{ "openapi": "3.0.1", "info": { "title": "Broken Link Checker: 404s, Redirect Chains & Mixed Content", "description": "Crawl a website or check a list of URLs and find broken links (404, 410, 5xx), dead domains, redirect chains, mixed content and blocked resources, with the pages and anchor text where each link appears. Respects robots.txt.", "version": "0.1", "x-build-id": "sjfBnWHVaonWZRBqE" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/latamdatatools~broken-links-checker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-latamdatatools-broken-links-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/latamdatatools~broken-links-checker/runs": { "post": { "operationId": "runs-sync-latamdatatools-broken-links-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/latamdatatools~broken-links-checker/run-sync": { "post": { "operationId": "run-sync-latamdatatools-broken-links-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Websites to crawl", "type": "array", "description": "Home page (or any page) of each site. The Actor follows internal links up to the page and depth limits and checks every link it finds.", "items": { "type": "string" } }, "urls": { "title": "URLs to check (no crawling)", "type": "array", "description": "A plain list of URLs to check one by one: status code, redirect chain and final URL. Use for backlink lists, migrations or sitemap exports.", "items": { "type": "string" } }, "datasetId": { "title": "Dataset with URLs (optional)", "type": "string", "description": "Check the URLs in an Apify dataset (field set below). No crawling." }, "csvUrl": { "title": "CSV / Google Sheets URL (optional)", "type": "string", "description": "Public CSV with a header row, or a Google Sheets link shared as \"Anyone with the link\". No crawling." }, "urlField": { "title": "URL field", "type": "string", "description": "Field or column with the URL in the dataset or CSV.", "default": "url" }, "maxPages": { "title": "Max pages to crawl", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Internal HTML pages opened to find links (per run).", "default": 50 }, "maxDepth": { "title": "Max crawl depth", "minimum": 0, "maximum": 20, "type": "integer", "description": "Clicks away from the start URL (0 = only the start page).", "default": 3 }, "maxLinks": { "title": "Max links to check", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Unique URLs checked per run (pages + links + resources). Each checked URL is one billable event.", "default": 2000 }, "checkExternal": { "title": "Check external links", "type": "boolean", "description": "Also check links to other websites (never crawled, only checked).", "default": true }, "includeAssets": { "title": "Check images, scripts, stylesheets, iframes", "type": "boolean", "description": "Besides links, check resources and flag mixed content (http resources on https pages).", "default": true }, "ignoreUrlsContaining": { "title": "Ignore URLs containing", "type": "array", "description": "Skip links whose URL contains any of these texts (e.g. \"/logout\", \"?add-to-cart=\").", "items": { "type": "string" } }, "outputMode": { "title": "Output", "enum": [ "all", "problems", "problems-and-redirects" ], "type": "string", "description": "\"Problems only\" lists broken, errors, restricted and mixed content (every checked link is still billed).", "default": "all" }, "foundOnLimit": { "title": "Pages listed per link", "minimum": 1, "maximum": 100, "type": "integer", "description": "How many source pages (with anchor text) to list for each link. The total count is always given.", "default": 10 }, "maxConcurrency": { "title": "Requests in parallel", "minimum": 1, "maximum": 20, "type": "integer", "description": "Across different hosts. The same host is never hit more than once per second (or its robots.txt Crawl-delay).", "default": 5 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 60, "type": "integer", "description": "A link that does not answer in time is reported as an error (timeout).", "default": 20 } } }, "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 } } } } } } } } } }