{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Status Checker", "description": "Discover XML sitemaps and check each URL for HTTP status, redirects, response time, and broken links.", "version": "0.1", "x-build-id": "Le5cYtwi4DJcV8Fvl" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/plusonets~sitemap-url-status-checker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-plusonets-sitemap-url-status-checker", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/plusonets~sitemap-url-status-checker/runs": { "post": { "operationId": "runs-sync-plusonets-sitemap-url-status-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/plusonets~sitemap-url-status-checker/run-sync": { "post": { "operationId": "run-sync-plusonets-sitemap-url-status-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Website or sitemap URLs", "type": "array", "description": "Homepages or direct sitemap URLs. A homepage is expanded from robots.txt Sitemap lines and, when those are missing, from /sitemap.xml and other common sitemap paths. A .xml, .xml.gz, or other sitemap URL is parsed directly, including sitemap indexes.", "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 URLs", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stop after this many unique page URLs. Child sitemaps are not fetched once the cap is reached. The default is small so the standard run finishes quickly.", "default": 50 }, "checkStatus": { "title": "Check HTTP status", "type": "boolean", "description": "Request each page URL and record the status code, redirect chain, final URL, and response time. Uses HEAD, then GET when HEAD is rejected. Turn this off to only list sitemap URLs.", "default": true }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "When status checks are on, skip URLs that robots.txt disallows for this Actor's User-Agent. Sitemap discovery still reads Sitemap lines either way. Skipped URLs are listed and are not charged as URL checks.", "default": true }, "maxConcurrency": { "title": "Max concurrent requests per host", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many requests may be in flight to a single host. Applies to sitemap downloads and status checks.", "default": 4 }, "minDelayMillis": { "title": "Minimum delay per host (ms)", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Minimum gap between the start of requests to the same host. A robots.txt Crawl-delay is also applied, capped at 2 seconds so one site cannot stall the run.", "default": 200 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 3, "maximum": 60, "type": "integer", "description": "Time allowed for one HTTP request, including connection. Timeouts are recorded as broken and are not retried.", "default": 15 }, "maxRedirects": { "title": "Maximum redirects", "minimum": 0, "maximum": 10, "type": "integer", "description": "How many redirects to follow for one URL. The hop list and final URL are stored on the row. Hitting the cap is reported as broken.", "default": 5 }, "includeUrlGlobs": { "title": "Include URL globs", "type": "array", "description": "Optional patterns such as https://example.com/blog/*. When this list is non-empty, a page URL must match at least one pattern.", "default": [], "items": { "type": "string" } }, "excludeUrlGlobs": { "title": "Exclude URL globs", "type": "array", "description": "Page URLs matching any of these patterns are dropped. Example: https://example.com/tag/*.", "default": [], "items": { "type": "string" } } } }, "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 } } } } } } } } } }