Python处理文本文件中控制字符的方法

defstrip_control_characters(str_input):

 ifstr_input:

 importre

 # 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)

 returnstr_input

importre

defremove_control_chars(s):

 control_chars=''.join(map(unichr,range(0,32)+range(127,160)))

 control_char_re=re.compile('[%s]'%re.escape(control_chars))

 returncontrol_char_re.sub('', s)

cleaned_json=remove_control_chars(original_json)

obj=simplejson.loads(cleaned_json)