read a html file and Extract all of the japanese

import re
from bs4 import BeautifulSoup

def get_japanese(html_file):
  soup = BeautifulSoup(open(html_file), 'html.parser')
  japanese = soup.findAll(text=re.compile(".*[\u4E00-\u9FFF]+.*"))
  return japanese

get_japanese("test.html")