{
  "schemaVersion": 1,
  "dataset": {
    "id": "1792179688649-qbxnm1",
    "sourceName": "Books to Scrape",
    "sourceUrl": "https://books.toscrape.com/",
    "capturedAt": "2026-10-16T19:41:33.661Z",
    "recordCount": 48,
    "sampleCount": 12,
    "sampleSelection": "First 12 records in the saved normalized artifact, without editing product values.",
    "coverage": {
      "status": "partial",
      "pagesScanned": 5,
      "pagesDiscovered": 54,
      "pagesRemaining": 49,
      "stoppedReason": "max_extract_pages"
    }
  },
  "fields": {
    "name": {
      "present": 48,
      "missing": 0,
      "total": 48,
      "percent": 100
    },
    "sku": {
      "present": 0,
      "missing": 48,
      "total": 48,
      "percent": 0
    },
    "description": {
      "present": 0,
      "missing": 48,
      "total": 48,
      "percent": 0
    },
    "image": {
      "present": 48,
      "missing": 0,
      "total": 48,
      "percent": 100
    },
    "price": {
      "present": 48,
      "missing": 0,
      "total": 48,
      "percent": 100
    },
    "url": {
      "present": 48,
      "missing": 0,
      "total": 48,
      "percent": 100
    }
  },
  "sampleFields": {
    "name": {
      "present": 12,
      "missing": 0,
      "total": 12,
      "percent": 100
    },
    "sku": {
      "present": 0,
      "missing": 12,
      "total": 12,
      "percent": 0
    },
    "description": {
      "present": 0,
      "missing": 12,
      "total": 12,
      "percent": 0
    },
    "image": {
      "present": 12,
      "missing": 0,
      "total": 12,
      "percent": 100
    },
    "price": {
      "present": 12,
      "missing": 0,
      "total": 12,
      "percent": 100
    },
    "url": {
      "present": 12,
      "missing": 0,
      "total": 12,
      "percent": 100
    }
  },
  "provenance": {
    "method": "Existing successful local catalog-service/URL-worker batch, with the production extractor and saved source HTML. Reused without scanning. All 48 URLs, images and prices verified against its five saved listing pages.",
    "sourceFiles": [
      {
        "path": "qa-artifacts/books-catalog-verification/storage/books.toscrape.com/mvp/1792179688649-qbxnm1/products.normalized.json",
        "sha256": "436836fe3cd90a5d7c197517802a3a68940317c830a20c0badc7e0a138cf12e0",
        "bytes": 35204
      },
      {
        "path": "qa-artifacts/books-catalog-verification/storage/books.toscrape.com/mvp/1792179688649-qbxnm1/summary.json",
        "sha256": "9be398b0a44d2cd9f1ae48158e2e51d40c496f1232a6da5942a7b42ccd827b46",
        "bytes": 36410
      },
      {
        "path": "qa-artifacts/books-catalog-verification/storage/books.toscrape.com/mvp/1792179688649-qbxnm1/quality.json",
        "sha256": "8fe6e5b671364ddf04dc8efaf3ad28c06e87a8fb33998a2c1e10ab634ad03b4d",
        "bytes": 30405
      },
      {
        "path": "qa-artifacts/books-catalog-verification/storage/books.toscrape.com/mvp/1792179688649-qbxnm1/export.csv",
        "sha256": "b31d09c3bc09176312cde67d0136d97858bada4dda5d48c2a15919488291a90b",
        "bytes": 12168
      },
      {
        "path": "qa-artifacts/books-catalog-verification/storage/books.toscrape.com/mvp/1792179688649-qbxnm1/shopify-import.csv",
        "sha256": "7aa026e2481f2fdd81c3227764b4614c2c792b9d953ab224d3703d250cbf97f1",
        "bytes": 10028
      },
      {
        "path": "qa-artifacts/books-catalog-verification/storage/books.toscrape.com/mvp/1792179688649-qbxnm1/discovery.books_toscrape_com_catalogue_category_books_1_index_html.manual.html",
        "sha256": "0f452cd433bd68584b8ed324772b5b2e2b143cf148401caf7059a0e422090afd",
        "bytes": 50607
      },
      {
        "path": "qa-artifacts/books-catalog-verification/storage/books.toscrape.com/mvp/1792179688649-qbxnm1/discovery.books_toscrape_com_catalogue_category_books_new_adult_20_index_html.manual.html",
        "sha256": "76d8a52be615c7a92a6ccc39b605a099dc6d5604fb265b1c93bf21fbd6bc002c",
        "bytes": 28732
      },
      {
        "path": "qa-artifacts/books-catalog-verification/storage/books.toscrape.com/mvp/1792179688649-qbxnm1/discovery.books_toscrape_com_catalogue_category_books_academic_40_index_html.manual.html",
        "sha256": "66d7061f9a5fd8f80feea158b14e3ef8ff15e2ab4aca66449fe71f5dc060d84a",
        "bytes": 21359
      },
      {
        "path": "qa-artifacts/books-catalog-verification/storage/books.toscrape.com/mvp/1792179688649-qbxnm1/discovery.books_toscrape_com_catalogue_category_books_add_a_comment_18_index_html.manual.html",
        "sha256": "07cbde187877b52186e307027adcd6c546cf0701115827f1ea2acd8d2add4493",
        "bytes": 50931
      },
      {
        "path": "qa-artifacts/books-catalog-verification/storage/books.toscrape.com/mvp/1792179688649-qbxnm1/discovery.books_toscrape_com_catalogue_category_books_adult_fiction_29_index_html.manual.html",
        "sha256": "ee501436a89b371efcf6df4cb4235fa67ac4d6f7703041e0346da5181fff2892",
        "bytes": 21377
      }
    ],
    "transformations": [
      "Subset original CSV and Shopify CSV rows, preserving all retained cell values.",
      "Omit the optional Shopify Product Category column because source navigation labels are not verified Shopify taxonomy. No category is inferred; original product JSON and catalog CSV categories are unchanged.",
      "Cache the 12 existing public source cover URLs as local JPEG assets.",
      "Recompute field completeness from the immutable 48-record dataset and the 12-record sample."
