{ "openapi": "3.0.1", "info": { "title": "Broken Link & Redirect Checker", "description": "Find broken links, redirect chains, redirect loops and soft-404s on your website. Seeds pages from sitemaps, checks internal and external links politely (robots.txt-aware, about 1 request per second per host) and lists which page links to each problem. Clean JSON for SEO audits and AI agents.", "version": "0.1", "x-build-id": "cA1GSgx9JMAu65E9x" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/madpai~broken-link-checker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-madpai-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/madpai~broken-link-checker/runs": { "post": { "operationId": "runs-sync-madpai-broken-link-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/madpai~broken-link-checker/run-sync": { "post": { "operationId": "run-sync-madpai-broken-link-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "urls" ], "properties": { "urls": { "title": "Websites or start pages", "type": "array", "description": "Your site(s) to check: domains (example.com) or start page URLs. Only these sites are crawled; links to other sites are checked once each but never crawled.", "items": { "type": "string" } }, "seedFromSitemap": { "title": "Seed pages from sitemaps", "type": "boolean", "description": "Also crawl pages listed in the site's XML sitemap (found via robots.txt or /sitemap.xml), so pages without inbound links are covered too.", "default": true }, "maxPagesPerSite": { "title": "Max pages to crawl per site", "minimum": 1, "maximum": 5000, "type": "integer", "description": "How many pages per site are fetched and scanned for links. Each page can contain many links.", "default": 50 }, "maxLinks": { "title": "Max links to check", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Total cap on unique links checked (crawled pages count too). You pay per link checked, so this also caps cost. At about 1 request per second per host, large single-site runs take longer than the default 5-minute timeout.", "default": 1000 }, "checkExternalLinks": { "title": "Check links to other sites", "type": "boolean", "description": "Check outbound links too (one request each, robots.txt respected, about 1 request per second per host). External pages are never crawled.", "default": true }, "checkAssets": { "title": "Also check images, scripts and stylesheets", "type": "boolean", "description": "Check img/script src and stylesheet/icon link href in addition to a[href] links.", "default": false }, "includeRegex": { "title": "Only report links matching (regex)", "type": "string", "description": "Check and report only links matching this case-insensitive regular expression, e.g. /docs/. Pages are still crawled to find links." }, "excludeRegex": { "title": "Skip links matching (regex)", "type": "string", "description": "Don't crawl or check URLs matching this case-insensitive regular expression, e.g. /tag/|\\?replytocom=." }, "maxRedirects": { "title": "Max redirects to follow", "minimum": 1, "maximum": 30, "type": "integer", "description": "Redirect hops followed per link before it is reported as a loop (too many redirects).", "default": 10 }, "requestDelayMs": { "title": "Delay between requests to your site (ms)", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Per-host delay (about 1 request per second by default). robots.txt Crawl-delay is honoured if longer (max 30 s). Values under 1000 ms only apply to your own sites with \"I own these sites\" checked; other hosts always get at least 1 s.", "default": 1000 }, "maxConcurrency": { "title": "Hosts in parallel", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many sites or hosts are processed at once. Requests to any single host stay sequential and rate-limited.", "default": 5 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Don't fetch URLs disallowed by robots.txt (reported as blocked-by-robots, free). Can only be turned off for your own sites, together with \"I own these sites\". External hosts' robots.txt is always respected.", "default": true }, "ownSiteConfirmed": { "title": "I own or am authorised to crawl these sites", "type": "boolean", "description": "Only check this for your own sites. It allows turning off robots.txt and using delays under 1 second on the sites in \"urls\" (not on external hosts).", "default": 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 }, "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 } } } } } } } } } }