{ "openapi": "3.0.1", "info": { "title": "Broken Link Checker: Crawl a Site, Find 404s & Redirects", "description": "`Broken link checker: crawl a site over plain HTTP, check every link once for 404s, redirect chains and timeouts. $0.40 per 1,000 links.`", "version": "0.1", "x-build-id": "NUQEVjWMF5jMc2gR0" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ataism~broken-link-checker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ataism-broken-link-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/ataism~broken-link-checker/runs": { "post": { "operationId": "runs-sync-ataism-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/ataism~broken-link-checker/run-sync": { "post": { "operationId": "run-sync-ataism-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", "properties": { "startUrls": { "title": "Start URLs", "type": "array", "description": "Pages to start crawling from, one per line. Only pages on the same site (same host, www ignored) are crawled; links to other sites are only checked. Social-media and Google hosts are refused.", "items": { "type": "string" } }, "sitemapUrls": { "title": "Sitemap URLs", "type": "array", "description": "Optional sitemap.xml URLs (index files and .xml.gz work, up to 25 files). Their URLs are checked too, and the report lists sitemap URLs no crawled page links to and crawled pages missing from the sitemap. You can use a sitemap without start URLs.", "items": { "type": "string" } }, "maxPages": { "title": "Max pages to crawl", "minimum": 1, "maximum": 10000, "type": "integer", "description": "How many same-site pages are fetched and read for links. Default 100, hard cap 10,000. Same-site links beyond this cap are still checked, just not read. Crawling is limited by the per-host rate, so 100 pages take a few minutes.", "default": 100 }, "maxLinks": { "title": "Max unique links", "minimum": 1, "maximum": 20000, "type": "integer", "description": "Upper limit of unique link targets per run (each one is a row). Default 5,000, hard cap 20,000. Further links are ignored and the report says so.", "default": 5000 }, "checkExternal": { "title": "Check external links", "type": "boolean", "description": "Also check links to other sites (checked once each, never crawled). Their robots.txt is obeyed too: disallowed links are not requested and come back as free blocked rows.", "default": true }, "includeResources": { "title": "Include images, scripts and stylesheets", "type": "boolean", "description": "Also check img src, script src and link href targets, not just a href links.", "default": false }, "onlyProblems": { "title": "Only output problems", "type": "boolean", "description": "Output and charge only rows that are not OK (broken, redirect, timeout; blocked rows are listed free). Working links are still counted in the report. On a healthy site this means a lot of unpaid crawling, so the run stops after 1,000 requests that produced no charged row.", "default": false }, "allowSlowHosts": { "title": "Allow slow hosts", "type": "boolean", "description": "Some sites ask crawlers, in robots.txt (Crawl-delay), to wait more than 2 seconds between requests. The Actor always waits the full delay and never shortens it. Off (default): links on such a site you are crawling are not requested; they come back as free rows with errorCode slow-host. On: delays of 2 to 2.8 seconds are honoured in full; over 2.8 seconds the site is always skipped (maximum this Actor honours). A slow site makes the run long, and compute is billed while the run waits, so turn this on only when you need that site checked. Applies to the sites you crawl; other sites linked from them are checked once per link and their robots.txt is not read.", "default": false }, "ignoreQueryParams": { "title": "Ignore query parameters", "type": "array", "description": "Query parameter names (for example utm_source, ref, sort) removed from every link before de-duplication, so tracking or sorting variants of one page are one row. Session IDs in jsessionid and PHPSESSID are always ignored when de-duplicating; sid is not (many sites use it as a content ID), add it here if it is a session ID on your site. The first URL found is the one requested.", "items": { "type": "string" } }, "requestsPerSecondPerHost": { "title": "Requests per second per host", "minimum": 0.1, "maximum": 4, "type": "number", "description": "Start rate for each host, external hosts included. Default 1, maximum 4. A larger Crawl-delay in robots.txt on a site you crawl wins and is never shortened (see Allow slow hosts).", "default": 1 }, "maxConcurrency": { "title": "Max parallel requests", "minimum": 1, "maximum": 20, "type": "integer", "description": "Global cap on requests in flight across all hosts (1 to 20).", "default": 10 }, "maxDurationMinutes": { "title": "Max run time (minutes)", "minimum": 1, "maximum": 360, "type": "integer", "description": "The run stops cleanly after this time and saves what it has. Default 60, maximum 360.", "default": 60 }, "mode": { "title": "Mode", "type": "string", "description": "Internal: \"selfTest\" runs the maintainer health check and saves no items.", "default": "run" } } }, "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 } } } } } } } } } }