Sitemap Analyzer
Paste a sitemap.xml to count URLs, group them by section, and flag issues before you train a bot on them.
Tip: open yoursite.com/sitemap.xml and paste the source here.
What this sitemap analyzer does
Paste a sitemap.xml and this free sitemap analyzer instantly counts the URLs, de-duplicates them, groups them by top-level section, and flags common problems — duplicate entries, insecure http:// links, and whether the file is a sitemap index that points at child sitemaps.
It's built for one job in particular: sizing up a site's content before you crawl or train an AI assistant on it. Knowing you have 40 useful pages versus 4,000 auto-generated ones changes how you scope training — and what it costs to embed.
How to analyze your sitemap
- Open
yoursite.com/sitemap.xml(or find it in your robots.txt). - View the page source and copy the raw XML.
- Paste it above to see the URL count, section breakdown, and any issues.
- Decide which sections are worth training on, then confirm each key page is AI-ready with the RAG readiness checker.
From sitemap to a trained assistant
Once you know which pages matter, you can point an assistant straight at them. How to train an AI chatbot on your own website content walks through the full pipeline, and the robots.txt generator helps you control which crawlers reach those pages in the first place.
Sitemap analyzer FAQ
A sitemap analyzer reads your sitemap.xml and summarizes what's in it: how many URLs it lists, how those pages group by section, and whether it has issues like duplicate entries, insecure http:// links, or a nested sitemap index. It's a quick way to see the shape of a site before you crawl or train on it.
Most sites publish it at yoursite.com/sitemap.xml or link it from yoursite.com/robots.txt (look for the Sitemap: line). Open that URL, view the page source, and paste the raw XML here. Large sites often use a sitemap index that points to several child sitemaps — analyze those too.
Quality beats quantity. Train on the pages that answer real questions — docs, FAQ, pricing, policies — not every tag and pagination URL a sitemap lists. Use this analyzer to spot the sections worth including, then run the important pages through the RAG readiness checker before you train.
Watch for duplicate URLs (they waste crawl budget), http:// links that should be https://, and orphaned or thin pages that add noise. If it's a sitemap index rather than a URL set, expand the child sitemaps. Clean sitemaps crawl faster and produce a tidier training set.
Yes — it's free and runs entirely in your browser. Nothing is uploaded; paste your XML and the analysis happens on the page. No sign-up required.