Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.olostep.com/llms.txt

Use this file to discover all available pages before exploring further.

NPM Package: olostep

​
Getting started

npm install olostep

import Olostep from 'olostep';

const client = new Olostep({apiKey: process.env.OLOSTEP_API_KEY});

// Minimal scrape example
const result = await client.scrapes.create('https://example.com');
console.log(result.id, result.html_content);
The NodeJS SDK accepts both camelCase and snake_case for all parameters. Use snake_case if you’re building for AI agents, it matches the API’s native field names.

​
Usage

​
Scraping

Scrape a single URL with various options: 
import Olostep, {Format} from 'olostep';

const client = new Olostep({apiKey: 'your_api_key'});

// Simple scrape
const scrape = await client.scrapes.create('https://example.com');

// With multiple formats
const scrape = await client.scrapes.create({
  url: 'https://example.com',
  formats: [Format.HTML, Format.MARKDOWN, Format.TEXT],
  waitBeforeScraping: 1000,
  removeImages: true
});

// Access the content
console.log(scrape.html_content);
console.log(scrape.markdown_content);

// Get scrape by ID
const fetched = await client.scrapes.get(scrape.id);

​
Batch Processing

Process multiple URLs in a single batch: 
// Using URL strings (custom IDs auto-generated)
const batch = await client.batches.create([
  'https://example.com',
  'https://example.org',
  'https://example.net'
]);

// Or with explicit custom IDs
const batch = await client.batches.create([
  {url: 'https://example.com', customId: 'site-1'},
  {url: 'https://example.org', customId: 'site-2'}
]);

console.log(`Batch ${batch.id} created with ${batch.total_urls} URLs`);

// Wait for completion
await batch.waitTillDone({
  checkEveryNSecs: 5,
  timeoutSeconds: 120
});

// Get batch info
const info = await batch.info();
console.log(info);

// Stream individual results
for await (const item of batch.items()) {
  console.log(item.custom_id);
}

​
Crawling

Crawl an entire website: 
const crawl = await client.crawls.create({
  url: 'https://example.com',
  maxPages: 100,
  maxDepth: 3,
  includeUrls: ['*/blog/*'],
  excludeUrls: ['*/admin/*']
});

console.log(`Crawl ${crawl.id} started`);

// Wait for completion
await crawl.waitTillDone({
  checkEveryNSecs: 10,
  timeoutSeconds: 300
});

// Get crawl info
const info = await crawl.info();
console.log(`Crawled ${info.pages_crawled} pages`);

// Stream crawled pages
for await (const page of crawl.pages()) {
  console.log(page.url, page.status_code);
}

​
Site Mapping

Generate a sitemap of URLs from a website: 
const map = await client.maps.create({
  url: 'https://example.com',
  topN: 100,
  includeSubdomain: true,
  searchQuery: 'blog posts'
});

console.log(`Map ${map.id} created`);

// Stream URLs
for await (const url of map.urls()) {
  console.log(url);
}

// Get map info
const info = await map.info();

​
AI-Powered Answers

Get answers from web pages using AI: 
import Olostep from 'olostep';

const client = new Olostep({apiKey: 'your_api_key'});

// Simple task: pass a string directly
const answer = await client.answers.create(
  'What is the main topic of https://example.com?'
);
console.log(answer.answer);
console.log(answer.sources);

// With structured JSON output
const structured = await client.answers.create({
  task: 'Extract all product names and prices from https://example.com',
  jsonFormat: {
    products: [{name: '', price: ''}]
  }
});
console.log(structured.json_content);

// Retrieve a previously created answer by ID
const fetched = await client.answers.get(answer.id);
console.log(fetched.answer);

​
Content Retrieval

Retrieve previously scraped content: 
// Get content in specific format(s)
const content = await client.retrieve(retrieveId, Format.MARKDOWN);
console.log(content.markdown_content);

// Multiple formats
const content = await client.retrieve(retrieveId, [
  Format.HTML,
  Format.MARKDOWN
]);

​
Advanced Options

​
Custom Actions

Perform browser actions before scraping: 
const scrape = await client.scrapes.create({
  url: 'https://example.com',
  actions: [
    {type: 'wait', milliseconds: 2000},
    {type: 'click', selector: '#load-more'},
    {type: 'scroll', distance: 1000},
    {type: 'fill_input', selector: '#search', value: 'query'}
  ]
});

​
Geographic Location

Scrape from different countries using predefined country codes or any valid country code string: 
import Olostep, {Country} from 'olostep';

const client = new Olostep({apiKey: 'your_api_key'});

// Using predefined enum values (US, DE, FR, GB, SG)
const scrape = await client.scrapes.create({
  url: 'https://example.com',
  country: Country.DE  // Germany
});

// Or use any valid country code as a string
const scrape2 = await client.scrapes.create({
  url: 'https://example.com',
  country: 'jp'  // Japan
});

​
LLM Extraction

Extract structured data using LLMs: 
const scrape = await client.scrapes.create({
  url: 'https://example.com',
  llmExtract: {
    schema: {
      title: 'string',
      price: 'number',
      description: 'string'
    },
    prompt: 'Extract product information from this page'
  }
});

​
Client Configuration

import Olostep from 'olostep';

const client = new Olostep({
  apiKey: 'your_api_key',
  apiBaseUrl: 'https://api.olostep.com/v1',  // optional
  timeoutMs: 150000,  // 150 seconds (optional)
  retry: {
    maxRetries: 3,
    initialDelayMs: 1000
  },
  userAgent: 'MyApp/1.0'  // optional
});

​
Feature highlights

  • Async-first client with full TypeScript support.
  • Type-safe inputs using TypeScript enums and interfaces (Formats, Countries, Actions, etc.).
  • Rich resource namespaces with both shorthand calls (client.scrapes.create()) and explicit methods (client.scrapes.get()).
  • Shared transport layer with retries, timeouts, and JSON decoding.
  • Comprehensive error hierarchy