# Extract typed JSON

`POST https://api.crawl4ai.com/extract`

Pull structured, typed data out of a page with an instruction and/or a JSON schema. Give a URL (we fetch it) or your own content.
## Request

curl:

```bash
curl https://api.crawl4ai.com/extract \
  -H "Authorization: Bearer sk_live_..." \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://news.ycombinator.com",
    "instruction": "the top stories on the front page",
    "schema": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "title":  { "type": "string"  },
          "points": { "type": "integer" },
          "url":    { "type": "string"  }
        },
        "required": ["title", "points"]
      }
    },
    "example": [
      { "title": "Show HN: My project", "points": 128, "url": "https://..." }
    ]
  }'
```

## Body

| Name | Type | Default | Description |
|---|---|---|---|
| url | string | - | Page to read. We fetch it for you. |
| content | string | - | Your own text/markdown/html to extract from, instead of a URL. |
| instruction | string | - | Plain-English description of what to pull out. |
| schema | object | - | JSON schema each returned record must match — gives you typed, predictable output. |
| example | object | - | A sample of the shape you want (structure, not values). |



> **Note**
>
> Give a URL **or** `content` (plus an `instruction` and/or `schema`). Long pages are chunked and re-assembled automatically.



**Try it with your key**

Run this call in the playground and see the real answer, the time and the units.
[Open the playground](https://crawl4ai.com/#playground)



---
Source: https://crawl4ai.com/docs/extract/