python编码转换实验

Python 2.6.6 (r266:84292, Jul 23 2015, 15:22:56) 

[GCC 4.4.7 20120313 (Red Hat 4.4.7-11)] on linux2

Type "help", "copyright", "credits" or "license" for more information.

>>> print ord('A')

65

>>>     

... 

>>> a = {"a":"1","b","2"}

  File "<stdin>", line 1

    a = {"a":"1","b","2"}

                    ^

SyntaxError: invalid syntax

>>> a = {"a":"1","b":"2"}

>>> str(a)

"{'a': '1', 'b': '2'}"

>>> print a

{'a': '1', 'b': '2'}

>>> print type(a)

<type 'dict'>

>>> print type(str(a))

<type 'str'>

>>> b = [1,2,3]

>>> print type(b)

<type 'list'>

>>> print type(str(b))

<type 'str'>

>>> str(b)

'[1, 2, 3]'

>>> b.__class__

<type 'list'>

>>> str(b).__class__

<type 'str'>

>>> isinstance(a, str)

False

>>> isinstance(a, dict)

True

>>> isinstance(a, unicode)

False

>>> isinstance(a, utf-8)  

Traceback (most recent call last):

  File "<stdin>", line 1, in <module>

NameError: name 'utf' is not defined

>>> isinstance(a, 'utf-8')

Traceback (most recent call last):

  File "<stdin>", line 1, in <module>

TypeError: isinstance() arg 2 must be a class, type, or tuple of classes and types

>>> isinstance(a, type)   

False

>>> isinstance(a, unicode)

False

>>> isinstance(a, unicode)

False

>>> import chardet

>>> chardet.detect(a)

Traceback (most recent call last):

  File "<stdin>", line 1, in <module>

  File "/usr/lib/python2.6/site-packages/chardet/__init__.py", line 30, in detect

    u.feed(aBuf)

  File "/usr/lib/python2.6/site-packages/chardet/universaldetector.py", line 74, in feed

    if aBuf[:3] == codecs.BOM:

TypeError: unhashable type

>>> chardet.detect(str(a))

{'confidence': 1.0, 'encoding': 'ascii'}

>>> chardet.detect(str(b))

{'confidence': 1.0, 'encoding': 'ascii'}

>>> c = ["我","是"]

>>> chardet.detect(str(c))

{'confidence': 1.0, 'encoding': 'ascii'}

>>> print c

['\xe6\x88\x91', '\xe6\x98\xaf']

>>> c.encode('unicode')

Traceback (most recent call last):

  File "<stdin>", line 1, in <module>

AttributeError: 'list' object has no attribute 'encode'

>>> str(c).encode('unicode')

Traceback (most recent call last):

  File "<stdin>", line 1, in <module>

LookupError: unknown encoding: unicode

>>> str(c).encode('utf-8')  

"['\\xe6\\x88\\x91', '\\xe6\\x98\\xaf']"

>>> d = str(c)

>>> chardet.detect(d)

{'confidence': 1.0, 'encoding': 'ascii'}

>>> chardet.detect(c)

Traceback (most recent call last):

  File "<stdin>", line 1, in <module>

  File "/usr/lib/python2.6/site-packages/chardet/__init__.py", line 30, in detect

    u.feed(aBuf)

  File "/usr/lib/python2.6/site-packages/chardet/universaldetector.py", line 108, in feed

    if self._highBitDetector.search(aBuf):

TypeError: expected string or buffer

>>> chardet.detect(d)

{'confidence': 1.0, 'encoding': 'ascii'}

>>> print d

['\xe6\x88\x91', '\xe6\x98\xaf']

>>> print dc

Traceback (most recent call last):

  File "<stdin>", line 1, in <module>

NameError: name 'dc' is not defined

>>> print c

['\xe6\x88\x91', '\xe6\x98\xaf']

>>> print d.decode('ascii')

['\xe6\x88\x91', '\xe6\x98\xaf']

>>> print type(d.decode('ascii'))

<type 'unicode'>

>>> print d.decode('ascii')      

['\xe6\x88\x91', '\xe6\x98\xaf']

>>> chardet.detect(c.decode('ascii')

... )

Traceback (most recent call last):

