{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor", "description": "Extract every URL from any website's sitemaps. Finds sitemaps via robots.txt or common paths, follows sitemap indexes, reads gzip, RSS/Atom and text sitemaps, and returns lastmod, priority, hreflang, images and news. Optional HTTP status checks.", "version": "1.0", "x-build-id": "nG9LVxufdN7R51OPC" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/tidyrow~sitemap-url-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-tidyrow-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/tidyrow~sitemap-url-extractor/runs": { "post": { "operationId": "runs-sync-tidyrow-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/tidyrow~sitemap-url-extractor/run-sync": { "post": { "operationId": "run-sync-tidyrow-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 (e.g. https://example.com) or direct sitemap/feed URLs. For a homepage, the Actor finds the sitemaps through robots.txt, then tries common paths like /sitemap.xml.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxUrlsPerSite": { "title": "Max URLs per site", "minimum": 0, "type": "integer", "description": "Stop after saving this many URLs for one site. 0 means no limit.", "default": 0 }, "restrictToStartPath": { "title": "Only URLs under the start path", "type": "boolean", "description": "If a start URL has a path (e.g. https://example.com/blog/), keep only URLs under that path. Has no effect for homepages or direct sitemap URLs.", "default": true }, "includeUrlPatterns": { "title": "Include only URLs matching", "type": "array", "description": "Regular expressions (case-insensitive). If set, only URLs that match at least one are saved. Example: /blog/", "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Exclude URLs matching", "type": "array", "description": "Regular expressions (case-insensitive). URLs that match any are skipped. Example: \\.(pdf|jpg)$", "items": { "type": "string" } }, "lastmodSince": { "title": "Modified since", "type": "string", "description": "Keep only URLs whose lastmod date is on or after this date. Absolute (2024-01-31) or relative (30 days). URLs without lastmod are skipped when this is set." }, "includeAlternates": { "title": "Include hreflang alternates", "type": "boolean", "description": "Add the language/region alternates () listed for each URL.", "default": false }, "includeImages": { "title": "Include image sitemap data", "type": "boolean", "description": "Add image URLs, titles and captions from image sitemaps.", "default": false }, "includeVideos": { "title": "Include video sitemap data", "type": "boolean", "description": "Add video titles, thumbnails and content URLs from video sitemaps.", "default": false }, "includeNews": { "title": "Include news sitemap data", "type": "boolean", "description": "Add title, publication name, language and publication date from Google News sitemaps.", "default": false }, "checkStatus": { "title": "Check HTTP status of each URL", "type": "boolean", "description": "Send a lightweight request to every saved URL and record its status code and redirect target.", "default": false }, "statusCheckConcurrency": { "title": "Status check concurrency (per site)", "minimum": 1, "maximum": 20, "type": "integer", "description": "Parallel status checks per site. Keep it low to stay polite to the server.", "default": 5 }, "respectRobotsTxt": { "title": "Respect robots.txt for status checks", "type": "boolean", "description": "Skip status checks for URLs that robots.txt disallows. They are saved with statusError \"blocked by robots.txt\".", "default": true }, "useRobotsTxt": { "title": "Discover sitemaps from robots.txt", "type": "boolean", "description": "Read the Sitemap: lines in robots.txt.", "default": true }, "tryCommonPaths": { "title": "Try common sitemap paths", "type": "boolean", "description": "If robots.txt lists no sitemap, try /sitemap.xml, /sitemap_index.xml, /wp-sitemap.xml and similar.", "default": true }, "maxSitemapsPerSite": { "title": "Max sitemap files per site", "minimum": 1, "type": "integer", "description": "Safety limit on how many sitemap files to read for one site.", "default": 5000 }, "maxDepth": { "title": "Max sitemap index depth", "minimum": 0, "maximum": 50, "type": "integer", "description": "How many levels of nested sitemap indexes to follow.", "default": 10 }, "maxConcurrency": { "title": "Sites in parallel", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many sites to process at the same time.", "default": 5 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Timeout for each HTTP request.", "default": 30 }, "maxRetries": { "title": "Max retries", "minimum": 0, "maximum": 10, "type": "integer", "description": "Retries for network errors, HTTP 429 and 5xx responses.", "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 } } } } } } } } } }