Question

我是Python新手，我对如何使用Python读取和写入CSV文件有疑问。我的文件包含德国，法语等。根据我的代码，可以在Python中正确读取文件，但是当我将其写入新的CSV文件时，unicode会变成一些奇怪的字符。

数据如下： enter image description here

我的代码是：

import csv

f=open('xxx.csv','rb')
reader=csv.reader(f)

wt=open('lll.csv','wb')
writer=csv.writer(wt,quoting=csv.QUOTE_ALL)

wt.close()
f.close()

结果如下： enter image description here

请您告诉我应该怎样做才能解决问题？非常感谢你！

Answer 1

确保您根据需要进行编码和解码。

此示例将utf-8中的一些示例文本往返到csv文件并返回演示：

# -*- coding: utf-8 -*-
import csv

tests={'German': [u'Straße',u'auslösen',u'zerstören'], 
       'French': [u'français',u'américaine',u'épais'], 
       'Chinese': [u'中國的',u'英語',u'美國人']}

with open('/tmp/utf.csv','w') as fout:
    writer=csv.writer(fout)    
    writer.writerows([tests.keys()])
    for row in zip(*tests.values()):
        row=[s.encode('utf-8') for s in row]
        writer.writerows([row])

with open('/tmp/utf.csv','r') as fin:
    reader=csv.reader(fin)
    for row in reader:
        temp=list(row)
        fmt=u'{:<15}'*len(temp)
        print fmt.format(*[s.decode('utf-8') for s in temp])

打印：

German         Chinese        French         
Straße         中國的            français       
auslösen       英語             américaine     
zerstören      美國人            épais

Answer 2

另一种选择：

使用unicodecsv包中的代码...

https://pypi.python.org/pypi/unicodecsv/

>>> import unicodecsv as csv
>>> from io import BytesIO
>>> f = BytesIO()
>>> w = csv.writer(f, encoding='utf-8')
>>> _ = w.writerow((u'é', u'ñ'))
>>> _ = f.seek(0)
>>> r = csv.reader(f, encoding='utf-8')
>>> next(r) == [u'é', u'ñ']
True

此模块与STDLIB csv模块API兼容。

Answer 3

csv module documentation末尾有一个例子，演示了如何处理Unicode。以下是直接从example复制的。请注意，读取或写入的字符串将是Unicode字符串。例如，不要将字节字符串传递给UnicodeWriter.writerows。

import csv,codecs,cStringIO

class UTF8Recoder:
    def __init__(self, f, encoding):
        self.reader = codecs.getreader(encoding)(f)
    def __iter__(self):
        return self
    def next(self):
        return self.reader.next().encode("utf-8")

class UnicodeReader:
    def __init__(self, f, dialect=csv.excel, encoding="utf-8-sig", **kwds):
        f = UTF8Recoder(f, encoding)
        self.reader = csv.reader(f, dialect=dialect, **kwds)
    def next(self):
        '''next() -> unicode
        This function reads and returns the next line as a Unicode string.
        '''
        row = self.reader.next()
        return [unicode(s, "utf-8") for s in row]
    def __iter__(self):
        return self

class UnicodeWriter:
    def __init__(self, f, dialect=csv.excel, encoding="utf-8-sig", **kwds):
        self.queue = cStringIO.StringIO()
        self.writer = csv.writer(self.queue, dialect=dialect, **kwds)
        self.stream = f
        self.encoder = codecs.getincrementalencoder(encoding)()
    def writerow(self, row):
        '''writerow(unicode) -> None
        This function takes a Unicode string and encodes it to the output.
        '''
        self.writer.writerow([s.encode("utf-8") for s in row])
        data = self.queue.getvalue()
        data = data.decode("utf-8")
        data = self.encoder.encode(data)
        self.stream.write(data)
        self.queue.truncate(0)

    def writerows(self, rows):
        for row in rows:
            self.writerow(row)

with open('xxx.csv','rb') as fin, open('lll.csv','wb') as fout:
    reader = UnicodeReader(fin)
    writer = UnicodeWriter(fout,quoting=csv.QUOTE_ALL)
    for line in reader:
        writer.writerow(line)

输入（UTF-8编码）：

American,美国人
French,法国人
German,德国人

输出：

"American","美国人"
"French","法国人"
"German","德国人"

