{
"openapi": "3.0.1",
"info": {
"title": "Sitemap Generator — XML Sitemap Crawler",
"description": "Crawl a website, discover indexable URLs, and generate XML sitemaps with crawl diagnostics, canonical checks, status codes, and exportable URL inventory.",
"version": "1.0",
"x-build-id": "M9TVP5ZEjZrVOtOdC"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/junipr~sitemap-generator/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-junipr-sitemap-generator",
"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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/junipr~sitemap-generator/runs": {
"post": {
"operationId": "runs-sync-junipr-sitemap-generator",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/junipr~sitemap-generator/run-sync": {
"post": {
"operationId": "run-sync-junipr-sitemap-generator",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"startUrl": {
"title": "Start URL",
"type": "string",
"description": "The root URL to start crawling from. Must include protocol (https://).",
"default": "https://crawlee.dev"
},
"maxPages": {
"title": "Max Pages",
"minimum": 1,
"maximum": 5000,
"type": "integer",
"description": "Maximum number of pages to crawl. Higher values take longer but produce a more complete sitemap.",
"default": 1
},
"maxDepth": {
"title": "Max Crawl Depth",
"minimum": 0,
"maximum": 10,
"type": "integer",
"description": "Maximum link-following depth from start URL. 0 means only the start URL. Higher values discover deeper pages.",
"default": 0
},
"includePatterns": {
"title": "Include URL Patterns",
"type": "array",
"description": "URL patterns to include (glob syntax). Empty means include all URLs. Examples: \"/blog/*\", \"*.html\", \"/products/*\".",
"items": {
"type": "string"
},
"default": []
},
"excludePatterns": {
"title": "Exclude URL Patterns",
"type": "array",
"description": "URL patterns to exclude (glob syntax). Applied after include patterns. Common file extensions are excluded by default.",
"items": {
"type": "string"
},
"default": [
"*.pdf",
"*.zip",
"*.jpg",
"*.png",
"*.gif",
"*.svg",
"*.css",
"*.js"
]
},
"excludeQueryParams": {
"title": "Exclude Query Parameters",
"type": "boolean",
"description": "Treat URLs with different query parameters as the same page for deduplication.",
"default": true
},
"respectCanonical": {
"title": "Respect Canonical URLs",
"type": "boolean",
"description": "Follow tags. Index the canonical URL and skip duplicates.",
"default": true
},
"stayWithinDomain": {
"title": "Stay Within Domain",
"type": "boolean",
"description": "Only crawl pages on the same domain as the start URL.",
"default": true
},
"stayWithinPath": {
"title": "Stay Within Path",
"type": "boolean",
"description": "Only crawl pages under the same path prefix as the start URL.",
"default": false
},
"includeLastmod": {
"title": "Include Last Modified",
"type": "boolean",
"description": "Include in the sitemap. Detected from Last-Modified header, tags, or schema.org dateModified.",
"default": true
},
"includeChangefreq": {
"title": "Include Change Frequency",
"type": "boolean",
"description": "Include in the sitemap. Estimated from content type heuristics.",
"default": true
},
"includePriority": {
"title": "Include Priority",
"type": "boolean",
"description": "Include in the sitemap. Calculated from page depth and inbound link count.",
"default": true
},
"defaultChangefreq": {
"title": "Default Change Frequency",
"enum": [
"always",
"hourly",
"daily",
"weekly",
"monthly",
"yearly",
"never"
],
"type": "string",
"description": "Default changefreq value when not estimable from content type.",
"default": "weekly"
},
"sitemapFormat": {
"title": "Sitemap Format",
"enum": [
"xml",
"txt",
"both"
],
"type": "string",
"description": "Output format: xml (standard XML sitemap), txt (plain URL list), or both.",
"default": "xml"
},
"splitAtCount": {
"title": "Split at URL Count",
"minimum": 1000,
"maximum": 50000,
"type": "integer",
"description": "Auto-split sitemap at this many URLs and generate a sitemap index. Per sitemap protocol spec, max is 50,000.",
"default": 50000
},
"checkExistingSitemap": {
"title": "Check Existing Sitemap",
"type": "boolean",
"description": "Check for existing sitemaps at robots.txt and common paths before crawling.",
"default": false
},
"existingSitemapAction": {
"title": "Existing Sitemap Action",
"enum": [
"merge",
"replace",
"compare"
],
"type": "string",
"description": "What to do when an existing sitemap is found: merge (combine with crawled), replace (ignore existing), or compare (output diff).",
"default": "merge"
},
"sitemapPaths": {
"title": "Sitemap Paths to Check",
"type": "array",
"description": "Additional paths to check for existing sitemaps, besides robots.txt.",
"items": {
"type": "string"
},
"default": [
"/sitemap.xml",
"/sitemap_index.xml",
"/sitemap/"
]
},
"crawlerType": {
"title": "Crawler Type",
"enum": [
"cheerio",
"playwright"
],
"type": "string",
"description": "Crawler engine: cheerio (fast, static HTML) or playwright (JS rendering for SPAs).",
"default": "cheerio"
},
"maxConcurrency": {
"title": "Max Concurrency",
"minimum": 1,
"maximum": 25,
"type": "integer",
"description": "Maximum concurrent requests (Cheerio) or browser pages (Playwright). Higher values crawl faster but use more resources.",
"default": 1
},
"requestTimeout": {
"title": "Request Timeout (ms)",
"minimum": 5000,
"maximum": 120000,
"type": "integer",
"description": "Timeout per page request in milliseconds.",
"default": 30000
},
"maxRetries": {
"title": "Max Retries",
"minimum": 0,
"maximum": 5,
"type": "integer",
"description": "Retry failed page requests up to this many times.",
"default": 2
},
"respectRobotsTxt": {
"title": "Respect robots.txt",
"type": "boolean",
"description": "Honor robots.txt crawl directives and delays. Recommended to leave enabled.",
"default": true
},
"userAgent": {
"title": "User Agent",
"type": "string",
"description": "Custom User-Agent string sent with all requests.",
"default": "JuniprSitemapBot/1.0"
},
"proxyConfiguration": {
"title": "Proxy Configuration",
"type": "object",
"description": "Proxy settings. Defaults to Apify datacenter proxies.",
"default": {
"useApifyProxy": true
}
},
"httpHeaders": {
"title": "HTTP Headers",
"type": "object",
"description": "Custom HTTP headers for all requests.",
"default": {}
},
"cookies": {
"title": "Cookies",
"type": "array",
"description": "Cookies to set for all requests. Each object needs name, value, and domain.",
"items": {
"type": "object",
"properties": {
"name": {
"type": "string",
"title": "Cookie Name",
"description": "Name of the cookie"
},
"value": {
"type": "string",
"title": "Cookie Value",
"description": "Value of the cookie"
},
"domain": {
"type": "string",
"title": "Cookie Domain",
"description": "Domain the cookie applies to"
}
},
"required": [
"name",
"value",
"domain"
]
}
}
}
},
"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
}
}
}
}
}
}
}
}
}
}