{
  "openapi": "3.0.1",
  "info": {
    "title": "Sitemap Extractor – All URLs from sitemap.xml + Status Check",
    "description": "Extract every URL from any website's sitemap.xml: auto-discovery via robots.txt, nested sitemap indexes, .xml.gz, image/news/video/hreflang tags and lastmod. Filter by date or glob, get only new URLs, and optionally check HTTP status, redirects and canonical per URL.",
    "version": "0.1",
    "x-build-id": "9cdBqRMrcSYniZUaR"
  },
  "servers": [
    {
      "url": "https://api.apify.com/v2"
    }
  ],
  "paths": {
    "/acts/gazidev~sitemap-url-extractor/run-sync-get-dataset-items": {
      "post": {
        "operationId": "run-sync-get-dataset-items-gazidev-sitemap-url-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": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    },
    "/acts/gazidev~sitemap-url-extractor/runs": {
      "post": {
        "operationId": "runs-sync-gazidev-sitemap-url-extractor",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor and returns information about the initiated run in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$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": {
                  "$ref": "#/components/schemas/runsResponseSchema"
                }
              }
            }
          }
        }
      }
    },
    "/acts/gazidev~sitemap-url-extractor/run-sync": {
      "post": {
        "operationId": "run-sync-gazidev-sitemap-url-extractor",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$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": [
          "startUrls"
        ],
        "properties": {
          "startUrls": {
            "title": "Websites, sitemap URLs or robots.txt URLs",
            "type": "array",
            "description": "Any mix of: a domain (`example.com` – the sitemap is found automatically via robots.txt `Sitemap:` lines, then `/sitemap.xml`, `/sitemap_index.xml`, `/wp-sitemap.xml`, `/sitemap.xml.gz`…), a direct sitemap URL (`https://example.com/sitemap_index.xml`, `.xml.gz`, `.txt`, RSS/Atom feed) or a `robots.txt` URL. Sitemap indexes are followed recursively.",
            "default": [
              "https://crawlee.dev"
            ],
            "items": {
              "type": "string"
            }
          },
          "maxUrls": {
            "title": "Max URLs (total)",
            "minimum": 0,
            "type": "integer",
            "description": "Stop after saving this many URLs in total (0 = no limit, extract everything). You pay only for URLs saved.",
            "default": 1000
          },
          "maxUrlsPerSite": {
            "title": "Max URLs per website",
            "minimum": 0,
            "type": "integer",
            "description": "Limit per website when you give several sites (0 = no per-site limit).",
            "default": 0
          },
          "checkStatus": {
            "title": "Check HTTP status of every URL",
            "type": "boolean",
            "description": "Request each URL (HEAD, falling back to GET when the server refuses HEAD) and add `status`, `finalUrl`, `redirectHops`, `redirectChain`, `contentType`, `responseMs` and `X-Robots-Tag`. Finds 404s, redirects and dead pages listed in your sitemap. Charged per URL checked.",
            "default": false
          },
          "extractCanonical": {
            "title": "Also read canonical + meta robots",
            "type": "boolean",
            "description": "Uses GET instead of HEAD and reads the first 64 KB of each HTML page to add `canonical`, `canonicalMatchesUrl` (self-canonical?) and `metaRobots` (noindex…). Needs `Check HTTP status` on.",
            "default": false
          },
          "statusConcurrency": {
            "title": "Status checks in parallel",
            "minimum": 1,
            "maximum": 50,
            "type": "integer",
            "description": "Parallel status requests overall. At most 5 requests per host run at the same time, so target servers are not hammered.",
            "default": 20
          },
          "includeGlobs": {
            "title": "Include only URLs matching (globs)",
            "type": "array",
            "description": "Keep only URLs matching at least one pattern. `*` matches anything. Patterns without a scheme match anywhere in the URL, e.g. `/blog/*`, `*/products/*`, `https://example.com/de/*`.",
            "items": {
              "type": "string"
            }
          },
          "excludeGlobs": {
            "title": "Exclude URLs matching (globs)",
            "type": "array",
            "description": "Drop URLs matching any of these patterns, e.g. `*/tag/*`, `*.pdf`, `*?page=*`.",
            "items": {
              "type": "string"
            }
          },
          "lastmodSince": {
            "title": "Only URLs modified since",
            "type": "string",
            "description": "Keep only URLs whose `<lastmod>` (or news publication date / feed date) is on or after this date. Absolute (`2025-01-31`) or relative (`7 days`, `24 hours`, `3 months`)."
          },
          "keepUrlsWithoutLastmod": {
            "title": "Keep URLs without lastmod",
            "type": "boolean",
            "description": "When `Only URLs modified since` is set, also keep URLs that have no `<lastmod>` at all (by default they are dropped).",
            "default": false
          },
          "onlyNew": {
            "title": "Only new URLs since the last run",
            "type": "boolean",
            "description": "Remembers the URLs already returned for each website (in a named key-value store) and outputs only URLs not seen in previous runs. Schedule it daily to monitor competitors' new pages, products or articles. The first run returns everything.",
            "default": false
          },
          "stateKey": {
            "title": "Monitoring state name",
            "type": "string",
            "description": "Optional. Use different names to keep separate 'seen URLs' memories for different tasks watching the same site."
          },
          "includeSiteSummaryRows": {
            "title": "Add a summary row per website to the dataset",
            "type": "boolean",
            "description": "The per-site summary (sitemaps found, URL counts, newest/oldest lastmod, status-code histogram, failed sitemaps) is always saved to the key-value store record `SUMMARY`. Turn this on to also append it to the dataset as rows with `type: \"site-summary\"` (free).",
            "default": false
          },
          "discoverCommonPaths": {
            "title": "Try common sitemap paths",
            "type": "boolean",
            "description": "If robots.txt lists no (working) sitemap, try `/sitemap.xml`, `/sitemap_index.xml`, `/wp-sitemap.xml`, `/sitemap-index.xml`, `/sitemap.xml.gz` and `/sitemap.txt`.",
            "default": true
          },
          "maxSitemapDepth": {
            "title": "Max sitemap index depth",
            "minimum": 1,
            "maximum": 10,
            "type": "integer",
            "description": "How deep nested sitemap indexes are followed (index → index → sitemap). Loops are detected automatically.",
            "default": 5
          },
          "maxConcurrency": {
            "title": "Websites in parallel",
            "minimum": 1,
            "maximum": 50,
            "type": "integer",
            "description": "How many websites are processed at the same time (each reads up to 3 sitemaps in parallel).",
            "default": 5
          },
          "requestTimeoutSecs": {
            "title": "Request timeout (seconds)",
            "minimum": 5,
            "maximum": 180,
            "type": "integer",
            "description": "Per-request timeout. Failed requests are retried.",
            "default": 30
          },
          "proxyConfiguration": {
            "title": "Proxy configuration",
            "type": "object",
            "description": "Optional. Sitemaps are public and rarely blocked; only use a proxy for sites that block datacenter IPs.",
            "default": {
              "useApifyProxy": false
            }
          }
        }
      },
      "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
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}