{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor", "description": "Extract every URL from any website's XML sitemaps: auto-discovers sitemaps via robots.txt, follows sitemap indexes and .gz files, returns lastmod, hreflang, images, robots.txt status and optional HTTP status codes. $0.30 per 1,000 URLs.", "version": "1.0", "x-build-id": "BeyuMPByAbBkDB0aC" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/jakob_jerich~sitemap-url-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-jakob_jerich-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/jakob_jerich~sitemap-url-extractor/runs": { "post": { "operationId": "runs-sync-jakob_jerich-sitemap-url-extractor", "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/jakob_jerich~sitemap-url-extractor/run-sync": { "post": { "operationId": "run-sync-jakob_jerich-sitemap-url-extractor", "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": "Website addresses (e.g. https://www.example.com) or direct sitemap URLs (e.g. https://www.example.com/sitemap.xml, .xml.gz, sitemap index, RSS/Atom feed or plain-text URL list). For a website, sitemaps are discovered from robots.txt and the usual locations.", "items": { "type": "string" } }, "maxUrlsPerSite": { "title": "Max URLs per site", "minimum": 0, "maximum": 5000000, "type": "integer", "description": "Stop after saving this many URLs for each start URL. Use 0 for no limit. You pay per saved URL, so this also caps your cost.", "default": 10000 }, "includePatterns": { "title": "Only include URLs matching", "type": "array", "description": "Optional. Keep only URLs that match at least one of these regular expressions (case-insensitive), e.g. \"/blog/\" or \"/products/.+\". Leave empty to keep all.", "default": [], "items": { "type": "string" } }, "excludePatterns": { "title": "Exclude URLs matching", "type": "array", "description": "Optional. Drop URLs that match any of these regular expressions (case-insensitive), e.g. \"/tag/\" or \"\\\\?page=\".", "default": [], "items": { "type": "string" } }, "lastmodAfter": { "title": "Only URLs modified after", "type": "string", "description": "Optional. Keep only URLs whose sitemap is on or after this date. Accepts an absolute date (2026-01-31) or a relative period (\"7 days\", \"2 weeks\", \"3 months\"). URLs without a lastmod are kept unless you enable the option below. Great for finding new or updated pages." }, "dropUrlsWithoutLastmod": { "title": "Drop URLs without lastmod", "type": "boolean", "description": "If enabled, URLs that have no date in the sitemap are skipped.", "default": false }, "sameDomainOnly": { "title": "Same domain only", "type": "boolean", "description": "Keep only URLs on the same domain as the start URL (www. is ignored). Disable to also keep URLs on other domains or subdomains that appear in the sitemap.", "default": true }, "checkStatus": { "title": "Check HTTP status of each URL", "type": "boolean", "description": "If enabled, sends a lightweight HEAD request to every saved URL and records the HTTP status code and redirect target (redirects are not followed, so you see 301/302 issues in your sitemap). URLs disallowed by robots.txt are not requested. Slower: roughly 5–20 URLs per second.", "default": false }, "statusConcurrency": { "title": "Status check concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many status-check requests run in parallel. Keep it low to be polite to the website.", "default": 5 }, "maxSitemapFiles": { "title": "Max sitemap files per site", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Safety limit on how many sitemap files (including nested sitemap indexes) are read per start URL.", "default": 500 }, "discoverSitemaps": { "title": "Guess sitemap locations", "type": "boolean", "description": "If robots.txt declares no sitemap, try the usual locations: /sitemap.xml, /sitemap_index.xml, /sitemap-index.xml, /wp-sitemap.xml and /sitemap.txt.", "default": true } } }, "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 } } } } } } } } } }