获取 Python 可以编码的所有编码的列表

我正在编写一个脚本，该脚本将尝试将字节编码到 Python 2.6中的许多不同编码中。有没有什么方法可以得到一个可用编码的列表，我可以迭代？

我尝试这样做的原因是因为用户有一些没有正确编码的文本。有很多有趣的角色。我知道是哪个 Unicode字符搞砸了。我希望能够给他们一个类似于“您的文本编辑器将字符串解释为 X 编码，而不是 Y 编码”的答案。我想我会尝试用一种编码方式对这个字符进行编码，然后再用另一种编码方式对它进行解码，看看我们是否得到了相同的字符序列。

例如:

for encoding1, encoding2 in itertools.permutation(encodinglist(), 2):
try:
unicode_string = my_unicode_character.encode(encoding1).decode(encoding2)
except:
pass
93433 次浏览
小开

You could use a technique to list all modules in the encodings package.

import pkgutil
import encodings


false_positives = set(["aliases"])


found = set(name for imp, name, ispkg in pkgutil.iter_modules(encodings.__path__) if not ispkg)
found.difference_update(false_positives)
print found
小开

I doubt there is such method/functionality in codecs module, but if you see encoding/__init__.py, search function searches thru encodings modules folder, so you may do the same e.g.

>>> os.listdir(os.path.dirname(encodings.__file__))
['cp500.pyc', 'utf_16_le.py', 'gb18030.py', 'mbcs.pyc', 'undefined.pyc', 'idna.pyc', 'punycode.pyc', 'cp850.py', 'big5hkscs.pyc', 'mac_arabic.py', '__init__.pyc', 'string_escape.py', 'hz.py', 'cp037.py', 'cp737.py', 'iso8859_5.pyc', 'iso8859_13.pyc', 'cp861.pyc', 'cp862.py', 'iso8859_9.pyc', 'cp949.py', 'base64_codec.pyc', 'koi8_r.py', 'iso8859_2.py', 'ptcp154.pyc', 'uu_codec.pyc', 'mac_croatian.pyc', 'charmap.pyc', 'iso8859_15.pyc', 'euc_jp.py', 'cp1250.py', 'iso8859_10.pyc', 'koi8_r.pyc', 'unicode_escape.pyc', 'cp863.pyc', 'iso8859_4.pyc', 'cp852.py', 'unicode_internal.py', 'big5hkscs.py', 'cp1257.pyc', 'cp1254.py', 'shift_jisx0213.py', 'shift_jis.pyc', 'cp869.pyc', 'hp_roman8.py', 'iso8859_4.py', 'cp775.py', 'cp1251.py', 'mac_cyrillic.pyc', 'mac_greek.pyc', 'mac_roman.pyc', 'iso8859_11.pyc', 'iso8859_6.py', 'utf_8_sig.py', 'iso8859_3.py', 'iso2022_jp_1.py', 'ascii.py', 'cp1026.pyc', 'cp1250.pyc', 'cp950.py', 'raw_unicode_escape.py', 'euc_jis_2004.pyc', 'cp775.pyc', 'euc_kr.py', 'mac
_greek.py', 'big5.pyc', 'shift_jis_2004.pyc', 'gbk.pyc', 'cp1254.pyc', 'cp1255.pyc', 'cp855.pyc', 'string_escape.pyc', 'cp949.pyc', 'cp1258.pyc', 'iso8859_3.pyc', 'mac_iceland.pyc', 'cp1251.pyc', 'cp860.py', 'cp856.py', 'cp874.py', 'iso2022_kr.py', 'cp856.pyc', 'rot_13.py', 'palmos.py', 'iso2022_jp_2.pyc', 'mac_farsi.py', 'koi8_u.pyc', 'cp1256.py', 'iso8859_10.py', 'tis_620.py', 'iso8859_14.pyc', 'cp1253.py', 'cp1258.py', 'cp437.py', 'cp862.pyc', 'mac_turkish.py', 'undefined.py', 'euc_kr.pyc', 'gb18030.pyc', 'aliases.pyc', 'iso8859_9.py', 'uu_codec.py', 'gbk.py', 'quopri_codec.pyc', 'iso8859_7.py', 'mac_iceland.py', 'iso8859_2.pyc', 'euc_jis_2004.py', 'iso2022_jp_3.pyc', 'cp874.pyc', '__init__.py', 'mac_roman.py', 'iso8859_16.py', 'cp866.py', 'unicode_internal.pyc', 'mac_turkish.pyc', 'johab.pyc', 'cp037.pyc', 'punycode.py', 'cp1253.pyc', 'euc_jisx0213.pyc', 'iso2022_jp_2004.pyc', 'iso2022_kr.pyc', 'zlib_codec.pyc', 'cp932.py', 'cp1255.py', 'iso2022_jp_1.pyc', 'cp857.pyc', 'cp424.pyc',
'iso2022_jp_2.py', 'iso2022_jp.pyc', 'mbcs.py', 'utf_8.py', 'palmos.pyc', 'cp1252.pyc', 'aliases.py', 'quopri_codec.py', 'latin_1.pyc', 'iso2022_jp.py', 'zlib_codec.py', 'cp1026.py', 'cp860.pyc', 'cp1252.py', 'hex_codec.pyc', 'iso8859_1.pyc', 'cp850.pyc', 'cp861.py', 'iso8859_15.py', 'cp865.pyc', 'hp_roman8.pyc', 'iso8859_7.pyc', 'mac_latin2.py', 'iso8859_11.py', 'mac_centeuro.pyc', 'iso8859_6.pyc', 'ascii.pyc', 'mac_centeuro.py', 'iso2022_jp_3.py', 'bz2_codec.py', 'mac_arabic.pyc', 'euc_jisx0213.py', 'tis_620.pyc', 'shift_jis_2004.py', 'utf_8.pyc', 'cp855.py', 'mac_romanian.pyc', 'iso8859_8.py', 'cp869.py', 'ptcp154.py', 'utf_16_be.py', 'iso2022_jp_ext.pyc', 'bz2_codec.pyc', 'base64_codec.py', 'latin_1.py', 'charmap.py', 'hz.pyc', 'cp950.pyc', 'cp875.pyc', 'cp1006.pyc', 'utf_16.py', 'shift_jisx0213.pyc', 'cp424.py', 'cp932.pyc', 'iso8859_5.py', 'mac_romanian.py', 'utf_8_sig.pyc', 'iso8859_1.py', 'cp875.py', 'cp437.pyc', 'cp865.py', 'utf_7.py', 'utf_16_be.pyc', 'rot_13.pyc', 'euc_jp.p
yc', 'raw_unicode_escape.pyc', 'iso8859_8.pyc', 'utf_16.pyc', 'iso8859_14.py', 'iso8859_16.pyc', 'cp852.pyc', 'cp737.pyc', 'mac_croatian.py', 'mac_latin2.pyc', 'iso2022_jp_ext.py', 'cp1140.py', 'mac_cyrillic.py', 'cp1257.py', 'cp500.py', 'cp1140.pyc', 'shift_jis.py', 'unicode_escape.py', 'cp864.py', 'cp864.pyc', 'cp857.py', 'hex_codec.py', 'mac_farsi.pyc', 'idna.py', 'johab.py', 'utf_7.pyc', 'cp863.py', 'iso8859_13.py', 'koi8_u.py', 'gb2312.pyc', 'cp1256.pyc', 'cp866.pyc', 'iso2022_jp_2004.py', 'utf_16_le.pyc', 'gb2312.py', 'cp1006.py', 'big5.py']

