{ "openapi": "3.0.1", "info": { "title": "Sitemap Validator & URL Extractor", "description": "Find a site's XML sitemaps from robots.txt, validate every file, extract all URLs with lastmod/changefreq/priority, diff against a previous run, and optionally check HTTP status. Broken or unreadable sitemaps are reported, never silently skipped.", "version": "0.0", "x-build-id": "cNwoOqneuUOeRksIW" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/lintlab~sitemap-doctor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-lintlab-sitemap-doctor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/lintlab~sitemap-doctor/runs": { "post": { "operationId": "runs-sync-lintlab-sitemap-doctor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/lintlab~sitemap-doctor/run-sync": { "post": { "operationId": "run-sync-lintlab-sitemap-doctor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Site or sitemap URLs", "type": "array", "description": "Required list of HTTP(S) site roots or sitemap URLs. Site roots are inspected, then robots.txt Sitemap directives are used; /sitemap.xml and /sitemap_index.xml are fallbacks. Each successfully parsed sitemap file incurs the sitemap-file event price.", "default": [ { "url": "https://www.sitemaps.org/" } ], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxUrls": { "title": "Maximum URL records", "minimum": 1, "maximum": 200000, "type": "integer", "description": "Maximum dataset URL records for the whole run, including duplicate occurrences and removed diff records. Default 10000; range 1–200000. Unique current URLs incur the URL extraction event price after they are pushed.", "default": 10000 }, "maxSitemapFiles": { "title": "Maximum sitemap files", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum number of sitemap files fetched across the run. Default 200; each file that is fetched and parsed successfully incurs one sitemap-file event charge.", "default": 200 }, "checkStatus": { "title": "Check URL HTTP status", "type": "boolean", "description": "When true, send HEAD requests (GET fallback for HTTP 405/501), at most 5 concurrently per host, while honoring robots.txt. Every URL check completed with an HTTP response incurs one status-check event charge. Default false.", "default": false }, "statusSampleSize": { "title": "Status check sample size", "minimum": 0, "maximum": 200000, "type": "integer", "description": "Number of unique extracted URLs to status-check. Use 0 to check all when checkStatus is true. Default 0; unit is URLs.", "default": 0 }, "previousDatasetId": { "title": "Previous dataset ID", "type": "string", "description": "Optional Apify dataset ID from an earlier Sitemap Doctor run. Current URLs are marked added or unchanged, and URLs missing now are emitted as removed records. Removed records are not charged." }, "sameHostOnly": { "title": "Follow only same-host sitemap files", "type": "boolean", "description": "When true (default), sitemap indexes do not lead to sitemap files on another hostname. Cross-host page URLs are still emitted and flagged so an agent can diagnose them.", "default": true } } }, "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 } } } } } } } } } }