Find all the Japanese characters in the html file

import re
def find_japanese(file):
  japanese_regex = re.compile(r'[\u3000-\u303f\u3040-\u309f\u30a0-\u30ff\uff00-\uff9f\u4e00-\u9faf\u3400-\u4dbf]')
  text = open(file)
  text = text.read()
  text = text.strip().split()
  japanese = []
  for i in text:
    if japanese_regex.search(i):
      japanese.append(i)
  return japanese
    
find_japanese('html_file.txt')