{
  "@context": "https://schema.org",
  "@type": "Dataset",
  "name": "Website Crawler Controlled Benchmark 2026",
  "description": "Four controlled crawl attempts across two public documentation hosts, with runtime, page count, content size, cost, and observed failure notes.",
  "url": "https://konabayev.com/data/website-crawler-controlled-benchmark-2026.json",
  "datePublished": "2026-07-10",
  "creator": {"@type":"Person","@id":"https://konabayev.com/#person","name":"Tugelbay Konabayev","url":"https://konabayev.com/author/tugelbay-konabayev/"},
  "license": "https://creativecommons.org/licenses/by/4.0/",
  "measurementTechnique": "Single-run controlled crawl with a five-page cap; same public starting URL per provider attempt",
  "variablesMeasured": ["status", "pages", "unique pages", "elapsed seconds", "usage cost", "content characters", "observed issue"],
  "distribution": [
    {"@type":"DataDownload","encodingFormat":"text/csv","contentUrl":"https://konabayev.com/data/website-crawler-controlled-benchmark-2026.csv"},
    {"@type":"DataDownload","encodingFormat":"application/json","contentUrl":"https://konabayev.com/data/website-crawler-controlled-benchmark-2026.json"},
    {"@type":"DataDownload","encodingFormat":"application/x-ndjson","contentUrl":"https://konabayev.com/data/website-crawler-controlled-benchmark-2026.jsonl"}
  ],
  "data": [
    {"provider":"Tugelbay Website Content Crawler","target":"https://docs.apify.com/actors","status":"SUCCEEDED","pages":5,"unique_pages":5,"elapsed_seconds":7.523,"usage_usd":0.00024258,"content_chars":21137,"observed_issue":"None","audited_at":"2026-07-10"},
    {"provider":"Firecrawl local crawl route","target":"https://docs.apify.com/actors","status":"TIMED_OUT","pages":0,"unique_pages":0,"elapsed_seconds":90,"usage_usd":null,"content_chars":0,"observed_issue":"Router marked host degraded; local wrapper timed out","audited_at":"2026-07-10"},
    {"provider":"Tugelbay Website Content Crawler","target":"https://docs.firecrawl.dev","status":"SUCCEEDED","pages":5,"unique_pages":4,"elapsed_seconds":8.398,"usage_usd":0.00029211,"content_chars":3597,"observed_issue":"One duplicate canonical URL in five returned rows","audited_at":"2026-07-10"},
    {"provider":"Firecrawl local crawl route","target":"https://docs.firecrawl.dev","status":"TIMED_OUT","pages":0,"unique_pages":0,"elapsed_seconds":90,"usage_usd":null,"content_chars":0,"observed_issue":"Local wrapper timed out; no product-wide conclusion","audited_at":"2026-07-10"}
  ]
}
