jcrawler

Asynchronous control flow wrapper to crawl websites

How to Install

  npm install jcrawler

Usage

  const jcrawler = require('jcrawler')
  const puppeteer = require('puppeteer')

  (async () => {
    const crawler = jcrawler({
      puppeteer,
      concurrency: 2,
      rateLimit: 1000, // 1 second
      retries: 5,
      retryInterval: 1000, // 1 second
      backoff: 2, // multiplies the retryInterval for each retry
      log: true
    })

    crawler
      .on('data', data => console.log(data)) // events: data, error and end
      .on('error', err => console.error(err))
      .on('end', (data, results) => console.log(results.timer.time))

    const fruits = ['apple', 'banana', 'orange']

    await crawler.each(fruits, async (browser, page, fruit) => {
      // using puppeteer
      await page.goto('http://google.com')
      await page.type("input[title='Search']", fruit)
      await page.click("input[value=\"I'm Feeling Lucky\"]")
      await page.screenshot({ path: `${fruit}.png`) })
    })
  })()

License

MIT License - Daniel Sousa