrawl handle scale. Mass-requesting indexing on pages you have not changed accomplishes nothing and signals nothing.

Frequently Asked Questions

What is the difference between “Discovered – currently not indexed” and “Crawled – currently not indexed”?

“Discovered” means Google knows the URL but has not crawled it, a crawl-priority problem fixed with internal linking, reduced click depth, and less crawl waste. “Crawled – currently not indexed” means Google fetched the page and judged it not worth indexing, a content-value problem fixed by adding unique value or consolidating. The fixes do not transfer between the two.

Does requesting indexing in URL Inspection force a page into the index?

No. Request indexing triggers a crawl, not an index decision. Google still applies its value judgment, so for an unchanged thin page it usually just confirms the rejection sooner. Use it after genuinely improving a page or for a few high-priority URLs, not as a mass workaround.

Why is my page indexed in my browser’s view but showing not indexed in Search Console?

Run Test Live URL in URL Inspection to see how Googlebot renders it. A page that looks complete in your browser can render blank or partial to Googlebot if key content depends on JavaScript Google is not executing or if a blocked resource breaks rendering. Also scan robots.txt for a Disallow on that path.

Sources

Page indexing report – Search Console Help: https://support.google.com/webmasters/answer/7440203
URL Inspection Tool – Search Console Help: https://support.google.com/webmasters/answer/9012289
Crawling and indexing topics – Google Search Central: https://developers.google.com/search/docs/crawling-indexing

Related posts:

  1. Old Blog Posts Are Cannibalizing New Content Your new post is objectively better and it still cannot outrank the old one you wrote three years ago, because Google ranks the URL it already trusts. Accumulated authority signals......
  2. Your Bot Detection Is Blocking Googlebot and You Don’t Know It Aggressive bot protection can challenge or block legitimate crawlers when the rules are ordered so that a strict challenge fires before the verified-bot allowance does. That is why a sudden,......
  3. Google Keeps Choosing the Wrong Canonical A canonical tag is a hint, not a directive, and Google says so directly: it takes your declared canonical into consideration, but it can and does select a different URL......
  4. How to Do SEO for a Two-Sided Platform A two-sided platform needs two separate keyword strategies, one for supply and one for demand, and the SEO budget should concentrate on the constrained side: whichever side is harder to......
  5. Why Your Staging Site Is Ranking Instead of Production Staging out-ranking production is a canonical signal inversion, not a simple case of an exposed test server, and treating it as the latter is why the usual fixes fail. Production,......
  6. Google Is Indexing Your Search Results Pages Internal site-search results pages get indexed for a simple reason: they are crawlable and discoverable like any other URL. A search box that submits via a GET request turns every......
  7. Original Research as an SEO Moat Original research is defensible for one reason: the asset is data your competitors cannot replicate. Informational content gets reverse-engineered within weeks, because anyone can read the same sources and rewrite......
  8. Why Your Accordion Content Doesn’t Rank for Long-Tail Queries Your collapsed accordion content is almost certainly indexed. It sits in the rendered DOM, Googlebot reads it, and you can confirm it is there. The problem is weight, not visibility......
  9. SEO and Engineering Collaboration: Communication Protocols for Technical Requests SEO requests stall not because engineers undervalue search but because the requests arrive in a form engineering cannot consume. An email saying "we need to fix our canonical tags for......
  10. How to Build a Multilingual SEO Strategy The strategic decisions come before any hreflang tag, and getting them right is most of the work. Multilingual SEO is a sequence of investment choices: which languages to build for,......
  11. How to Do SEO for a New Website with Zero Budget Zero-budget SEO is not a cheaper version of funded SEO; it is a different strategy that trades money for time and scope. Money buys speed, scale, and tooling. Without it,......
  12. Edge SEO: Implementing Changes at the CDN Layer Edge SEO ships header, redirect, hreflang, schema, and meta changes in hours by running serverless workers at the CDN layer, instead of waiting weeks for an engineering backlog to clear.......
  13. Your CDN’s Edge Caching Is Breaking Hreflang for International Visitors When geo-IP detection or geo-redirects run at your origin behind a location-unaware CDN, two failures stack. The edge caches one country's response (or one geo-redirect outcome) under the URL alone......
  14. SEO Sprint Planning: Agile Workflows for Search Optimization Teams Sprint methodology works for SEO only after one adaptation, and getting that adaptation right is the whole game. SEO's feedback loop runs weeks to months beyond the sprint boundary: you......
  15. Data Pages That Journalists Actually Link To Journalists link to data they can cite at deadline, and that constraint dictates everything about how the page is built. A reporter on a tight clock needs a single URL......