{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor: sitemap.xml Parser, robots.txt & .gz", "description": "Every URL a site publishes in its sitemaps, in one clean table. Finds sitemaps via robots.txt, follows sitemap indexes and unzips .gz files; one JSON row per URL with lastmod. Filter by date to see new or updated pages. $0.30 per 1,000 URLs; sites without a sitemap aren't charged.", "version": "0.2", "x-build-id": "YK3WMSnhPkwt15Djs" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/saif-tools~sitemap-url-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-saif-tools-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/saif-tools~sitemap-url-extractor/runs": { "post": { "operationId": "runs-sync-saif-tools-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/saif-tools~sitemap-url-extractor/run-sync": { "post": { "operationId": "run-sync-saif-tools-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "startUrls" ], "properties": { "startUrls": { "title": "Websites or sitemap URLs", "type": "array", "description": "Domains (e.g. https://example.com) or direct sitemap URLs (e.g. https://example.com/sitemap.xml). For domains, sitemaps are discovered from robots.txt, then common locations (/sitemap.xml, /sitemap_index.xml).", "items": { "type": "string" } }, "maxUrls": { "title": "Max URLs (total)", "minimum": 0, "maximum": 1000000, "type": "integer", "description": "Stop after this many page URLs across all inputs. 0 = no limit (hard cap 1,000,000).", "default": 10000 }, "maxUrlsPerSite": { "title": "Max URLs per site", "minimum": 0, "maximum": 1000000, "type": "integer", "description": "Per-input limit so one huge site does not use the whole budget. 0 = no per-site limit.", "default": 0 }, "maxSitemaps": { "title": "Max sitemap files per site", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Safety limit on how many sitemap files (including nested index children) are fetched per site.", "default": 500 }, "includePatterns": { "title": "Include URL patterns (regex)", "type": "array", "description": "Only keep URLs matching at least one of these regular expressions, e.g. /blog/ or \\.html$. Empty = keep all.", "default": [], "items": { "type": "string" } }, "excludePatterns": { "title": "Exclude URL patterns (regex)", "type": "array", "description": "Drop URLs matching any of these regular expressions.", "default": [], "items": { "type": "string" } }, "lastmodAfter": { "title": "Only URLs modified after (date)", "type": "string", "description": "ISO date like 2026-01-01. URLs without lastmod are kept unless 'Drop URLs without lastmod' is on." }, "dropUrlsWithoutLastmod": { "title": "Drop URLs without lastmod", "type": "boolean", "description": "Only applies when a lastmod date filter is set.", "default": false }, "sameDomainOnly": { "title": "Same domain only", "type": "boolean", "description": "Ignore URLs (and child sitemaps) on other hosts than the input site.", "default": true }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip sitemap files whose path is disallowed for our user agent in robots.txt.", "default": true }, "requestDelayMs": { "title": "Delay between requests to one host (ms)", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Politeness delay between sitemap downloads on the same host.", "default": 300 } } }, "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 } } } } } } } } } }