{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor — SEO & Change Monitor", "description": "Extract URLs from XML and gzipped sitemaps, nested indexes and robots.txt discovery. Export lastmod, priority, hreflang, image/video data, filter URLs, audit status/redirects and page indexability, fall back to crawling, and compare persistent snapshots for URL changes.", "version": "0.2", "x-build-id": "f3qEfhcczVmMhQWbd" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/zenomastro~sitemap-url-extractor-pro/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-zenomastro-sitemap-url-extractor-pro", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/zenomastro~sitemap-url-extractor-pro/runs": { "post": { "operationId": "runs-sync-zenomastro-sitemap-url-extractor-pro", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/zenomastro~sitemap-url-extractor-pro/run-sync": { "post": { "operationId": "run-sync-zenomastro-sitemap-url-extractor-pro", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "sites" ], "properties": { "sites": { "title": "Websites or sitemap URLs", "minItems": 1, "maxItems": 100, "type": "array", "description": "Public site homepages or direct .xml/.xml.gz sitemap URLs.", "default": [ "https://example.com" ], "items": { "type": "string" } }, "maxSitemaps": { "title": "Maximum sitemap files", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Maximum sitemap files. Configure this value to control the Actor run; bounded defaults are chosen for reliable production use.", "default": 200 }, "maxUrls": { "title": "Maximum unique URLs", "minimum": 1, "maximum": 200000, "type": "integer", "description": "Maximum unique URLs. Configure this value to control the Actor run; bounded defaults are chosen for reliable production use.", "default": 25000 }, "includeMetadata": { "title": "Include lastmod/changefreq/priority", "type": "boolean", "description": "Include lastmod/changefreq/priority. Configure this value to control the Actor run; bounded defaults are chosen for reliable production use.", "default": true }, "includeMedia": { "title": "Extract image and video sitemap data", "type": "boolean", "description": "Extract image and video sitemap data. Configure this value to control the Actor run; bounded defaults are chosen for reliable production use.", "default": true }, "includeHreflang": { "title": "Extract hreflang alternates", "type": "boolean", "description": "Extract hreflang alternates. Configure this value to control the Actor run; bounded defaults are chosen for reliable production use.", "default": true }, "includeUrlPatterns": { "title": "Include URL regex patterns", "type": "array", "description": "When non-empty, only URLs matching at least one regular expression are emitted.", "default": [], "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Exclude URL regex patterns", "type": "array", "description": "URLs matching any expression are skipped.", "default": [], "items": { "type": "string" } }, "checkStatusCodes": { "title": "Audit live HTTP status and redirects", "type": "boolean", "description": "Audit live HTTP status and redirects. Configure this value to control the Actor run; bounded defaults are chosen for reliable production use.", "default": false }, "statusCheckLimit": { "title": "Maximum URLs to status-check", "minimum": 1, "maximum": 20000, "type": "integer", "description": "Maximum URLs to status-check. Configure this value to control the Actor run; bounded defaults are chosen for reliable production use.", "default": 2000 }, "statusConcurrency": { "title": "Status-check concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Status-check concurrency. Configure this value to control the Actor run; bounded defaults are chosen for reliable production use.", "default": 12 }, "fallbackCrawl": { "title": "Fallback crawl when no sitemap works", "type": "boolean", "description": "Crawl same-origin HTML links only when a site yields no sitemap URLs.", "default": false }, "fallbackCrawlLimit": { "title": "Fallback crawl page limit", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Fallback crawl page limit. Configure this value to control the Actor run; bounded defaults are chosen for reliable production use.", "default": 100 }, "snapshotMode": { "title": "Change detection", "enum": [ "none", "compare", "compare_update" ], "type": "string", "description": "Change detection. Configure this value to control the Actor run; bounded defaults are chosen for reliable production use.", "default": "compare_update" }, "snapshotId": { "title": "Optional snapshot ID", "type": "string", "description": "Use a stable ID when scheduling repeated audits. Otherwise one is derived from the input." }, "snapshotStoreName": { "title": "Persistent snapshot store", "type": "string", "description": "Persistent snapshot store. Configure this value to control the Actor run; bounded defaults are chosen for reliable production use.", "default": "sitemap-intelligence-snapshots" }, "maxSnapshotUrls": { "title": "Maximum URLs kept in a snapshot", "minimum": 100, "maximum": 100000, "type": "integer", "description": "Maximum URLs kept in a snapshot. Configure this value to control the Actor run; bounded defaults are chosen for reliable production use.", "default": 25000 }, "emitChanges": { "title": "Emit URL change rows", "type": "boolean", "description": "Emit URL change rows. Configure this value to control the Actor run; bounded defaults are chosen for reliable production use.", "default": true }, "requestTimeoutSecs": { "title": "Request timeout", "minimum": 5, "maximum": 120, "type": "integer", "description": "Request timeout. Configure this value to control the Actor run; bounded defaults are chosen for reliable production use.", "default": 25 }, "retries": { "title": "Request retries", "minimum": 0, "maximum": 5, "type": "integer", "description": "Request retries. Configure this value to control the Actor run; bounded defaults are chosen for reliable production use.", "default": 2 }, "maxSitemapSizeMb": { "title": "Maximum sitemap response size (MB)", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum sitemap response size (MB). Configure this value to control the Actor run; bounded defaults are chosen for reliable production use.", "default": 25 }, "auditIndexability": { "title": "Audit indexability signals", "type": "boolean", "description": "Fetch a bounded subset of sitemap URLs and record title, canonical, meta robots, X-Robots-Tag and a factual indexability state.", "default": false }, "indexabilityAuditLimit": { "title": "Maximum indexability pages", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Hard cap for HTML indexability audits.", "default": 500 }, "indexabilityConcurrency": { "title": "Indexability concurrency", "minimum": 1, "maximum": 30, "type": "integer", "description": "Parallel page fetches used only for optional indexability auditing.", "default": 8 } } }, "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 } } } } } } } } } }