{ "openapi": "3.0.1", "info": { "title": "SEO Audit & Broken Link Checker: Site Crawler", "description": "Crawl a website and get a per-page SEO audit plus every broken link, redirect and blocked URL: titles, meta, H1, alt, canonicals, duplicates, sitemap & robots checks.", "version": "1.0", "x-build-id": "JZAzgDQvFOQjwUA4P" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/vantum~seo-audit-broken-links/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-vantum-seo-audit-broken-links", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/vantum~seo-audit-broken-links/runs": { "post": { "operationId": "runs-sync-vantum-seo-audit-broken-links", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/vantum~seo-audit-broken-links/run-sync": { "post": { "operationId": "run-sync-vantum-seo-audit-broken-links", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 to audit", "type": "array", "description": "One or more websites (home page or any start page). Each site is crawled separately, staying on its own domain. Example: https://crawlee.dev", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxPagesPerSite": { "title": "Max pages per site", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Stop after this many HTML pages per site (each saved page = 1 charged event). 0 = no limit. Use a dry run first to see how big the site is.", "default": 100 }, "maxDepth": { "title": "Max click depth", "minimum": 0, "maximum": 100, "type": "integer", "description": "How many clicks away from the start page to crawl. Empty = unlimited. Sitemap URLs count as depth 1." }, "includeSubdomains": { "title": "Include subdomains", "type": "boolean", "description": "Also crawl blog.example.com, shop.example.com… when starting from example.com. www and the bare domain are always treated as the same site.", "default": false }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip internal URLs that robots.txt disallows (they are counted in the summary).", "default": true }, "useSitemaps": { "title": "Use sitemaps", "type": "boolean", "description": "Read sitemap.xml (and sitemaps listed in robots.txt) to find pages and to check sitemap quality: broken, redirecting, noindex and orphan URLs.", "default": true }, "ignoreQueryStrings": { "title": "Ignore query strings", "type": "boolean", "description": "Treat /page?sort=x and /page as the same page. Useful for shops and faceted navigation. Tracking parameters (utm_*, gclid, fbclid…) are always ignored.", "default": false }, "includeUrlPatterns": { "title": "Only crawl URLs containing", "type": "array", "description": "Crawl only pages whose URL contains one of these texts (e.g. /blog/). Wrap in slashes for a regular expression: /\\/p\\/\\d+$/. The start page is always audited.", "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Never crawl URLs containing", "type": "array", "description": "Skip pages whose URL contains one of these texts (e.g. /tag/, ?replytocom=). Regex allowed in /slashes/. Links to them are still checked.", "items": { "type": "string" } }, "checkExternalLinks": { "title": "Check external links", "type": "boolean", "description": "Check that links to other websites still work (HEAD, then GET if needed). Turn off for a faster internal-only audit.", "default": true }, "checkImagesAndAssets": { "title": "Check images, scripts & stylesheets", "type": "boolean", "description": "Also check every image, script, stylesheet and iframe URL used on the audited pages.", "default": true }, "maxLinkChecksPerSite": { "title": "Max link checks per site", "minimum": 0, "maximum": 200000, "type": "integer", "description": "Safety cap on how many unique URLs are checked per site (internal pages first, then resources, then external). 0 = no cap. Link checks are free.", "default": 5000 }, "linkRows": { "title": "Link rows in the dataset", "enum": [ "none", "broken", "brokenAndInternalRedirects", "allProblems" ], "type": "string", "description": "Which problem URLs get their own row (with the pages linking to them). Link rows are always free.", "default": "brokenAndInternalRedirects" }, "onlyPagesWithIssues": { "title": "Save only pages with issues", "type": "boolean", "description": "Save (and pay for) only pages that have at least one issue. All pages are still crawled and counted in the summary.", "default": false }, "dryRun": { "title": "Dry run (free size estimate)", "type": "boolean", "description": "Only open the start page, robots.txt and sitemaps and estimate how many pages would be audited and what it would cost. Nothing is charged.", "default": false }, "maxConcurrency": { "title": "Max parallel requests", "minimum": 1, "maximum": 30, "type": "integer", "description": "Lower this (e.g. 3) for small or fragile servers.", "default": 10 }, "userAgent": { "title": "User-Agent", "type": "string", "description": "Custom User-Agent header. Empty = a current desktop Chrome string." } } }, "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 } } } } } } } } } }