python使用正则表达式去除中文文本多余空格，保留英文之间空格方法详解

def clean_space(text):
  """"
  处理多余的空格
  """
  match_regex = re.compile(u'[\u4e00-\u9fa5。\.,，:：《》、\(\)（）]{1} +(?<![a-zA-Z])|\d+ +| +\d+|[a-z A-Z]+')
  should_replace_list = match_regex.findall(text)
  order_replace_list = sorted(should_replace_list,key=lambda i:len(i),reverse=True)
  for i in order_replace_list:
    if i == u' ':
      continue
    new_i = i.strip()
    text = text.replace(i,new_i)
  return text

import re 

s = "     info has been found (+/- 100 pages, and 4.5 mb of .pdf files) now i have to wait untill our team leader has processed it and learns html.     "
re.sub(" +", " ", s)

s = "     info has been found (+/- 100 pages, and 4.5 mb of .pdf files) now i have to wait untill our team leader has processed it and learns html.     "

s = ' '.join(s.split())
s