{ "openapi": "3.0.1", "info": { "title": "Broken Link Checker - Find 404s and Dead Links", "description": "Crawl any website and find broken links, 404 errors, redirect chains, timeouts, and SSL failures. Essential for SEO audits, QA, and content maintenance. Export data, run via API, schedule and monitor runs, or integrate with other tools.", "version": "1.0", "x-build-id": "2m7n2Fs6b3ybybJCt" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/santamaria-automations~broken-link-checker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-santamaria-automations-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/santamaria-automations~broken-link-checker/runs": { "post": { "operationId": "runs-sync-santamaria-automations-broken-link-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/santamaria-automations~broken-link-checker/run-sync": { "post": { "operationId": "run-sync-santamaria-automations-broken-link-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "websites" ], "properties": { "websites": { "title": "Websites", "type": "array", "description": "List of starting URLs to check. You can provide bare domains (example.com) or full URLs (https://example.com/blog). Each website is crawled independently and gets its own summary record.", "items": { "type": "string" } }, "maxDepth": { "title": "Max Crawl Depth", "minimum": 0, "maximum": 10, "type": "integer", "description": "How many levels of internal links to follow from the seed URL. Depth 0 = only the seed page, depth 1 = seed + pages it links to, depth 2 = two hops, etc. External links are always checked but never crawled.", "default": 2 }, "maxUrlsPerSite": { "title": "Max URLs per Site", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Safety cap on the number of unique links checked per website. Prevents runaway jobs on very large sites. Increase for full audits, decrease for quick sanity checks.", "default": 1000 }, "checkExternal": { "title": "Check External Links", "type": "boolean", "description": "Also check links that point to other domains (ads, partners, sources, CDNs). Disable to only check links within the same domain as the seed URL.", "default": true }, "followRedirects": { "title": "Follow Redirects", "type": "boolean", "description": "Follow 3xx redirects up to 10 hops and record the full redirect chain. Disable to treat any 3xx as a standalone result and stop at the first hop.", "default": true }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Honor the robots.txt of each target site and skip URLs the site asks bots not to crawl.", "default": true }, "timeoutSeconds": { "title": "Timeout (seconds)", "minimum": 2, "maximum": 120, "type": "integer", "description": "HTTP timeout applied to every link check. Links that take longer than this are classified as 'timeout'.", "default": 15 }, "concurrency": { "title": "Concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Number of parallel link checks. Higher values check more links per second but put more load on the target server.", "default": 10 }, "userAgent": { "title": "User Agent", "type": "string", "description": "Custom User-Agent header sent with every request. Leave empty to use the default bot identifier." }, "includeOK": { "title": "Include OK Links", "type": "boolean", "description": "Include links that returned 2xx OK in the output. By default only broken links and redirects are emitted to keep the dataset small.", "default": false }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Optional Apify proxy settings. Most public sites work fine without proxy -- enable only if you hit rate limits.", "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 } } }, "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 } } } } } } } } } }