{
  "openapi": "3.0.1",
  "info": {
    "title": "Sitemap Link Inventory: All URLs + Broken-Link Check, $1/1k",
    "description": "Find every sitemap for a domain (robots.txt, nested indexes, .gz, .txt, common paths) and return all URLs with lastmod, priority, images, hreflang, path groups and duplicates. Optional broken-link, redirect, noindex checks. Partial results never fail the run. $0.001 per sitemap file / link checked.",
    "version": "0.1",
    "x-build-id": "lBxsGOYjJhwB7D7FX"
  },
  "servers": [
    {
      "url": "https://api.apify.com/v2"
    }
  ],
  "paths": {
    "/acts/transparent_meteorite~sitemap-link-inventory/run-sync-get-dataset-items": {
      "post": {
        "operationId": "run-sync-get-dataset-items-transparent_meteorite-sitemap-link-inventory",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$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/transparent_meteorite~sitemap-link-inventory/runs": {
      "post": {
        "operationId": "runs-sync-transparent_meteorite-sitemap-link-inventory",
        "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/transparent_meteorite~sitemap-link-inventory/run-sync": {
      "post": {
        "operationId": "run-sync-transparent_meteorite-sitemap-link-inventory",
        "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": "Domains or sitemap URLs",
            "type": "array",
            "description": "One per row. A bare domain or site URL (https:// is added if missing) triggers discovery: robots.txt Sitemap lines first, then common paths such as /sitemap.xml. A URL that looks like a sitemap (.xml, .xml.gz, .txt, or 'sitemap' in the path) is fetched directly. Public hosts only; private IPs and localhost are refused.",
            "default": [
              "https://crawlee.dev"
            ],
            "items": {
              "type": "string"
            }
          },
          "maxUrlsPerSite": {
            "title": "Max URLs per site",
            "minimum": 1,
            "maximum": 500000,
            "type": "integer",
            "description": "Hard cap on unique URLs returned per site. Reading stops (and the download is aborted) once it is reached, so a 2-million-URL sitemap does not stall the run. The site summary says when the cap truncated results.",
            "default": 1000
          },
          "checkMode": {
            "title": "Link check mode",
            "enum": [
              "off",
              "sitemapUrls",
              "pageLinks"
            ],
            "type": "string",
            "description": "off: inventory only. sitemapUrls: request the sitemap URLs (HEAD, GET fallback) and flag 404, 5xx, unreachable, redirects and noindex. pageLinks: request the internal links found on the pages listed below (or the home page of each start URL). Each request made is a billable 'link checked' event.",
            "default": "off"
          },
          "maxSitemapFiles": {
            "title": "Max sitemap files per site",
            "minimum": 1,
            "maximum": 1000,
            "type": "integer",
            "description": "Cap on sitemap files fetched per site, counting index files. Nested indexes are followed up to 6 levels deep.",
            "default": 50
          },
          "includeDuplicates": {
            "title": "Emit duplicate URL rows",
            "type": "boolean",
            "description": "Duplicates are always counted and listed in the site summary. Turn this on to also emit a row (isDuplicate = true) for every repeat occurrence.",
            "default": false
          },
          "pageUrls": {
            "title": "Pages to scan (pageLinks mode)",
            "type": "array",
            "description": "Pages whose internal links are checked when Link check mode is 'pageLinks'. Leave empty to use the home page of each start URL. The page fetch itself is not billed; each link checked is.",
            "items": {
              "type": "string"
            }
          },
          "maxLinksToCheck": {
            "title": "Max links to check",
            "minimum": 0,
            "maximum": 5000,
            "type": "integer",
            "description": "sitemapUrls mode: per site, an evenly spaced sample across the whole inventory (not just the first rows). pageLinks mode: per page. This is the cost ceiling for check mode.",
            "default": 100
          },
          "checkIndexability": {
            "title": "Read noindex signals",
            "type": "boolean",
            "description": "Uses a GET for each checked URL (first 256 KB) to read meta robots, plus the X-Robots-Tag header, so noindex pages in the sitemap are flagged. Turn off for HEAD-only, lighter checks.",
            "default": true
          },
          "checkCanonical": {
            "title": "Flag canonical mismatches",
            "type": "boolean",
            "description": "Compare each checked page's rel=canonical with its sitemap URL (trailing slash ignored). Off by default.",
            "default": false
          },
          "checkConcurrency": {
            "title": "Check concurrency",
            "minimum": 1,
            "maximum": 20,
            "type": "integer",
            "description": "Parallel link checks. Requests to the same host are still spaced by the delay below.",
            "default": 5
          },
          "requestDelayMs": {
            "title": "Delay between requests to one host (ms)",
            "minimum": 100,
            "maximum": 10000,
            "type": "integer",
            "description": "Minimum gap between requests to the same host. A larger robots.txt Crawl-delay (up to 10 s) overrides this.",
            "default": 300
          },
          "requestTimeoutSecs": {
            "title": "Request timeout (seconds)",
            "minimum": 5,
            "maximum": 60,
            "type": "integer",
            "description": "Time to first response headers for each request. Slow servers become 'timeout' rows, never failed runs.",
            "default": 20
          },
          "timeBudgetSecs": {
            "title": "Time budget (seconds)",
            "minimum": 30,
            "maximum": 3300,
            "type": "integer",
            "description": "Soft limit for the whole run. When it passes, the actor stops fetching and returns what it has with status 'partial-time-budget'.",
            "default": 540
          },
          "userAgent": {
            "title": "User-Agent",
            "type": "string",
            "description": "Sent on every request and matched against robots.txt (the default token is SitemapLinkInventoryBot).",
            "default": "SitemapLinkInventoryBot/1.0 (+https://apify.com/transparent_meteorite)"
          },
          "monitorMode": {
            "title": "Monitor mode (only new or changed)",
            "type": "boolean",
            "description": "Recurring-run mode: return only sitemap URLs that are new or whose lastmod changed since the last monitor run; sites without lastmod only report new URLs. Best with Check mode off. The first run is a baseline and returns everything in scope. Unchanged records are not returned and not charged. Schedule the actor (Schedules tab) to get a recurring feed. Each row gets a changeType of new or changed.",
            "default": false
          },
          "reportRemoved": {
            "title": "Also report removed (monitor mode)",
            "type": "boolean",
            "description": "With monitor mode on, also emit one row with changeType \"removed\" for URLs that were in a site's sitemap in an earlier run and are gone now, only for sites whose sitemaps were read completely this run. Removed rows are free: they are not charged and never count toward your charge limit or max results. Nothing is reported as removed on the baseline run, when the fetch was incomplete or hit a cap, or when your input filters changed since the baseline (the next run re-learns the baseline instead). Default off.",
            "default": false
          },
          "monitorName": {
            "title": "Monitor name",
            "type": "string",
            "description": "Name of the saved baseline. Use a different name per watch list so schedules do not overwrite each other. Default is 'default'.",
            "default": "default"
          }
        }
      },
      "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
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}