    ],
    "confidence": "Stored confidence is the original extractor score, not a validated accuracy measurement.",
    "publicationScope": "Public Books to Scrape sandbox product records only. No customer records, claims, credentials, or private storage objects."
  },
  "files": [
    {
      "url": "/assets/examples/data/products.json",
      "sha256": "383445fa732f7689c7ac7c3b093806c052c6f18e81bea040bb16a8d9a4928cb1",
      "bytes": 8886
    },
    {
      "url": "/assets/examples/data/verified-dataset.json",
      "sha256": "7e38b5a9ab9d88e4a097349a5c40ad996741e7398fc0970e8afb4bf623643d66",
      "bytes": 35205
    },
    {
      "url": "/assets/examples/data/catalog.csv",
      "sha256": "2f2a23e805b3569ab07b980effce20936488753763eadeef640e7da429308ca1",
      "bytes": 3120
    },
    {
      "url": "/assets/examples/data/shopify.csv",
      "sha256": "3ce387cc3df5732fc96903f344afe3226a3feae2a51a73129ab2b7041e48b581",
      "bytes": 2584
    },
    {
      "url": "/assets/examples/data/quality.json",
      "sha256": "d46ca50a8091fda241de8408f081b19e55d7c8c0843d7e8b06c2ad69bd478204",
      "bytes": 2864
    },
    {
      "url": "/assets/examples/data/source-evidence.json",
      "sha256": "1c25412db8ddc470f93fd856da39a77dc845976fd6d9abe654e75588cded6fb4",
      "bytes": 8430
    }
  ],
  "images": [
    {
      "productUrl": "https://books.toscrape.com/catalogue/a-brush-of-wings-angels-walking-3_651/index.html",
      "sourceUrl": "https://books.toscrape.com/media/cache/4d/16/4d163d43cb4aa624e599330a39abace5.jpg",
      "localUrl": "/assets/examples/images/a-brush-of-wings-angels-walking-3_651.jpg",
      "sha256": "2fd4bc1610148dc6b5615d9982db75d27f5ed143a664fcfdf71501a0d410b1c3",
      "bytes": 10619
    },
    {
      "productUrl": "https://books.toscrape.com/catalogue/a-light-in-the-attic_1000/index.html",
      "sourceUrl": "https://books.toscrape.com/media/cache/2c/da/2cdad67c44b002e7ead0cc35693c0e8b.jpg",
      "localUrl": "/assets/examples/images/a-light-in-the-attic_1000.jpg",
      "sha256": "4752d0ef411fb1c4aad31d69425d075c219345c386fd94f43ddfbf4495ea0437",
      "bytes": 9876
    },
    {
      "productUrl": "https://books.toscrape.com/catalogue/a-peoples-history-of-the-united-states_654/index.html",
      "sourceUrl": "https://books.toscrape.com/media/cache/75/20/75200336c141156746000f7055df344a.jpg",
      "localUrl": "/assets/examples/images/a-peoples-history-of-the-united-states_654.jpg",
      "sha256": "e5954f1b77f1bfce4861fb93293b228cf1c7420522b041cdd4d023ef03998539",
      "bytes": 9543
    },
    {
      "productUrl": "https://books.toscrape.com/catalogue/a-series-of-catastrophes-and-miracles-a-true-story-of-love-science-and-cancer_655/index.html",
      "sourceUrl": "https://books.toscrape.com/media/cache/9b/20/9b2076ce7414103a093ce2459d089969.jpg",
      "localUrl": "/assets/examples/images/a-series-of-catastrophes-and-miracles-a-true-story-of-love-science-and-cancer_655.jpg",
      "sha256": "7c42e5f89156458bd91ff632fdb76204415fed623725433f69443451b8099aba",
      "bytes": 7782
    },
    {
      "productUrl": "https://books.toscrape.com/catalogue/angels-walking-angels-walking-1_662/index.html",
      "sourceUrl": "https://books.toscrape.com/media/cache/50/0e/500eeb810e940424827580574e46852c.jpg",
      "localUrl": "/assets/examples/images/angels-walking-angels-walking-1_662.jpg",
      "sha256": "f4478ce0cdf723c1bbfb9176d63393526aaf8a8e1569f1d62249b02801a6ff67",
      "bytes": 9105
    },
    {
      "productUrl": "https://books.toscrape.com/catalogue/cell_674/index.html",
      "sourceUrl": "https://books.toscrape.com/media/cache/0b/97/0b97282ed82b771ed328e05386a84adb.jpg",
      "localUrl": "/assets/examples/images/cell_674.jpg",
      "sha256": "fe052e5bbc9818d46af0536cce83bc3d2b6e5ebcfe49d7b461883cccaa0a45f6",
