{
"openapi": "3.0.1",
"info": {
"title": "Website SEO Audit Crawler – Broken Links, Schema & llms.txt",
"description": "Website SEO audit crawler: on-page issues (title, meta description, H1, canonical, hreflang, noindex), broken internal and external links, schema.org JSON-LD errors, sitemap and robots.txt checks, AI-crawler rules (GPTBot, ClaudeBot…) and llms.txt. One row per page plus a site summary.",
"version": "1.0",
"x-build-id": "fwLqnqzWVS2GCU7M5"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/openharvest~website-seo-audit/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-openharvest-website-seo-audit",
"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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/openharvest~website-seo-audit/runs": {
"post": {
"operationId": "runs-sync-openharvest-website-seo-audit",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/openharvest~website-seo-audit/run-sync": {
"post": {
"operationId": "run-sync-openharvest-website-seo-audit",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": "Websites to audit",
"type": "array",
"description": "Homepage or any start URL of each website. example.com, https://www.example.com/ and https://example.com/blog/ all work. Each URL is audited as a separate site (same host only).",
"default": [
"https://crawlee.dev"
],
"items": {
"type": "string"
}
},
"maxPagesPerSite": {
"title": "Max pages per site",
"minimum": 1,
"maximum": 10000,
"type": "integer",
"description": "Maximum number of HTML pages to crawl and audit per website. You pay per audited page, so this also caps your cost.",
"default": 50
},
"checkExternalLinks": {
"title": "Check external links",
"type": "boolean",
"description": "Check outgoing links to other domains for broken (4xx/5xx, dead domain), redirected, blocked and timed-out targets. Each checked link is a separate 'external-link' event.",
"default": true
},
"maxExternalLinksPerSite": {
"title": "Max external links to check per site",
"minimum": 0,
"maximum": 5000,
"type": "integer",
"description": "Upper limit of unique external links checked per website (in the order they were found). Set to 0 to skip the check.",
"default": 100
},
"useSitemap": {
"title": "Use XML sitemap",
"type": "boolean",
"description": "Read the sitemap(s) listed in robots.txt (or /sitemap.xml). Sitemap URLs are queued right after the links on the start page, and every page is flagged when it is in the sitemap but returns an error, is noindex or canonicalised.",
"default": true
},
"respectRobotsTxt": {
"title": "Respect robots.txt",
"type": "boolean",
"description": "Skip pages that robots.txt disallows for generic crawlers (User-agent: *). Turn off only for sites you own.",
"default": true
},
"includeSubdomains": {
"title": "Include subdomains",
"type": "boolean",
"description": "Treat subdomains (e.g. blog.example.com when auditing example.com) as part of the site: crawl them and do not count links to them as external.",
"default": false
},
"maxConcurrency": {
"title": "Max concurrency",
"minimum": 1,
"maximum": 20,
"type": "integer",
"description": "Maximum parallel page requests (all sites together). Keep it low to be polite to the audited server.",
"default": 5
},
"proxyConfiguration": {
"title": "Proxy configuration",
"type": "object",
"description": "Usually not needed. If a site answers HTTP 403 / Cloudflare challenges (reported as free BLOCKED rows), try Apify Proxy, ideally the RESIDENTIAL group.",
"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
}
}
}
}
}
}
}
}
}
}