  File "<stdin>", line 1, in <module>

AttributeError: 'list' object has no attribute 'decode'

>>> chardet.detect(d.decode('ascii'))

Traceback (most recent call last):

  File "<stdin>", line 1, in <module>

  File "/usr/lib/python2.6/site-packages/chardet/__init__.py", line 25, in detect

    raise ValueError('Expected a bytes object, not a unicode object')

ValueError: Expected a bytes object, not a unicode object

>>> type(d)

<type 'str'>

>>> print type(d.decode('ascii'))

<type 'unicode'>

>>>  print d.decode('ascii') 

  File "<stdin>", line 1

    print d.decode('ascii') 

    ^

IndentationError: unexpected indent

>>> print d.decode('ascii') 

['\xe6\x88\x91', '\xe6\x98\xaf']

>>> print d.decode('ascii').encode('utf-8')

['\xe6\x88\x91', '\xe6\x98\xaf']

>>> print d.decode('ascii').encode('utf-8')[0]

[

>>> print d.decode('ascii')  

['\xe6\x88\x91', '\xe6\x98\xaf']

>>> e = d.decode('ascii')  

>>> print e

['\xe6\x88\x91', '\xe6\x98\xaf']

>>> type(e)

<type 'unicode'>

>>> f = e.encode('utf-8')

>>> f

"['\\xe6\\x88\\x91', '\\xe6\\x98\\xaf']"

>>> print f

['\xe6\x88\x91', '\xe6\x98\xaf']

>>> type(f)

<type 'str'>

>>> print f.decode("unicode_escape")

['', 'ˉ']

>>> print f.encode("raw_unicode_escape")

['\xe6\x88\x91', '\xe6\x98\xaf']

>>> print f.encode("raw_unicode_escape").decode('utf-8')

['\xe6\x88\x91', '\xe6\x98\xaf']

>>> print b

[1, 2, 3]

>>> print c

['\xe6\x88\x91', '\xe6\x98\xaf']

>>> print type(c)

<type 'list'>

>>> print type(d)

<type 'str'>

>>> print d

['\xe6\x88\x91', '\xe6\x98\xaf']

>>> import syss

Traceback (most recent call last):

  File "<stdin>", line 1, in <module>

ImportError: No module named syss

>>> import sys

>>> reload(sys)

<module 'sys' (built-in)>

>>> sys.setdefaultencoding('utf-8')

>>> print d

['\xe6\x88\x91', '\xe6\x98\xaf']

>>> print type(c)

<type 'list'>

>>> print type(d)

<type 'str'>

>>> cc = ["我","是"]

>>> print cc

['\xe6\x88\x91', '\xe6\x98\xaf']

>>> print type(cc)

<type 'list'>

>>> dd = str(cc)

>>> pirnt dd

  File "<stdin>", line 1

    pirnt dd

           ^

SyntaxError: invalid syntax

>>> print dd

['\xe6\x88\x91', '\xe6\x98\xaf']

>>> print type(dd)

<type 'str'>

>>> chardet.detect(d)

{'confidence': 1.0, 'encoding': 'ascii'}

>>> chardet.detect(dd)

{'confidence': 1.0, 'encoding': 'ascii'}

>>> sys.defaultencoding()

Traceback (most recent call last):

  File "<stdin>", line 1, in <module>

AttributeError: 'module' object has no attribute 'defaultencoding'

>>> sys.defaultencoding

Traceback (most recent call last):

  File "<stdin>", line 1, in <module>

AttributeError: 'module' object has no attribute 'defaultencoding'

>>> sys.defaultencode

Traceback (most recent call last):

  File "<stdin>", line 1, in <module>

AttributeError: 'module' object has no attribute 'defaultencode'

>>> sys.defaultencode()

Traceback (most recent call last):

  File "<stdin>", line 1, in <module>

AttributeError: 'module' object has no attribute 'defaultencode'

>>> sys.defaultencoding()

Traceback (most recent call last):

  File "<stdin>", line 1, in <module>

AttributeError: 'module' object has no attribute 'defaultencoding'

>>> sys.defaultencode

Traceback (most recent call last):

