AgentcyAlpha
Services/Sitemap Parser

Sitemap Parser

XML sitemap parsing, URL inventory, content freshness analysis, and site structure mapping.

OVERVIEW

Sitemap Parser fetches your XML sitemaps and turns them into actionable intelligence about your site's structure. It discovers sitemaps from robots.txt, recursively parses sitemap indexes, and analyzes URL inventory — how many pages you have, which sections are largest, how fresh your content is, and whether you have image or video sitemaps.

Ask about your sitemap health, page count, content freshness, or site structure. Agentcy fetches and parses your sitemaps in real time, then presents a structured analysis including URL counts by path prefix, lastmod freshness distribution, and sitemap issue detection.

This is an always-available bundled service — no setup required. Works on any domain with a public sitemap.

EXAMPLE QUESTIONS
11 SAMPLES

How many pages are in my sitemap?

Parse the sitemap for my domain

What does the sitemap look like for my site?

When were sitemap pages last modified?

Does my site have an image sitemap?

Show me the site structure from the sitemap

How fresh is the content in my sitemap?

What sections of my site have the most pages?

Check sitemap health for my domain

Does my site have a video sitemap?

Are there any sitemap issues?

WHAT YOU CAN ASK ABOUT
8 EXAMPLES
Total URL count across all sitemaps
URL distribution by path prefix (e.g., /blog/, /products/, /pages/)
Lastmod date freshness distribution
Sitemap index detection (recursive parsing)
Image sitemap detection
Video sitemap detection
Robots.txt sitemap directives
Changefreq and priority analysis
REQUIREMENTS
Google Account
Not required
API Key
Not required
External Subscription
Not required
Domain Configuration
None — zero-config service
SETUP
3 STEPS
  1. 01

    No setup needed — Sitemap Parser is always available for all accounts

  2. 02

    No API keys or domain configuration required

  3. 03

    Start asking about any domain's sitemap

DATA FRESHNESS

24-hour cache. Sitemaps change infrequently — results reflect the sitemap state at query time.

TIPS
4

Sites without a sitemap (no sitemap.xml or robots.txt directive) will return an error — not all sites publish sitemaps

Very large sitemaps (100,000+ URLs) are sampled rather than fully parsed to keep response times reasonable

Lastmod dates are only as accurate as the site maintains them — many sites set lastmod to the crawl date, not the actual content update

Password-protected or blocked sitemaps (via robots.txt or auth) cannot be accessed

WORKS WELL WITH
3 SERVICES
v1.0Need help?