but as anybody can register a codec, so that won't be exhaustive list.

小开

Probably you can do this:

from encodings.aliases import aliases
print aliases.keys()
小开
最佳答案

Unfortunately encodings.aliases.aliases.keys() is NOT an appropriate answer.

aliases(as one would/should expect) contains several cases where different keys are mapped to the same value e.g. 1252 and windows_1252 are both mapped to cp1252. You could save time if instead of aliases.keys() you use set(aliases.values()).

BUT THERE'S A WORSE PROBLEM: aliases doesn't contain codecs that don't have aliases (like cp856, cp874, cp875, cp737, and koi8_u).

>>> from encodings.aliases import aliases
>>> def find(q):
...     return [(k,v) for k, v in aliases.items() if q in k or q in v]
...
>>> find('1252') # multiple aliases
[('1252', 'cp1252'), ('windows_1252', 'cp1252')]
>>> find('856') # no codepage 856 in aliases
[]
>>> find('koi8') # no koi8_u in aliases
[('cskoi8r', 'koi8_r')]
>>> 'x'.decode('cp856') # but cp856 is a valid codec
u'x'
>>> 'x'.decode('koi8_u') # but koi8_u is a valid codec
u'x'
>>>

It's also worth noting that however you obtain a full list of codecs, it may be a good idea to ignore the codecs that aren't about encoding/decoding character sets, but do some other transformation e.g. zlib, quopri, and base64.

Which brings us to the question of WHY you want to "try encoding bytes into many different encodings". If we know that, we may be able to steer you in the right direction.

For a start, that's ambiguous. One DEcodes bytes into unicode, and one ENcodes unicode into bytes. Which do you want to do?

