{
  "title": "Sitemap URL Extractor - Links, Lastmod & Nested Indexes",
  "type": "object",
  "schemaVersion": 1,
  "description": "Example: {\"sitemapUrls\": [\"https://docs.python.org/sitemap.xml\"], \"maxResults\": 3}. Successful source parsing is billed, including zero-match checks; set maxTotalChargeUsd as an Apify run option.",
  "properties": {
    "sitemapUrls": {
      "type": "array",
      "title": "Sitemap URLs",
      "description": "Pass 1–50 public sitemap URLs, e.g. ['https://docs.python.org/sitemap.xml']. Exact source URLs only; no website discovery. XML must be at most 8 MB decompressed. Successfully parsed sources are billed even when filters leave zero rows.",
      "prefill": [
        "https://docs.python.org/sitemap.xml"
      ],
      "sectionCaption": "Sources",
      "items": {
        "type": "string"
      },
      "editor": "stringList"
    },
    "maxResults": {
      "type": "integer",
      "title": "Maximum output rows",
      "description": "1000 for URLs or 100 for entries by default. Caps delivered rows across all sources after filters. Reaching this cap stops further source requests.",
      "minimum": 1,
      "maximum": 100000,
      "default": 1000
    },
    "sinceDate": {
      "type": "string",
      "title": "Earliest date",
      "description": "Empty (default) keeps every date. Example: \"2026-10-01\" or \"2026-10-01T12:00:00Z\". Inclusive UTC cutoff on lastmod or publication date (updated date when publication is absent). Rows with missing or invalid dates are excluded when set. Source parsing is still billed.",
      "sectionCaption": "Filters",
      "default": "",
      "editor": "textfield"
    },
    "urlContains": {
      "type": "array",
      "title": "URL path or text filter",
      "description": "[] (default) keeps all URLs. Example: [\"/products/\", \"/blog/\"] keeps URLs containing either literal substring, case insensitive. Filters apply before the result cap and URL billing; source parsing remains billed.",
      "default": [],
      "items": {
        "type": "string"
      },
      "editor": "stringList"
    },
    "maxSources": {
      "type": "integer",
      "title": "Maximum sitemap files",
      "description": "30 (default), including index files, malformed responses and failed requests. Example: 5 limits processing to five unique source URLs. Nested indexes are followed breadth first; loops and repeated sources are skipped. Source fees apply only to successfully parsed files.",
      "minimum": 1,
      "maximum": 100,
      "sectionCaption": "Repeat runs and cost limits",
      "default": 30
    },
    "excludeIds": {
      "type": "array",
      "title": "Previously returned IDs",
      "description": "[] (default) keeps all unseen rows within this run. Pass id values from an earlier dataset, e.g. [\"previous-id\"], to omit them. No state is remembered automatically. Source parsing remains billed even when every row is excluded.",
      "default": [],
      "items": {
        "type": "string"
      },
      "editor": "stringList"
    }
  },
  "required": [
    "sitemapUrls"
  ]
}
