- #coding=utf-8
- import sys
- print sys.getdefaultencoding() # --> ascii
- u1 = '中国'
- print type(u1), repr(u1) # --> <type 'str'> '\\xe4\\xb8\\xad\\xe5\\x9b\\xbd'
- u2 = u'中国2009'
- print type(u2), repr(u2) # --> <type 'unicode'> u'\\u4e2d\\u56fd2009'
- # str --> unicode
- print '# str --> unicode'
- u1_1 = u1.decode('utf8')
- print type(u1_1), repr(u1_1) # --> <type 'unicode'> u'\\u4e2d\\u56fd'
- u1_2 = unicode(u1, 'utf8')
- print type(u1_2), repr(u1_2) # --> <type 'unicode'> u'\\u4e2d\\u56fd'
- # unicode --> str
- print '# unicode --> str'
- u2_1 = u2.encode('utf8')
- print type(u2_1), repr(u2_1) # --> <type 'str'> '\\xe4\\xb8\\xad\\xe5\\x9b\\xbd2009'
- u2_2 = u2.encode('gbk')
- print type(u2_2), repr(u2_2) # --> <type 'str'> '\\xd6\\xd0\\xb9\\xfa2009'
- u2_3 = u2.encode('gb2312')
- print type(u2_3), repr(u2_3) # --> <type 'str'> '\\xd6\\xd0\\xb9\\xfa2009'
- #该片段来自于http://www.codesnippet.cn/detail/20112012493.html
来源: http://www.codesnippet.cn/detail/20112012493.html