{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor: All Site URLs, Lastmod & Status", "description": "Get every URL a website publishes in its XML sitemaps: auto-discovers sitemaps via robots.txt, follows sitemap indexes and .gz files, returns lastmod, priority, hreflang, image/news data. Optional HTTP status check. $0.40 per 1,000 URLs.", "version": "1.0", "x-build-id": "dMEFyQX74Z24q4edO" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/saadhazz~sitemap-url-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-saadhazz-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/saadhazz~sitemap-url-extractor/runs": { "post": { "operationId": "runs-sync-saadhazz-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/saadhazz~sitemap-url-extractor/run-sync": { "post": { "operationId": "run-sync-saadhazz-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "startUrls" ], "properties": { "startUrls": { "title": "Websites or sitemap URLs", "type": "array", "description": "A domain (example.com), a homepage URL, or a direct sitemap URL (…/sitemap.xml, …/sitemap_index.xml, .xml.gz, .txt). For domains we read robots.txt `Sitemap:` lines, then try standard locations (/sitemap.xml, /sitemap_index.xml, /wp-sitemap.xml …).", "default": [ "https://crawlee.dev" ], "items": { "type": "string" } }, "maxUrls": { "title": "Max URLs (total)", "minimum": 1, "type": "integer", "description": "Stop after this many unique URLs across all websites. You pay only for URLs saved.", "default": 10000 }, "maxUrlsPerSite": { "title": "Max URLs per website", "minimum": 0, "type": "integer", "description": "Optional cap per website (0 = no per-site cap). Useful when you list many sites and want a sample from each.", "default": 0 }, "includePatterns": { "title": "Only URLs matching", "type": "array", "description": "Keep only URLs that contain one of these strings or match a glob (e.g. `/blog/`, `*/products/*`). Prefix with `re:` for a regular expression. Leave empty to keep all.", "default": [], "items": { "type": "string" } }, "excludePatterns": { "title": "Skip URLs matching", "type": "array", "description": "Drop URLs that contain one of these strings or match a glob/`re:` regex (e.g. `/tag/`, `?page=`).", "default": [], "items": { "type": "string" } }, "lastmodAfter": { "title": "Only URLs modified after (date)", "pattern": "^(\\d{4}-\\d{2}-\\d{2}.*)?$", "type": "string", "description": "ISO date like 2026-01-01. Keeps only URLs whose sitemap is on/after this date (URLs without lastmod are dropped when this is set). Great for finding new or updated pages." }, "checkHttpStatus": { "title": "Check live HTTP status of each URL", "type": "boolean", "description": "Sends a HEAD request (GET fallback) to each URL and adds `httpStatus` and `redirectTo`: find broken (404) or redirected pages listed in your sitemap. Respects robots.txt. Billed per checked URL.", "default": false }, "sameDomainOnly": { "title": "Same domain only", "type": "boolean", "description": "Skip URLs in the sitemaps that point to other domains.", "default": true }, "maxSitemapsPerSite": { "title": "Max sitemap files per website", "minimum": 1, "type": "integer", "description": "Safety cap on the number of sitemap files (including children of sitemap indexes) read per website.", "default": 500 }, "perHostConcurrency": { "title": "Max parallel requests per host", "minimum": 1, "maximum": 10, "type": "integer", "description": "Keep this low to be polite to the website (we also honour Retry-After).", "default": 4 } } }, "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 } } } } } } } } } }