{ "openapi": "3.0.1", "info": { "title": "SEO Site Audit Scraper", "description": "Audit any website for SEO: crawl pages, check titles, meta tags, headings, canonicals, noindex, status codes, redirect chains and broken links, read robots.txt and sitemaps. One row per page with issue codes.", "version": "0.1", "x-build-id": "XBrrqGcO3dXBnk1aF" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/datawatcher~seo-site-audit-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-datawatcher-seo-site-audit-scraper", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/datawatcher~seo-site-audit-scraper/runs": { "post": { "operationId": "runs-sync-datawatcher-seo-site-audit-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/datawatcher~seo-site-audit-scraper/run-sync": { "post": { "operationId": "run-sync-datawatcher-seo-site-audit-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Websites to audit, one per line. The crawl stays on the host of each URL. Public sites only; private and local addresses are refused.", "items": { "type": "string" } }, "maxPages": { "title": "Max pages", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum pages fetched per start URL. The crawl never runs unbounded. Free plan Apify users get at most 1000 rows per run.", "default": 50 }, "maxDepth": { "title": "Max depth", "minimum": 0, "maximum": 20, "type": "integer", "description": "Clicks from the start URL to follow. 0 reads only the start URL.", "default": 3 }, "mode": { "title": "Mode", "enum": [ "crawl", "urlList", "sitemap" ], "type": "string", "description": "crawl follows links from the start URLs and audits every page. urlList checks exactly the URLs you give (status, redirects, final URL and the page checks) and follows no links. sitemap reads the sitemap and checks the status of each listed URL.", "default": "crawl" }, "includeSubdomains": { "title": "Include subdomains", "type": "boolean", "description": "Also crawl subdomains of each start host (blog.example.com for example.com). Off - only the exact host.", "default": false }, "includeUrlPatterns": { "title": "Only URLs matching", "type": "array", "description": "Crawl only URLs that match one of these glob patterns, e.g. https://example.com/blog/**. Empty - all URLs of the site. Start URLs are always read.", "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Skip URLs matching", "type": "array", "description": "Skip URLs that match one of these glob patterns, e.g. **/*.pdf or **/tag/**. Wins over the include list.", "items": { "type": "string" } }, "userAgent": { "title": "User agent", "type": "string", "description": "The User-Agent header of every request, and the name robots.txt rules are matched against. The default says who we are.", "default": "SeoSiteAuditBot/1.0 (+https://apify.com/datawatcher/seo-site-audit-scraper)" }, "requestDelayMs": { "title": "Delay between requests (ms)", "minimum": 500, "maximum": 10000, "type": "integer", "description": "Minimum pause between two requests to the same host. Never below 500 ms, so the audit stays polite.", "default": 500 }, "emitLinkRows": { "title": "Write internal link rows", "type": "boolean", "description": "Also write one row per internal link (the full link graph, billed per row). Off - broken links and redirect chains still come as rows, and every page row carries a free broken-link summary.", "default": false }, "readSitemap": { "title": "Read sitemap", "type": "boolean", "description": "Read robots.txt and the sitemap (index files too) and add the listed URLs to the crawl.", "default": true }, "checkExternalLinks": { "title": "Check external links", "type": "boolean", "description": "Also request links to other sites (one request each) to find broken outbound links.", "default": false }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip pages that robots.txt disallows. Skipped pages still show as a finding.", "default": true }, "maxRequestRetries": { "title": "Max request retries", "minimum": 0, "maximum": 5, "type": "integer", "description": "Retries of a request that failed on a network error or a server error. A block (403, 429) is never retried.", "default": 2 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Time limit of one page request.", "default": 30 } } }, "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 } } } } } } } } } }