{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor & XML Sitemap Scraper (Index, Gzip)", "description": "Extract every URL from a website's sitemap.xml: give a domain and it finds sitemaps via robots.txt, follows sitemap indexes, reads .gz, text and RSS sitemaps, and recovers broken XML. Returns lastmod, changefreq, priority, optional HTTP status. $0.20 per 1,000 URLs.", "version": "1.0", "x-build-id": "NwA9ikEhXkmjvJKrB" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ventura_workalong~sitemap-url-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ventura_workalong-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/ventura_workalong~sitemap-url-extractor/runs": { "post": { "operationId": "runs-sync-ventura_workalong-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/ventura_workalong~sitemap-url-extractor/run-sync": { "post": { "operationId": "run-sync-ventura_workalong-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 (`example.com`), page URLs, `robots.txt` URLs or direct sitemap URLs (`https://example.com/sitemap_index.xml`, `.xml.gz`, `.txt`). For a domain, sitemaps are discovered from robots.txt, then from common locations like /sitemap.xml.", "items": { "type": "string" } }, "maxUrlsPerSite": { "title": "Max URLs per site", "minimum": 0, "type": "integer", "description": "Stop after this many unique URLs per input. 0 = no limit (all URLs). The prefilled 100 is for a quick try.", "default": 0 }, "includeUrlPatterns": { "title": "Include URL patterns (regex)", "type": "array", "description": "Keep only URLs matching at least one of these regular expressions (case-insensitive), e.g. `/blog/` or `/products/.+`.", "default": [], "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Exclude URL patterns (regex)", "type": "array", "description": "Drop URLs matching any of these regular expressions, e.g. `/tag/` or `\\?page=`.", "default": [], "items": { "type": "string" } }, "lastmodFrom": { "title": "Last modified on or after", "type": "string", "description": "Only URLs whose sitemap `lastmod` is on or after this date (YYYY-MM-DD or ISO 8601). URLs without a lastmod are excluded when a date filter is set." }, "lastmodTo": { "title": "Last modified on or before", "type": "string", "description": "Only URLs whose sitemap `lastmod` is on or before this date. URLs without a lastmod are excluded when a date filter is set." }, "includeImages": { "title": "Include image URLs", "type": "boolean", "description": "Add the `images` list from image sitemap extensions (`image:loc`).", "default": false }, "includeAlternates": { "title": "Include hreflang alternates", "type": "boolean", "description": "Add the `alternates` list (`xhtml:link rel=alternate hreflang`) for multilingual sites.", "default": false }, "checkStatus": { "title": "Check HTTP status of each URL", "type": "boolean", "description": "Send one HEAD request per URL and return `httpStatus` (redirects are reported, not followed, with `redirectTo`). Slower: requests to one site are rate-limited. Charged per checked URL.", "default": false }, "maxStatusChecks": { "title": "Max status checks per run", "minimum": 0, "type": "integer", "description": "Upper limit on HTTP status checks in this run (only with status checking on).", "default": 1000 }, "maxSitemapsPerSite": { "title": "Max sitemap files per site", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Safety cap on sitemap files read per input (sitemap indexes can list thousands).", "default": 1000 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip sitemaps and pages that robots.txt disallows for this bot, and honor Crawl-delay.", "default": true }, "maxRequestsPerSecondPerHost": { "title": "Max requests per second per site", "minimum": 0.2, "maximum": 5, "type": "number", "description": "Politeness limit for each host (0.2 to 5). Robots.txt Crawl-delay overrides it when slower.", "default": 1 }, "maxConcurrency": { "title": "Sites in parallel", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many inputs are processed at the same time.", "default": 5 } } }, "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 } } } } } } } } } }