{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor: All Pages, New & Removed URLs", "description": "Get every URL of a website: from sitemaps (index, gzip) or a polite crawl when there is none. Flags new and removed pages between runs, checks HTTP status, many domains per run. Respects robots.txt. $0.15–$0.30 per 1,000 URLs.", "version": "1.0", "x-build-id": "oTxifAX6VBqgwgrDT" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/urlwright~sitemap-url-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-urlwright-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/urlwright~sitemap-url-extractor/runs": { "post": { "operationId": "runs-sync-urlwright-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/urlwright~sitemap-url-extractor/run-sync": { "post": { "operationId": "run-sync-urlwright-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": [ "startUrls" ], "properties": { "startUrls": { "title": "Domains or sitemap URLs", "type": "array", "description": "List of domains (example.com), site origins (https://example.com), or direct sitemap URLs (https://example.com/sitemap.xml).", "items": { "type": "string" } }, "checkStatus": { "title": "Check HTTP status for each URL", "type": "boolean", "description": "When enabled, perform a polite HEAD (GET fallback) status check per extracted URL.", "default": false }, "maxUrls": { "title": "Max URLs", "minimum": 1, "maximum": 500000, "type": "integer", "description": "Hard cap on URLs written to the dataset across the whole run.", "default": 10000 }, "maxSitemapDepth": { "title": "Max sitemap index depth", "minimum": 0, "maximum": 20, "type": "integer", "description": "How deep to follow nested sitemap indexes (0 = only leaf urlsets from the first level).", "default": 5 }, "crawlFallback": { "title": "Crawl fallback", "enum": [ "off", "whenNoSitemap", "always" ], "type": "string", "description": "When to BFS-crawl for href/canonical links: off | whenNoSitemap (also if sitemap yields 0 URLs) | always. Crawl always honors robots.txt + crawl-delay per host. Default whenNoSitemap.", "default": "whenNoSitemap" }, "includeSubdomains": { "title": "Include subdomains in crawl", "type": "boolean", "description": "When true, crawl (including redirect hops) may follow subdomains of the same registrable domain (Public Suffix List, e.g. beispiel.de → shop.beispiel.de). Foreign domains are never followed. Each subdomain uses its own robots.txt. Default false = exact hostname only.", "default": false }, "maxCrawlPages": { "title": "Max crawl pages", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Max HTML pages to fetch during crawl fallback (PPE crawled-page charged per successful page).", "default": 100 }, "maxCrawlDepth": { "title": "Max crawl depth", "minimum": 0, "maximum": 20, "type": "integer", "description": "Max link depth from the site origin during crawl fallback (0 = homepage only).", "default": 2 }, "compareWithPrevious": { "title": "Compare with previous run", "type": "boolean", "description": "Store the URL set per domain in a named key-value store and set changeStatus (new|removed|unchanged). Ideal for Apify Schedules.", "default": false }, "onlyChanges": { "title": "Only output changes", "type": "boolean", "description": "When compareWithPrevious is on, write only new and removed URLs (skip unchanged). Cheaper for scheduled monitoring.", "default": false }, "concurrency": { "title": "Concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Max parallel HTTP requests for status checks, sitemap fetches, and crawl pages.", "default": 5 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Timeout per HTTP request.", "default": 20 }, "requestsPerSecond": { "title": "Requests per second (polite rate limit)", "minimum": 0.5, "maximum": 20, "type": "number", "description": "Per-host polite rate limit (minimum 0.5). Combined with robots.txt crawl-delay when present (stricter wins). Domains whose robots.txt crawl-delay exceeds 10 seconds are skipped.", "default": 2 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Honor Disallow / crawl-delay for sitemap discovery, sitemap URL extraction, and status checks. Crawl fallback always respects robots.txt (and crawl-delay) per host, regardless of this option. Always recommended.", "default": true }, "userAgent": { "title": "User-Agent", "type": "string", "description": "HTTP User-Agent used for all requests.", "default": "UrlwrightBot/1.0 (sitemap; +https://urlwright.com/bot)" } } }, "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 } } } } } } } } } }