{ "openapi": "3.0.1", "info": { "title": "Sitemap Extractor — Get All Website URLs from sitemap.xml", "description": "Sitemap extractor & sitemap.xml parser: get all URLs of any website. Auto-finds sitemaps via robots.txt, follows nested indexes and .gz, returns lastmod, images, hreflang, news/video data, optional status check. CSV/JSON/Excel or API. $0.50 per 1,000 URLs.", "version": "1.1", "x-build-id": "v86HjPMf9cDLQJRuz" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/plumbline-data~sitemap-url-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-plumbline-data-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/plumbline-data~sitemap-url-extractor/runs": { "post": { "operationId": "runs-sync-plumbline-data-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/plumbline-data~sitemap-url-extractor/run-sync": { "post": { "operationId": "run-sync-plumbline-data-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "startUrls" ], "properties": { "startUrls": { "title": "Websites or sitemap URLs", "type": "array", "description": "Homepages (https://example.com) or direct sitemap links (https://example.com/sitemap.xml, .xml.gz, .txt, RSS/Atom). One row per URL found is returned.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "discoverFromRobotsTxt": { "title": "Discover sitemaps from robots.txt", "type": "boolean", "description": "Read the site's robots.txt and follow every `Sitemap:` line.", "default": true }, "tryCommonLocations": { "title": "Try common sitemap locations", "type": "boolean", "description": "If robots.txt lists nothing usable, probe /sitemap.xml, /sitemap_index.xml, /wp-sitemap.xml, /sitemap.xml.gz, /sitemap.txt and similar.", "default": true }, "restrictToInputPath": { "title": "Restrict to input path", "type": "boolean", "description": "If you enter a sub-path such as https://example.com/blog/, return only URLs under /blog/ (and look for /blog/sitemap.xml first). Has no effect for homepages or direct sitemap URLs.", "default": true }, "maxSitemapsPerSite": { "title": "Max sitemap files per site", "minimum": 1, "type": "integer", "description": "Safety cap on how many sitemap files (including nested ones) are downloaded per site.", "default": 1000 }, "includeUrlPatterns": { "title": "Include only URLs matching (regex)", "type": "array", "description": "Keep only URLs matching at least one of these regular expressions, e.g. `/blog/` or `\\.pdf$`. Leave empty to keep everything.", "default": [], "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Exclude URLs matching (regex)", "type": "array", "description": "Drop URLs matching any of these regular expressions, e.g. `/tag/` or `\\?page=`.", "default": [], "items": { "type": "string" } }, "lastmodFrom": { "title": "Only URLs modified since", "type": "string", "description": "Keep only URLs whose is on/after this date (YYYY-MM-DD). Great for monitoring new or updated pages." }, "skipUrlsWithoutLastmod": { "title": "Skip URLs without lastmod (when date filter is set)", "type": "boolean", "description": "When 'Only URLs modified since' is set, also drop URLs that have no value.", "default": false }, "maxUrlsPerSite": { "title": "Max URLs per site", "minimum": 0, "type": "integer", "description": "Stop after this many URLs per site. 0 = no limit.", "default": 0 }, "deduplicate": { "title": "Remove duplicate URLs", "type": "boolean", "description": "Return each URL only once per site even if it appears in several sitemaps.", "default": true }, "includeExtensions": { "title": "Include images, hreflang, news & video data", "type": "boolean", "description": "Extract image, hreflang alternate, Google News and video sitemap extensions.", "default": true }, "checkStatus": { "title": "Check HTTP status of each URL", "type": "boolean", "description": "Send a lightweight HEAD request to each URL and return status code and final (redirected) URL. Pages disallowed by robots.txt are skipped. Slower on large sites.", "default": false }, "statusCheckConcurrency": { "title": "Status check concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Parallel status checks (1–50). Requests per host are additionally capped by 'Max concurrency per host'.", "default": 10 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip status checks and sitemap probes that robots.txt disallows. Sitemaps explicitly listed in robots.txt are always read.", "default": true }, "maxConcurrencyPerHost": { "title": "Max concurrency per host", "minimum": 1, "maximum": 16, "type": "integer", "description": "Maximum parallel requests to one host. The Actor also slows down automatically when a site answers 429/503.", "default": 2 }, "delayBetweenRequestsMs": { "title": "Delay between requests to the same host (ms)", "minimum": 0, "type": "integer", "description": "Optional pause between requests to one host.", "default": 0 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 180, "type": "integer", "description": "Timeout per HTTP request.", "default": 30 }, "maxRetries": { "title": "Max retries", "minimum": 0, "maximum": 8, "type": "integer", "description": "Retries for timeouts, 429 and 5xx responses (exponential backoff, honours Retry-After).", "default": 3 } } }, "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 } } } } } } } } } }