In [3]: print cc.Convert2Unicode('\·*媛媛。')
\·*媛媛。
In [4]: print cc.Convert2Unicode(u'\·*媛媛。')
\·*媛媛。
In [5]: print cc.Convert2Unicode(u'\·*媛媛。'.encode('raw_unicode_escape'))
---------------------------------------------------------------------------
UnicodeDecodeError Traceback (most recent call last)
<ipython-input-5-60d2bf3b7095> in <module>()
----> 1 print cc.Convert2Unicode(u'\·*媛媛。'.encode('raw_unicode_escape'))
/Users/fuwenlan/HQM/venv/lib/python2.7/site-packages/CodeConvert.pyc in Convert2Unicode(kw)
225 @staticmethod
226 def Convert2Unicode(kw):
--> 227 return convert_2_unicode(kw)
228
229 @staticmethod
/Users/fuwenlan/HQM/venv/lib/python2.7/site-packages/CodeConvert.pyc in convert_2_unicode(kw)
203 def convert_2_unicode(kw):
204 if isinstance(kw, basestring):
--> 205 return convert_2_unicode_basestring(kw_escape(kw))
206 elif isinstance(kw, dict):
207 return dict((convert_2_unicode(k), convert_2_unicode(v)) for k, v in kw.items())
/Users/fuwenlan/HQM/venv/lib/python2.7/site-packages/CodeConvert.pyc in convert_2_unicode_basestring(kw, debug)
158 print_tip_unicode('unicode_without_u', debug)
159 else:
--> 160 ret = kw.decode('utf8')
161 print_tip_unicode('utf8', debug)
162 return ret
/Users/fuwenlan/HQM/venv/lib/python2.7/encodings/utf_8.pyc in decode(input, errors)
14
15 def decode(input, errors='strict'):
---> 16 return codecs.utf_8_decode(input, errors, True)
17
18 class IncrementalEncoder(codecs.IncrementalEncoder):
UnicodeDecodeError: 'utf8' codec can't decode byte 0xb7 in position 1: invalid start byte
In [6]: u'\·*媛媛。'.encode('raw_unicode_escape')
Out[6]: '\\\xb7*\\u5a9b\\u5a9b\\u3002'
In [7]:
