# Function: OpenRead(file)

# A text file can be encoded using:
#   (1) The default operating system code page, Or
#   (2) utf8 with a BOM header
#
#  If a text file is encoded with utf8, and does not have a BOM header,
#  the user can manually add a BOM header to the text file
#  using a text editor such as notepad++, and rerun the python script,
#  otherwise the file is read as a codepage file with the 
#  invalid codepage characters removed

import sys
if int(sys.version[0]) != 3:
    print('Aborted: Python 3.x required')
    sys.exit(1)

def bomType(file):
    """
    returns file encoding string for open() function

    EXAMPLE:
        bom = bomtype(file)
        open(file, encoding=bom, errors='ignore')
    """

    f = open(file, 'rb')
    b = f.read(4)
    f.close()

    if (b[0:3] == b'\xef\xbb\xbf'):
        return "utf8"

    # Python automatically detects endianess if utf-16 bom is present
    # write endianess generally determined by endianess of CPU
    if ((b[0:2] == b'\xfe\xff') or (b[0:2] == b'\xff\xfe')):
        return "utf16"

    if ((b[0:5] == b'\xfe\xff\x00\x00') 
              or (b[0:5] == b'\x00\x00\xff\xfe')):
        return "utf32"

    # If BOM is not provided, then assume its the codepage
    #     used by your operating system
    return "cp1252"
    # For the United States its: cp1252


def OpenRead(file):
    bom = bomType(file)
    return open(file, 'r', encoding=bom, errors='ignore')


#######################
# Testing it
#######################
fout = open("myfile1.txt", "w", encoding="cp1252")
fout.write("* hi there (cp1252)")
fout.close()

fout = open("myfile2.txt", "w", encoding="utf8")
fout.write("\u2022 hi there (utf8)")
fout.close()

# this case is still treated like codepage cp1252
#   (User responsible for making sure that all utf8 files
#   have a BOM header)
fout = open("badboy.txt", "wb")
fout.write(b"hi there.  barf(\x81\x8D\x90\x9D)")
fout.close()

# Read Example file with Bom Detection
fin = OpenRead("myfile1.txt")
L = fin.readline()
print(L)
fin.close()

# Read Example file with Bom Detection
fin = OpenRead("myfile2.txt")
L =fin.readline() 
print(L) #requires QtConsole to view, Cmd.exe is cp1252
fin.close()

# Read CP1252 with a few undefined chars without barfing
fin = OpenRead("badboy.txt")
L =fin.readline() 
print(L)
fin.close()

# Check that bad characters are still in badboy codepage file
fin = open("badboy.txt", "rb")
fin.read(20)
fin.close()

下面是一个读取并接受一个chardet编码预测的例子，如果它很大，则从文件中读取n_lines。

Chardet还提供了它的编码预测的概率(即置信度)(还没有看到他们是如何提出的)，它与Chardet .predict()的预测一起返回，所以如果你喜欢，你可以以某种方式使用它。

import chardet
from pathlib import Path

def predict_encoding(file_path: Path, n_lines: int=20) -> str:
    '''Predict a file's encoding using chardet'''

    # Open the file as binary data
    with Path(file_path).open('rb') as f:
        # Join binary lines for specified number of lines
        rawdata = b''.join([f.readline() for _ in range(n_lines)])

    return chardet.detect(rawdata)['encoding']

一些文本文件知道它们的编码，大多数则不是。意识到:

具有BOM的文本文件 XML文件以UTF-8编码或其编码在序言中给出 JSON文件总是用UTF-8编码

没有意识到:

CSV文件 任意文本文件

有些编码是通用的，即它们可以解码任何字节序列，有些则不是。US-ASCII不是万能的，因为任何大于127的字节都不能映射到任何字符。UTF-8不是万能的，因为任何字节序列都是无效的。

相反，Latin-1, Windows-1252等是通用的(即使一些字节没有正式映射到一个字符):

>>> [b.to_bytes(1, 'big').decode("latin-1") for b in range(256)]
['\x00', ..., 'ÿ']

给定一个以字节序列编码的随机文本文件，除非该文件知道其编码，否则无法确定其编码，因为有些编码是通用的。但有时可以排除非通用编码。所有通用编码仍然是可能的。chardet模块使用字节的频率来猜测哪种编码最适合已编码的文本。

如果你不想使用这个模块或类似的模块，这里有一个简单的方法:

检查文件是否知道其编码(BOM) 检查非通用编码并接受第一个可以解码字节的编码(ASCII在UTF-8之前，因为它更严格) 选择一个回退编码。

如果您只检查一个示例，那么第二步有点风险，因为文件其余部分中的某些字节可能是无效的。

代码:

def guess_encoding(data: bytes, fallback: str = "iso8859_15") -> str:
    """
    A basic encoding detector.
    """
    for bom, encoding in [
        (codecs.BOM_UTF32_BE, "utf_32_be"),
        (codecs.BOM_UTF32_LE, "utf_32_le"),
        (codecs.BOM_UTF16_BE, "utf_16_be"),
        (codecs.BOM_UTF16_LE, "utf_16_le"),
        (codecs.BOM_UTF8, "utf_8_sig"),
    ]:
        if data.startswith(bom):
            return encoding

    if all(b < 128 for b in data):
        return "ascii"  # you may want to use the fallback here if data is only a sample.

    decoder = codecs.getincrementaldecoder("utf_8")()
    try:
        decoder.decode(data, final=False)
    except UnicodeDecodeError:
        return fallback
    else:
        return "utf_8"  # not certain if data is only a sample

记住，非通用编码可能会失败。decode方法的errors参数可以设置为'ignore'， 'replace'或'backslashreplace'以避免异常。

这个网站有python代码识别ascii，编码bom和utf8 no bom: https://unicodebook.readthedocs.io/guess_encoding.html。将文件读入字节数组(data): http://www.codecodex.com/wiki/Read_a_file_into_a_byte_array。举个例子。我在osx。

#!/usr/bin/python                                                                                                  

import sys

def isUTF8(data):
    try:
        decoded = data.decode('UTF-8')
    except UnicodeDecodeError:
        return False
    else:
        for ch in decoded:
            if 0xD800 <= ord(ch) <= 0xDFFF:
                return False
        return True

def get_bytes_from_file(filename):
    return open(filename, "rb").read()

filename = sys.argv[1]
data = get_bytes_from_file(filename)
result = isUTF8(data)
print(result)


PS /Users/js> ./isutf8.py hi.txt                                                                                     
True

很久以前，我有这样的需求。

阅读我的旧代码，我发现了这个:

    import urllib.request
    import chardet
    import os
    import settings

    [...]
    file = 'sources/dl/file.csv'
    media_folder = settings.MEDIA_ROOT
    file = os.path.join(media_folder, str(file))
    if os.path.isfile(file):
        file_2_test = urllib.request.urlopen('file://' + file).read()
        encoding = (chardet.detect(file_2_test))['encoding']
        return encoding

这为我工作，并返回ascii

这可能会有帮助

from bs4 import UnicodeDammit
with open('automate_data/billboard.csv', 'rb') as file:
   content = file.read()

suggestion = UnicodeDammit(content)
suggestion.original_encoding
#'iso-8859-1'