{ "openapi": "3.0.1", "info": { "title": "Broken Link Checker & SEO Site Audit - 404s & Redirects", "description": "Crawl a website and check every internal and external link: 404s, 5xx, DNS errors, timeouts and redirect chains, with the page and anchor text. Plus an on-page SEO audit per page. Bot-blocked links are flagged, not false 'broken'. $0.003 per page.", "version": "0.1", "x-build-id": "8kmH1OkRRtXgBKLyW" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/rjmacarthy~broken-link-checker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-rjmacarthy-broken-link-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/rjmacarthy~broken-link-checker/runs": { "post": { "operationId": "runs-sync-rjmacarthy-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/rjmacarthy~broken-link-checker/run-sync": { "post": { "operationId": "run-sync-rjmacarthy-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": "Start URLs", "type": "array", "description": "Websites (or sections) to crawl, e.g. https://example.com/. The crawler stays on each start URL's host (www. ignored) and checks every link it finds.", "default": [ { "url": "https://books.toscrape.com/" } ], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxPages": { "title": "Max pages per site", "minimum": 0, "type": "integer", "description": "Maximum pages to crawl and audit per start URL. Each page is one charged event; all links on it are checked at no extra cost. 0 = no limit (careful: big sites have thousands of pages).", "default": 50 }, "maxDepth": { "title": "Max crawl depth", "minimum": 0, "type": "integer", "description": "How many clicks away from the start URL to crawl. 0 = audit the start URL only (its links are still checked).", "default": 5 }, "checkExternalLinks": { "title": "Check external links", "type": "boolean", "description": "Also check links pointing to other websites. External sites that block bots (403, 999, captcha) are reported as 'unverified', not 'broken'.", "default": true }, "checkImages": { "title": "Check images", "type": "boolean", "description": "Also check URLs for broken images.", "default": false }, "includeUrlPatterns": { "title": "Include URL patterns", "type": "array", "description": "Only crawl pages whose URL matches one of these. Glob with * (e.g. https://example.com/blog/*) or a regex in slashes (e.g. /\\/docs\\//). Links to other pages are still checked.", "default": [], "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Exclude URL patterns", "type": "array", "description": "Never crawl pages matching these (glob with * or /regex/), e.g. */tag/* or /\\?page=\\d+/. Links to them are still checked.", "default": [], "items": { "type": "string" } }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Do not crawl pages that robots.txt disallows. Single link checks (one HEAD request) are still made.", "default": true }, "followRedirectsReport": { "title": "Report internal redirects", "type": "boolean", "description": "Report internal links that redirect (with the full 3xx chain) as linkStatus 'redirect'. Turn off to treat redirects that end in 200 as 'ok'.", "default": true }, "outputMode": { "title": "Output", "enum": [ "broken-only", "all-links" ], "type": "string", "description": "broken-only: one page item per page plus one item per broken / timed-out / redirecting link. all-links: one page item per page plus one item per link checked (any status).", "default": "broken-only" }, "onlyNew": { "title": "Only new broken links", "type": "boolean", "description": "Monitoring mode: output only broken links that were not reported in the previous run for the same site (page items are still output). Schedule the Actor to get alerts on new broken links.", "default": false }, "maxExternalLinksPerPage": { "title": "Max external links per page", "minimum": 0, "type": "integer", "description": "Cap on external links checked per page (link farms, footers). 0 = no limit.", "default": 100 }, "maxConcurrency": { "title": "Max parallel requests per host", "minimum": 1, "maximum": 10, "type": "integer", "description": "Parallel requests to any one host. Keep it low to be polite to the site.", "default": 3 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Usually not needed. Enable Apify Proxy (datacenter) if your site blocks the run's IP. Residential proxies are not supported: if selected, the Actor falls back to Apify datacenter 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 } } } } } } } } } }