Sitemap Freshness & Schema Integrity Auditor
Pricing
from $0.22 / 1,000 audited urls
Audit sitemap lastmod, schema dates, and page freshness with static HTTP checks and deterministic issue codes.
You can access the Sitemap Freshness & Schema Integrity Auditor programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.1", "x-build-id": "Iar4bxv1c0kBnFbGX" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/sebastian-actors~sitemap-freshness-schema-integrity-auditor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-sebastian-actors-sitemap-freshness-schema-integrity-auditor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/sebastian-actors~sitemap-freshness-schema-integrity-auditor/runs": { "post": { "operationId": "runs-sync-sebastian-actors-sitemap-freshness-schema-integrity-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/sebastian-actors~sitemap-freshness-schema-integrity-auditor/run-sync": { "post": { "operationId": "run-sync-sebastian-actors-sitemap-freshness-schema-integrity-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", "properties": { "sitemapUrls": { "title": "Sitemap URLs", "type": "array", "description": "XML sitemap URLs to discover HTML pages from. Use this for the strongest audit because sitemap lastmod can be compared with page and schema dates.", "items": { "type": "string" } }, "urls": { "title": "Additional URLs", "type": "array", "description": "Individual HTML page URLs to check. Do not put sitemap.xml or robots.txt here; put sitemap files in Sitemap URLs.", "items": { "type": "string" } }, "maxPages": { "title": "Max pages", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum number of pages to analyze after sitemap expansion and URL deduplication.", "default": 100 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Maximum number of pages fetched in parallel. Keep this conservative for polite, low-cost audits.", "default": 5 }, "requestDelayMs": { "title": "Delay between requests per origin in ms", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Polite delay between requests to the same origin, in milliseconds.", "default": 250 }, "requestTimeoutSecs": { "title": "Request timeout seconds", "minimum": 5, "maximum": 60, "type": "integer", "description": "Timeout for sitemap and page HTTP requests, in seconds.", "default": 20 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Check robots.txt and skip URLs disallowed for this crawler before fetching pages.", "default": true }, "includeSeoBasics": { "title": "Include basic SEO context", "type": "boolean", "description": "Extract title, meta description, canonical, H1, robots meta, Open Graph, and Twitter metadata as context.", "default": true }, "includeSchemaValidation": { "title": "Include local schema checks", "type": "boolean", "description": "Parse JSON-LD and check common recommended fields for supported Article, Recipe, Product, and organization-style schema.", "default": true }, "includeRawDateCandidates": { "title": "Include raw date candidates", "type": "boolean", "description": "Include all raw date candidates found in schema, meta tags, and visible semantic elements. Useful for debugging, but more verbose.", "default": false }, "dateMismatchToleranceDays": { "title": "Date mismatch tolerance days", "minimum": 0, "maximum": 30, "type": "integer", "description": "Number of days allowed between date sources before a mismatch issue is flagged.", "default": 3 }, "userAgent": { "title": "User agent", "type": "string", "description": "User-Agent header used for static HTTP requests.", "default": "Sitemap Freshness & Schema Integrity Auditor (+https://apify.com/)" } } }, "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 Freshness & Schema Integrity 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: