{
  "data": {
    "id": "5p1KhiOdH5c83j2Ec",
    "userId": "HIMU0xktu1JeZb4Xl",
    "name": "sitemap-url-extractor",
    "username": "fetch_cat",
    "description": "Extract clean URL inventories from XML sitemaps and sitemap indexes with filters, deduplication, and metadata.",
    "isPublic": true,
    "createdAt": "2026-07-03T20:56:24.176Z",
    "modifiedAt": "2026-07-18T17:09:44.826Z",
    "taggedBuilds": {
      "latest": {
        "buildId": "bgSV5yv4tjYsgoJAF",
        "finishedAt": "2026-07-18T17:09:44.826Z",
        "buildNumberInt": 100011,
        "buildNumber": "0.1.11"
      }
    },
    "stats": {
      "totalBuilds": 11,
      "totalRuns": 107,
      "totalUsers": 2,
      "totalUsers7Days": 1,
      "totalUsers30Days": 1,
      "totalUsers90Days": 1,
      "lastRunStartedAt": "2026-08-26T05:30:57.128Z",
      "actorReviewCount": 0,
      "actorReviewRating": 0,
      "bookmarkCount": 0,
      "publicActorRunStats30Days": {
        "ABORTED": 0,
        "FAILED": 0,
        "SUCCEEDED": 30,
        "TIMED-OUT": 0,
        "TOTAL": 30
      }
    },
    "versions": [
      {
        "versionNumber": "0.1",
        "sourceType": "SOURCE_FILES",
        "buildTag": "latest"
      }
    ],
    "defaultRunOptions": {
      "build": "latest",
      "timeoutSecs": 300,
      "memoryMbytes": 256
    },
    "exampleRunInput": {
      "body": "{\n  \"startUrls\": [{ \"url\": \"https://apify.com/sitemap.xml\" }],\n  \"maxUrls\": 20,\n  \"maxSitemaps\": 10,\n  \"sameDomainOnly\": true,\n  \"dedupe\": true,\n  \"proxyConfiguration\": { \"useApifyProxy\": false }\n}",
      "contentType": "application/json; charset=utf-8"
    },
    "categories": [
      "SEO_TOOLS",
      "DEVELOPER_TOOLS",
      "AUTOMATION"
    ],
    "isDeprecated": false,
    "title": "Sitemap URL Extractor",
    "pictureUrl": "https://apify-image-uploads-prod.s3.us-east-1.amazonaws.com/HIMU0xktu1JeZb4Xl-actor-5p1KhiOdH5c83j2Ec-Hos8GiQ7Vg-sitemap-url-extractor-actor-icon.png",
    "seoTitle": "Sitemap URL Extractor for XML Sitemap URLs",
    "seoDescription": "Extract URLs from XML sitemaps and sitemap indexes. Filter, dedupe, export URL inventories, lastmod dates, priorities, and source sitemap files fast.",
    "pricingInfos": [
      {
        "pricingModel": "PAY_PER_EVENT",
        "startedAt": "2026-07-03T20:59:02.050Z",
        "pricingPerEvent": {
          "actorChargeEvents": {
            "start": {
              "eventTitle": "Start",
              "eventDescription": "One-time fee per run",
              "eventPriceUsd": 0.005,
              "isOneTimeEvent": true
            },
            "result": {
              "eventTitle": "Sitemap URL extracted",
              "eventDescription": "Per URL extracted from sitemap files",
              "eventTieredPricingUsd": {
                "FREE": {
                  "tieredEventPriceUsd": 0.000575
                },
                "BRONZE": {
                  "tieredEventPriceUsd": 0.0005
                },
                "SILVER": {
                  "tieredEventPriceUsd": 0.00039
                },
                "GOLD": {
                  "tieredEventPriceUsd": 0.0003
                },
                "PLATINUM": {
                  "tieredEventPriceUsd": 0.0002
                },
                "DIAMOND": {
                  "tieredEventPriceUsd": 0.00014
                }
              },
              "isPrimaryEvent": true
            }
          }
        },
        "isPriceChangeNotificationSuppressed": true,
        "reasonForChange": "Initial private actor PPE pricing for APIA-1187.",
        "createdAt": "2026-07-03T20:59:02.453Z",
        "apifyMarginPercentage": 0.2
      },
      {
        "pricingModel": "PAY_PER_EVENT",
        "startedAt": "2026-07-03T21:01:12.931Z",
        "pricingPerEvent": {
          "actorChargeEvents": {
            "start": {
              "eventTitle": "Start",
              "eventDescription": "One-time fee per run",
              "eventPriceUsd": 0.005,
              "isOneTimeEvent": true
            },
            "result": {
              "eventTitle": "Result extracted",
              "eventDescription": "Charged per sitemap URL extracted.",
              "eventPriceUsd": 0.000024266,
              "isPrimaryEvent": true
            }
          }
        },
        "isPriceChangeNotificationSuppressed": true,
        "reasonForChange": "Formula-derived BRONZE flat fallback for APIA-1187; platform rejected tiered event payload for private actor.",
        "createdAt": "2026-07-03T21:01:13.015Z",
        "apifyMarginPercentage": 0.2
      },
      {
        "pricingModel": "PAY_PER_EVENT",
        "startedAt": "2026-07-03T21:03:22.926Z",
        "pricingPerEvent": {
          "actorChargeEvents": {
            "start": {
              "eventTitle": "Run started",
              "eventDescription": "One-time fee charged when a run starts.",
              "eventPriceUsd": 0.005,
              "isOneTimeEvent": true
