Olostep NodeJS SDK

npm install olostep

import Olostep from 'olostep';

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

// Esempio minimo di scraping
const result = await client.scrapes.create('https://example.com');
console.log(result.id, result.html_content);

import Olostep, {Format} from 'olostep';

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

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

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

// Accedi al contenuto
console.log(scrape.html_content);
console.log(scrape.markdown_content);

// Ottieni lo scrape tramite ID
const fetched = await client.scrapes.get(scrape.id);

// Utilizzando stringhe URL (ID personalizzati generati automaticamente)
const batch = await client.batches.create([
  'https://example.com',
  'https://example.org',
  'https://example.net'
]);

// Oppure con ID personalizzati espliciti
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} creato con ${batch.total_urls} URL`);

// Attendi il completamento
await batch.waitTillDone({
  checkEveryNSecs: 5,
  timeoutSeconds: 120
});

// Ottieni informazioni sul batch
const info = await batch.info();
console.log(info);

// Stream dei risultati individuali
for await (const item of batch.items()) {
  console.log(item.customId);
}

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

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

// Attendi il completamento
await crawl.waitTillDone({
  checkEveryNSecs: 10,
  timeoutSeconds: 300
});

// Ottieni informazioni sul crawl
const info = await crawl.info();
console.log(`Crawled ${info.pages_crawled} pagine`);

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

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

console.log(`Mappa ${map.id} creata`);

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

// Ottieni informazioni sulla mappa
const info = await map.info();

// Ottieni contenuto in formato specifico
const content = await client.retrieve(retrieveId, Format.MARKDOWN);
console.log(content.markdown_content);

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

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'}
  ]
});

import Olostep, {Country} from 'olostep';

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

// Utilizzando valori enum predefiniti (US, DE, FR, GB, SG)
const scrape = await client.scrapes.create({
  url: 'https://example.com',
  country: Country.DE  // Germania
});

// Oppure usa qualsiasi codice paese valido come stringa
const scrape2 = await client.scrapes.create({
  url: 'https://example.com',
  country: 'jp'  // Giappone
});

const scrape = await client.scrapes.create({
  url: 'https://example.com',
  llmExtract: {
    schema: {
      title: 'string',
      price: 'number',
      description: 'string'
    },
    // Facoltativamente fornisci un prompt per guidare l'estrazione
    prompt: 'Estrai informazioni sul prodotto da questa pagina'
  }
});

import Olostep from 'olostep';

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