What are you really trying to achieve: Are you trying to determine which codec to use to decode some incoming bytes, and plan to attempt this with all possible codecs? [note: latin1 will decode anything] Are you trying to determine the language of some unicode text by trying to encode it with all possible codecs? [note: utf8 will encode anything].

小开

Maybe you should try using the Universal Encoding Detector (chardet) library instead of implementing it yourself.

>>> import chardet
>>> s = '\xe2\x98\x83' # ☃
>>> chardet.detect(s)
{'confidence': 0.505, 'encoding': 'utf-8'}
小开

The Python source code has a script at Tools/unicode/listcodecs.py which lists all codecs.

Among the listed codecs, however, there are some that are not Unicode-to-byte converters, like base64_codec, quopri_codec and bz2_codec, as @John Machin pointed out.

小开

Other answers here seem to indicate that constructing this list programmatically is difficult and fraught with traps. However, doing so is probably unnecessary since the documentation contains a complete list of the standard encodings Python supports, and has done since Python 2.3.

You can find these lists (for each stable version of the language so far released) at:

Below are the lists for each documented version of Python. Note that if you want backwards-compatibility rather than just supporting a particular version of Python, you can just copy the list from the latest Python version and check whether each encoding exists in the Python running your program before trying to use it.

Python 2.3 (59 encodings)

['ascii',
'cp037',
'cp424',
'cp437',
'cp500',
'cp737',
'cp775',
'cp850',
'cp852',
'cp855',
'cp856',
'cp857',
'cp860',
'cp861',
'cp862',
'cp863',
'cp864',
'cp865',
'cp869',
'cp874',
'cp875',
'cp1006',
'cp1026',
'cp1140',
'cp1250',
'cp1251',
'cp1252',
'cp1253',
'cp1254',
'cp1255',
'cp1256',
'cp1257',
'cp1258',
'latin_1',
'iso8859_2',
'iso8859_3',
'iso8859_4',
'iso8859_5',
'iso8859_6',
'iso8859_7',
'iso8859_8',
'iso8859_9',
'iso8859_10',
'iso8859_13',
'iso8859_14',
'iso8859_15',
'koi8_r',
'koi8_u',
'mac_cyrillic',
'mac_greek',
'mac_iceland',
'mac_latin2',
'mac_roman',
'mac_turkish',
'utf_16',
'utf_16_be',
'utf_16_le',
'utf_7',
'utf_8']

Python 2.4 (85 encodings)

['ascii',
'big5',
'big5hkscs',
'cp037',
'cp424',
'cp437',
'cp500',
'cp737',
'cp775',
'cp850',
'cp852',
'cp855',
'cp856',
'cp857',
'cp860',
'cp861',
'cp862',
'cp863',
'cp864',
'cp865',
'cp866',
'cp869',
'cp874',
'cp875',
'cp932',
'cp949',
'cp950',
'cp1006',
'cp1026',
'cp1140',
'cp1250',
'cp1251',
'cp1252',
'cp1253',
'cp1254',
'cp1255',
'cp1256',
'cp1257',
'cp1258',
'euc_jp',
'euc_jis_2004',
'euc_jisx0213',
'euc_kr',
'gb2312',
'gbk',
'gb18030',
'hz',
'iso2022_jp',
'iso2022_jp_1',
'iso2022_jp_2',
'iso2022_jp_2004',
'iso2022_jp_3',
'iso2022_jp_ext',
'iso2022_kr',
'latin_1',
'iso8859_2',
'iso8859_3',
'iso8859_4',
'iso8859_5',
'iso8859_6',
'iso8859_7',
'iso8859_8',
'iso8859_9',
'iso8859_10',
'iso8859_13',
'iso8859_14',
'iso8859_15',
'johab',
'koi8_r',
'koi8_u',
'mac_cyrillic',
'mac_greek',
'mac_iceland',
'mac_latin2',
'mac_roman',
'mac_turkish',
'ptcp154',
'shift_jis',
'shift_jis_2004',
'shift_jisx0213',
'utf_16',
'utf_16_be',
'utf_16_le',
'utf_7',
'utf_8']

Python 2.5 (86 encodings)

