{ "openapi": "3.0.1", "info": { "title": "Broken Link Checker", "description": "Crawl any website and find every broken link, dead image and redirect chain, reported with the exact page and anchor text each one sits on. Covers internal and external links, and tells a genuine 404 apart from a site that simply blocks robots.", "version": "0.1", "x-build-id": "LxMHiu6WGTiQAG0Tr" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/arched_friend~broken-link-checker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-arched_friend-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/arched_friend~broken-link-checker/runs": { "post": { "operationId": "runs-sync-arched_friend-broken-link-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/arched_friend~broken-link-checker/run-sync": { "post": { "operationId": "run-sync-arched_friend-broken-link-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "type": "array", "description": "The site to check, as a domain or full URL. Add more than one to check several sites in the same run.", "items": { "type": "string" } }, "maxPages": { "title": "Maximum pages to crawl", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Upper limit on how many pages of the site to open looking for links. This is what the run is charged on.", "default": 200 }, "maxDepth": { "title": "Maximum crawl depth", "minimum": 0, "maximum": 20, "type": "integer", "description": "How many clicks from the starting page to follow. 0 checks only the pages you list.", "default": 5 }, "includeSubdomains": { "title": "Treat subdomains as the same site", "type": "boolean", "description": "Count blog.example.com as part of example.com, both for crawling and for deciding what counts as an internal link.", "default": true }, "checkExternalLinks": { "title": "Check links to other sites", "type": "boolean", "description": "Also verify links pointing away from your site. These are where most rot happens, since you do not control them.", "default": true }, "checkImages": { "title": "Check images too", "type": "boolean", "description": "Also verify every image source, which finds broken images as well as broken links.", "default": false }, "excludePatterns": { "title": "Skip URLs containing", "type": "array", "description": "Do not crawl any URL containing one of these strings, for example /admin or ?print=. Links to them are still checked.", "items": { "type": "string" } }, "reportWorkingLinks": { "title": "Include working links in the output", "type": "boolean", "description": "Return every link checked rather than only the problems. Useful for a full audit export, noisier for routine monitoring.", "default": false }, "requestTimeoutSecs": { "title": "Timeout per link", "minimum": 5, "maximum": 120, "type": "integer", "description": "How long to wait for each link before recording it as a timeout.", "default": 15 }, "maxConcurrency": { "title": "Parallel requests", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many pages and links to handle at once. Links are checked by a worker pool, so one slow link never blocks the others. Lower this if a site rate limits you.", "default": 20 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional, and off by default. Checking links does not need a proxy; turn one on only if a site rate limits you during a large crawl." } } }, "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 } } } } } } } } } }