{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor: All Pages, Lastmod & Status", "description": "Get every page URL from a website's sitemaps with lastmod dates, hreflang alternates, Google News titles and optional HTTP status checks. Auto-discovers sitemaps via robots.txt, follows indexes and .gz files. From $0.08 per 1,000 URLs.", "version": "0.2", "x-build-id": "1HOSsBVSJv2V2F7q4" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/tidyharvest~sitemap-urls-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-tidyharvest-sitemap-urls-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/tidyharvest~sitemap-urls-extractor/runs": { "post": { "operationId": "runs-sync-tidyharvest-sitemap-urls-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/tidyharvest~sitemap-urls-extractor/run-sync": { "post": { "operationId": "run-sync-tidyharvest-sitemap-urls-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": [ "urls" ], "properties": { "urls": { "title": "Websites or sitemap URLs", "type": "array", "description": "One per line. A domain or homepage (`apify.com`, `https://www.bbc.com`) finds its sitemaps automatically; a section URL (`https://www.bbc.com/news`, `https://site.com/blog/`) returns only the pages under that path; a sitemap URL (`.../sitemap.xml`, `.xml.gz`, `.txt`, or a sitemap index) is read directly. Sitemap indexes are followed to every child sitemap.", "items": { "type": "string" } }, "onlyUnderPath": { "title": "Section URLs: only pages under that path", "type": "boolean", "description": "When you enter a section URL such as `https://www.bbc.com/news` or `https://site.com/blog/`, return only URLs under that path. Turn off to get the whole site for any URL you enter.", "default": true }, "includeUrlPatterns": { "title": "Only URLs containing", "type": "array", "description": "Keep a URL only if it contains one of these strings (e.g. `/blog/`, `/products/`). Empty = all.", "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Skip URLs containing", "type": "array", "description": "Drop URLs containing any of these (e.g. `/tag/`, `?page=`).", "items": { "type": "string" } }, "lastmodAfter": { "title": "Changed on or after (lastmod)", "type": "string", "description": "Only URLs whose sitemap `lastmod` is on or after this date: new or updated pages since your last run. URLs without a lastmod are skipped when this is set." }, "checkStatus": { "title": "Check HTTP status of each URL", "type": "boolean", "description": "Request each URL (HEAD, GET fallback) and add `statusCode`, `finalUrl` and `httpLastModified` (the server's Last-Modified header), to find broken links and redirects listed in the sitemap. Slower on big sites.", "default": false }, "maxUrlsPerSite": { "title": "Max URLs per site", "minimum": 0, "type": "integer", "description": "0 or empty = no limit." }, "maxItems": { "title": "Max URLs in total", "minimum": 0, "type": "integer", "description": "Hard cap on results for the whole run (also caps your cost), shared fairly between your sites: each gets an equal share and sites with fewer URLs pass the rest on. 0 or empty = no limit. Big sites list hundreds of thousands of URLs (apify.com ~300k), so set this for a first look." } } }, "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 } } } } } } } } } }