      "bytes": 10125
    },
    {
      "productUrl": "https://books.toscrape.com/catalogue/code-name-verity-code-name-verity-1_680/index.html",
      "sourceUrl": "https://books.toscrape.com/media/cache/f5/58/f55886d1bf600529a35e1bd932c78ca0.jpg",
      "localUrl": "/assets/examples/images/code-name-verity-code-name-verity-1_680.jpg",
      "sha256": "ac67f877095fc586c6814e3c36f1d8c87e8a9448483ba97d6ac2e90aff4bd783",
      "bytes": 9187
    },
    {
      "productUrl": "https://books.toscrape.com/catalogue/fifty-shades-freed-fifty-shades-3_156/index.html",
      "sourceUrl": "https://books.toscrape.com/media/cache/18/d8/18d8e02c75c2ef23556c9746fae57e43.jpg",
      "localUrl": "/assets/examples/images/fifty-shades-freed-fifty-shades-3_156.jpg",
      "sha256": "984e6615b7e4c35e0ad34cca99a2414543f9f4da72bccee39f5916a7fe1b2aac",
      "bytes": 8145
    },
    {
      "productUrl": "https://books.toscrape.com/catalogue/its-only-the-himalayas_981/index.html",
      "sourceUrl": "https://books.toscrape.com/media/cache/27/a5/27a53d0bb95bdd88288eaf66c9230d7e.jpg",
      "localUrl": "/assets/examples/images/its-only-the-himalayas_981.jpg",
      "sha256": "eefd1eba26ecfcc3642d34986eed36e916c5a0afa3f179e6bec9f273bfebaa1a",
      "bytes": 11095
    },
    {
      "productUrl": "https://books.toscrape.com/catalogue/judo-seven-steps-to-black-belt-an-introductory-guide-for-beginners_903/index.html",
      "sourceUrl": "https://books.toscrape.com/media/cache/5f/52/5f52b1bc6d45daab2e330c744feb0359.jpg",
      "localUrl": "/assets/examples/images/judo-seven-steps-to-black-belt-an-introductory-guide-for-beginners_903.jpg",
      "sha256": "66451bf6911353b54a9593a813ca7b41a177ac2f22ed8d9f64e2c2f8918d2fed",
      "bytes": 7533
    },
    {
      "productUrl": "https://books.toscrape.com/catalogue/libertarianism-for-beginners_982/index.html",
      "sourceUrl": "https://books.toscrape.com/media/cache/0b/bc/0bbcd0a6f4bcd81ccb1049a52736406e.jpg",
      "localUrl": "/assets/examples/images/libertarianism-for-beginners_982.jpg",
      "sha256": "fc388c75954f7dc74c7ed01b4ed4bf4dea50ca4f9aeae38ba413b484bb6a5e6f",
      "bytes": 10883
    },
    {
      "productUrl": "https://books.toscrape.com/catalogue/logan-kade-fallen-crest-high-55_384/index.html",
      "sourceUrl": "https://books.toscrape.com/media/cache/d9/4e/d94e6206c2decd3acd9a61b2cbac7eaf.jpg",
      "localUrl": "/assets/examples/images/logan-kade-fallen-crest-high-55_384.jpg",
      "sha256": "30d6c57bccd252431b5c44f872d2e982748e69e6bfcd822ccb7e24b97136de61",
      "bytes": 7845
    }
  ],
  "limitations": [
    "This saved batch contains 48 products from 5 of 54 discovered listing pages; 49 pages remained. It is not the complete catalog.",
    "The next continuation attempt failed with a Shopify category conflict. Only the successful, internally consistent first batch is included.",
    "SKUs and descriptions are absent from the extracted listing records. This does not establish that those fields are absent from product detail pages.",
    "Some titles are truncated listing text and some categories are navigation labels. Original extraction values are preserved and need review.",
    "Price normalization is verified from saved raw price text. No enrichment or title repair was performed.",
    "Books to Scrape is a public scraping sandbox. Prices and availability are demonstration data, not a live commercial catalog.",
    "The optional Shopify Product Category column is omitted because the saved category labels are not verified Shopify taxonomy values. No category is inferred; remaining source export cells, including Published=TRUE, are preserved.",
    "Shopify headers and record consistency are checked locally; no Shopify store import was performed. Review incomplete fields and publication settings before import."
  ]
}