['ascii',
'big5',
'big5hkscs',
'cp037',
'cp424',
'cp437',
'cp500',
'cp737',
'cp775',
'cp850',
'cp852',
'cp855',
'cp856',
'cp857',
'cp860',
'cp861',
'cp862',
'cp863',
'cp864',
'cp865',
'cp866',
'cp869',
'cp874',
'cp875',
'cp932',
'cp949',
'cp950',
'cp1006',
'cp1026',
'cp1140',
'cp1250',
'cp1251',
'cp1252',
'cp1253',
'cp1254',
'cp1255',
'cp1256',
'cp1257',
'cp1258',
'euc_jp',
'euc_jis_2004',
'euc_jisx0213',
'euc_kr',
'gb2312',
'gbk',
'gb18030',
'hz',
'iso2022_jp',
'iso2022_jp_1',
'iso2022_jp_2',
'iso2022_jp_2004',
'iso2022_jp_3',
'iso2022_jp_ext',
'iso2022_kr',
'latin_1',
'iso8859_2',
'iso8859_3',
'iso8859_4',
'iso8859_5',
'iso8859_6',
'iso8859_7',
'iso8859_8',
'iso8859_9',
'iso8859_10',
'iso8859_13',
'iso8859_14',
'iso8859_15',
'johab',
'koi8_r',
'koi8_u',
'mac_cyrillic',
'mac_greek',
'mac_iceland',
'mac_latin2',
'mac_roman',
'mac_turkish',
'ptcp154',
'shift_jis',
'shift_jis_2004',
'shift_jisx0213',
'utf_16',
'utf_16_be',
'utf_16_le',
'utf_7',
'utf_8',
'utf_8_sig']

Python 2.6 (90 encodings)

['ascii',
'big5',
'big5hkscs',
'cp037',
'cp424',
'cp437',
'cp500',
'cp737',
'cp775',
'cp850',
'cp852',
'cp855',
'cp856',
'cp857',
'cp860',
'cp861',
'cp862',
'cp863',
'cp864',
'cp865',
'cp866',
'cp869',
'cp874',
'cp875',
'cp932',
'cp949',
'cp950',
'cp1006',
'cp1026',
'cp1140',
'cp1250',
'cp1251',
'cp1252',
'cp1253',
'cp1254',
'cp1255',
'cp1256',
'cp1257',
'cp1258',
'euc_jp',
'euc_jis_2004',
'euc_jisx0213',
'euc_kr',
'gb2312',
'gbk',
'gb18030',
'hz',
'iso2022_jp',
'iso2022_jp_1',
'iso2022_jp_2',
'iso2022_jp_2004',
'iso2022_jp_3',
'iso2022_jp_ext',
'iso2022_kr',
'latin_1',
'iso8859_2',
'iso8859_3',
'iso8859_4',
'iso8859_5',
'iso8859_6',
'iso8859_7',
'iso8859_8',
'iso8859_9',
'iso8859_10',
'iso8859_13',
'iso8859_14',
'iso8859_15',
'iso8859_16',
'johab',
'koi8_r',
'koi8_u',
'mac_cyrillic',
'mac_greek',
'mac_iceland',
'mac_latin2',
'mac_roman',
'mac_turkish',
'ptcp154',
'shift_jis',
'shift_jis_2004',
'shift_jisx0213',
'utf_32',
'utf_32_be',
'utf_32_le',
'utf_16',
'utf_16_be',
'utf_16_le',
'utf_7',
'utf_8',
'utf_8_sig']

Python 2.7 (93 encodings)

['ascii',
'big5',
'big5hkscs',
'cp037',
'cp424',
'cp437',
'cp500',
'cp720',
'cp737',
'cp775',
'cp850',
'cp852',
'cp855',
'cp856',
'cp857',
'cp858',
'cp860',
'cp861',
'cp862',
'cp863',
'cp864',
'cp865',
'cp866',
'cp869',
'cp874',
'cp875',
'cp932',
'cp949',
'cp950',
'cp1006',
'cp1026',
'cp1140',
'cp1250',
'cp1251',
'cp1252',
'cp1253',
'cp1254',
'cp1255',
'cp1256',
'cp1257',
'cp1258',
'euc_jp',
'euc_jis_2004',
'euc_jisx0213',
'euc_kr',
'gb2312',
'gbk',
'gb18030',
'hz',
'iso2022_jp',
'iso2022_jp_1',
'iso2022_jp_2',
'iso2022_jp_2004',
'iso2022_jp_3',
'iso2022_jp_ext',
'iso2022_kr',
'latin_1',
'iso8859_2',
'iso8859_3',
'iso8859_4',
'iso8859_5',
'iso8859_6',
'iso8859_7',
'iso8859_8',
'iso8859_9',
'iso8859_10',
'iso8859_11',
'iso8859_13',
'iso8859_14',
'iso8859_15',
'iso8859_16',
'johab',
'koi8_r',
'koi8_u',
'mac_cyrillic',
'mac_greek',
'mac_iceland',
'mac_latin2',
'mac_roman',
'mac_turkish',
'ptcp154',
'shift_jis',
'shift_jis_2004',
'shift_jisx0213',
'utf_32',
'utf_32_be',
'utf_32_le',
'utf_16',
'utf_16_be',
'utf_16_le',
'utf_7',
'utf_8',
'utf_8_sig']

