reference: http://stackoverflow.com/questions/7291120/python-and-unicode-code-point-extraction #python3 for i in range(1,100000): # try range(44032,55203) for Korean print(i, chr(i), repr(chr(i)), repr(chr(i).encode('utf8'))) if i%30==0: input("Enter to continue") #python2 for i in range(1,100000): print i, unichr(i), repr(unichr(i)), repr(unichr(i).encode('utf8')) if i%30==0: raw_input("Enter to continue") #result 1 u'\x01' '\x01' 2 u'\x02' '\x02' 3 u'\x03' '\x03' 4 u'\x04' '\x04' 5 u'\x05' '\x05' 6 u'\x06' '\x06' 7 u'\x07' '\x07' 8 u'\x08' '\x08' ...snipped... 241 ñ u'\xf1' '\xc3\xb1' 242 ò u'\xf2' '\xc3\xb2' 243 ó u'\xf3' '\xc3\xb3' 244 ô u'\xf4' '\xc3\xb4'