{ "openapi": "3.0.1", "info": { "title": "Sitemap Scraper - All URLs from XML Sitemaps + Status Check", "description": "Every URL from a website's XML sitemaps (robots.txt discovery, indexes, .gz, text sitemaps) with lastmod, images, hreflang and news tags. Optional HTTP status/redirect check. Monitoring of new URLs.", "version": "0.1", "x-build-id": "3htDckFLYdLdvA4qO" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/tinyrex~sitemap-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-tinyrex-sitemap-scraper", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/tinyrex~sitemap-scraper/runs": { "post": { "operationId": "runs-sync-tinyrex-sitemap-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/tinyrex~sitemap-scraper/run-sync": { "post": { "operationId": "run-sync-tinyrex-sitemap-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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, sitemaps or robots.txt", "type": "array", "description": "Website URLs or domains (sitemaps are discovered from robots.txt and common paths like /sitemap.xml), direct sitemap URLs (XML, .xml.gz, text) or robots.txt URLs. Many sites per run.", "default": [ "https://apify.com" ], "items": { "type": "string" } }, "maxUrlsPerSite": { "title": "Max URLs per site", "minimum": 0, "type": "integer", "description": "Maximum URLs saved per website. 0 = no limit.", "default": 500 }, "includeUrlPatterns": { "title": "Include URL patterns", "type": "array", "description": "Keep only URLs containing one of these strings, or matching a /regex/ (e.g. /blog/ or /\\/products\\//). Empty = all.", "default": [], "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Exclude URL patterns", "type": "array", "description": "Drop URLs containing one of these strings or matching a /regex/.", "default": [], "items": { "type": "string" } }, "lastModifiedWithinDays": { "title": "Last modified within (days)", "minimum": 0, "type": "integer", "description": "Only URLs whose sitemap lastmod is within the last N days (URLs without lastmod are dropped). 0 = any.", "default": 0 }, "includeImages": { "title": "Include images and videos", "type": "boolean", "description": "Include image and video sitemap entries for each URL.", "default": true }, "includeAlternates": { "title": "Include hreflang alternates", "type": "boolean", "description": "Include hreflang language alternates for each URL.", "default": true }, "checkStatus": { "title": "Check HTTP status of every URL", "type": "boolean", "description": "Request every URL (HEAD, falls back to GET) and add status code, final URL, redirect chain, response time and content type. Finds broken (4xx/5xx) and redirected sitemap URLs. Charged separately per checked URL.", "default": false }, "respectRobotsTxt": { "title": "Respect robots.txt for status checks", "type": "boolean", "description": "Do not request URLs that robots.txt disallows (they are reported, not checked).", "default": true }, "statusConcurrency": { "title": "Status check concurrency per site", "minimum": 1, "maximum": 20, "type": "integer", "description": "Parallel requests per site during status checks. Keep it low to be polite.", "default": 3 }, "onlyNewUrls": { "title": "Only new URLs (monitoring)", "type": "boolean", "description": "Return only URLs not returned by previous runs with the same state key. Schedule it to get new pages of a site.", "default": false }, "stateKey": { "title": "State key", "type": "string", "description": "Name of the saved state for Only new URLs. Use different keys for different monitors.", "default": "default" }, "maxSitemapsPerSite": { "title": "Max sitemaps per site", "minimum": 1, "type": "integer", "description": "Safety cap on how many sitemap files are read per site.", "default": 1000 }, "maxConcurrency": { "title": "Sites in parallel", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many websites are processed in parallel.", "default": 3 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional proxy, only needed for sites that block datacenter IPs.", "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 }, "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 } } } } } } } } } }