            },
            "result": {
              "eventTitle": "Result extracted",
              "eventDescription": "Charged per sitemap URL extracted.",
              "isPrimaryEvent": true,
              "eventTieredPricingUsd": {
                "FREE": {
                  "tieredEventPriceUsd": 0.000345
                },
                "BRONZE": {
                  "tieredEventPriceUsd": 0.0003
                },
                "SILVER": {
                  "tieredEventPriceUsd": 0.000234
                },
                "GOLD": {
                  "tieredEventPriceUsd": 0.00018
                },
                "PLATINUM": {
                  "tieredEventPriceUsd": 0.00012
                },
                "DIAMOND": {
                  "tieredEventPriceUsd": 0.000084
                }
              }
            }
          }
        },
        "isPriceChangeNotificationSuppressed": true,
        "reasonForChange": "Canonical tiered PPE pricing for APIA-1187; set at low competitor-aligned $0.0003 BRONZE after platform rejected tiny formula-derived tiered prices.",
        "createdAt": "2026-07-03T21:03:23.003Z",
        "apifyMarginPercentage": 0.2
      },
      {
        "pricingModel": "PAY_PER_EVENT",
        "startedAt": "2026-07-03T21:32:22.192Z",
        "pricingPerEvent": {
          "actorChargeEvents": {
            "start": {
              "eventTitle": "Run started",
              "eventDescription": "One-time fee charged when a run starts. Covers fixed startup cost (init, first HTTP setup).",
              "eventPriceUsd": 0.005,
              "isOneTimeEvent": true
            },
            "result": {
              "eventTitle": "Result extracted",
              "eventDescription": "Charged per sitemap URL extracted.",
              "isPrimaryEvent": true,
              "eventTieredPricingUsd": {
                "FREE": {
                  "tieredEventPriceUsd": 0.000028
                },
                "BRONZE": {
                  "tieredEventPriceUsd": 0.000024
                },
                "SILVER": {
                  "tieredEventPriceUsd": 0.000019
                },
                "GOLD": {
                  "tieredEventPriceUsd": 0.000015
                },
                "PLATINUM": {
                  "tieredEventPriceUsd": 0.000012
                },
                "DIAMOND": {
                  "tieredEventPriceUsd": 0.00001
                }
              }
            }
          }
        },
        "isPriceChangeNotificationSuppressed": true,
        "reasonForChange": "Formula-derived canonical tiered PPE pricing for APIA-1187 QA fix; aligns BRONZE with pricing calculator floor; DIAMOND set to observed platform minimum accepted precision.",
        "createdAt": "2026-07-03T21:32:22.272Z",
        "apifyMarginPercentage": 0.2
      }
    ],
    "notice": "NONE",
    "isCritical": false,
    "isGeneric": false,
    "hasNoDataset": false,
    "isSourceCodeHidden": true,
    "standbyUrl": null,
    "actorPermissionLevel": "LIMITED_PERMISSIONS",
    "readmeSummary": "## Sitemap URL Extractor\n\nA tool that reads XML sitemaps and sitemap indexes to produce a structured URL inventory: it discovers sitemap files (including indexes), follows child sitemaps recursively, and extracts normalized URLs with source sitemap metadata, recursive depth, sitemap-provided metadata (last modified dates, change frequency, priority), HTTP metadata (status code and content type), and discovery timestamps. The Actor supports supplying sitemap URLs or website root URLs (it will probe common sitemap locations), URL normalization and cross-sitemap deduplication, include/exclude path filtering, optional same-hostname restriction, and configurable limits for large sites — enabling automated, repeatable extraction of clean URL lists and sitemap metadata for downstream analysis.\n\n## Use cases\n\n- Build a seed list for a crawler or crawler operators seeding downstream crawling jobs.  \n- Export all blog post or documentation URLs from a site.  \n- Extract product or category page URLs from e-commerce sitemaps.  \n- Compare sitemap URL counts or inventories over time for monitoring and audits.  \n- Detect recently changed pages using sitemap last-modified metadata.  \n- Audit sitemap coverage for product, help, documentation, or category pages.  \n- Create clean URL lists for link checking, QA regression tests, or content inventories.  \n- Feed extracted URL lists into rank tracking, monitoring, or data enrichment workflows.",
    "deploymentKey": "ssh-rsa AAAAB3NzaC1yc2EAAAADAQABAAABAQCr7lZ+oVR0wz6+q5trPj/OyZXZUoImd446B6AvXoGe2/6NDLZf5ModJHRrIlVpbEaSjg1zabSwpH5XHf0OKO77lw+toNPBi0qJpHTk1aGEFsxr7l4PNLHavwlD7io3NvunP4N6e1QF5+Rukx5hG/abxRxUzxd2YidNZ61bturf2ZGGjJhBtEX/eaxZOO3Whvf/dHdKxG8nFjFlKXXd81CU1AlWx6eqPnizjhYUPO6IQT8dqBGzNgM1bbvThmrGHr58rDh45p9qwn9X9E+abSj3Y2qTsM0wt5lvZyfpHrqqBT7kU2JQFfO040QjP1GewGzHluxSQC8RLGKlPnHdeXcH \n"
  }
}