Does it find existing structured data on the page?

Yes. JSON-LD, microdata, and RDFa schemas already embedded in the page are extracted first. The LLM then supplements with any missing fields visible in the rendered content.

Can I define a custom extraction schema?

Yes. Pass a JSON schema via `target_schema` and the extractor will map page content to your fields. The LLM understands field names and descriptions to find the right data.

How does it handle paginated content?

Set `follow_pagination` to true and the extractor will detect 'next page' links and aggregate data across multiple pages. A `max_pages` limit prevents runaway crawling.

data

HTML
JSON
Converter

Extract structured data from web pages using a combination of CSS/XPath selectors and LLM-based extraction. Captures product details, article metadata, contact information, and custom schemas from any website.

Max file size: 50 MB

Estimated: 2-8 sec per page

2 input formats

How It Works

Provide a URL or upload an HTML file.

Existing structured data (JSON-LD, microdata, RDFa) is extracted first.

An LLM analyzes the page to extract additional structured fields.

Results are merged and validated against your target schema.

Clean JSON output is returned with confidence scores.

Code Examples

import os, requests

API = "https://api.mixpeek.com"
H = {"Authorization": f"Bearer {os.environ['MIXPEEK_API_KEY']}",
     "X-Namespace": os.environ["NAMESPACE_ID"]}

# 1. a bucket, with a schema that declares the field you will send
bucket = requests.post(f"{API}/v1/buckets", headers=H, json={
    "bucket_name": "html-inputs",
    "bucket_schema": {"properties": {"html": {"type": "text"}}},
}).json()

# 2. land the file as an object. the URL goes in data, on the blob
requests.post(f"{API}/v1/buckets/{bucket['bucket_id']}/objects", headers=H, json={
    "key_prefix": "run-1",
    "blobs": [{"property": "html", "type": "text",
               "data": "https://example.com/page.html"}],
})

# 3. a collection over that bucket, running the extractor
collection = requests.post(f"{API}/v1/collections", headers=H, json={
    "collection_name": "html-to-structured-data",
    "source": {"type": "bucket", "bucket_ids": [bucket["bucket_id"]]},
    "feature_extractor": {"feature_extractor_name": "web_scraper", "version": "v1"},
}).json()

# 4. run extraction over the bucket
requests.post(f"{API}/v1/buckets/{bucket['bucket_id']}/batches", headers=H, json={
    "collection_ids": [collection["collection_id"]],
    "auto_submit": True,
})

# 5. read the output
docs = requests.get(
    f"{API}/v1/collections/{collection['collection_id']}/documents", headers=H
).json()
print(docs)

Use Cases

Scrape product details from e-commerce pages

Extract article metadata from news sites

Capture business listings from directory pages

Build structured datasets from web sources

Supported Input Formats

HTML

XHTML

Quick Info

Categorydata

Max File Size50 MB

Est. Time2-8 sec per page

Extractorweb-scraper

Processing millions of files?

Run this as a managed pipeline over your whole library, no infrastructure to build or maintain. Talk to us about processing at scale.

Run it over a library

Mixpeek runs this conversion as a pipeline over a whole library in your object storage, with the output landing as queryable documents. It is not a single-file converter.

Frequently Asked Questions

Related Converters

PDF

JSON

PDF to Structured Data

Extract structured key-value pairs, tables, and form fields from PDF documents. Uses layout analysis and LLM extraction to produce clean JSON output, even from complex forms and invoices.

JSON

Embeddings

JSON to Embeddings

Convert JSON objects and arrays into semantic vector embeddings. Supports nested structures, field selection, and configurable serialization strategies for optimal embedding quality.