{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://www.keywordbarrage.com/schemas/web-scraping-scraper-schema.json",
  "title": "Web Data ExtractionData Extraction Engine Data Extraction Schema",
  "description": "Machine-readable DaaS extraction schema for Web Data ExtractionData Extraction Engine under sector 'core-scraping-waf-bypass'. Optimized for LLM agents, RAG ingestion, and automated API callers.",
  "type": "object",
  "required": [
    "record_id",
    "target_url",
    "extraction_timestamp",
    "clearance_cookies",
    "tls_ja3"
  ],
  "properties": {
    "record_id": {
      "type": "string",
      "format": "uuid",
      "description": "Unique deterministic ingestion identifier for the extracted record."
    },
    "target_url": {
      "type": "string",
      "format": "uri",
      "description": "Source URL inspected and extracted by KeywordBarrage engine."
    },
    "extraction_timestamp": {
      "type": "string",
      "format": "date-time",
      "description": "ISO-8601 UTC timestamp of execution."
    },
    "clearance_cookies": {
      "type": "string",
      "description": "Clearance Cookies"
    },
    "tls_ja3": {
      "type": "string",
      "description": "TLS JA3/JA4 Fingerprints"
    },
    "unrestricted_payload_streams": {
      "type": "string",
      "description": "Unrestricted Payload Streams"
    },
    "dom_render_trees": {
      "type": "string",
      "description": "DOM Render Trees"
    },
    "http": {
      "type": "string",
      "description": "HTTP/2 Session Tokens"
    }
  },
  "x-sector": "core-scraping-waf-bypass",
  "x-updated-date": "2026-10-08",
  "x-platform-slug": "web-scraping-scraper",
  "x-endpoint-url": "https://www.keywordbarrage.com/scrapers/web-scraping-scraper.html"
}