{"@id": "sitemap-source", "@type": "Source", "name": "List URLs from a Sitemap file", "description": "Extract all URLs from a Sitemap file, including those found after following Sitemap Index files. Use RegEx filters to import only URLs that match a specific pattern.", "cost": "1 credit per 150 URLs parsed.", "schemaVersion": "2026-09-12", "settingsSchema": {"type": "object", "properties": {"sitemapUrl": {"type": "string", "format": "uri", "title": "Sitemap URL", "description": "An URL to fetch a XML Sitemap. If the XML is a Sitemap Index, related Sitemaps will be followed. Ex: https://www.datablist.com/sitemap.xml"}, "filterRegex": {"type": "string", "title": "Regex Filter", "description": "If set, only webpage URLs matching the Regex will be created. Ex: 'datablist\\.com\\/blog\\/' to filter blog pages in the Datablist sitemap."}, "sitemapSourceLimit": {"type": "number", "title": "Limit", "description": "If set, the enrichment will stop after {Limit} webpage URLs are found. Default to 95,000. Note: Collections are limited to 100,000 items when synced to the cloud."}}, "additionalProperties": true, "required": ["sitemapUrl"]}, "outputSchema": {"type": "object", "properties": {"sitemapPageUrl": {"type": "string", "format": "uri", "title": "Page Url"}, "sitemapLastUpdated": {"type": "string", "format": "date-time", "title": "Page Last Modified"}}, "additionalProperties": true, "required": ["sitemapPageUrl"]}, "limits": {"executionDeadlineSeconds": 86400}}