---
name: "html-to-dataset-extractor"
description: "Extract a repeated HTML structure into rows with traceable missing values. Use when the user needs: Get a CSV or JSON table, extraction rules and validation results."
metadata: {"version": "2026-10-17.1", "category": "data-parsing", "publisher": "AIDiveForge"}
---

# HTML-to-Dataset Extractor

Get a CSV or JSON table, extraction rules and validation results.

## Requirements

Provide the HTML or an accessible page and the fields you need.

## Workflow

1. Inspect the rendered or supplied structure and identify one repeated record boundary.
2. Map fields to selectors or explicit text rules; keep the source URL or row locator.
3. Handle absent fields as null/empty according to the output contract, and normalize whitespace without altering meaning.
4. Deduplicate only with an explicit key and verify source record count against output row count.
5. Validate required fields and sample rows against the source. Report pagination or dynamic-content limits.

## Worked example

Read `examples/input.txt` and `examples/expected.txt` before adapting the workflow.

## Acceptance checks

Produce two rows and keep Beta’s missing price empty. Do not reuse Alpha’s price or drop the second row.

## Limits

Selectors are site-specific and may change. This workflow does not bypass access restrictions or guarantee extraction from every site.

Worked example included. Model-specific performance and vendor compatibility have not been benchmarked.