{ "openapi": "3.0.1", "info": { "title": "Broken Link Checker: Find 404s, Redirects & Dead Links", "description": "Crawl your website and find every broken internal and external link, with the page it's on, the anchor text, status code, redirect chain and timeouts. Respects robots.txt. Cheap per-page and per-link pricing.", "version": "0.1", "x-build-id": "74i9VBbnbdhybChSh" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/eddie-power-dev~broken-link-checker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-eddie-power-dev-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/eddie-power-dev~broken-link-checker/runs": { "post": { "operationId": "runs-sync-eddie-power-dev-broken-link-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/eddie-power-dev~broken-link-checker/run-sync": { "post": { "operationId": "run-sync-eddie-power-dev-broken-link-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "startUrls" ], "properties": { "startUrls": { "title": "Website URLs", "maxItems": 20, "type": "array", "description": "Where to start crawling (usually your home page). The crawler stays on these domains. Up to 20.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxPages": { "title": "Max pages to crawl", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum number of pages on your site to load and scan for links.", "default": 100 }, "maxDepth": { "title": "Max crawl depth", "minimum": 0, "maximum": 20, "type": "integer", "description": "How many clicks away from the start URL to crawl. Links found on the deepest pages are still checked.", "default": 3 }, "maxLinksToCheck": { "title": "Max extra links to check", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Cap on links checked without crawling (external links and internal links beyond the page/depth limits).", "default": 5000 }, "checkExternalLinks": { "title": "Check external links", "type": "boolean", "description": "Also check links to other websites (one HEAD request each, falling back to GET).", "default": true }, "checkResources": { "title": "Check images, scripts and stylesheets", "type": "boolean", "description": "Also check img, script, iframe, source and stylesheet/icon URLs, not just links.", "default": false }, "includeSubdomains": { "title": "Treat subdomains as internal", "type": "boolean", "description": "Crawl subdomains of the start domains too (www. is always treated as the same site).", "default": false }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip internal pages disallowed by robots.txt (and honour Crawl-delay up to 10 s). Recommended. Only turn off for your own site.", "default": true }, "reportMode": { "title": "What to report", "enum": [ "broken", "brokenAndRedirects", "all" ], "type": "string", "description": "Only problems, problems plus redirected links, or every link checked.", "default": "brokenAndRedirects" }, "treatBlockedAsBroken": { "title": "Count 401/403/429 as broken", "type": "boolean", "description": "Many sites (LinkedIn, Cloudflare-protected sites) block bots with 403/429/999. By default these are reported as BLOCKED_BY_SITE, not broken.", "default": false }, "excludeUrlContains": { "title": "Skip URLs containing", "maxItems": 50, "type": "array", "description": "Plain text fragments; any link containing one is skipped (e.g. /logout, ?replytocom=).", "items": { "type": "string" } }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Requests in flight at once (across all hosts).", "default": 5 }, "perHostDelayMs": { "title": "Delay between requests to the same host (ms)", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Politeness delay per host. robots.txt Crawl-delay is used if larger.", "default": 250 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 3, "maximum": 60, "type": "integer", "description": "A link that takes longer than this is reported as TIMEOUT.", "default": 15 } } }, "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 } } } } } } } } } }