Skip to main content
The scrape capability extracts structured HTML content from URLs, preserving the page structure for data extraction.

​
Providers

ProviderFeatures
FirecrawlJavaScript rendering, handles dynamic content
ScraperAPIRotating proxies, handles blocks

​
Basic Usage

const result = await saturn.scrape({
  url: 'https://example.com/products',
});

console.log(result.data.html);
// → Raw HTML content

​
Parameters

​
url
string
required
The URL to scrape.
​
provider
string
Specific provider to use (firecrawl or scraperapi).
​
waitFor
number
Milliseconds to wait for JavaScript rendering.

​
Response

interface ScrapeResponse {
  data: {
    html: string;       // Raw HTML content
    url: string;        // Final URL (after redirects)
    statusCode: number; // HTTP status code
  };
  metadata: {
    chargedUsdCents: number;
    provider: string;
    latencyMs: number;
    auditId: string;
  };
}

​
Examples

​
Extract Product Data

const page = await saturn.scrape({
  url: 'https://store.example.com/product/123',
});

// Use LLM to extract structured data
const extraction = await saturn.reason({
  prompt: `Extract product information from this HTML as JSON:
  - name
  - price
  - description
  - availability

  HTML:
  ${page.data.html}`,
});

const product = JSON.parse(extraction.data.content);

​
Handle Dynamic Content

// Wait for JavaScript to render
const page = await saturn.scrape({
  url: 'https://spa.example.com',
  waitFor: 3000, // Wait 3 seconds
});

​
When to Use scrape vs read

CapabilityUse caseReturns
readArticles, blog posts, documentationClean text
scrapeData extraction, structured contentRaw HTML
Use scrape when you need to:
  • Extract specific elements (prices, tables, lists)
  • Parse structured data
  • Work with page layout

​
Pricing

ProviderCost per page
Firecrawl~$0.002
ScraperAPI~$0.005

​
Combining with LLM Extraction

async function extractJobListings(url: string) {
  const page = await saturn.scrape({ url });

  const jobs = await saturn.reason({
    prompt: `Extract job listings from this HTML as JSON array:
    Each job should have: title, company, location, salary (if listed)

    HTML:
    ${page.data.html}`,
  });

  return JSON.parse(jobs.data.content);
}