  File "<stdin>", line 1, in <module>

AttributeError: 'module' object has no attribute 'defaultencode'

>>> q = '中国'

>>> type(q)

<type 'str'>

>>> chardet.detect(q0

... )

Traceback (most recent call last):

  File "<stdin>", line 1, in <module>

NameError: name 'q0' is not defined

>>> chardet.detect(q)

{'confidence': 0.75249999999999995, 'encoding': 'utf-8'}

>>> p = ['中国', '复兴']

>>> chardet.detect(p)   

Traceback (most recent call last):

  File "<stdin>", line 1, in <module>

  File "/usr/lib/python2.6/site-packages/chardet/__init__.py", line 30, in detect

    u.feed(aBuf)

  File "/usr/lib/python2.6/site-packages/chardet/universaldetector.py", line 108, in feed

    if self._highBitDetector.search(aBuf):

TypeError: expected string or buffer

>>> chardet.detect(str(p))

{'confidence': 1.0, 'encoding': 'ascii'}

>>> print type(dd)

<type 'str'>

>>> print dd.decode('unicode_escape')

['', 'ˉ']

>>> print type(dd.decode('unicode_escape'))

<type 'unicode'>

>>> dd

"['\\xe6\\x88\\x91', '\\xe6\\x98\\xaf']"

>>> print dd

['\xe6\x88\x91', '\xe6\x98\xaf']

>>> print dd.encode('raw_unicode_escape')

['\xe6\x88\x91', '\xe6\x98\xaf']

>>> print type(dd.encode('raw_unicode_escape'))

<type 'str'>

>>> print type(dd.encode('raw_unicode_escape').decode('utf-8'))

<type 'unicode'>

>>> print type(dd.encode('raw_unicode_escape').decode('utf-8')

... )

<type 'unicode'>

>>> print dd

['\xe6\x88\x91', '\xe6\x98\xaf']

>>> print dd, type(dd)

['\xe6\x88\x91', '\xe6\x98\xaf'] <type 'str'>

>>> print dd.encode('raw_unicode_escape'), type(dd.encode('raw_unicode_escape'))

['\xe6\x88\x91', '\xe6\x98\xaf'] <type 'str'>

>>> print dd.decode('utf-8'), type(dd.decode('utf-8')

... )

['\xe6\x88\x91', '\xe6\x98\xaf'] <type 'unicode'>

>>> print dd.decode('utf-8')

['\xe6\x88\x91', '\xe6\x98\xaf']

>>> print dd

['\xe6\x88\x91', '\xe6\x98\xaf']

>>> print ee

Traceback (most recent call last):

  File "<stdin>", line 1, in <module>

NameError: name 'ee' is not defined

>>> ee = u"dd"

>>> ee = u"['\xe6\x88\x91', '\xe6\x98\xaf']"

>>> print ee

['', 'ˉ']

>>> ee

u"['\xe6\x88\x91', '\xe6\x98\xaf']"

>>> ee = [u'中国', u'复兴']

>>> type(ee)

<type 'list'>

>>> print ee

[u'\u4e2d\u56fd', u'\u590d\u5174']

>>> print str(ee)

[u'\u4e2d\u56fd', u'\u590d\u5174']

>>> printee

Traceback (most recent call last):

  File "<stdin>", line 1, in <module>

NameError: name 'printee' is not defined

>>> print ee

[u'\u4e2d\u56fd', u'\u590d\u5174']

>>> print json.dumps(ee).decode('unicode_escape')

Traceback (most recent call last):

  File "<stdin>", line 1, in <module>

NameError: name 'json' is not defined

>>> import json

>>> print json.dumps(ee).decode('unicode_escape')

["中国", "复兴"]

>>> print str(ee).decode('unicode_escape')       

[u'中国', u'复兴']

>>> x = '中国'

>>> print x

中国

>>> x

'\xe4\xb8\xad\xe5\x9b\xbd'

>>> type(x)

<type 'str'>

>>> chardet.detect(x)

{'confidence': 0.75249999999999995, 'encoding': 'utf-8'}

>>> y = x.decode('utf-8')

>>> y

u'\u4e2d\u56fd'

>>> print y

中国

>>> chardet.detect(y)    

