Python处理文本文件中控制字符的方法

strip_control_characters = lambda s:"".join(i for i in s if 31<ord(i)<127)

def strip_control_characters(str_input): 
 if str_input: 
 import re 
 # unicode invalid characters 
 RE_XML_ILLEGAL = u'([\u0000-\u0008\u000b-\u000c\u000e-\u001f\ufffe-\uffff])' + \
   u'|' + \
   u'([%s-%s][^%s-%s])|([^%s-%s][%s-%s])|([%s-%s]$)|(^[%s-%s])' % \
   (unichr(0xd800),unichr(0xdbff),unichr(0xdc00),unichr(0xdfff), 
    unichr(0xd800),unichr(0xdbff),unichr(0xdc00),unichr(0xdfff), 
    unichr(0xd800),unichr(0xdbff),unichr(0xdc00),unichr(0xdfff), 
    ) 
 str_input = re.sub(RE_XML_ILLEGAL, "", input) 
 # ascii control characters 
 str_input = re.sub(r"[\x01-\x1F\x7F]", "", input) 
 return str_input

import re
 
def remove_control_chars(s):
 control_chars = ''.join(map(unichr, range(0,32) + range(127,160)))
 control_char_re = re.compile('[%s]' % re.escape(control_chars))
 
 return control_char_re.sub('', s)
 
cleaned_json = remove_control_chars(original_json)
obj = simplejson.loads(cleaned_json)