{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor: Bulk XML Sitemap Parser", "description": "Extract every URL from a website's XML sitemaps: robots.txt discovery, nested sitemap indexes and gzip. Returns url, lastmod, changefreq, priority and source sitemap. Include/exclude filters. Plain HTTP, no browser. $0.50 per 1,000 URLs, failures free.", "version": "0.1", "x-build-id": "QRQR7y5MeVQjD8MJJ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/hillcountrybots~sitemap-url-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-hillcountrybots-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/hillcountrybots~sitemap-url-extractor/runs": { "post": { "operationId": "runs-sync-hillcountrybots-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/hillcountrybots~sitemap-url-extractor/run-sync": { "post": { "operationId": "run-sync-hillcountrybots-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": "Website or sitemap URLs", "type": "array", "description": "Required. Website home pages and/or direct sitemap URLs (https://example.com/ or https://example.com/sitemap.xml). A domain without https:// is accepted. Private, local and internal addresses are refused (free).", "items": { "type": "string" } }, "discoverFromRobots": { "title": "Discover sitemaps from robots.txt", "type": "boolean", "description": "Fetch /robots.txt on each website and collect every Sitemap: line.", "default": true }, "tryCommonPaths": { "title": "Also try common sitemap paths", "type": "boolean", "description": "If robots.txt lists no sitemap (or in addition to it), try /sitemap.xml, /sitemap_index.xml and their .gz versions on the same origin.", "default": true }, "includePatterns": { "title": "Include patterns (optional)", "type": "array", "description": "If set, only URLs matching at least one pattern are kept. Use * as a wildcard (e.g. https://example.com/blog/*) or a /regex/ in slashes. Compared against the full URL. Leave empty to keep all.", "items": { "type": "string" } }, "excludePatterns": { "title": "Exclude patterns (optional)", "type": "array", "description": "URLs matching any of these patterns are dropped (after include filters). Same syntax as include patterns: * wildcards or /regex/.", "items": { "type": "string" } }, "maxUrls": { "title": "Max URLs", "minimum": 1, "type": "integer", "description": "Exact maximum number of unique URLs to return in this run. Caps spend: at most maxUrls x $0.0005. The example starts at 25 so a one-click run finishes in seconds; raise it for a full site. Invalid, failed and filtered rows do not count toward this cap and are not charged.", "default": 10000 }, "maxSitemaps": { "title": "Max sitemap files", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Exact maximum number of unique sitemap files (indexes and urlsets) to fetch, to cap run time on huge sites. Common-path probes that 404 still count as a fetched attempt.", "default": 200 }, "maxConcurrency": { "title": "Concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Sitemap files fetched in parallel (1-10). Keep this modest; many sites rate-limit sitemap requests.", "default": 4 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Seconds to wait for one sitemap or robots.txt response before retrying (up to 3 attempts with backoff).", "default": 30 } } }, "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 } } } } } } } } } }