{ "openapi": "3.0.1", "info": { "title": "Broken Link Checker: Site Crawler with Source Pages", "description": "Crawl your whole website and find every broken link, redirecting link, and dead external link, with the exact page and link text where each one appears, so you know what to fix.", "version": "1.0", "x-build-id": "1b7tndNy5ezpEBxVF" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/creativefour~broken-link-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-creativefour-broken-link-crawler", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/creativefour~broken-link-crawler/runs": { "post": { "operationId": "runs-sync-creativefour-broken-link-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/creativefour~broken-link-crawler/run-sync": { "post": { "operationId": "run-sync-creativefour-broken-link-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 to check", "type": "array", "description": "The home page (or any page) of the site to crawl. Every page on the same site is followed; www and non-www count as the same site.", "items": { "type": "string" } }, "maxPages": { "title": "Max pages to crawl", "minimum": 1, "type": "integer", "description": "Stop crawling after this many pages. Links found on those pages are still all checked.", "default": 500 }, "onlyProblems": { "title": "Report only problems", "type": "boolean", "description": "Save only broken, redirecting, or erroring links (you pay only for these). Turn off to get every link.", "default": true }, "checkExternalLinks": { "title": "Check external links", "type": "boolean", "description": "Also check links that point to other websites (one lightweight request each; external sites are never crawled).", "default": true }, "includeResources": { "title": "Check images, scripts, and stylesheets", "type": "boolean", "description": "Also check img, script, stylesheet, icon, video, audio, and iframe sources.", "default": false }, "includeSubdomains": { "title": "Crawl subdomains", "type": "boolean", "description": "Treat subdomains (blog.example.com) as part of the site.", "default": false }, "excludeUrlPatterns": { "title": "Skip URLs matching", "type": "array", "description": "Regular expressions (or plain text) for URLs to ignore, for example /tag/ or \\?replytocom=", "items": { "type": "string" } }, "maxDepth": { "title": "Max link depth", "minimum": 0, "type": "integer", "description": "How many clicks away from the start page to crawl.", "default": 10 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Don't crawl or check pages of your site that robots.txt disallows.", "default": true }, "perHostConcurrency": { "title": "Max concurrent requests per site", "minimum": 1, "maximum": 20, "type": "integer", "description": "Keeps the crawl polite to your server.", "default": 3 }, "maxConcurrency": { "title": "Max concurrent requests overall", "minimum": 1, "maximum": 100, "type": "integer", "description": "Across all sites when checking external links.", "default": 10 }, "timeoutSecs": { "title": "Timeout per request (seconds)", "minimum": 1, "maximum": 120, "type": "integer", "description": "How long to wait for each request before recording a timeout error.", "default": 15 }, "maxRedirects": { "title": "Max redirects per link", "minimum": 1, "maximum": 30, "type": "integer", "description": "Stop following a redirect chain after this many hops.", "default": 10 }, "userAgent": { "title": "User agent", "type": "string", "description": "The User-Agent header sent with every request, and the name robots.txt rules are matched against.", "default": "Mozilla/5.0 (compatible; BrokenLinkCrawler/1.0; +https://apify.com)" } } }, "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 } } } } } } } } } }