{ "openapi": "3.0.1", "info": { "title": "Link Status Checker", "description": "Check internal and external links discovered while crawling user-supplied start URLs. Each result includes the target, status category, HTTP code, final URL, redirect chain, anchor text and source page. The checker uses HEAD requests with a GET fallback and records redirect hops for review.", "version": "0.1", "x-build-id": "Txhvs1QtNXQQcT26y" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/axiomworks~broken-link-checker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-axiomworks-broken-link-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/axiomworks~broken-link-checker/runs": { "post": { "operationId": "runs-sync-axiomworks-broken-link-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/axiomworks~broken-link-checker/run-sync": { "post": { "operationId": "run-sync-axiomworks-broken-link-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "startUrls": { "title": "Start URLs", "type": "array", "description": "Required: websites or pages to start from, as [{\"url\": \"https://example.com/\"}] or plain strings (up to 10 is sensible). A URL ending in .xml is read as a sitemap: its page URLs (up to maxPages) are checked as start pages. A bare host like 'iana.org' gets https://. The crawl stays on each start URL's site (subdomains included by default). A dead or blocked start URL returns 0 rows for it and is named in the status message and the SUMMARY record." }, "maxDepth": { "title": "Maximum crawl depth", "type": "integer", "description": "How many clicks deep to crawl from the start URLs, 0-10, default 1. 0 checks only the links on the start page(s); 1 also crawls the internal pages they link to, and so on. Bounded by maxPages and maxItems.", "default": 1 }, "maxPages": { "title": "Maximum pages to crawl", "type": "integer", "description": "Maximum number of HTML pages fetched and scanned for links, across all start URLs, 1-10000, default 20. Every link on a crawled page is checked; each unique URL is checked only once per run.", "default": 20 }, "maxItems": { "title": "Maximum results", "type": "integer", "description": "Maximum number of link rows to return across all start URLs and pages, 1-1000000, default 500. One row = one link on one page. The run stops as soon as this many rows are saved, and you are charged only for rows returned.", "default": 500 }, "checkExternalLinks": { "title": "Check external links", "type": "boolean", "description": "Default true: links to other websites are checked and returned (they are never crawled). false = only links on the same site are checked and returned.", "default": true }, "includeSubdomains": { "title": "Treat subdomains as internal", "type": "boolean", "description": "Default true: blog.example.com counts as the same site as example.com (crawled, linkType 'internal'). false = only the exact start host counts as internal (www. is ignored either way).", "default": true }, "onlyBroken": { "title": "Only return broken links", "type": "boolean", "description": "Default false: every link is returned. true = only rows with isBroken true (status 400 or higher, blocked, network error or redirect loop); the whole site is still crawled and checked, and maxItems counts broken rows only.", "default": false }, "excludeUrlPatterns": { "title": "Exclude URL patterns", "type": "array", "description": "Regular expressions (case-insensitive); links whose URL matches any of them are neither crawled, checked nor returned, e.g. 'logout' or '/wp-admin/'. Default: none.", "default": [], "items": { "type": "string" } }, "maxRedirects": { "title": "Maximum redirects", "type": "integer", "description": "Redirect hops to follow per link, 0-30, default 10. A link that redirects more often is reported as linkStatus 'redirect_loop' with error TOO_MANY_REDIRECTS.", "default": 10 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "type": "integer", "description": "Seconds to wait for a response before a link counts as a network error, 3-120, default 15 (connecting is capped at 10 s).", "default": 15 }, "maxConcurrency": { "title": "Maximum concurrent checks", "type": "integer", "description": "Link checks in flight at once, 1-20, default 5. Never more than 2 at a time per host, with a 200-500 ms pause between requests to the same host, so sites are not hammered.", "default": 5 }, "userAgent": { "title": "User-Agent", "type": "string", "description": "User-Agent header for every request. Empty (default) sends a current desktop Chrome User-Agent." }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Default: no proxy, the checks run from Apify's servers. If a start page answers 403/429 it is retried once through Apify Proxy (datacenter, then residential). Set a proxy here to send every request through it. Single links that answer 403/429/999 are reported as 'blocked'.", "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 } } } } } } } } } }