{
  "openapi": "3.0.1",
  "info": {
    "title": "Sitemap Extractor API: All URLs, Lastmod, Sitemap Index",
    "description": "Every URL of any website from its sitemaps: lastmod, changefreq, priority, hreflang, images, news. Finds sitemaps via robots.txt, follows nested indexes, .gz, text and RSS. Only-new mode for monitoring. No login. MCP-ready for AI agents. Errors and empty results are free. $0.20 per 1,000 URLs.",
    "version": "0.1",
    "x-build-id": "8KBEwFjDVjj9pREmq"
  },
  "servers": [
    {
      "url": "https://api.apify.com/v2"
    }
  ],
  "paths": {
    "/acts/actose~sitemap-extractor/run-sync-get-dataset-items": {
      "post": {
        "operationId": "run-sync-get-dataset-items-actose-sitemap-extractor",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    },
    "/acts/actose~sitemap-extractor/runs": {
      "post": {
        "operationId": "runs-sync-actose-sitemap-extractor",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor and returns information about the initiated run in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/runsResponseSchema"
                }
              }
            }
          }
        }
      }
    },
    "/acts/actose~sitemap-extractor/run-sync": {
      "post": {
        "operationId": "run-sync-actose-sitemap-extractor",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    }
  },
  "components": {
    "schemas": {
      "inputSchema": {
        "type": "object",
        "required": [
          "urls"
        ],
        "properties": {
          "urls": {
            "title": "Domains or sitemap URLs",
            "type": "array",
            "description": "One per line. Accepted: a domain (example.com), any page of the site (https://example.com/blog/), a robots.txt URL, or a sitemap URL (XML, .xml.gz, sitemap index, text, RSS/Atom). For a domain, the sitemaps are discovered from robots.txt, then from /sitemap.xml, /sitemap_index.xml, /wp-sitemap.xml.",
            "items": {
              "type": "string"
            }
          },
          "maxUrls": {
            "title": "Max URLs (total)",
            "minimum": 0,
            "type": "integer",
            "description": "Stop after this many URLs across all inputs. 0 = no limit. You pay only for the URLs delivered.",
            "default": 10000
          },
          "maxUrlsPerInput": {
            "title": "Max URLs per input",
            "minimum": 0,
            "type": "integer",
            "description": "Limit for each domain or sitemap of the list, so that one huge site does not use the whole budget. 0 = no limit.",
            "default": 0
          },
          "includePatterns": {
            "title": "Only URLs matching",
            "type": "array",
            "description": "Keep only URLs that match at least one of these regular expressions (or plain text), e.g. /blog/ or /products/. Case-insensitive. URLs filtered out are not charged.",
            "items": {
              "type": "string"
            }
          },
          "excludePatterns": {
            "title": "Exclude URLs matching",
            "type": "array",
            "description": "Drop URLs that match any of these regular expressions (or plain text), e.g. /tag/ or \\?page=.",
            "items": {
              "type": "string"
            }
          },
          "modifiedAfter": {
            "title": "Modified after",
            "type": "string",
            "description": "Keep only URLs whose lastmod is on or after this date. Absolute (2026-01-01) or relative (7 days, 2 weeks, 3 months)."
          },
          "keepUrlsWithoutLastmod": {
            "title": "Keep URLs without lastmod",
            "type": "boolean",
            "description": "With a 'Modified after' date: also keep URLs whose sitemap gives no lastmod (otherwise they are dropped).",
            "default": false
          },
          "deduplicate": {
            "title": "Remove duplicate URLs",
            "type": "boolean",
            "description": "A URL listed in several sitemaps is returned (and charged) only once.",
            "default": true
          },
          "onlyNew": {
            "title": "Only new URLs since the last run",
            "type": "boolean",
            "description": "For scheduled runs: return only the URLs not delivered by a previous run with the same input. The history is kept in the named key-value store 'sitemap-extractor-state'. The first run returns everything.",
            "default": false
          },
          "onlyNewMode": {
            "title": "What counts as new",
            "enum": [
              "new",
              "newOrUpdated"
            ],
            "type": "string",
            "description": "'new': URLs never seen before. 'newOrUpdated': also URLs whose lastmod changed since the last run.",
            "default": "new"
          },
          "stateKey": {
            "title": "History name (optional)",
            "type": "string",
            "description": "Name of the history used by 'Only new'. Leave empty to get one history per input configuration. Set the same name in two tasks to share it."
