{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "$id": "https://raw.githubusercontent.com/api-evangelist/screaming-frog/main/json-schema/screaming-frog-crawl-result-schema.json",
  "title": "Screaming Frog Crawl Result",
  "description": "Schema for a URL crawl result from the Screaming Frog SEO Spider",
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "format": "uri",
      "description": "The crawled URL"
    },
    "status_code": {
      "type": "integer",
      "description": "HTTP response status code (e.g., 200, 301, 404)"
    },
    "status": {
      "type": "string",
      "description": "Human-readable HTTP status description"
    },
    "title": {
      "type": "string",
      "description": "HTML page title content"
    },
    "title_length": {
      "type": "integer",
      "description": "Length of the page title in characters"
    },
    "meta_description": {
      "type": "string",
      "description": "Meta description content"
    },
    "meta_description_length": {
      "type": "integer",
      "description": "Length of meta description in characters"
    },
    "h1": {
      "type": "string",
      "description": "First H1 heading content"
    },
    "h2": {
      "type": "string",
      "description": "First H2 heading content"
    },
    "word_count": {
      "type": "integer",
      "minimum": 0,
      "description": "Total word count on the page"
    },
    "content_type": {
      "type": "string",
      "description": "HTTP Content-Type response header value"
    },
    "size": {
      "type": "integer",
      "minimum": 0,
      "description": "Page size in bytes"
    },
    "indexability": {
      "type": "string",
      "enum": ["Indexable", "Non-Indexable"],
      "description": "Whether the page is indexable by search engines"
    },
    "indexability_status": {
      "type": "string",
      "description": "Reason for non-indexability (e.g., noindex, canonical, blocked by robots)"
    },
    "canonical_url": {
      "type": "string",
      "format": "uri",
      "description": "Canonical URL specified via rel=canonical"
    },
    "redirect_url": {
      "type": "string",
      "format": "uri",
      "description": "URL that this page redirects to (for 3xx status codes)"
    },
    "inlinks": {
      "type": "integer",
      "minimum": 0,
      "description": "Number of internal links pointing to this URL"
    },
    "outlinks": {
      "type": "integer",
      "minimum": 0,
      "description": "Number of links on this page pointing to other URLs"
    },
    "crawl_depth": {
      "type": "integer",
      "minimum": 0,
      "description": "Click depth from the start URL"
    },
    "response_time": {
      "type": "number",
      "description": "Server response time in seconds"
    }
  },
  "required": ["url", "status_code"]
}