Python 3.0 (89 encodings)

['ascii',
'big5',
'big5hkscs',
'cp037',
'cp424',
'cp437',
'cp500',
'cp737',
'cp775',
'cp850',
'cp852',
'cp855',
'cp856',
'cp857',
'cp860',
'cp861',
'cp862',
'cp863',
'cp864',
'cp865',
'cp866',
'cp869',
'cp874',
'cp875',
'cp932',
'cp949',
'cp950',
'cp1006',
'cp1026',
'cp1140',
'cp1250',
'cp1251',
'cp1252',
'cp1253',
'cp1254',
'cp1255',
'cp1256',
'cp1257',
'cp1258',
'euc_jp',
'euc_jis_2004',
'euc_jisx0213',
'euc_kr',
'gb2312',
'gbk',
'gb18030',
'hz',
'iso2022_jp',
'iso2022_jp_1',
'iso2022_jp_2',
'iso2022_jp_2004',
'iso2022_jp_3',
'iso2022_jp_ext',
'iso2022_kr',
'latin_1',
'iso8859_2',
'iso8859_3',
'iso8859_4',
'iso8859_5',
'iso8859_6',
'iso8859_7',
'iso8859_8',
'iso8859_9',
'iso8859_10',
'iso8859_13',
'iso8859_14',
'iso8859_15',
'johab',
'koi8_r',
'koi8_u',
'mac_cyrillic',
'mac_greek',
'mac_iceland',
'mac_latin2',
'mac_roman',
'mac_turkish',
'ptcp154',
'shift_jis',
'shift_jis_2004',
'shift_jisx0213',
'utf_32',
'utf_32_be',
'utf_32_le',
'utf_16',
'utf_16_be',
'utf_16_le',
'utf_7',
'utf_8',
'utf_8_sig']

Python 3.1 (90 encodings)

['ascii',
'big5',
'big5hkscs',
'cp037',
'cp424',
'cp437',
'cp500',
'cp737',
'cp775',
'cp850',
'cp852',
'cp855',
'cp856',
'cp857',
'cp860',
'cp861',
'cp862',
'cp863',
'cp864',
'cp865',
'cp866',
'cp869',
'cp874',
'cp875',
'cp932',
'cp949',
'cp950',
'cp1006',
'cp1026',
'cp1140',
'cp1250',
'cp1251',
'cp1252',
'cp1253',
'cp1254',
'cp1255',
'cp1256',
'cp1257',
'cp1258',
'euc_jp',
'euc_jis_2004',
'euc_jisx0213',
'euc_kr',
'gb2312',
'gbk',
'gb18030',
'hz',
'iso2022_jp',
'iso2022_jp_1',
'iso2022_jp_2',
'iso2022_jp_2004',
'iso2022_jp_3',
'iso2022_jp_ext',
'iso2022_kr',
'latin_1',
'iso8859_2',
'iso8859_3',
'iso8859_4',
'iso8859_5',
'iso8859_6',
'iso8859_7',
'iso8859_8',
'iso8859_9',
'iso8859_10',
'iso8859_13',
'iso8859_14',
'iso8859_15',
'iso8859_16',
'johab',
'koi8_r',
'koi8_u',
'mac_cyrillic',
'mac_greek',
'mac_iceland',
'mac_latin2',
'mac_roman',
'mac_turkish',
'ptcp154',
'shift_jis',
'shift_jis_2004',
'shift_jisx0213',
'utf_32',
'utf_32_be',
'utf_32_le',
'utf_16',
'utf_16_be',
'utf_16_le',
'utf_7',
'utf_8',
'utf_8_sig']

Python 3.2 (92 encodings)

['ascii',
'big5',
'big5hkscs',
'cp037',
'cp424',
'cp437',
'cp500',
'cp720',
'cp737',
'cp775',
'cp850',
'cp852',
'cp855',
'cp856',
'cp857',
'cp858',
'cp860',
'cp861',
'cp862',
'cp863',
'cp864',
'cp865',
'cp866',
'cp869',
'cp874',
'cp875',
'cp932',
'cp949',
'cp950',
'cp1006',
'cp1026',
'cp1140',
'cp1250',
'cp1251',
'cp1252',
'cp1253',
'cp1254',
'cp1255',
'cp1256',
'cp1257',
'cp1258',
'euc_jp',
'euc_jis_2004',
'euc_jisx0213',
'euc_kr',
'gb2312',
'gbk',
'gb18030',
'hz',
'iso2022_jp',
'iso2022_jp_1',
'iso2022_jp_2',
'iso2022_jp_2004',
'iso2022_jp_3',
'iso2022_jp_ext',
'iso2022_kr',
'latin_1',
'iso8859_2',
'iso8859_3',
'iso8859_4',
'iso8859_5',
'iso8859_6',
'iso8859_7',
'iso8859_8',
'iso8859_9',
'iso8859_10',
'iso8859_13',
'iso8859_14',
'iso8859_15',
'iso8859_16',
'johab',
'koi8_r',
'koi8_u',
'mac_cyrillic',
'mac_greek',
'mac_iceland',
'mac_latin2',
'mac_roman',
'mac_turkish',
'ptcp154',
'shift_jis',
'shift_jis_2004',
'shift_jisx0213',
'utf_32',
'utf_32_be',
'utf_32_le',
'utf_16',
'utf_16_be',
'utf_16_le',
'utf_7',
'utf_8',
'utf_8_sig']