Traceback (most recent call last):

  File "<stdin>", line 1, in <module>

  File "/usr/lib/python2.6/site-packages/chardet/__init__.py", line 25, in detect

    raise ValueError('Expected a bytes object, not a unicode object')

ValueError: Expected a bytes object, not a unicode object

>>> x

'\xe4\xb8\xad\xe5\x9b\xbd'

>>> x = '\xe4\xb8\xad\xe5\x9b\xbd'

>>> print x

中国

>>> x

'\xe4\xb8\xad\xe5\x9b\xbd'

>>> x = u'\xe4\xb8\xad\xe5\x9b\xbd'

>>> print x

-

>>> x.decode('utf-8')

u'\xe4\xb8\xad\xe5\x9b\xbd'

>>> print x.decode('utf-8')

-

>>> chardet.detect(x)

Traceback (most recent call last):

  File "<stdin>", line 1, in <module>

  File "/usr/lib/python2.6/site-packages/chardet/__init__.py", line 25, in detect

    raise ValueError('Expected a bytes object, not a unicode object')

ValueError: Expected a bytes object, not a unicode object

>>> print type(x)

<type 'unicode'>

>>> x

u'\xe4\xb8\xad\xe5\x9b\xbd'

>>> pirnt x

  File "<stdin>", line 1

    pirnt x

          ^

SyntaxError: invalid syntax

>>> print x

-

>>> print x.encode('raw_unicode_escape')

中国

>>> y = x.encode('raw_unicode_escape')  

>>> y

'\xe4\xb8\xad\xe5\x9b\xbd'

>>> type y

  File "<stdin>", line 1

    type y

         ^

SyntaxError: invalid syntax

>>> type(y)

<type 'str'>

>>> print y

中国

>>> chardet.detect(y)

{'confidence': 0.75249999999999995, 'encoding': 'utf-8'}

>>> z = y.encode('utf-8')

>>> print z

中国

>>> z 

'\xe4\xb8\xad\xe5\x9b\xbd'

>>> y

'\xe4\xb8\xad\xe5\x9b\xbd'

>>> type(z)

<type 'str'>

>>> type(y)

<type 'str'>

>>> chardet.detect(y)    

{'confidence': 0.75249999999999995, 'encoding': 'utf-8'}

>>> y

'\xe4\xb8\xad\xe5\x9b\xbd'

>>> z = y.encode('utf-8')

>>> z = y.decode('utf-8')

>>> z

u'\u4e2d\u56fd'

>>> print z

中国

>>> type(z)

<type 'unicode'>

>>> a 

u'\xe4\xb8\xad\xe5\x9b\xbd'

>>> f='\u53eb\u6211'  

>>> print f

\u53eb\u6211

>>> f

'\\u53eb\\u6211'

>>> type(f)

<type 'str'>

>>> chardet.detect(f)

{'confidence': 1.0, 'encoding': 'ascii'}

>>> f.decode('ascii')

u'\\u53eb\\u6211'

>>> print f.decode('ascii')

\u53eb\u6211

>>> f.decode('unicode_escape')

u'\u53eb\u6211'

>>> print f.decode('unicode_escape')

叫我

>>> sys.getdefaultencoding()

'utf-8'

>>> dd = { 'name': u'功夫熊猫' }

>>> print dd

{'name': u'\u529f\u592b\u718a\u732b'}

>>> dd

{'name': u'\u529f\u592b\u718a\u732b'}

>>> dd2 = { 'name': '功夫熊猫' }

>>> dd2

{'name': '\xe5\x8a\x9f\xe5\xa4\xab\xe7\x86\x8a\xe7\x8c\xab'}

>>> print simplejson.dumps(dd, ensure_ascii=False)

Traceback (most recent call last):

  File "<stdin>", line 1, in <module>

NameError: name 'simplejson' is not defined

>>> print json.dumps(dd, ensure_ascii=False)      

{"name": "功夫熊猫"}

>>> print json.dumps(dd2, ensure_ascii=False)

{"name": "功夫熊猫"}

>>> print dd2

{'name': '\xe5\x8a\x9f\xe5\xa4\xab\xe7\x86\x8a\xe7\x8c\xab'}

>>>