{ "openapi": "3.0.1", "info": { "title": "XML Sitemap URL Extractor & Sitemap to CSV", "description": "Get every URL from a website's XML sitemap as JSON, CSV or Excel. Give a domain or sitemap URL: it finds sitemaps via robots.txt, follows indexes and .gz files, and returns one row per page with lastmod, images and hreflang. Optional HTTP status check and new-page monitoring.", "version": "0.1", "x-build-id": "XixtYpmuS7bL594DM" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/swillz~sitemap-url-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-swillz-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/swillz~sitemap-url-extractor/runs": { "post": { "operationId": "runs-sync-swillz-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/swillz~sitemap-url-extractor/run-sync": { "post": { "operationId": "run-sync-swillz-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Required. Array of objects, e.g. [{\"url\":\"https://example.com\"}] or [{\"url\":\"https://example.com/sitemap.xml\"}]. A home page triggers sitemap auto-discovery (robots.txt + common paths); a sitemap URL is read directly.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxUrls": { "title": "Max URLs (total)", "minimum": 0, "type": "integer", "description": "Stop after this many URLs across all sites (default 1000; 0 = no limit). Large sites list 100k+ URLs: raise this deliberately. Also applies to API and AI-agent calls that omit it.", "default": 1000 }, "maxUrlsPerSite": { "title": "Max URLs per site", "minimum": 0, "type": "integer", "description": "Stop after this many URLs from each start URL (0 = no limit). Useful when one big site would use up maxUrls.", "default": 0 }, "includeUrlPatterns": { "title": "Include URL patterns", "type": "array", "description": "Only output URLs matching at least one pattern. Use a glob (e.g. */blog/*) or a regular expression (e.g. /products/\\d+). Case-insensitive.", "default": [], "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Exclude URL patterns", "type": "array", "description": "Drop URLs matching any of these globs or regular expressions (e.g. */tag/*).", "default": [], "items": { "type": "string" } }, "lastmodFrom": { "title": "Modified after", "type": "string", "description": "Only URLs whose lastmod date is on/after this date. Absolute (2026-01-31) or relative (7 days, 24 hours, 2 weeks). URLs without lastmod are excluded when a date filter is set." }, "lastmodTo": { "title": "Modified before", "type": "string", "description": "Only URLs whose lastmod date is on/before this date. Absolute or relative." }, "onlyNewUrls": { "title": "Only new URLs since the last run (monitoring)", "type": "boolean", "description": "Remembers URLs between runs (in a named key-value store) and outputs only URLs not seen before. The first run outputs everything and saves the baseline. Ideal with a schedule to get alerts on new pages, products or articles.", "default": false }, "stateKey": { "title": "Monitoring state key", "type": "string", "description": "Optional name for the remembered URL set. Defaults to a hash of the start URLs. Use different keys for independent monitors." }, "checkUrlStatus": { "title": "Check HTTP status of every URL", "type": "boolean", "description": "Sends a HEAD request (GET fallback) to each output URL and adds httpStatus and finalUrl (redirect target). Finds broken (404) and redirected sitemap entries. Slower; charged as an extra event per URL.", "default": false }, "statusCheckConcurrency": { "title": "Status check concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many HTTP status checks run at the same time (only with checkUrlStatus). Lower it if the site rate-limits you.", "default": 10 }, "includeImages": { "title": "Include image URLs", "type": "boolean", "description": "Add the image URLs listed for each page (image:loc tags in image sitemaps).", "default": false }, "includeAlternates": { "title": "Include hreflang alternates", "type": "boolean", "description": "Add hreflang language alternates (xhtml:link tags) for each page.", "default": false }, "restrictToStartPath": { "title": "Restrict to start URL path", "type": "boolean", "description": "When a start URL has a path (e.g. https://example.com/blog/), output only URLs under that path and try that path's own sitemap first.", "default": true }, "discoverFromRobotsTxt": { "title": "Discover sitemaps from robots.txt", "type": "boolean", "description": "Read Sitemap: lines from /robots.txt when a website (not a sitemap) is given.", "default": true }, "tryCommonSitemapPaths": { "title": "Try common sitemap paths", "type": "boolean", "description": "If robots.txt lists no sitemap, try /sitemap.xml, /sitemap_index.xml, /wp-sitemap.xml, /sitemap.txt and similar.", "default": true }, "maxSitemapDepth": { "title": "Max sitemap index depth", "minimum": 0, "maximum": 20, "type": "integer", "description": "How deep to follow nested sitemap indexes.", "default": 5 }, "maxSitemaps": { "title": "Max sitemap files", "minimum": 1, "type": "integer", "description": "Safety limit on the number of sitemap files fetched per run.", "default": 1000 }, "sitemapConcurrency": { "title": "Sitemap download concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Sitemap files fetched in parallel per site.", "default": 5 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 180, "type": "integer", "description": "Timeout for each sitemap or status-check HTTP request, in seconds.", "default": 30 }, "maxRetries": { "title": "Max retries per request", "minimum": 0, "maximum": 10, "type": "integer", "description": "Retries on network errors, 403, 429 and 5xx with exponential backoff (honours Retry-After).", "default": 3 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Usually not needed — sitemaps are meant for bots. Enable Apify Proxy only for sites that block datacenter traffic.", "default": { "useApifyProxy": false } }, "emitStatusRows": { "title": "Add status rows for empty sites", "type": "boolean", "description": "Add one free row (status \"no_results\" plus a reason) for each start URL that returned no URLs, so you or an AI agent can see why. Not charged. Turn off for a pure URL list.", "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 } } } } } } } } } }