{
"openapi": "3.0.1",
"info": {
"title": "Sitemap URL Extractor: sitemap.xml, Get All Website URLs",
"description": "Sitemap.xml parser: extract every page URL of a website from its XML sitemaps, with robots.txt auto-discovery, nested sitemap indexes, gzip and text sitemaps, lastmod, hreflang and images. URL pattern and date filters plus a new-pages monitor. $0.20 per 1,000 URLs.",
"version": "1.0",
"x-build-id": "6oYpYQnZKbUnmYEcx"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/sysco32~sitemap-url-extractor/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-sysco32-sitemap-url-extractor",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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/sysco32~sitemap-url-extractor/runs": {
"post": {
"operationId": "runs-sync-sysco32-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/sysco32~sitemap-url-extractor/run-sync": {
"post": {
"operationId": "run-sync-sysco32-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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
}
},
"components": {
"schemas": {
"inputSchema": {
"type": "object",
"properties": {
"startUrls": {
"title": "Websites or sitemap URLs",
"type": "array",
"description": "A homepage such as https://example.com (sitemaps are discovered from robots.txt and common paths) or a direct sitemap URL (.xml, .xml.gz, .txt, sitemap index).",
"default": [
"https://apify.com"
],
"items": {
"type": "string"
}
},
"maxUrlsPerSite": {
"title": "Max URLs per site",
"minimum": 1,
"type": "integer",
"description": "Upper limit of page URLs returned per website. Set high (e.g. 100000) for a full crawl list.",
"default": 100
},
"includePatterns": {
"title": "Include URL patterns (regex)",
"type": "array",
"description": "Keep only URLs matching at least one pattern, e.g. /blog/, /products?/, \\.html$.",
"items": {
"type": "string"
}
},
"excludePatterns": {
"title": "Exclude URL patterns (regex)",
"type": "array",
"description": "Drop URLs matching any pattern, e.g. /tag/, /page/\\d+.",
"items": {
"type": "string"
}
},
"lastmodAfter": {
"title": "Modified after",
"type": "string",
"description": "Keep only URLs whose lastmod is on or after this date, e.g. 2026-10-01. URLs without lastmod are dropped when set."
},
"sitemapFilter": {
"title": "Only child sitemaps containing",
"type": "array",
"description": "In sitemap indexes, follow only child sitemaps whose URL contains one of these strings, e.g. post, product, news.",
"items": {
"type": "string"
}
},
"maxSitemapsPerSite": {
"title": "Max sitemap files per site",
"minimum": 1,
"type": "integer",
"description": "Safety limit for huge sitemap indexes.",
"default": 200
},
"includeExtras": {
"title": "Include hreflang, images and news data",
"type": "boolean",
"description": "Add hreflang alternates, image URLs, Google News title and publication date and a video flag when the sitemap has them.",
"default": true
},
"onlyNewUrls": {
"title": "Only new URLs (monitoring mode)",
"type": "boolean",
"description": "Remember the URLs already seen per site and return only URLs that appeared since the last run: track competitors' new pages, products, blog posts or landing pages.",
"default": false
},
"stateStoreName": {
"title": "State store name",
"type": "string",
"description": "Named key-value store for seen URLs. Use a different name for each independent monitor.",
"default": "sitemap-url-extractor-seen"
}
}
},
"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
}
}
}
}
}
}
}
}
}
}