{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor: Get All Website URLs — Sitemoss", "description": "Sitemap URL extractor: get all URLs of a website from its XML sitemaps. Finds sitemaps via robots.txt, follows sitemap indexes and .gz files, returns lastmod, changefreq, priority, hreflang and image counts. Monitor mode returns only new and updated pages. $0.40 per 1,000 URLs, no start fee.", "version": "0.1", "x-build-id": "H5jfZ2doJbUusaTb2" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/cybermax~sitemap-url-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-cybermax-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/cybermax~sitemap-url-extractor/runs": { "post": { "operationId": "runs-sync-cybermax-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/cybermax~sitemap-url-extractor/run-sync": { "post": { "operationId": "run-sync-cybermax-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": [ "urls" ], "properties": { "urls": { "title": "Websites or sitemap URLs", "type": "array", "description": "One per line: a domain (example.com), any page of the site (https://www.example.com/blog) or a sitemap URL (https://example.com/post-sitemap.xml, .xml.gz or .txt). For a domain, Sitemoss reads the Sitemap: lines in robots.txt, then tries /sitemap.xml, /sitemap_index.xml and /wp-sitemap.xml, and follows every sitemap index.", "items": { "type": "string" } }, "maxUrlsPerSite": { "title": "Max URLs per site", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Stop after this many URLs for one site. Each delivered URL is one charged result.", "default": 1000 }, "urlPattern": { "title": "Only URLs matching (regex)", "type": "string", "description": "Optional, e.g. /blog/|/products/ . Skipped URLs are free." }, "excludePattern": { "title": "Skip URLs matching (regex)", "type": "string", "description": "Optional, e.g. /tag/|/author/|\\?page=" }, "lastmodAfter": { "title": "Only pages modified after", "type": "string", "description": "Optional date (2026-10-01). Keeps only URLs whose sitemap lastmod is on or after it; URLs without a lastmod are skipped (free)." }, "sameSiteOnly": { "title": "Only URLs on the site's own domain", "type": "boolean", "description": "Drop sitemap entries that point to other domains.", "default": false }, "maxSitemapsPerSite": { "title": "Max sitemap files per site", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Safety limit for huge sitemap indexes.", "default": 200 }, "timeoutSecs": { "title": "Request timeout (s)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Timeout per sitemap download (retried twice on errors).", "default": 30 }, "maxConcurrency": { "title": "Sites in parallel", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many sites to read at the same time.", "default": 5 }, "monitor": { "title": "Monitor mode: new and updated pages only", "type": "boolean", "description": "For scheduled runs. Remembers every URL and its lastmod per site and returns only URLs that are new or whose lastmod changed since the last monitor run (field change = new | updated). Unchanged URLs are not returned and not charged. The first monitor run returns everything as new.", "default": false }, "monitorKey": { "title": "Watchlist name", "type": "string", "description": "Optional name for this watchlist's saved state (e.g. competitor-blogs), so you can change the site list without starting over." } } }, "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 } } } } } } } } } }