Sitemap URL Status Auditor
Pricing
Pay per event
Go to Apify Store
Sitemap URL Status Auditor
Audit XML sitemaps for broken URLs, redirects, HTTP status codes, response timing, content type, canonical tags, and robots metadata.
Sitemap URL Status Auditor
Pricing
Pay per event
Audit XML sitemaps for broken URLs, redirects, HTTP status codes, response timing, content type, canonical tags, and robots metadata.
You can access the Sitemap URL Status Auditor programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.1", "x-build-id": "ufdQ5P0TzOfcADEhE" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/automation-lab~sitemap-url-status-auditor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-automation-lab-sitemap-url-status-auditor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/automation-lab~sitemap-url-status-auditor/runs": { "post": { "operationId": "runs-sync-automation-lab-sitemap-url-status-auditor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/automation-lab~sitemap-url-status-auditor/run-sync": { "post": { "operationId": "run-sync-automation-lab-sitemap-url-status-auditor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Sitemap URLs or websites", "type": "array", "description": "XML sitemap URLs, sitemap index URLs, or website roots/domains. Website roots automatically use /sitemap.xml.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "domains": { "title": "Additional domains", "type": "array", "description": "Optional domains or website URLs to check via /sitemap.xml, one per item.", "items": { "type": "string" } }, "maxUrls": { "title": "Maximum URLs to audit", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum unique page URLs checked across all sitemap sources.", "default": 20 }, "maxSitemaps": { "title": "Maximum sitemap files", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum XML sitemap documents to fetch while expanding sitemap indexes.", "default": 20 }, "maxDepth": { "title": "Maximum sitemap index depth", "minimum": 0, "maximum": 10, "type": "integer", "description": "How many nested sitemap-index levels to follow.", "default": 3 }, "concurrency": { "title": "URL check concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Parallel page URL checks. Lower this for fragile websites.", "default": 10 }, "requestTimeoutSecs": { "title": "Request timeout seconds", "minimum": 5, "maximum": 120, "type": "integer", "description": "Timeout for each sitemap or page request.", "default": 20 }, "maxRetries": { "title": "Retries per request", "minimum": 0, "maximum": 5, "type": "integer", "description": "Retry transient network failures before recording an error row.", "default": 1 }, "headFirst": { "title": "Use HEAD before GET", "type": "boolean", "description": "Check URLs with HEAD first, then fallback to GET for servers that block or mishandle HEAD.", "default": true }, "followRedirects": { "title": "Follow redirects", "type": "boolean", "description": "Follow HTTP redirects and report the final URL and redirect count.", "default": true }, "includePageMetadata": { "title": "Extract canonical and robots meta", "type": "boolean", "description": "Fetch each page with GET to extract canonical URL and robots meta. This is slower but useful for SEO audits.", "default": false }, "userAgent": { "title": "User-Agent", "type": "string", "description": "Polite User-Agent sent to target websites.", "default": "Automation-Lab-Sitemap-URL-Status-Auditor/1.0 (+https://apify.com/automation-lab/sitemap-url-status-auditor)" } } }, "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 } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Sitemap URL Status Auditor from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: