{ "openapi": "3.0.1", "info": { "title": "SEO Audit Tool & Meta Tag Checker: Crawler, Broken Links", "description": "SEO audit tool and SEO crawler: audit every page for technical SEO (status codes, redirect chains, titles, meta descriptions, H1s, canonicals, noindex, alt text, hreflang, Open Graph, JSON-LD). Works as a meta tag checker and broken link checker. Every page gets issues and a 0-100 score.", "version": "0.1", "x-build-id": "bYssNFfcb8i7ZPbe0" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/data-done-right~seo-audit-tool/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-data-done-right-seo-audit-tool", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/data-done-right~seo-audit-tool/runs": { "post": { "operationId": "runs-sync-data-done-right-seo-audit-tool", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/data-done-right~seo-audit-tool/run-sync": { "post": { "operationId": "run-sync-data-done-right-seo-audit-tool", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrl" ], "properties": { "startUrl": { "title": "Website URL", "type": "string", "description": "The page to start from, usually the home page. The crawler stays on this website (same domain; www and non-www count as the same site) and follows links from here. Example: https://www.example.com/." }, "maxPages": { "title": "Max pages to audit", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Stops after this many pages. Each audited page you receive is one billed result, so this also caps the cost.", "default": 100 }, "maxDepth": { "title": "Max link depth", "minimum": 0, "maximum": 100, "type": "integer", "description": "How many clicks away from the start URL to go. 0 = only the start URL, 1 = the start URL and the pages it links to.", "default": 10 }, "useSitemap": { "title": "Also audit pages from the sitemap", "type": "boolean", "description": "Add the URLs listed in the site's XML sitemap (found via robots.txt or /sitemap.xml) to the crawl, so pages without internal links are audited too. Each row then shows inSitemap.", "default": false }, "sitemapUrls": { "title": "Sitemap URLs (optional)", "type": "array", "description": "Exact sitemap or sitemap index URLs to read instead of auto-discovery. Implies 'Also audit pages from the sitemap'.", "items": { "type": "string" } }, "includeSubdomains": { "title": "Include subdomains", "type": "boolean", "description": "Treat subdomains (blog.example.com, docs.example.com) as part of the site. Off = only the start URL's host (plus its www / non-www twin).", "default": false }, "includeUrlPatterns": { "title": "Only crawl URLs containing", "type": "array", "description": "Optional. e.g. /blog/ or /en/. Prefix with re: for a regular expression. The start URL is always audited.", "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Skip URLs containing", "type": "array", "description": "Optional. e.g. /tag/, ?sort=, /cart. Prefix with re: for a regular expression. Links to skipped URLs are still link-checked.", "items": { "type": "string" } }, "checkLinks": { "title": "Check internal links that were not crawled", "type": "boolean", "description": "Send a quick HEAD request to every internal link the crawl did not visit (beyond Max pages or depth, PDFs, images), so broken links are found site-wide. Included in the page price.", "default": true }, "checkExternalLinks": { "title": "Check external links", "type": "boolean", "description": "Also check every outgoing link to other websites for 4xx/5xx errors, timeouts and redirects. Billed per unique external URL checked (external-link-check event).", "default": false }, "maxLinkChecks": { "title": "Max link checks", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Upper limit on extra link checks, applied separately to internal links that were not crawled and to external links (so 1000 = up to 1000 of each). Links that point to pages already audited never count against it.", "default": 1000 }, "reportPages": { "title": "Pages to include in the dataset", "enum": [ "all", "issues", "warnings", "errors" ], "type": "string", "description": "Which audited pages to return. You pay only for returned pages; the SUMMARY record always covers every audited page.", "default": "all" }, "maxConcurrency": { "title": "Parallel requests", "minimum": 1, "maximum": 10, "type": "integer", "description": "Requests in flight at once. Keep it low for small servers. A Crawl-delay in robots.txt is honored (up to 10 s).", "default": 5 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 3, "maximum": 120, "type": "integer", "description": "A page or link that does not answer in time is reported as a timeout (one retry).", "default": 20 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Usually not needed. Use it only if your own server rate-limits the crawler by IP.", "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 } } } } } } } } } }