{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor & Status Checker", "description": "Extract every URL from a website's XML sitemaps, including nested sitemap indexes, gzipped sitemaps and robots.txt discovery. Get lastmod and an optional HTTP status for each URL. If a site blocks the run, you get a row that says why. Export to CSV, JSON or Excel.", "version": "0.0", "x-build-id": "Qp2gxFjqPyQNN2nSo" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/bjgomes~sitemap-url-extractor-status-checker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-bjgomes-sitemap-url-extractor-status-checker", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/bjgomes~sitemap-url-extractor-status-checker/runs": { "post": { "operationId": "runs-sync-bjgomes-sitemap-url-extractor-status-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/bjgomes~sitemap-url-extractor-status-checker/run-sync": { "post": { "operationId": "run-sync-bjgomes-sitemap-url-extractor-status-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "The websites or sitemaps to read, as objects like {\"url\": \"https://example.com\"}. A homepage (or any page) stands for its whole site: its sitemaps are found from robots.txt, then /sitemap.xml and /sitemap_index.xml. A URL with .xml, .gz or 'sitemap' in its path is read directly as a sitemap. Nested sitemap indexes and gzipped sitemaps are followed. You get one row per URL found.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxUrls": { "title": "Maximum URLs", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Stop after this many unique URLs across all inputs. Each URL is one charged row, so this caps the cost. Use 10 to 100 for a quick sample. With onlyChanges on, at most 50,000.", "default": 1000 }, "checkStatus": { "title": "Check HTTP status of each URL", "type": "boolean", "description": "true: also request each URL and add statusCode, finalUrl, redirectCount and responseTimeMs, to find 404s and redirects. Slower, and each URL that answers is charged a status check on top. URLs that robots.txt disallows are listed but not requested. false: list the URLs only.", "default": false }, "onlyChanges": { "title": "Changes only", "type": "boolean", "description": "For scheduled monitoring. true: output only what changed since this job's last run, each row with change 'new', 'removed' or (with checkStatus) 'changed'. Every URL read is still charged. The first run marks every URL new. A job is the same startUrls, maxUrls and checkStatus. Its state is kept in your account's key-value store 'sitemap-url-extractor-changes'. maxUrls can be at most 50,000. false: the full list.", "default": false }, "resetChanges": { "title": "Start changes-only over", "type": "boolean", "description": "With onlyChanges on: forget this job's saved state, so every URL counts as new and the state is replaced. Ignored when onlyChanges is off.", "default": false }, "maxConcurrency": { "title": "Maximum concurrent requests", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many status checks run at once. Never more than 4 at a time to one host, and robots.txt Crawl-delay is honoured. Only matters with checkStatus on.", "default": 5 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 1, "maximum": 120, "type": "integer", "description": "Seconds to wait for any one sitemap, robots.txt or page request before recording it as a timeout.", "default": 20 } } }, "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 } } } } } } } } } }