{ "openapi": "3.0.1", "info": { "title": "Dead Link Finder (Site Crawl): 404 and Redirect Report", "description": "Crawl your website and get one row per broken or redirecting link: 404, 410, 5xx, DNS, timeout, SSL errors, redirect loops and long chains, with source page, anchor text and how many pages link to it. robots.txt honoured.", "version": "0.1", "x-build-id": "qXOCEKTUTF3ommsy0" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/transparent_meteorite~dead-link-finder-site-crawl/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-transparent_meteorite-dead-link-finder-site-crawl", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/transparent_meteorite~dead-link-finder-site-crawl/runs": { "post": { "operationId": "runs-sync-transparent_meteorite-dead-link-finder-site-crawl", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/transparent_meteorite~dead-link-finder-site-crawl/run-sync": { "post": { "operationId": "run-sync-transparent_meteorite-dead-link-finder-site-crawl", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 from, for example https://example.com/. The crawl stays on the same website (www and non-www count as the same site). Several start URLs = several sites in one run.", "default": [ { "url": "https://crawler-test.com/" } ], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxPages": { "title": "Max pages to crawl", "minimum": 1, "maximum": 10000, "type": "integer", "description": "How many HTML pages of your site to open and read links from, for example 25 for a quick check or 2000 for a full audit. Links found on those pages are all checked, even when they point to pages beyond this limit.", "default": 25 }, "maxLinksChecked": { "title": "Max links to check", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Hard cap on unique URLs checked in one run (crawled pages included), for example 1000. This is also your cost cap: you pay per link checked.", "default": 1000 }, "checkExternalLinks": { "title": "Check external links", "type": "boolean", "description": "Also check links that point to other websites (one status request each, never crawled). Turn off to audit internal links only.", "default": true }, "includeSubdomains": { "title": "Treat subdomains as internal", "type": "boolean", "description": "When on, blog.example.com and shop.example.com count as part of example.com and get crawled too.", "default": false }, "checkResources": { "title": "Also check images, scripts and stylesheets", "type": "boolean", "description": "Check img, script, stylesheet, icon, iframe and media URLs as well as normal links. Finds broken images; adds more links to check.", "default": false }, "excludeUrlPatterns": { "title": "Skip URLs containing", "type": "array", "description": "URLs that contain any of these texts are skipped and never charged. Use * as a wildcard, for example /wp-admin/, ?replytocom= or https://twitter.com/*.", "items": { "type": "string" } }, "internalRequestsPerSecond": { "title": "Requests per second to your site", "minimum": 1, "maximum": 10, "type": "integer", "description": "Polite crawl speed on your own site, for example 3. A robots.txt Crawl-delay slows it further (up to 10 seconds between requests).", "default": 3 }, "externalRequestsPerMinutePerHost": { "title": "Requests per minute per external host", "minimum": 1, "maximum": 120, "type": "integer", "description": "Rate limit for each external website you link to, for example 30 per minute, so a page with 200 links to the same site never floods it.", "default": 30 }, "maxConcurrency": { "title": "Max parallel requests", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many requests may be in flight at once across all hosts, for example 8. The per-host limits above still apply.", "default": 8 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 3, "maximum": 60, "type": "integer", "description": "A link that does not answer within this many seconds (one retry) is reported as a timeout, for example 15.", "default": 15 }, "reportRedirects": { "title": "Report redirects", "enum": [ "all", "chains_only", "none" ], "type": "string", "description": "Which redirecting links get a row, for example all to clean up every 301. Redirect loops are always reported as errors.", "default": "all" }, "includeSummaryRow": { "title": "Add a summary row", "type": "boolean", "description": "Append one rowType=summary row with totals by error type to the dataset. The same summary is always saved as the OUTPUT record.", "default": false }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Not needed for most sites (plain HTTP from Apify). Use a proxy only if your site blocks data-centre IPs, for example Apify Proxy.", "default": { "useApifyProxy": 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 } } } } } } } } } }