{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor – Get All URLs from XML Sitemaps", "description": "Extract every URL from a website's sitemaps. Auto-discovers sitemaps via robots.txt, follows nested indexes, handles .xml.gz, text, RSS/Atom and malformed XML. Returns lastmod, hreflang and optional HTTP status. $0.50 per 1,000 URLs; failed sitemaps are free.", "version": "0.0", "x-build-id": "EswgamzF1pU8skgyl" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/chris_elder~sitemap-url-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-chris_elder-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/chris_elder~sitemap-url-extractor/runs": { "post": { "operationId": "runs-sync-chris_elder-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/chris_elder~sitemap-url-extractor/run-sync": { "post": { "operationId": "run-sync-chris_elder-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "startUrls" ], "properties": { "startUrls": { "title": "Websites or sitemap URLs", "type": "array", "description": "Website homepages (sitemaps are auto-discovered from robots.txt and common locations) or direct sitemap URLs (.xml, .xml.gz, .txt, RSS/Atom).", "default": [ { "url": "https://crawlee.dev" } ], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxUrls": { "title": "Max URLs", "minimum": 1, "maximum": 5000000, "type": "integer", "description": "Stop after this many unique URLs (across all inputs). You pay per URL returned, so this caps your cost.", "default": 10000 }, "includeUrlPatterns": { "title": "Include URL patterns (regex)", "type": "array", "description": "Only keep URLs matching at least one of these regular expressions (case-insensitive), e.g. /blog/ or \\.pdf$", "default": [], "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Exclude URL patterns (regex)", "type": "array", "description": "Drop URLs matching any of these regular expressions, e.g. /tag/ or \\?page=", "default": [], "items": { "type": "string" } }, "lastmodAfter": { "title": "Only URLs modified after", "type": "string", "description": "Keep only URLs whose is on/after this date (YYYY-MM-DD). URLs without lastmod are dropped when this is set. Great for 'what changed since last week' monitoring." }, "sameHostOnly": { "title": "Same host only", "type": "boolean", "description": "Drop URLs whose host differs from the input website (www. is ignored).", "default": false }, "includeAlternates": { "title": "Include hreflang alternates", "type": "boolean", "description": "Output language versions for each URL.", "default": true }, "includeImages": { "title": "Include image URLs", "type": "boolean", "description": "Output the list of URLs per page (the image count is always included).", "default": false }, "checkStatus": { "title": "Check HTTP status of each URL", "type": "boolean", "description": "Send one polite HEAD request per URL (falls back to GET) and add statusCode, finalUrl and redirected. Finds broken (4xx/5xx) and redirecting URLs listed in sitemaps. Charged as an extra event per URL checked. Respects robots.txt.", "default": false }, "maxStatusChecks": { "title": "Max status checks", "minimum": 0, "type": "integer", "description": "Upper limit of URLs to status-check per run.", "default": 1000 }, "maxSitemaps": { "title": "Max sitemap files per website", "minimum": 1, "type": "integer", "description": "Safety limit on how many sitemap files are downloaded per input.", "default": 500 }, "maxDepth": { "title": "Max sitemap index depth", "minimum": 0, "maximum": 10, "type": "integer", "description": "How deep to follow nested sitemap indexes.", "default": 5 }, "requestDelayMs": { "title": "Delay between requests to the same host (ms)", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Politeness delay. The default keeps load on target websites negligible.", "default": 300 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip guessed sitemap locations and status checks that robots.txt disallows. Sitemaps declared in robots.txt are always fetched.", "default": true } } }, "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 } } } } } } } } } }