{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor – All URLs, Changes & Redirects", "description": "Get every URL from any website's sitemaps: robots.txt discovery, sitemap indexes, .gz, image/video/news, hreflang, lastmod filters, new/removed URL monitoring and status, redirect and canonical checks.", "version": "0.1", "x-build-id": "HPVK4m1rPaoA4M97i" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/mikumans~sitemap-extractor-pro/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-mikumans-sitemap-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/mikumans~sitemap-extractor-pro/runs": { "post": { "operationId": "runs-sync-mikumans-sitemap-extractor-pro", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/mikumans~sitemap-extractor-pro/run-sync": { "post": { "operationId": "run-sync-mikumans-sitemap-extractor-pro", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrls" ], "properties": { "startUrls": { "title": "Websites or sitemap URLs", "type": "array", "description": "Domains/website URLs (sitemaps found via robots.txt and common paths) or direct sitemap URLs (.xml, .xml.gz, sitemap indexes).", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxUrls": { "title": "Max URLs per site", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Stop after this many page URLs per start URL.", "default": 1000 }, "maxSitemaps": { "title": "Max sitemap files per site", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Safety cap on sitemap files processed.", "default": 500 }, "lastmodFrom": { "title": "Lastmod from", "type": "string", "description": "Only URLs with lastmod on/after this date (YYYY-MM-DD). URLs without lastmod are excluded when a date filter is set." }, "lastmodTo": { "title": "Lastmod to", "type": "string", "description": "Only URLs with lastmod on/before this date (YYYY-MM-DD)." }, "includeUrlPattern": { "title": "Include URL pattern (regex)", "type": "string", "description": "Only keep URLs matching this regular expression." }, "excludeUrlPattern": { "title": "Exclude URL pattern (regex)", "type": "string", "description": "Drop URLs matching this regular expression." }, "includeMedia": { "title": "Image, video and news data", "type": "boolean", "description": "Extract image:, video: and news: sitemap extensions.", "default": true }, "includeHreflang": { "title": "Hreflang alternates", "type": "boolean", "description": "Extract xhtml:link hreflang alternates.", "default": true }, "diffWithPreviousRun": { "title": "Diff with previous run", "type": "boolean", "description": "Mark URLs as new/existing and list removed URLs compared with the last run for the same site (state kept in the named store 'sitemap-extractor-state').", "default": true }, "onlyNewUrls": { "title": "Output only new URLs", "type": "boolean", "description": "With diff enabled, output only URLs not seen in the previous run (great for monitoring).", "default": false }, "stateKey": { "title": "State key (optional)", "type": "string", "description": "Custom key for diff state. By default the state is tied to the start URL plus filters, so different filter sets are tracked separately. Removed URLs are only reported when the run was not cut off by Max URLs." }, "checkStatus": { "title": "Check page status", "type": "boolean", "description": "Request each URL: HTTP status, redirects (with chain), final URL, response time.", "default": false }, "detectCanonical": { "title": "Detect canonical and meta robots", "type": "boolean", "description": "With status checks, read rel=canonical (HTML or Link header) and meta robots.", "default": true }, "statusConcurrency": { "title": "Status check concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Parallel page requests.", "default": 10 }, "requestTimeoutSecs": { "title": "Request timeout (s)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Timeout per request.", "default": 30 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional proxy for sites that block datacenter IPs (e.g. some news publishers).", "default": { "useApifyProxy": false } } } }, "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 } } } } } } } } } }