{ "openapi": "3.0.1", "info": { "title": "Sitemap and Broken Link Checker with On-Page SEO Audit", "description": "Check your sitemap URLs, any list of URLs, or every link on your pages: status, redirect chain, noindex, canonical, robots.txt, and broken links with the page and anchor text they sit on. On-page SEO rules (title, meta description, H1, canonical, alt text, schema, hreflang) with fix hints.", "version": "0.4", "x-build-id": "z0E5WzutnYwaQaFmX" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/madrasco~sitemap-health-check/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-madrasco-sitemap-health-check", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/madrasco~sitemap-health-check/runs": { "post": { "operationId": "runs-sync-madrasco-sitemap-health-check", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/madrasco~sitemap-health-check/run-sync": { "post": { "operationId": "run-sync-madrasco-sitemap-health-check", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "url": { "title": "Your website or sitemap", "type": "string", "description": "Replace this scraping-practice bookstore with your own website or sitemap. Crawl starts at this page (at the home page for a sitemap URL), reads sitemap pages, and follows links on the same site. For a URL list or a page-links check, paste one URL per line here." }, "mode": { "title": "What to check", "enum": [ "crawl", "sitemap", "urlList", "pageLinks" ], "type": "string", "description": "Recommended: crawl same-site pages and compare them with the sitemap. Other choices check only what you supply: sitemap URLs, a URL list, or links on supplied pages. No login or JavaScript execution.", "default": "sitemap" }, "maxUrls": { "title": "Maximum pages or URLs to check", "minimum": 1, "maximum": 50000, "type": "integer", "description": "The example stops at 50 pages. Raise this for your site. Sitemap-listed pages and pages found through links share this limit. Results say when the limit prevents further checks.", "default": 5000 }, "maxDepth": { "title": "How many link steps to follow", "minimum": 0, "maximum": 10, "type": "integer", "description": "Crawl only. Home/start pages and sitemap-listed pages start at 0. Follow at most this many links from each starting page. 0 reads starting pages only.", "default": 3 }, "onlyProblems": { "title": "Show only problems and sitemap differences", "type": "boolean", "description": "Hide healthy rows, but retain sitemap differences and login information in crawl mode. Totals still include all checked pages.", "default": false }, "checkPageTags": { "title": "Read search visibility settings", "type": "boolean", "description": "Check whether pages ask search engines not to index them or point to another preferred URL (canonical). Sitemap and URL-list checks only: crawl and page-links checks always read HTML.", "default": true }, "checkOnPage": { "title": "Check page titles and SEO basics", "type": "boolean", "description": "Read titles, descriptions, headings, image descriptions and other on-page SEO signals. Requires HTML; crawl and page-links checks always read HTML.", "default": true }, "maxSitemaps": { "title": "Maximum sitemap files to read", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Limit on sitemap files, counting index files and their children.", "default": 100 }, "delaySecs": { "title": "Pause between requests (seconds)", "minimum": 0, "maximum": 30, "type": "integer", "description": "Minimum pause per host, with at least one second enforced between requests. A longer robots.txt crawl delay wins in crawl mode (other checks cap it at 10 seconds).", "default": 1 }, "timeoutSecs": { "title": "Request timeout (s)", "minimum": 3, "maximum": 60, "type": "integer", "description": "Per request.", "default": 20 }, "maxCrawlSecs": { "title": "Crawl time limit (seconds)", "minimum": 10, "maximum": 3600, "type": "integer", "description": "Crawl only. Time budget for sitemap discovery, request waits and page checks. Stops when the next wait cannot fit and saves accumulated results with a time-limit flag. May finish sooner to leave time to save results before the platform timeout.", "default": 240 }, "maxLinks": { "title": "Maximum links to inspect", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Crawl: cap same-site link observations across checked pages. Page-links check: cap unique links checked. Summary reports when reached.", "default": 2000 }, "checkExternalLinks": { "title": "Include other sites in supplied-page link checks", "type": "boolean", "description": "Only for \"Check links on supplied pages\". Crawl always stays on the input site (www and non-www included).", "default": true }, "checkImages": { "title": "Include images in supplied-page link checks", "type": "boolean", "description": "Only for \"Check links on supplied pages\". Crawl follows page links, not image addresses.", "default": true } } }, "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 } } } } } } } } } }