Skip to main content

Quickstart

Get started with Helix Parse in under 2 minutes.

Prerequisites​

Before you begin, you'll need:

Parse a URL​

Send a URL to extract structured content from any web page.

curl -X POST https://api.feeds.onhelix.ai/parse \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://www.bbc.com/news/technology-67988517"
  }'

Response:

{
  "success": true,
  "data": {
    "jobId": "a3e2f8d1-7c4b-4e9a-b6d5-1f8a2c3e4d5b",
    "hasPrimaryContent": true,
    "consumability": {
      "isConsumable": true,
      "reason": "Page contains a full news article with a clear headline, body text, and publication metadata"
    },
    "primaryContent": {
      "title": "Apple Vision Pro: First look at the mixed reality headset",
      "description": "Apple's long-awaited mixed reality headset offers a glimpse into the future of spatial computing, but at a steep price point.",
      "author": "James Clayton",
      "publisher": "BBC News",
      "publishedAt": "2024-01-18T14:23:00.000Z",
      "updatedAt": null,
      "isSponsored": false,
      "isDigest": false,
      "accessRestrictionType": null,
      "text": {
        "simplifiedHtml": "<p>Apple has officially launched the Vision Pro, its first major new product category in nearly a decade.</p><p>The mixed reality headset, priced at $3,499, blends digital content with the physical world using what Apple calls \"spatial computing\".</p>"
      },
      "video": null,
      "primaryImage": {
        "url": "https://ichef.bbci.co.uk/news/1024/cpsprodpb/vivo/live/images/2024/1/18/vision-pro-hands-on.jpg",
        "caption": "The Apple Vision Pro headset on display at Apple's Cupertino headquarters",
        "credit": "Getty Images"
      },
      "originallyPublished": null
    },
    "scrape": {
      "httpStatus": 200
    }
  }
}

What happens behind the scenes:

  • A headless browser loads and renders the page
  • AI extracts the structured content, including title, author, body text, and images
  • The page is assessed for consumability to determine if it contains meaningful standalone content

Parse Raw HTML​

If you already have the HTML, you can pass it directly instead of a URL.

curl -X POST https://api.feeds.onhelix.ai/parse \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "html": "<html><head><title>Product Launch Announcement</title></head><body><article><h1>Acme Corp Launches the Nova Series</h1><p>By Sarah Chen | March 5, 2025</p><p>Acme Corporation today announced the Nova Series, a new line of enterprise networking hardware designed for AI-native data centers. The Nova 9000 switch delivers 51.2 Tbps of throughput while reducing power consumption by 40% compared to previous generations.</p><p>\"Enterprises need infrastructure that keeps pace with the demands of large-scale AI workloads,\" said CTO David Park.</p></article></body></html>",
    "title": "Product Launch Announcement"
  }'

Response:

{
  "success": true,
  "data": {
    "jobId": "b7d1c9e4-5a3f-4b8d-9e2c-6f7a8b9c0d1e",
    "hasPrimaryContent": true,
    "consumability": {
      "isConsumable": true,
      "reason": "Page contains a complete article about a product launch with clear structure and attribution"
    },
    "primaryContent": {
      "title": "Acme Corp Launches the Nova Series",
      "description": "Acme Corporation announces the Nova Series, a new line of enterprise networking hardware designed for AI-native data centers.",
      "author": "Sarah Chen",
      "publisher": null,
      "publishedAt": "2025-03-05T00:00:00.000Z",
      "updatedAt": null,
      "isSponsored": false,
      "isDigest": false,
      "accessRestrictionType": null,
      "text": {
        "simplifiedHtml": "<p>Acme Corporation today announced the Nova Series, a new line of enterprise networking hardware designed for AI-native data centers. The Nova 9000 switch delivers 51.2 Tbps of throughput while reducing power consumption by 40% compared to previous generations.</p><p>\"Enterprises need infrastructure that keeps pace with the demands of large-scale AI workloads,\" said CTO David Park.</p>"
      },
      "video": null,
      "primaryImage": null,
      "originallyPublished": null
    }
  }
}

When to use this mode:

  • You have pre-rendered content from your own pipeline
  • Working with server-side rendered pages you've already fetched
  • Integrating Parse into a custom scraping workflow

What You Get Back​

All responses use the standard envelope: { "success": true, "data": { ... } }

The data object contains:

  • hasPrimaryContent -- boolean indicating whether the page had extractable content
  • consumability -- assessment of whether the page has meaningful standalone content
  • primaryContent -- the extracted content (title, author, text, images, etc.)
  • scrape -- HTTP metadata from the scrape (URL mode only)

See the Overview for a deeper understanding of how Parse works, or the API Reference for complete field documentation.

Next Steps​