{ "openapi": "3.0.1", "info": { "title": "Broken Link Checker – Find 404s and Dead Links API", "description": "Pay per crawled page, not per link: crawl a site within robots.txt and check every link on each page for 404s, 5xx errors, DNS and TLS failures and redirects. Anti-bot and robots.txt refusals are never called broken. No personal data.", "version": "1.0", "x-build-id": "8CwWoMBrWttSEkAEN" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/rowcraft~broken-link-checker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-rowcraft-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/rowcraft~broken-link-checker/runs": { "post": { "operationId": "runs-sync-rowcraft-broken-link-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/rowcraft~broken-link-checker/run-sync": { "post": { "operationId": "run-sync-rowcraft-broken-link-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Websites or pages", "type": "array", "description": "The sites to check, one per line: a domain (example.com) or a page address (https://www.example.com/blog). The crawl starts there and follows the links of the same site. Several addresses of one site are crawled together.", "items": { "type": "string" } }, "maxPagesPerSite": { "title": "Pages to crawl per site", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "How many pages of each site are read, breadth first from the start address. Every page read is one charged row; the links on it are checked for free. Start small (5 to 20) to see the result, then raise it.", "default": 50 }, "checkExternalLinks": { "title": "Check links to other websites", "type": "boolean", "description": "Also verify the links that lead to other websites (one request per address, robots.txt of each host read first). Switch off to check only the links inside the site.", "default": true }, "includeImages": { "title": "Also check images", "type": "boolean", "description": "Verify the address of every image (img tag) on the pages as well. Off by default: images multiply the number of requests.", "default": false }, "onlyPagesWithBrokenLinks": { "title": "Only deliver pages with broken links", "type": "boolean", "description": "Deliver (and charge) only the pages where at least one broken link was found. Pages without broken links are still read and checked, but are skipped and not charged.", "default": false }, "includeSubdomains": { "title": "Follow subdomains", "type": "boolean", "description": "Treat blog.example.com and shop.example.com as part of example.com: their pages are crawled and their links count as internal. Off: subdomains are checked as external links only.", "default": false }, "maxItems": { "title": "Maximum pages delivered", "minimum": 0, "type": "integer", "description": "Stop after this many rows are delivered in total. 0 = no limit.", "default": 0 }, "maxExternalHosts": { "title": "Maximum external websites to check", "minimum": 1, "maximum": 100000, "type": "integer", "description": "A page that links to hundreds of other websites costs one robots.txt and one request for each of them. Links to websites beyond this number are counted as not checked.", "default": 1000 }, "onlyNew": { "title": "Only new rows since the last run", "type": "boolean", "description": "Remember the rows already delivered to you (in a key-value store in your Apify account) and deliver only rows that appeared since the last run with the same state key. The first run delivers everything that matches; later runs cost only the new rows. Ideal for schedules.", "default": false }, "stateName": { "title": "State name", "type": "string", "description": "Name of the memory used by \"Only new rows\". Use a different name for each schedule or search (for example `stockholm-python`) so they do not share one memory.", "default": "default" }, "notifyUrl": { "title": "Notify this URL when the run ends", "type": "string", "description": "A webhook address that receives one JSON POST with the number of new rows and links to the dataset: a Slack or Discord incoming webhook, a Make, n8n or Zapier catch hook, or your own endpoint. The message is also in the `text` (Slack) and `content` (Discord) fields." }, "notifyWhenEmpty": { "title": "Notify also when there are no new rows", "type": "boolean", "description": "By default the notification is sent only when at least one row was delivered.", "default": false }, "requestIntervalMs": { "title": "Delay between requests to one host (ms)", "minimum": 200, "maximum": 10000, "type": "integer", "description": "Default 1000 ms (one request per second to the same host; different hosts are checked in parallel). The Crawl-delay of a robots.txt is honoured up to 10 s. Checking your own site? 200 ms is the minimum.", "default": 1000 } } }, "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 } } } } } } } } } }