{ "openapi": "3.0.1", "info": { "title": "Sitemap Indexability & AI Crawler Audit API", "description": "Audit sitemap URLs, robots.txt, HTTP status, canonical/noindex signals, and AI crawler access as structured JSON for technical SEO and agents.", "version": "0.1", "x-build-id": "zTFCyHrmvYtLgHqef" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/dobus~sitemap-indexability-ai-crawler-audit/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-dobus-sitemap-indexability-ai-crawler-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/dobus~sitemap-indexability-ai-crawler-audit/runs": { "post": { "operationId": "runs-sync-dobus-sitemap-indexability-ai-crawler-audit", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/dobus~sitemap-indexability-ai-crawler-audit/run-sync": { "post": { "operationId": "run-sync-dobus-sitemap-indexability-ai-crawler-audit", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "domains": { "title": "Domains", "type": "array", "description": "Domains or website homepages to audit. The Actor discovers robots.txt and sitemap.xml automatically.", "items": { "type": "string" } }, "sitemapUrls": { "title": "Sitemap URLs", "type": "array", "description": "Optional sitemap.xml or sitemap index URLs to audit directly.", "items": { "type": "string" } }, "urls": { "title": "Direct URLs", "type": "array", "description": "Optional individual URLs to audit even if they are not present in a sitemap.", "items": { "type": "string" } }, "maxUrlsPerSite": { "title": "Maximum URLs per site", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Safety limit for sitemap URLs checked per website.", "default": 100 }, "includeNestedSitemaps": { "title": "Follow sitemap indexes", "type": "boolean", "description": "Follow nested sitemaps found inside sitemap index files.", "default": true }, "sameHostOnly": { "title": "Same host only", "type": "boolean", "description": "Keep only URLs whose host matches the audited domain or sitemap host.", "default": true }, "checkHttpStatus": { "title": "Check HTTP status", "type": "boolean", "description": "Fetch each URL and return status code, final URL, redirect flag, and content type.", "default": true }, "checkIndexability": { "title": "Check indexability signals", "type": "boolean", "description": "Parse HTML for meta robots noindex and canonical tags when HTML is returned.", "default": true }, "checkRobotsTxt": { "title": "Check robots.txt", "type": "boolean", "description": "Read robots.txt and report whether standard crawlers are allowed to fetch each URL.", "default": true }, "checkAiCrawlerAccess": { "title": "Check AI crawler access", "type": "boolean", "description": "Report whether common AI crawler user agents are allowed by robots.txt.", "default": true }, "aiCrawlerUserAgents": { "title": "AI crawler user agents", "type": "array", "description": "AI-related user agents to evaluate against robots.txt.", "default": [ "GPTBot", "ChatGPT-User", "ClaudeBot", "PerplexityBot", "Google-Extended", "CCBot" ], "items": { "type": "string" } }, "requestsPerSecond": { "title": "Requests per second", "minimum": 0.2, "maximum": 10, "type": "number", "description": "Per-run rate limit. Keep this conservative for third-party sites.", "default": 2 }, "timeoutSecs": { "title": "Request timeout seconds", "minimum": 5, "maximum": 60, "type": "integer", "description": "Timeout for robots.txt, sitemap, and URL fetches.", "default": 20 }, "customUserAgent": { "title": "Custom User-Agent", "type": "string", "description": "Optional identifiable User-Agent for HTTP requests. Include a contact URL or email when auditing sites you control.", "default": "Sitemap Indexability AI Crawler Audit (+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 } } } } } } } } } }