{ "openapi": "3.0.1", "info": { "title": "Broken Link Checker: Bulk URL Status, Redirects & Source Pages", "description": "Find broken links on any site: crawl, URL list or sitemap. Status codes, redirect chains and the page each link is on. $0.80 per 1,000 URLs, failures free.", "version": "0.1", "x-build-id": "bQ7KWJ20y2VWAf1f4" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/hillcountrybots~broken-link-checker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-hillcountrybots-broken-link-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/hillcountrybots~broken-link-checker/runs": { "post": { "operationId": "runs-sync-hillcountrybots-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/hillcountrybots~broken-link-checker/run-sync": { "post": { "operationId": "run-sync-hillcountrybots-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": "Start URLs", "type": "array", "description": "Required. One per line. Crawl mode: the homepage or page to start crawling from (a bare domain like example.com works). List mode: every URL you want checked. Sitemap mode: a website (its sitemap is found via robots.txt or /sitemap.xml) or a direct sitemap URL. Private, local and internal addresses are refused for free.", "items": { "type": "string" } }, "mode": { "title": "Mode", "enum": [ "crawl", "list", "sitemap" ], "type": "string", "description": "crawl = follow internal links from the start pages and check every link found (internal, external and optionally assets). list = check only the URLs you pasted. sitemap = check every URL listed in the site's XML sitemap (find dead pages your sitemap still advertises).", "default": "crawl" }, "maxPagesToCrawl": { "title": "Max pages to crawl (crawl mode)", "minimum": 1, "maximum": 10000, "type": "integer", "description": "How many internal HTML pages are opened to collect links. Each crawled page is also checked. 10 for a quick look, 100 to 500 for a typical small business site. Ignored in list and sitemap modes.", "default": 50 }, "maxUrlsToCheck": { "title": "Max URLs to check (spend cap)", "minimum": 1, "type": "integer", "description": "Total unique URLs checked in this run, crawled pages included. This caps spend: only URLs that return an HTTP status are charged. The run's own max-charge setting is also respected. Links found after the cap is reached are counted in RUN_SUMMARY as skippedOverCap.", "default": 1000 }, "checkExternalLinks": { "title": "Check external links", "type": "boolean", "description": "Also check links that point to other websites (crawl mode). External sites are checked once per URL with HEAD and never crawled.", "default": true }, "includeAssets": { "title": "Check images, scripts and stylesheets", "type": "boolean", "description": "Also check img src, script src and stylesheet/icon links found on crawled pages. Finds missing images and dead CDN files. Adds more URLs per page.", "default": false }, "outputMode": { "title": "Output", "enum": [ "all", "problemsOnly" ], "type": "string", "description": "all = one row per checked URL. problemsOnly = store only broken, unreachable, blocked, redirect and skipped rows (the healthy URLs are still checked and counted in RUN_SUMMARY and charged).", "default": "all" }, "includePatterns": { "title": "Only check URLs matching", "type": "array", "description": "Optional. Globs with * (e.g. https://example.com/blog/*) or /regex/. Links that do not match are not checked or crawled.", "default": [], "items": { "type": "string" } }, "excludePatterns": { "title": "Skip URLs matching", "type": "array", "description": "Optional. Globs or /regex/, e.g. */tag/* or https://twitter.com/*. Matching links are not checked or crawled.", "default": [], "items": { "type": "string" } }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "On (recommended): URLs disallowed by a site's robots.txt are not fetched and are reported as skipped (free).", "default": true }, "maxConcurrency": { "title": "Total concurrency", "minimum": 1, "maximum": 30, "type": "integer", "description": "Requests in flight across all hosts (1-30).", "default": 10 }, "maxConcurrencyPerHost": { "title": "Concurrency per host", "minimum": 1, "maximum": 5, "type": "integer", "description": "Requests in flight to any single host (1-5). Keep this low to be polite to small sites.", "default": 2 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 60, "type": "integer", "description": "Seconds to wait for a response before a URL is marked unreachable (timeouts are retried once for crawled pages).", "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 } } } } } } } } } }