{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor: Get All URLs of Any Website", "description": "Extract all URLs from any website's sitemap.xml. Auto-discovers sitemaps via robots.txt, follows sitemap indexes, reads .xml.gz, text, RSS and Atom sitemaps, returns lastmod, hreflang, image and news data, and detects new URLs between runs.", "version": "0.1", "x-build-id": "kKFZWqGLUecEZ3viN" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/datawright-labs~sitemap-url-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-datawright-labs-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/datawright-labs~sitemap-url-extractor/runs": { "post": { "operationId": "runs-sync-datawright-labs-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/datawright-labs~sitemap-url-extractor/run-sync": { "post": { "operationId": "run-sync-datawright-labs-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "One per line. Enter a website (e.g. https://example.com or example.com) to auto-discover its sitemaps from robots.txt and common locations, or paste a sitemap URL directly (sitemap.xml, sitemap index, .xml.gz, .txt, RSS or Atom feed).", "default": [ "https://crawlee.dev" ], "items": { "type": "string" } }, "maxUrlsPerSite": { "title": "Max URLs per site", "minimum": 0, "type": "integer", "description": "Stop saving URLs for a site after this many (after filters). 0 = no limit. Tip: also set 'Maximum cost per run' in the run options to cap spend.", "default": 0 }, "includePatterns": { "title": "URL must contain (any of)", "type": "array", "description": "Keep only URLs matching at least one pattern. Plain text = case-insensitive 'contains' (e.g. /blog/), * = wildcard (e.g. */products/*), or a regular expression between slashes (e.g. /\\/20(25|26)\\//). Leave empty for all URLs.", "default": [], "items": { "type": "string" } }, "excludePatterns": { "title": "URL must NOT contain", "type": "array", "description": "Drop URLs matching any of these patterns (same syntax as above), e.g. /tag/ or ?page=.", "default": [], "items": { "type": "string" } }, "modifiedAfter": { "title": "Modified after (lastmod)", "type": "string", "description": "Only URLs whose date is on/after this date. Use YYYY-MM-DD or a relative period like '7 days', '24 hours', '2 weeks'. URLs without a lastmod are dropped when this is set. Child sitemaps whose own lastmod is older are skipped entirely, which makes runs much faster." }, "sameHostOnly": { "title": "Only URLs on the same host", "type": "boolean", "description": "Drop URLs whose hostname differs from the site (www. is ignored). Useful for sitemaps that list CDN or partner URLs.", "default": false }, "monitorStateKey": { "title": "Monitoring key (detect new URLs)", "type": "string", "description": "Give this monitor a name (e.g. competitor-blogs) and schedule the Actor. Each URL then gets isNew = true/false compared with the previous run that used the same key, and the SITES record reports new and removed URL counts. State is kept in your named key-value store 'sitemap-url-extractor-state'." }, "onlyNewUrls": { "title": "Output only new URLs", "type": "boolean", "description": "With a monitoring key, save (and pay for) only URLs not seen in the previous run. The first run just records the baseline and outputs nothing.", "default": false }, "includeAlternates": { "title": "Include hreflang alternates", "type": "boolean", "description": "Add the xhtml:link hreflang alternates (language versions) of each URL.", "default": true }, "includeImages": { "title": "Include image URLs", "type": "boolean", "description": "Add the list of image URLs from image sitemaps (imageCount is always included).", "default": false }, "includeNews": { "title": "Include Google News fields", "type": "boolean", "description": "Add news title, publication name, language and publication date from news sitemaps.", "default": true }, "discoverFromRobotsTxt": { "title": "Discover sitemaps from robots.txt", "type": "boolean", "description": "Read the Sitemap: lines of the site's robots.txt.", "default": true }, "tryCommonLocations": { "title": "Try common sitemap locations", "type": "boolean", "description": "If robots.txt lists no sitemap, try /sitemap.xml, /sitemap_index.xml, /sitemap-index.xml, /wp-sitemap.xml, /sitemap.xml.gz and /sitemap.txt.", "default": true }, "maxSitemapsPerSite": { "title": "Max sitemap files per site", "minimum": 1, "type": "integer", "description": "Safety limit for huge sitemap indexes.", "default": 1000 }, "maxConcurrency": { "title": "Parallel downloads per site", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many sitemap files to download at once for each site.", "default": 5 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 300, "type": "integer", "description": "How long to wait for one sitemap or robots.txt download before retrying.", "default": 60 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Most sitemaps download fine without a proxy. Enable Apify Proxy if a site blocks you (HTTP 403/429).", "default": { "useApifyProxy": false } } } }, "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 } } } } } } } } } }