Retrievers
Sitemap Parser
Fetch an XML sitemap and return its entries — one dictionary per <url> with all its fields (loc, lastmod, changefreq, priority, image/video extensions), plus a flat list of the URLs. Supports both regular sitemaps and sitemap indexes (index sitemaps are followed and their child sitemaps parsed recursively).
Category: Retrievers · Plans: Trial, Starter, Pro, Premium, Enterprise · Type: SitemapParser
Inputs#
| Field | Type | Required | Default | What it does |
|---|---|---|---|---|
| Sitemap URL | Text | No | {input} | URL of the sitemap to parse. Can be a regular sitemap or a sitemap index. Gzip-compressed (.xml.gz) sitemaps are supported. |
| Max URLs | Number | No | 5000 | Maximum number of page URLs to collect before halting. Prevents unbounded memory usage on very large sitemaps. |
| Max Sitemaps | Number | No | 50 | Maximum number of sitemap documents to fetch when following a sitemap index. Bounds the work done on large index sitemaps. |
| Minimum Priority | Number | No | 0 | Drop entries whose <priority> is below this value (0.0–1.0). Leave at 0 to disable. Entries without a <priority> are always kept. (Advanced) |
| Change Frequency | Text | No | (empty) | Drop entries whose <changefreq> differs from this value. Leave as ‘Any’ to disable. Entries without a <changefreq> are always kept. Options: , always, hourly, daily, weekly, monthly, yearly, never (Advanced) |
| Modified After | Text | No | (empty) | Drop entries whose <lastmod> is before this date (W3C date/datetime, e.g. 2024-01-01 or 2024-01-01T00:00:00Z). Leave empty to disable. Entries without a <lastmod> are always kept. (Advanced) |
Outputs#
| Output | Type |
|---|---|
| Entries | Any |
| Urls | Any |
| Url Count | Any |
| Sitemap Count | Any |
Use as an agent tool#
Tool name: sitemapparser
Fetch an XML sitemap and return its entries — one dictionary per <url> with all its fields (loc, lastmod, changefreq, priority, image/video extensions), plus a flat list of the URLs. Supports both regular sitemaps and sitemap indexes (index sitemaps are followed and their child sitemaps parsed recursively).