{ "openapi": "3.0.1", "info": { "title": "Sitemap Scraper", "description": "Extract all URLs from any website's sitemap.xml with robots.txt discovery, gzip support, full metadata, and automatic retries", "version": "0.1", "x-build-id": "hLU11AK4W10JAgxvh" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/clintsa~sitemap-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-clintsa-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/clintsa~sitemap-scraper/runs": { "post": { "operationId": "runs-sync-clintsa-sitemap-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/clintsa~sitemap-scraper/run-sync": { "post": { "operationId": "run-sync-clintsa-sitemap-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "targets" ], "properties": { "targets": { "title": "Website URLs", "type": "array", "description": "Required. One or more website base URLs (e.g. `https://example.com`). The actor automatically discovers sitemaps via robots.txt and common paths (`/sitemap.xml`, `/sitemap_index.xml`). You can also paste direct sitemap URLs like `https://example.com/sitemap.xml`. URLs are normalized automatically.", "items": { "type": "string" } }, "maxItemsPerTarget": { "title": "Maximum URLs per target", "minimum": 0, "type": "integer", "description": "Limit the number of URLs returned per target. Set to `0` for all URLs. The prefilled health-check input returns one URL.", "default": 0 }, "maxDepth": { "title": "Maximum sitemap recursion depth", "minimum": 1, "maximum": 20, "type": "integer", "description": "How deep to follow nested sitemap indexes. `1` = only the top-level sitemap. `3` = up to 3 levels of sitemap indexes. Increase for sites with deeply nested sitemap structures.", "default": 5 }, "maxSitemaps": { "title": "Maximum sitemaps to process", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Safety limit on the total number of sitemap files to fetch per target. Prevents runaway on sites with thousands of nested sitemaps. Set to `0` for unlimited.", "default": 100 }, "timeoutMillis": { "title": "Request timeout (milliseconds)", "minimum": 5000, "maximum": 120000, "type": "integer", "description": "Timeout per HTTP request in milliseconds. Increase for slow sites.", "default": 30000 }, "concurrency": { "title": "Concurrent requests", "minimum": 1, "maximum": 10, "type": "integer", "description": "Number of concurrent HTTP requests for fetching sitemaps. Higher is faster but may trigger rate limits. `1` is safest.", "default": 3 }, "includeStatusCheck": { "title": "Include HTTP status check", "type": "boolean", "description": "When enabled, performs an HTTP HEAD request for each extracted URL to get the HTTP status code. Adds the `statusCode` field to output. Slower but useful for finding broken URLs.", "default": false }, "monitorId": { "title": "Change monitor ID", "type": "string", "description": "Persistent namespace for change tracking. Keep the same value for the same targets and filters. Use another value for an independent monitor or schedule.", "default": "default" }, "onlyChangesSince": { "title": "Return only changes since", "pattern": "^\\d{4}-\\d{2}-\\d{2}T.*$", "type": "string", "description": "Optional ISO 8601 timestamp such as `2026-08-01T00:00:00.000Z`. When set, the dataset contains only records detected as new, updated, or removed since that time. The first run creates the baseline." }, "useApifyProxy": { "title": "Use Apify Proxy", "type": "boolean", "description": "Sitemaps are public XML and normally work without a proxy. Enable only as a network fallback if you encounter IP-based blocking.", "default": false }, "proxyConfiguration": { "title": "Apify Proxy configuration", "type": "object", "description": "Optional proxy configuration used only when `useApifyProxy` is enabled." } } }, "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 } } } } } } } } } }