Tapochek.net HTML scraper that gets topics

tapochek-net-scraper.js

// OPEN https://tapochek.net/viewforum.php?f=910&start=0 FIRST
// THEN RUN THIS SCRIPT:

async function start() {
  const result = []

  async function parsePage(url) {
    const response = await fetch(url)

    if (!response.ok) {
      throw new Error(`HTTP error! status: ${response.status}`)
    }

    const arrayBuffer = await response.arrayBuffer()
    const decoder = new TextDecoder('windows-1251')
    const decodedString = decoder.decode(arrayBuffer)

    const parser = new DOMParser()
    const doc = parser.parseFromString(decodedString, 'text/html')

    const table = Array.from(doc.querySelectorAll('tbody > tr[id^=tr]')).filter(row => {
      const topicName = row.querySelector('a.torTopic')
      return topicName && topicName.textContent.trim().length > 0
    }).map(row => {
      const topicName = row.querySelector('a.torTopic')
      return {
        title: topicName.textContent.trim(),
        size: row.querySelector('a[href^="./download.php"]')?.textContent?.trim(),
        downloads: row.querySelector('p.med > b')?.textContent?.trim()
      }
    })

    result.push(...table)

    const nextPageLink = Array.from(doc.querySelectorAll('a[href^=viewforum]'))
      .find(a => a.textContent.trim() === 'След.')?.href

    return nextPageLink
  }

  let nextPage = window.location.href
  while (nextPage) {
    try {
      nextPage = await parsePage(nextPage)
    } catch (err) {
      console.error('Error fetching the page:', err)
      nextPage = null
    }
  }

  console.log(result)
}

start()

// NOW COPY LOGGED ARRAY AS JSON OBJECT FROM BROWSER'S CONSOLE