{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor", "description": "Extract all URLs from website sitemaps. Finds sitemaps in robots.txt, follows sitemap indexes, and reads gzip, news, image, and video sitemaps.", "version": "1.0", "x-build-id": "BngiQDudAnZiGg25z" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/appreciative_duct~sitemap-url-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-appreciative_duct-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/appreciative_duct~sitemap-url-extractor/runs": { "post": { "operationId": "runs-sync-appreciative_duct-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/appreciative_duct~sitemap-url-extractor/run-sync": { "post": { "operationId": "run-sync-appreciative_duct-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Website or sitemap URLs", "type": "array", "description": "One or more website addresses (https://example.com) or direct sitemap URLs (https://example.com/sitemap.xml). A website is expanded through robots.txt, common sitemap paths, and a homepage sitemap link.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxUrls": { "title": "Maximum URLs", "minimum": 1, "maximum": 2000000, "type": "integer", "description": "Stop after this many page URLs have been saved. The default is high enough for a normal site. Lower it for a sample.", "default": 20000 }, "includeUrlPatterns": { "title": "Include URL patterns", "type": "array", "description": "Optional JavaScript regular expressions, case-insensitive. A URL is kept when it matches at least one pattern. Leave empty to keep every URL.", "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Exclude URL patterns", "type": "array", "description": "Optional JavaScript regular expressions, case-insensitive. A URL that matches any pattern is dropped.", "items": { "type": "string" } }, "minLastmod": { "title": "Only URLs modified after", "type": "string", "description": "Optional ISO date, for example 2024-01-01. URLs whose lastmod is older are skipped. Child sitemaps with an older lastmod are not downloaded." }, "maxLastmod": { "title": "Only URLs modified before", "type": "string", "description": "Optional ISO date. URLs whose lastmod is newer are skipped." }, "includeUndated": { "title": "Include URLs with no lastmod", "type": "boolean", "description": "Used only when a modified-after or modified-before date is set. Off means undated URLs are skipped.", "default": false }, "deduplicate": { "title": "Deduplicate URLs", "type": "boolean", "description": "Keep the first copy of a URL when it appears in more than one sitemap. The fragment is ignored and the hostname is compared case-insensitively.", "default": true }, "includeImages": { "title": "Include image sitemap fields", "type": "boolean", "description": "Save image locations, titles, and captions from Google image sitemaps.", "default": true }, "includeVideos": { "title": "Include video sitemap fields", "type": "boolean", "description": "Save video title, description, thumbnail, and content or player URLs.", "default": true }, "includeNews": { "title": "Include news sitemap fields", "type": "boolean", "description": "Save the news title, publication name, language, and publication date.", "default": true }, "includeAlternates": { "title": "Include hreflang alternates", "type": "boolean", "description": "Save xhtml:link alternate URLs, including the language code.", "default": true }, "useRobotsTxt": { "title": "Read robots.txt", "type": "boolean", "description": "Read Sitemap directives from the website's robots.txt.", "default": true }, "probeCommonPaths": { "title": "Check common sitemap paths", "type": "boolean", "description": "Also request paths such as /sitemap.xml, /sitemap_index.xml, and /wp-sitemap.xml. This catches sitemaps that robots.txt forgot.", "default": true }, "maxIndexDepth": { "title": "Maximum sitemap index depth", "minimum": 0, "maximum": 10, "type": "integer", "description": "How many levels of sitemap indexes to follow. 1 is a normal index of URL files. The default 5 covers nested indexes.", "default": 5 }, "maxConcurrency": { "title": "Concurrent requests", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many sitemaps to download at once.", "default": 8 }, "maxRetries": { "title": "Retries", "minimum": 0, "maximum": 6, "type": "integer", "description": "Retries for timeouts, connection errors, HTTP 429, and HTTP 5xx. Waits with exponential backoff.", "default": 3 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Time limit for one HTTP request, including its redirects.", "default": 30 }, "maxSitemapBytes": { "title": "Maximum sitemap size (bytes)", "minimum": 100000, "maximum": 52428800, "type": "integer", "description": "Refuse a single sitemap larger than this. The sitemap protocol limit is 50 MB uncompressed.", "default": 20000000 } } }, "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 } } } } } } } } } }