{ "openapi": "3.0.1", "info": { "title": "Sitemap Generator - Crawl Website & Create XML Sitemap", "description": "Generate an XML sitemap for any website. Crawls internal pages from start URLs (with depth + page limits), deduplicates URLs, and stores a ready-to-submit sitemap.xml plus a structured dataset and summary for SEO audits.", "version": "1.0", "x-build-id": "TzYBrG61b0sSwQYnt" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrappy_garden~sitemap-generator/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrappy_garden-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrappy_garden~sitemap-generator/runs": { "post": { "operationId": "runs-sync-scrappy_garden-sitemap-generator", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrappy_garden~sitemap-generator/run-sync": { "post": { "operationId": "run-sync-scrappy_garden-sitemap-generator", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "startUrls" ], "properties": { "startUrls": { "title": "Start URLs", "type": "array", "description": "One or more URLs to start crawling from. The Actor will crawl internal links and generate a sitemap.xml.", "default": [ { "url": "https://example.com" } ], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxPages": { "title": "Max pages to crawl", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Maximum number of pages/requests to process (safety limit).", "default": 500 }, "maxDepth": { "title": "Max crawl depth", "minimum": 0, "maximum": 20, "type": "integer", "description": "How deep to follow internal links from the start URLs.", "default": 3 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 100, "type": "integer", "description": "Number of parallel HTTP requests.", "default": 10 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 180, "type": "integer", "description": "Maximum time per page fetch.", "default": 30 }, "ignoreUrlPatterns": { "title": "Ignore URL patterns (regex)", "type": "array", "description": "List of regex patterns. Matching URLs will be excluded from crawling/sitemap.", "items": { "type": "string" }, "default": [] }, "includeQueryParams": { "title": "Include query parameters (?a=b)", "type": "boolean", "description": "If enabled, URLs with different query strings will be treated as different URLs.", "default": false }, "includeFragments": { "title": "Include fragments (#section)", "type": "boolean", "description": "If enabled, fragments will be kept in URLs (usually not recommended for sitemaps).", "default": false }, "includeLastModified": { "title": "Include from HTTP Last-Modified", "type": "boolean", "description": "If enabled, uses the HTTP Last-Modified header when available.", "default": true }, "respectRobotsTxt": { "title": "Respect robots.txt (User-agent: *)", "type": "boolean", "description": "If enabled, URLs disallowed by robots.txt for User-agent: * will be skipped (best-effort).", "default": true }, "robotsTxtTimeoutSecs": { "title": "robots.txt timeout (seconds)", "minimum": 1, "maximum": 60, "type": "integer", "description": "How long to wait when downloading robots.txt for each hostname.", "default": 10 }, "changefreq": { "title": "Default (optional)", "enum": [ "", "always", "hourly", "daily", "weekly", "monthly", "yearly", "never" ], "type": "string", "description": "Optional sitemap hint applied to all URLs.", "default": "" }, "priority": { "title": "Default (optional)", "minimum": 0, "maximum": 1, "type": "number", "description": "Optional sitemap hint applied to all URLs (0.0 to 1.0)." }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Proxy settings for accessing websites.", "default": { "useApifyProxy": false } } } }, "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 } } } } } } } } } }