{ "openapi": "3.0.1", "info": { "title": "Sitemap Extractor - Hardened URL Inventory", "description": "Extract URL inventories from public HTTPS sitemap XML and gzip files with robots.txt discovery, bounded index traversal, and machine-readable coverage receipts. No page crawling, login, browser, proxy, or private-network access.", "version": "0.1", "x-build-id": "DNCfX9pfwEYeAfOpl" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/8tp~sitemap-url-extractor-coverage-api/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-8tp-sitemap-url-extractor-coverage-api", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/8tp~sitemap-url-extractor-coverage-api/runs": { "post": { "operationId": "runs-sync-8tp-sitemap-url-extractor-coverage-api", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/8tp~sitemap-url-extractor-coverage-api/run-sync": { "post": { "operationId": "run-sync-8tp-sitemap-url-extractor-coverage-api", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "sitemapUrls": { "title": "Explicit HTTPS sitemap URLs", "minItems": 0, "maxItems": 50, "uniqueItems": true, "type": "array", "description": "Public HTTPS sitemap XML or XML.GZ documents to read directly. Credentials, fragments, HTTP URLs, private destinations, and auth-like query parameters are rejected.", "items": { "type": "string", "minLength": 9, "maxLength": 2048, "pattern": "^https://" }, "default": [] }, "siteUrls": { "title": "HTTPS site origins", "minItems": 0, "maxItems": 50, "uniqueItems": true, "type": "array", "description": "Public HTTPS origins such as https://example.com. The Actor reads only /robots.txt and same-origin sitemap documents; it never requests page URLs.", "items": { "type": "string", "minLength": 9, "maxLength": 512, "pattern": "^https://[^/?#]+/?$" }, "default": [] }, "maxSitemaps": { "title": "Maximum sitemap documents", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Hard run-wide cap on root and child sitemap documents scheduled for reading.", "default": 100 }, "maxUrls": { "title": "Maximum unique page URLs", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Requested cap on unique loc values emitted to the default dataset. A fixed 32 MiB retained URL-output budget may stop earlier and reports OUTPUT_MEMORY_LIMIT with non-exact coverage.", "default": 10000 }, "maxDepth": { "title": "Maximum sitemap-index depth", "minimum": 0, "maximum": 10, "type": "integer", "description": "Maximum same-origin sitemap-index recursion depth. Explicit and robots-discovered root sitemaps are depth 0.", "default": 3 }, "maxCompressedBytes": { "title": "Maximum downloaded bytes per document", "minimum": 65536, "maximum": 10485760, "type": "integer", "description": "Hard pre-decompression byte cap for each robots or sitemap response. This participates in the 64 MiB concurrent document-memory budget.", "default": 2097152 }, "maxDecompressedBytes": { "title": "Maximum decoded bytes per document", "minimum": 65536, "maximum": 52428800, "type": "integer", "description": "Hard post-gzip byte cap for each robots or sitemap document, protecting against decompression bombs. It must be at least maxCompressedBytes and participates in the 64 MiB concurrent document-memory budget.", "default": 10485760 }, "requestTimeoutSeconds": { "title": "Request timeout", "minimum": 2, "maximum": 60, "type": "integer", "description": "Maximum connect-and-read time in seconds for one HTTPS attempt, also bounded by the run deadline.", "default": 15 }, "maxRunSeconds": { "title": "Maximum run duration", "minimum": 5, "maximum": 900, "type": "integer", "description": "Hard source-processing deadline in seconds, excluding final bounded storage writes.", "default": 120 }, "maxRetries": { "title": "Maximum transient retries", "minimum": 0, "maximum": 3, "type": "integer", "description": "Retries per document for bounded network failures, HTTP 408/429, and HTTP 5xx responses. Redirects do not consume this budget.", "default": 2 }, "maxConcurrency": { "title": "Maximum sitemap concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Maximum simultaneous same-origin sitemap reads. Deterministic windows enforce the 64 MiB source-body and 320 MiB transient decode/XML allocation models. Rows and receipts are sorted before storage for stable output order.", "default": 3 }, "maxIssueRows": { "title": "Maximum issue rows", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Maximum sanitized issue details stored in the separate issues dataset. Receipts retain the complete issue count when details are capped.", "default": 500 } } }, "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 } } } } } } } } } }