{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor — Nested Indexes, Gzip & lastmod", "description": "Turn any website into a clean list of its URLs. Finds the sitemap from robots.txt, follows nested sitemap indexes, unpacks .xml.gz, reads RSS/Atom feeds, and can return only pages changed since a date — the cheap way to re-crawl just what is new.", "version": "0.1", "x-build-id": "3GIJkzVAl5luDzeEX" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/relevate~sitemap-urls/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-relevate-sitemap-urls", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/relevate~sitemap-urls/runs": { "post": { "operationId": "runs-sync-relevate-sitemap-urls", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/relevate~sitemap-urls/run-sync": { "post": { "operationId": "run-sync-relevate-sitemap-urls", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "Websites or sitemap URLs", "type": "array", "description": "Give a plain domain such as example.com and the Actor finds the sitemap itself — first from robots.txt, then by probing the usual paths. Or pass a full URL to a sitemap, a sitemap index, an .xml.gz file or an RSS/Atom feed.", "default": [], "items": { "type": "string" } }, "lastmodAfter": { "title": "Only URLs changed after", "type": "string", "description": "Keep only URLs whose is newer than this date, e.g. 2026-07-01. This turns a full sitemap into an incremental feed of what changed — the cheap way to re-crawl only new pages. URLs with no are dropped when this is set." }, "includePattern": { "title": "Include URLs matching (regex)", "type": "string", "description": "Case-insensitive regular expression. Only matching URLs are kept — for example /blog/ or \\\\.pdf$" }, "excludePattern": { "title": "Exclude URLs matching (regex)", "type": "string", "description": "Case-insensitive regular expression. Matching URLs are dropped — for example /tag/|/author/" }, "maxUrls": { "title": "Maximum URLs", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Safety cap on how many URLs are returned in one run.", "default": 10000 }, "maxDepth": { "title": "Maximum sitemap nesting depth", "minimum": 1, "maximum": 10, "type": "integer", "description": "How deep to follow sitemap indexes that point at other sitemap indexes. 3 covers essentially every real site.", "default": 3 }, "outputSitemapList": { "title": "Return the sitemap map instead of URLs", "type": "boolean", "description": "Output one row per sitemap found — its type, how it was discovered, how many child sitemaps and URLs it holds — instead of the URLs themselves. Use it to understand a large site's sitemap structure before extracting from it.", "default": false }, "minExpectedResults": { "title": "Health check — minimum expected results", "minimum": 0, "type": "integer", "description": "Fail the run if fewer than this many records are produced. Use it in scheduled pipelines to get alerted when a sitemap moves or changes shape. 0 disables the check.", "default": 0 } } }, "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 } } } } } } } } } }