{ "openapi": "3.0.1", "info": { "title": "Sitemap Audit", "description": "Get a Sitemap Health Score (0-100) for any website. Discover, parse, and validate XML sitemaps. Find 404s, redirects, canonical mismatches, noindex conflicts, hreflang issues, missing pages and estimate crawl budget waste.", "version": "1.0", "x-build-id": "8DGVpFUR95AtH2XvJ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/apage~sitemap-audit/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-apage-sitemap-audit", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/apage~sitemap-audit/runs": { "post": { "operationId": "runs-sync-apage-sitemap-audit", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/apage~sitemap-audit/run-sync": { "post": { "operationId": "run-sync-apage-sitemap-audit", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Website URLs", "type": "array", "description": "Websites to audit. Enter domains (e.g., 'example.com') or full URLs. The actor will discover and analyze all sitemaps for each domain. One audit report is produced per domain.", "items": { "type": "string" } }, "sitemapUrls": { "title": "Explicit Sitemap URLs", "type": "array", "description": "Optional: specific sitemap URLs to audit (applied to all domains). These are added to any auto-discovered sitemaps. Useful when sitemaps are at non-standard locations.", "items": { "type": "string" } }, "autoDiscover": { "title": "Auto-Discover Sitemaps", "type": "boolean", "description": "Automatically discover sitemaps from robots.txt and common locations (/sitemap.xml, /sitemap_index.xml, etc.).", "default": true }, "validateUrls": { "title": "Validate URLs", "type": "boolean", "description": "Send HEAD requests to every URL in the sitemap to check for 404s, redirects, and robots.txt conflicts. Disable for faster parsing-only audits.", "default": true }, "deepInspection": { "title": "Deep Page Inspection", "type": "boolean", "description": "Fetch a sample of pages to check for canonical tag mismatches, noindex directives in sitemap, and hreflang consistency.", "default": true }, "inspectionSampleSize": { "title": "Inspection Sample Size", "minimum": 10, "maximum": 500, "type": "integer", "description": "Number of pages to deeply inspect per domain (only used when Deep Page Inspection is enabled). Higher values give more complete results but take longer.", "default": 100 }, "crawlDepth": { "title": "Missing Pages Crawl Depth", "minimum": 0, "maximum": 5, "type": "integer", "description": "Crawl each site to discover pages that are linked but missing from the sitemap. Set to 0 to disable crawling entirely.", "default": 3 }, "maxPagesToCrawl": { "title": "Max Pages to Crawl", "minimum": 50, "maximum": 5000, "type": "integer", "description": "Maximum number of pages to crawl per domain when looking for missing sitemap entries. Higher values find more missing pages but take longer and use more memory.", "default": 500 }, "maxUrlsToValidate": { "title": "Max URLs to Validate", "minimum": 100, "maximum": 50000, "type": "integer", "description": "Maximum number of sitemap URLs to validate via HEAD requests per domain. If the sitemap contains more URLs than this limit, a random sample will be validated. Prevents timeouts on very large sitemaps (10,000+ URLs).", "default": 2000 }, "maxUrlsToParse": { "title": "Max URLs to Parse", "minimum": 1000, "maximum": 500000, "type": "integer", "description": "Maximum number of URLs to collect during sitemap parsing. Enterprise sites can have 100,000+ URLs across dozens of sub-sitemaps — this cap prevents out-of-memory crashes. URLs beyond this limit are skipped (the audit still completes with a partial dataset).", "default": 50000 }, "maxConcurrency": { "title": "Max Concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum number of concurrent HTTP requests. Higher values are faster but may trigger rate limiting on some servers.", "default": 10 }, "outputFormat": { "title": "Output Format", "enum": [ "json", "csv" ], "type": "string", "description": "Format of the output data. JSON is default and works with Apify integrations. CSV is good for spreadsheets.", "default": "json" }, "proxyConfig": { "title": "Proxy Configuration", "type": "object", "description": "Proxy servers to use for HTTP requests. Datacenter proxies are usually sufficient. Use residential proxies for sites with aggressive bot protection.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "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 } } } } } } } } } }