{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor – All URLs from XML Sitemaps", "description": "Extract every URL from any website’s XML sitemaps: robots.txt discovery, nested indexes, .gz, lastmod filters. Fast, no browser, CSV/JSON export.", "version": "1.0", "x-build-id": "eQqKWsSvvU5bMaJhe" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/innovative_cookie~sitemap-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-innovative_cookie-sitemap-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/innovative_cookie~sitemap-extractor/runs": { "post": { "operationId": "runs-sync-innovative_cookie-sitemap-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/innovative_cookie~sitemap-extractor/run-sync": { "post": { "operationId": "run-sync-innovative_cookie-sitemap-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "urls" ], "properties": { "urls": { "title": "Websites, domains or sitemap URLs", "type": "array", "description": "One per line. A domain (example.com) or homepage URL triggers automatic discovery (robots.txt, then standard locations such as /sitemap.xml, /sitemap_index.xml, /wp-sitemap.xml). A direct sitemap URL (.xml, .xml.gz, .txt, sitemap index or RSS feed) is read as is.", "items": { "type": "string" } }, "maxUrlsPerSite": { "title": "Max URLs per site", "minimum": 0, "type": "integer", "description": "Stop after this many URLs for each site (after filters). 0 = no limit.", "default": 0 }, "maxUrls": { "title": "Max URLs in total", "minimum": 0, "type": "integer", "description": "Stop the whole run after this many URLs. 0 = no limit. Useful to cap cost.", "default": 0 }, "maxSitemapsPerSite": { "title": "Max sitemap files per site", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Safety cap on the number of sitemap files (including nested index children) read per site.", "default": 500 }, "includePatterns": { "title": "Include URLs matching (regex)", "type": "array", "description": "Keep only URLs matching at least one of these regular expressions (case-insensitive). Example: /blog/", "items": { "type": "string" }, "default": [] }, "excludePatterns": { "title": "Exclude URLs matching (regex)", "type": "array", "description": "Drop URLs matching any of these regular expressions. Example: \\.pdf$ or /tag/", "items": { "type": "string" }, "default": [] }, "lastmodFrom": { "title": "Modified after (lastmod from)", "type": "string", "description": "Keep only URLs whose is on or after this date (YYYY-MM-DD) or relative period (e.g. '7 days'). URLs without lastmod are dropped when a date filter is set." }, "lastmodTo": { "title": "Modified before (lastmod to)", "type": "string", "description": "Keep only URLs whose is on or before this date (YYYY-MM-DD)." }, "skipOldSitemaps": { "title": "Skip child sitemaps older than 'Modified after'", "type": "boolean", "description": "When a 'Modified after' date is set, do not download index children whose own is older. Saves time and cost on large sites.", "default": true }, "dedupe": { "title": "Remove duplicate URLs", "type": "boolean", "description": "Output each URL once per site, even if it appears in several sitemaps.", "default": true }, "includeAlternates": { "title": "Include hreflang alternates", "type": "boolean", "description": "Add the xhtml:link hreflang alternates of each URL (multilingual sites).", "default": false }, "includeImages": { "title": "Include image URLs", "type": "boolean", "description": "Add the image:loc URLs listed for each page (image sitemaps). The imageCount field is always present.", "default": false }, "checkStatus": { "title": "Check HTTP status of each URL", "type": "boolean", "description": "Send a lightweight HEAD request to every extracted URL and add statusCode and finalUrl (redirect target). Slower, billed as an extra event. Respects robots.txt.", "default": false }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Do not fetch guessed sitemap locations or check URLs that robots.txt disallows. Sitemaps declared in robots.txt are always allowed.", "default": true }, "guessSitemapLocations": { "title": "Try standard sitemap locations", "type": "boolean", "description": "If robots.txt declares no working sitemap, try /sitemap.xml, /sitemap_index.xml, /sitemap-index.xml, /wp-sitemap.xml, /sitemap.xml.gz, /sitemap/sitemap.xml, /sitemaps.xml and /sitemap.txt.", "default": true }, "maxConcurrency": { "title": "Sites processed in parallel", "minimum": 1, "maximum": 20, "type": "integer", "description": "Number of different sites processed at the same time. Requests to the same host are always spaced out.", "default": 5 }, "requestDelayMs": { "title": "Delay between requests to the same host (ms)", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Minimum pause between two requests to the same host. A robots.txt Crawl-delay is honoured if larger (capped by the next option).", "default": 250 }, "maxCrawlDelaySecs": { "title": "Max honoured Crawl-delay (s)", "minimum": 0, "maximum": 60, "type": "integer", "description": "Upper bound for the robots.txt Crawl-delay directive.", "default": 10 }, "requestTimeoutSecs": { "title": "Request timeout (s)", "minimum": 5, "maximum": 180, "type": "integer", "description": "Timeout for each HTTP request. Failed requests (network, 429, 5xx) are retried up to 3 times with backoff.", "default": 30 }, "failOnEmpty": { "title": "Fail the run when no URL is found", "type": "boolean", "description": "Mark the run as FAILED (instead of an empty SUCCEEDED run) when no input produced any URL, so schedules and integrations notice the problem.", "default": true } } }, "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 } } } } } } } } } }