{ "openapi": "3.0.1", "info": { "title": "Broken Link Checker - Sitemap & Site Audit (404s, Redirects)", "description": "Find broken links on any website from its sitemap or a capped crawl: 404s, 5xx, timeouts, DNS errors and redirect chains, with source page and anchor text. $0 when nothing is broken.", "version": "1.0", "x-build-id": "sq0yKYASffxJyxjr8" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/appetizing_horsefly~sitemap-broken-link-auditor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-appetizing_horsefly-sitemap-broken-link-auditor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/appetizing_horsefly~sitemap-broken-link-auditor/runs": { "post": { "operationId": "runs-sync-appetizing_horsefly-sitemap-broken-link-auditor", "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/appetizing_horsefly~sitemap-broken-link-auditor/run-sync": { "post": { "operationId": "run-sync-appetizing_horsefly-sitemap-broken-link-auditor", "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": [ "startUrl" ], "properties": { "startUrl": { "title": "Website or sitemap URL", "type": "string", "description": "Homepage (sitemaps are found through robots.txt, /sitemap.xml and /sitemap_index.xml) or a direct sitemap URL (.xml, .xml.gz, sitemap index or plain-text). Example: https://example.com or https://example.com/sitemap.xml", "default": "https://crawlee.dev" }, "followSitemaps": { "title": "Expand sitemaps", "type": "boolean", "description": "Read the site's sitemaps and sitemap indexes. Every URL listed there is checked (a 404 inside your sitemap is an SEO bug) and used as a page to crawl.", "default": true }, "crawlHtml": { "title": "Crawl pages for links", "type": "boolean", "description": "Open public HTML pages (from the sitemap, then same-site links) and check every link on them, with anchor text. Turn off to check only the URLs listed in the sitemap.", "default": true }, "checkExternal": { "title": "Check external links", "type": "boolean", "description": "Also check links that point to other domains. Turn off to audit internal links only.", "default": true }, "maxPages": { "title": "Max pages (hard cap)", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Most HTML pages to open and take links from (and most sitemap URLs to check). Hard limit 2000.", "default": 50 }, "maxLinks": { "title": "Max unique links to check (hard cap)", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Most unique link URLs checked per run. Each link is checked once even if it appears on many pages. Hard limit 10000.", "default": 1000 }, "maxSitemaps": { "title": "Max sitemap files", "minimum": 1, "maximum": 500, "type": "integer", "description": "Safety cap on nested sitemap files read.", "default": 50 }, "onlyBroken": { "title": "Only problems", "type": "boolean", "description": "Output only broken links, redirect chains and blocked links. Turn off to also output every OK link (OK rows are free).", "default": true }, "includeRedirects": { "title": "Include redirect chains", "type": "boolean", "description": "Output links that redirect (301/302/307/308) with the full chain and final URL, so you can update them to the final address. Redirect rows are free.", "default": true }, "includeBlocked": { "title": "Include blocked links (401/403/429)", "type": "boolean", "description": "Output links where the server refused an automated check (login walls, bot protection, rate limits). These are often fine in a browser, so they are free and marked type=blocked.", "default": true }, "countBlockedAsBroken": { "title": "Treat 401/403/429 as broken", "type": "boolean", "description": "Count refused links as broken (charged) instead of 'blocked'. Leave off unless those links should really be public.", "default": false }, "respectRobots": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip pages and links that the site's robots.txt disallows for crawlers.", "default": true }, "requestTimeoutSecs": { "title": "Request timeout (s)", "minimum": 3, "maximum": 60, "type": "integer", "description": "Seconds before a link counts as a TIMEOUT. Timeouts are retried once.", "default": 15 }, "concurrency": { "title": "Concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Parallel requests. Hard limit 20, to stay polite to sites.", "default": 10 }, "maxRunSecs": { "title": "Max run time (s)", "minimum": 60, "maximum": 3600, "type": "integer", "description": "Stop crawling and checking after this many seconds and output what was found.", "default": 600 } } }, "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 } } } } } } } } } }