Extraer imágenes de pdfs y guardarlas en subcarpetas

pdf-extract.js

'use strict'

const fs = require('fs-extra')
const spawn = require('child_process').spawn

const originalPath = __dirname + '/pdfs/original'
const extractedPath = __dirname + '/pdfs/extracted'

fs.removeSync(extractedPath)
fs.copySync(originalPath, extractedPath)
fs.walk(extractedPath).on('data', item => {
  let pathname = item.path.match(/(.*?)\.pdf/)
  let filename = item.path.match(/.{1,}\/(.*?\.pdf)/)

  pathname = pathname && pathname[1]
  filename = filename && filename[1]

  if (pathname && filename) {
    const filepath = pathname + '/' + filename

    fs.move(item.path, filepath, (err) => {
      if (err) return console.log(err)
      spawn('pdftohtml', [filepath]).stdout.on('close', () => {
        fs.removeSync(pathname + '/*.html')
        console.log(filename + ' ok!')
      })
    })
  }
})