Python 3.3 (93 encodings)

['ascii',
'big5',
'big5hkscs',
'cp037',
'cp424',
'cp437',
'cp500',
'cp720',
'cp737',
'cp775',
'cp850',
'cp852',
'cp855',
'cp856',
'cp857',
'cp858',
'cp860',
'cp861',
'cp862',
'cp863',
'cp864',
'cp865',
'cp866',
'cp869',
'cp874',
'cp875',
'cp932',
'cp949',
'cp950',
'cp1006',
'cp1026',
'cp1140',
'cp1250',
'cp1251',
'cp1252',
'cp1253',
'cp1254',
'cp1255',
'cp1256',
'cp1257',
'cp1258',
'cp65001',
'euc_jp',
'euc_jis_2004',
'euc_jisx0213',
'euc_kr',
'gb2312',
'gbk',
'gb18030',
'hz',
'iso2022_jp',
'iso2022_jp_1',
'iso2022_jp_2',
'iso2022_jp_2004',
'iso2022_jp_3',
'iso2022_jp_ext',
'iso2022_kr',
'latin_1',
'iso8859_2',
'iso8859_3',
'iso8859_4',
'iso8859_5',
'iso8859_6',
'iso8859_7',
'iso8859_8',
'iso8859_9',
'iso8859_10',
'iso8859_13',
'iso8859_14',
'iso8859_15',
'iso8859_16',
'johab',
'koi8_r',
'koi8_u',
'mac_cyrillic',
'mac_greek',
'mac_iceland',
'mac_latin2',
'mac_roman',
'mac_turkish',
'ptcp154',
'shift_jis',
'shift_jis_2004',
'shift_jisx0213',
'utf_32',
'utf_32_be',
'utf_32_le',
'utf_16',
'utf_16_be',
'utf_16_le',
'utf_7',
'utf_8',
'utf_8_sig']

Python 3.4 (96 encodings)

['ascii',
'big5',
'big5hkscs',
'cp037',
'cp273',
'cp424',
'cp437',
'cp500',
'cp720',
'cp737',
'cp775',
'cp850',
'cp852',
'cp855',
'cp856',
'cp857',
'cp858',
'cp860',
'cp861',
'cp862',
'cp863',
'cp864',
'cp865',
'cp866',
'cp869',
'cp874',
'cp875',
'cp932',
'cp949',
'cp950',
'cp1006',
'cp1026',
'cp1125',
'cp1140',
'cp1250',
'cp1251',
'cp1252',
'cp1253',
'cp1254',
'cp1255',
'cp1256',
'cp1257',
'cp1258',
'cp65001',
'euc_jp',
'euc_jis_2004',
'euc_jisx0213',
'euc_kr',
'gb2312',
'gbk',
'gb18030',
'hz',
'iso2022_jp',
'iso2022_jp_1',
'iso2022_jp_2',
'iso2022_jp_2004',
'iso2022_jp_3',
'iso2022_jp_ext',
'iso2022_kr',
'latin_1',
'iso8859_2',
'iso8859_3',
'iso8859_4',
'iso8859_5',
'iso8859_6',
'iso8859_7',
'iso8859_8',
'iso8859_9',
'iso8859_10',
'iso8859_11',
'iso8859_13',
'iso8859_14',
'iso8859_15',
'iso8859_16',
'johab',
'koi8_r',
'koi8_u',
'mac_cyrillic',
'mac_greek',
'mac_iceland',
'mac_latin2',
'mac_roman',
'mac_turkish',
'ptcp154',
'shift_jis',
'shift_jis_2004',
'shift_jisx0213',
'utf_32',
'utf_32_be',
'utf_32_le',
'utf_16',
'utf_16_be',
'utf_16_le',
'utf_7',
'utf_8',
'utf_8_sig']

Python 3.5 (98 encodings)

