{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor & Broken Link Checker", "description": "Sitemap URL extractor for public sites. Export URLs and lastmod values as JSON with robots.txt discovery; optionally include HTTP status, redirects and request errors.", "version": "1.0", "x-build-id": "OKCFc5gHpwEogR8LG" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/grit-77~sitemap-url-extractor-broken-link-checker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-grit-77-sitemap-url-extractor-broken-link-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/grit-77~sitemap-url-extractor-broken-link-checker/runs": { "post": { "operationId": "runs-sync-grit-77-sitemap-url-extractor-broken-link-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/grit-77~sitemap-url-extractor-broken-link-checker/run-sync": { "post": { "operationId": "run-sync-grit-77-sitemap-url-extractor-broken-link-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Sites, robots.txt or sitemap URLs", "type": "array", "description": "Public HTTP(S) sites, robots.txt files, or XML/gzip sitemap URLs. Site inputs use origin robots.txt and fall back to /sitemap.xml. Bare domains use HTTPS. Duplicates are removed. Maximum 1000 starting URLs.", "items": { "type": "string" } }, "checkStatus": { "title": "Check URL status", "type": "boolean", "description": "Check each extracted URL. Disabled: extract metadata without requesting page URLs.", "default": false }, "checkMethod": { "title": "HTTP check method", "enum": [ "HEAD", "GET" ], "type": "string", "description": "HEAD requests headers only. GET also closes after headers, without reading page bodies.", "default": "HEAD" }, "fallbackToGet": { "title": "GET fallback for rejected HEAD", "type": "boolean", "description": "Retry a HEAD check using GET when the final response is 405 or 501. The redirectChain then describes the GET request.", "default": true }, "maxItems": { "title": "Maximum output rows", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Hard cap on all dataset rows, including uncharged discovery diagnostics.", "default": 1000 }, "concurrency": { "title": "Concurrent requests", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum simultaneous HTTP requests and URL checker tasks.", "default": 10 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 1, "maximum": 120, "type": "integer", "description": "Timeout for each network operation and DNS lookup; retries and redirects can increase total time.", "default": 20 }, "maxRetries": { "title": "Retries per request", "minimum": 0, "maximum": 5, "type": "integer", "description": "Extra attempts for network errors and HTTP 408, 425, 429, 500, 502, 503 and 504. Exponential backoff; Retry-After is capped at 30 seconds.", "default": 2 }, "maxSitemaps": { "title": "Maximum sitemap files", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Global cap on fetched sitemap documents. robots.txt requests are additional.", "default": 1000 }, "maxDepth": { "title": "Maximum index nesting", "minimum": 0, "maximum": 50, "type": "integer", "description": "Initial sitemap is depth zero. A deeper source produces an uncharged diagnostic.", "default": 10 }, "maxRedirects": { "title": "Maximum followed redirects", "minimum": 0, "maximum": 30, "type": "integer", "description": "Limit per sitemap fetch or URL status check. Redirect loops and limits remain visible.", "default": 10 } } }, "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 } } } } } } } } } }