MarkUDown
Prompt Extract API — MarkUDown LLM web data extraction docs
POST
/api/prompt-extractPrompt Extract
Extract data from a page with a plain-language instruction — no schema. The LLM chooses the field names and returns an array of JSON objects.
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| url | string | required | — | URL of the page to extract from. |
| prompt | string | required | — | What to extract, in plain language. |
| main_content | boolean | optional | true | Extract only the main content (drops navigation, header and footer). |
| timeout | integer | optional | 60 | Page load timeout in seconds. |
| callback_url | string | optional | null | Webhook URL to POST the result to when the job completes. |
Request
curl -X POST https://api.scrapetechnology.com/api/prompt-extract \
-H "X-API-KEY: your-api-key" \
-H "Content-Type: application/json" \
-d '{"url": "https://quotes.toscrape.com/", "prompt": "Every quote with its author and tags"}'Response
// POST returns { "success": true, "id": "abc123", "url": "/api/extract/abc123" }
// Poll GET /api/extract/{id}
{
"success": true,
"id": "abc123",
"status": "completed",
"data": {
"success": true,
"data": [
{
"quote": "The world as we have created it is a process of our thinking...",
"author": "Albert Einstein",
"tags": ["change", "deep-thoughts", "thinking", "world"]
}
],
"total": 1,
"url": "https://quotes.toscrape.com/",
"processing_time_ms": 5400
}
}Python — pip install markudown
from markudown import MarkUDown
md = MarkUDown(api_key="your-api-key")
job = md.prompt_extract("https://quotes.toscrape.com/", "Every quote with its author and tags")
print(job["data"]["data"])Node.js — npm install markudown-sdk
import { MarkUDown } from "markudown-sdk";
const md = new MarkUDown({ apiKey: "your-api-key" });
const job = await md.promptExtract("https://quotes.toscrape.com/", "Every quote with its author and tags");
console.log(job.data.data);Prompt Extract jobs are polled at GET /api/extract/{id} (not /api/prompt-extract). Only the first 50,000 characters of the page's Markdown are sent to the LLM.
Cost: 5 credits per request.