['ascii',
'big5',
'big5hkscs',
'cp037',
'cp273',
'cp424',
'cp437',
'cp500',
'cp720',
'cp737',
'cp775',
'cp850',
'cp852',
'cp855',
'cp856',
'cp857',
'cp858',
'cp860',
'cp861',
'cp862',
'cp863',
'cp864',
'cp865',
'cp866',
'cp869',
'cp874',
'cp875',
'cp932',
'cp949',
'cp950',
'cp1006',
'cp1026',
'cp1125',
'cp1140',
'cp1250',
'cp1251',
'cp1252',
'cp1253',
'cp1254',
'cp1255',
'cp1256',
'cp1257',
'cp1258',
'cp65001',
'euc_jp',
'euc_jis_2004',
'euc_jisx0213',
'euc_kr',
'gb2312',
'gbk',
'gb18030',
'hz',
'iso2022_jp',
'iso2022_jp_1',
'iso2022_jp_2',
'iso2022_jp_2004',
'iso2022_jp_3',
'iso2022_jp_ext',
'iso2022_kr',
'latin_1',
'iso8859_2',
'iso8859_3',
'iso8859_4',
'iso8859_5',
'iso8859_6',
'iso8859_7',
'iso8859_8',
'iso8859_9',
'iso8859_10',
'iso8859_11',
'iso8859_13',
'iso8859_14',
'iso8859_15',
'iso8859_16',
'johab',
'koi8_r',
'koi8_t',
'koi8_u',
'kz1048',
'mac_cyrillic',
'mac_greek',
'mac_iceland',
'mac_latin2',
'mac_roman',
'mac_turkish',
'ptcp154',
'shift_jis',
'shift_jis_2004',
'shift_jisx0213',
'utf_32',
'utf_32_be',
'utf_32_le',
'utf_16',
'utf_16_be',
'utf_16_le',
'utf_7',
'utf_8',
'utf_8_sig']

Python 3.6 (98 encodings)

Same as previous version.

Python 3.7 (98 encodings)

Same as previous version.

Python 3.8 (97 encodings)

['ascii',
'big5',
'big5hkscs',
'cp037',
'cp273',
'cp424',
'cp437',
'cp500',
'cp720',
'cp737',
'cp775',
'cp850',
'cp852',
'cp855',
'cp856',
'cp857',
'cp858',
'cp860',
'cp861',
'cp862',
'cp863',
'cp864',
'cp865',
'cp866',
'cp869',
'cp874',
'cp875',
'cp932',
'cp949',
'cp950',
'cp1006',
'cp1026',
'cp1125',
'cp1140',
'cp1250',
'cp1251',
'cp1252',
'cp1253',
'cp1254',
'cp1255',
'cp1256',
'cp1257',
'cp1258',
'euc_jp',
'euc_jis_2004',
'euc_jisx0213',
'euc_kr',
'gb2312',
'gbk',
'gb18030',
'hz',
'iso2022_jp',
'iso2022_jp_1',
'iso2022_jp_2',
'iso2022_jp_2004',
'iso2022_jp_3',
'iso2022_jp_ext',
'iso2022_kr',
'latin_1',
'iso8859_2',
'iso8859_3',
'iso8859_4',
'iso8859_5',
'iso8859_6',
'iso8859_7',
'iso8859_8',
'iso8859_9',
'iso8859_10',
'iso8859_11',
'iso8859_13',
'iso8859_14',
'iso8859_15',
'iso8859_16',
'johab',
'koi8_r',
'koi8_t',
'koi8_u',
'kz1048',
'mac_cyrillic',
'mac_greek',
'mac_iceland',
'mac_latin2',
'mac_roman',
'mac_turkish',
'ptcp154',
'shift_jis',
'shift_jis_2004',
'shift_jisx0213',
'utf_32',
'utf_32_be',
'utf_32_le',
'utf_16',
'utf_16_be',
'utf_16_le',
'utf_7',
'utf_8',
'utf_8_sig']

Python 3.9 (97 encodings)

Same as previous version.

Python 3.10 (97 encodings)

Same as previous version.

Python 3.11 (97 encodings)

Same as previous version.

In case they're relevant to anyone's use case, note that the docs also list some Python-specific encodings, many of which seem to be primarily for use by Python's internals or are otherwise weird in some way, like the 'undefined' encoding which always throws an exception if you try to use it. You probably want to ignore these completely if, like the question-asker here, you're trying to figure out what encoding was used for some text you've come across in the real world. As of Python 3.7, the list is as follows:

["idna",
"mbcs",
"oem",
"palmos",
"punycode",
"raw_unicode_escape",
"rot_13",
"undefined",
"unicode_escape",
"unicode_internal",
"base64_codec",
"bz2_codec",
"hex_codec",
"quopri_codec",
"uu_codec",
"zlib_codec"]

Some older Python versions had a string_escape special encoding that I've not included in the above list because it's been removed from the language.

