{ "openapi": "3.0.1", "info": { "title": "Sitemap Extractor & Broken Link / Status Checker", "description": "Extract every URL from a website's sitemaps (robots.txt discovery, sitemap indexes, .xml.gz, hreflang, images) and check each page's HTTP status, redirect chain and response time. Finds broken pages and redirects for SEO audits and site migrations.", "version": "0.1", "x-build-id": "tKgyd12NDfhXnntIK" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/icyanstudio~sitemap-status-checker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-icyanstudio-sitemap-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/icyanstudio~sitemap-status-checker/runs": { "post": { "operationId": "runs-sync-icyanstudio-sitemap-status-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/icyanstudio~sitemap-status-checker/run-sync": { "post": { "operationId": "run-sync-icyanstudio-sitemap-status-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "startUrls": { "title": "Domains or sitemap URLs", "type": "array", "description": "A domain (example.com or https://example.com) to discover its sitemaps, or a direct sitemap URL (https://example.com/sitemap.xml, .xml.gz or .txt). Up to 100 entries.", "items": { "type": "string" }, "default": [ "https://crawlee.dev" ] }, "checkStatus": { "title": "Check HTTP status of each URL", "type": "boolean", "description": "Request every URL (HEAD, then GET if needed) and add status code, final URL, redirect chain, response time, content type and a broken flag. Turn off to only extract URLs from the sitemaps.", "default": true }, "followRedirects": { "title": "Follow redirects", "type": "boolean", "description": "Follow up to 10 redirects and report the final status. When off, a redirect is reported as its own 3xx status with the target in the redirect chain.", "default": true }, "lastmodAfter": { "title": "Only URLs modified after", "type": "string", "description": "Keep only URLs whose sitemap is on or after this date. Use a date (2025-01-31) or a relative age (7 days, 2 weeks, 6 months). URLs without a are skipped when this is set." }, "urlPattern": { "title": "Include URLs matching (regex)", "type": "string", "description": "Keep only URLs that match this regular expression (case-insensitive). Example: /blog/" }, "excludeUrlPattern": { "title": "Exclude URLs matching (regex)", "type": "string", "description": "Drop URLs that match this regular expression (case-insensitive). Example: \\.(pdf|jpg)$|/tag/" }, "maxUrls": { "title": "Maximum URLs", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stop after this many URLs (after filters and de-duplication). Each URL is one result, and the limit also caps the cost.", "default": 1000 }, "concurrency": { "title": "Concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Status checks running at the same time across all hosts. To be polite, at most 2 requests run at once against any single host, so a one-site sitemap is checked 2 URLs at a time.", "default": 5 } } }, "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 } } } } } } } } } }