          },
          "useRobotsTxt": {
            "title": "Read robots.txt",
            "type": "boolean",
            "description": "For domains and page URLs: read the Sitemap: lines of robots.txt.",
            "default": true
          },
          "tryCommonPaths": {
            "title": "Try the usual sitemap paths",
            "type": "boolean",
            "description": "If robots.txt declares no sitemap, try /sitemap.xml, /sitemap_index.xml, /sitemap-index.xml, /wp-sitemap.xml and /sitemap.txt.",
            "default": true
          },
          "maxDepth": {
            "title": "Max sitemap index depth",
            "minimum": 1,
            "maximum": 10,
            "type": "integer",
            "description": "How many levels of nested sitemap indexes to follow.",
            "default": 5
          },
          "maxSitemapsPerInput": {
            "title": "Max sitemap files per input",
            "minimum": 1,
            "type": "integer",
            "description": "Safety limit on the number of sitemap files read for one input.",
            "default": 1000
          },
          "saveUrlList": {
            "title": "Save a plain-text URL list",
            "type": "boolean",
            "description": "Also save all delivered URLs, one per line, in the key-value store record URL_LIST (up to 200,000 URLs). Handy for crawlers, LLM pipelines and wget.",
            "default": true
          },
          "maxConcurrency": {
            "title": "Sites in parallel",
            "minimum": 1,
            "maximum": 20,
            "type": "integer",
            "description": "How many inputs are processed at the same time. Within one site, at most 3 sitemap files are read at once, politely.",
            "default": 5
          },
          "proxyFallback": {
            "title": "Retry through a proxy if blocked",
            "type": "boolean",
            "description": "Requests go out directly. If a site refuses the connection (403/429), retry through Apify datacenter proxies. No extra cost for you.",
            "default": true
          },
          "residentialFallback": {
            "title": "Last resort: residential proxy",
            "type": "boolean",
            "description": "If datacenter IPs are refused too, try residential IPs (capped, see below). Never used to solve captchas or JavaScript challenges.",
            "default": true
          },
          "maxResidentialMb": {
            "title": "Residential traffic cap (MB)",
            "minimum": 1,
            "maximum": 200,
            "type": "integer",
            "description": "Maximum residential proxy traffic per run.",
            "default": 20
          }
        }
      },
      "runsResponseSchema": {
        "type": "object",
        "properties": {
          "data": {
            "type": "object",
            "properties": {
              "id": {
                "type": "string"
              },
              "actId": {
                "type": "string"
              },
              "userId": {
                "type": "string"
              },
              "startedAt": {
                "type": "string",
                "format": "date-time",
                "example": "2025-01-08T00:00:00.000Z"
              },
              "finishedAt": {
                "type": "string",
                "format": "date-time",
                "example": "2025-01-08T00:00:00.000Z"
              },
              "status": {
                "type": "string",
                "example": "READY"
              },
              "meta": {
                "type": "object",
                "properties": {
                  "origin": {
                    "type": "string",
                    "example": "API"
                  },
                  "userAgent": {
                    "type": "string"
                  }
                }
              },
              "stats": {
                "type": "object",
                "properties": {
                  "inputBodyLen": {
                    "type": "integer",
                    "example": 2000
                  },
                  "rebootCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "restartCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "resurrectCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "computeUnits": {
                    "type": "integer",
                    "example": 0
                  }
                }
              },
              "options": {
                "type": "object",
                "properties": {
                  "build": {
                    "type": "string",
                    "example": "latest"
                  },
                  "timeoutSecs": {
                    "type": "integer",
                    "example": 300
                  },
                  "memoryMbytes": {
                    "type": "integer",
                    "example": 1024
                  },
                  "diskMbytes": {
                    "type": "integer",
                    "example": 2048
                  }
                }
              },
              "buildId": {
                "type": "string"
              },
              "defaultKeyValueStoreId": {
                "type": "string"
              },
              "defaultDatasetId": {
                "type": "string"
              },
              "defaultRequestQueueId": {
                "type": "string"
              },
              "buildNumber": {
                "type": "string",
                "example": "1.0.0"
              },
              "containerUrl": {
                "type": "string"
              },
              "usage": {
                "type": "object",
                "properties": {
                  "ACTOR_COMPUTE_UNITS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_WRITES": {
                    "type": "integer",
                    "example": 1
                  },
                  "KEY_VALUE_STORE_LISTS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_INTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_EXTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_SERPS": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_UNBLOCKER_UNITS": {
                    "type": "integer",
                    "example": 0
                  }
                }
              },
              "usageTotalUsd": {
                "type": "number",
                "example": 0.00005
              },
              "usageUsd": {
                "type": "object",
                "properties": {
                  "ACTOR_COMPUTE_UNITS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_WRITES": {
                    "type": "number",
                    "example": 0.00005
                  },
                  "KEY_VALUE_STORE_LISTS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_INTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_EXTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_SERPS": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_UNBLOCKER_UNITS": {
                    "type": "integer",
                    "example": 0
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}