Finally, in case you'd like to update my tables above for a newer version of Python, here's the (crude, not very robust) script I used to generate them:

import re
import requests
import lxml.html
import pprint


previous = None
for version, url in [
('2.3', 'https://docs.python.org/2.3/lib/node130.html'),
('2.4', 'https://docs.python.org/2.4/lib/standard-encodings.html'),
('2.5', 'https://docs.python.org/2.5/lib/standard-encodings.html'),
('2.6', 'https://docs.python.org/2.6/library/codecs.html#standard-encodings'),
('2.7', 'https://docs.python.org/2.7/library/codecs.html#standard-encodings'),
('3.0', 'https://docs.python.org/3.0/library/codecs.html#standard-encodings'),
('3.1', 'https://docs.python.org/3.1/library/codecs.html#standard-encodings'),
('3.2', 'https://docs.python.org/3.2/library/codecs.html#standard-encodings'),
('3.3', 'https://docs.python.org/3.3/library/codecs.html#standard-encodings'),
('3.4', 'https://docs.python.org/3.4/library/codecs.html#standard-encodings'),
('3.5', 'https://docs.python.org/3.5/library/codecs.html#standard-encodings'),
('3.6', 'https://docs.python.org/3.6/library/codecs.html#standard-encodings'),
('3.7', 'https://docs.python.org/3.7/library/codecs.html#standard-encodings'),
('3.8', 'https://docs.python.org/3.8/library/codecs.html#standard-encodings'),
('3.9', 'https://docs.python.org/3.9/library/codecs.html#standard-encodings'),
('3.10', 'https://docs.python.org/3.10/library/codecs.html#standard-encodings'),
('3.11', 'https://docs.python.org/3.11/library/codecs.html#standard-encodings'),
]:
html = requests.get(url).text
# Work-around for weird HTML markup in recent versions of Python documentation:
html = re.sub('<[/]?p>', '', html)
doc = lxml.html.fromstring(html)
standard_encodings_table = doc.xpath(
'//table[preceding::h2[.//text()[contains(., "Standard Encodings")]]][//th/text()="Codec"]'
)[0]
codecs = standard_encodings_table.xpath('.//td[1]/text()')
print("## Python %s (%i encodings)\n" % (version, len(codecs)))
if codecs == previous:
print('_Same as previous version._\n')
else:
print('```python\n' + pprint.pformat(codecs) + '\n```\n')
previous = codecs
小开

Here's a programmatic way to list all the encodings defined in the stdlib encodings package, note that this won't list user defined encodings. This combines some of the tricks in the other answers but actually produces a working list using the codec's canonical name.

import encodings
import pkgutil
import pprint




all_encodings = set()


for _, modname, _ in pkgutil.iter_modules(
encodings.__path__, encodings.__name__ + '.',
):
try:
mod = __import__(modname, fromlist=[str('__trash')])
except (ImportError, LookupError):
# A few encodings are platform specific: mcbs, cp65001
# print('skip {}'.format(modname))
pass


try:
all_encodings.add(mod.getregentry().name)
except AttributeError as e:
# the `aliases` module doensn't actually provide a codec
# print('skip {}'.format(modname))
if 'regentry' not in str(e):
raise


pprint.pprint(sorted(all_encodings))
小开

From Python 3.7.6 Source, under /Tools/unicode/listcodecs.py:

""" List all available codec modules.


(c) Copyright 2005, Marc-Andre Lemburg (mal@lemburg.com).


Licensed to PSF under a Contributor Agreement.


"""


import os, codecs, encodings


_debug = 0


def listcodecs(dir):
names = []
for filename in os.listdir(dir):
if filename[-3:] != '.py':
continue
name = filename[:-3]
# Check whether we've found a true codec
try:
codecs.lookup(name)
except LookupError:
# Codec not found
continue
except Exception as reason:
# Probably an error from importing the codec; still it's
# a valid code name
if _debug:
print('* problem importing codec %r: %s' % \
(name, reason))
names.append(name)
return names




if __name__ == '__main__':
names = listcodecs(encodings.__path__[0])
names.sort()
print('all_codecs = [')
for name in names:
print('    %r,' % name)
print(']')

Then: 

if str(response.encoding) is "undefined" or \
str(response.encoding) not in names:
do_something()  # like set default to utf_8 and execute
pass
小开 
import os
def encodinglist():
r=[]
for i in os.listdir(os.path.split(__import__("encodings").__file__)[0]):
name=os.path.splitext(i)[0]
try:
"".encode(name)
except:
pass
else:
r.append(name.replace("_","-"))
return r

提交答案