Answer 4

因为python2中的str实际上是bytes。因此，如果要将unicode写到csv，则必须使用unicode编码将str编码为utf-8。

def py2_unicode_to_str(u):
    # unicode is only exist in python2
    assert isinstance(u, unicode)
    return u.encode('utf-8')

使用class csv.DictWriter(csvfile, fieldnames, restval='', extrasaction='raise', dialect='excel', *args, **kwds)：

py2
- csvfile：open(fp, 'w')
- 通过bytes编码的utf-8中的键和值
  - writer.writerow({py2_unicode_to_str(k): py2_unicode_to_str(v) for k,v in row.items()})
py3
- csvfile：open(fp, 'w')
- 通过普通词典将str作为row至writer.writerow(row)

最终代码

import sys

is_py2 = sys.version_info[0] == 2

def py2_unicode_to_str(u):
    # unicode is only exist in python2
    assert isinstance(u, unicode)
    return u.encode('utf-8')

with open('file.csv', 'w') as f:
    if is_py2:
        data = {u'Python中国': u'Python中国', u'Python中国2': u'Python中国2'}

        # just one more line to handle this
        data = {py2_unicode_to_str(k): py2_unicode_to_str(v) for k, v in data.items()}

        fields = list(data[0])
        writer = csv.DictWriter(f, fieldnames=fields)

        for row in data:
            writer.writerow(row)
    else:
        data = {'Python中国': 'Python中国', 'Python中国2': 'Python中国2'}

        fields = list(data[0])
        writer = csv.DictWriter(f, fieldnames=fields)

        for row in data:
            writer.writerow(row)

结论

在python3中，只需使用Unicode str。

在python2中，使用unicode处理文本，在发生I / O时使用str。

Answer 5

我遇到了同样的问题。答案是你已经做对了。这是MS Excel的问题。尝试使用其他编辑器打开文件，您会注意到您的编码已经成功。要使MS Excel满意，请从UTF-8转换为UTF-16。这应该有效：

class UnicodeWriter:
def __init__(self, f, dialect=csv.excel_tab, encoding="utf-16", **kwds):
    # Redirect output to a queue
    self.queue = StringIO.StringIO()
    self.writer = csv.writer(self.queue, dialect=dialect, **kwds)
    self.stream = f

    # Force BOM
    if encoding=="utf-16":
        import codecs
        f.write(codecs.BOM_UTF16)

    self.encoding = encoding

def writerow(self, row):
    # Modified from original: now using unicode(s) to deal with e.g. ints
    self.writer.writerow([unicode(s).encode("utf-8") for s in row])
    # Fetch UTF-8 output from the queue ...
    data = self.queue.getvalue()
    data = data.decode("utf-8")
    # ... and reencode it into the target encoding
    data = data.encode(self.encoding)

    # strip BOM
    if self.encoding == "utf-16":
        data = data[2:]

    # write to the target stream
    self.stream.write(data)
    # empty queue
    self.queue.truncate(0)

def writerows(self, rows):
    for row in rows:
        self.writerow(row)

Answer 6

我无法对上面的Mark做出回应，但我只做了一次修改，修正了单元格中的数据不是unicode，即float或int数据时导致的错误。我将此行替换为UnicodeWriter函数：“self.writer.writerow（[s.encode（”utf-8“）if type（s）== types.UnicodeType else s for s in row]）” ：

class UnicodeWriter:
    def __init__(self, f, dialect=csv.excel, encoding="utf-8-sig", **kwds):
       self.queue = cStringIO.StringIO()
        self.writer = csv.writer(self.queue, dialect=dialect, **kwds)
        self.stream = f
        self.encoder = codecs.getincrementalencoder(encoding)()
    def writerow(self, row):
        '''writerow(unicode) -> None
        This function takes a Unicode string and encodes it to the output.
        '''
        self.writer.writerow([s.encode("utf-8") if type(s)==types.UnicodeType else s for s in row])
        data = self.queue.getvalue()
        data = data.decode("utf-8")
        data = self.encoder.encode(data)
        self.stream.write(data)
        self.queue.truncate(0)

    def writerows(self, rows):
        for row in rows:
            self.writerow(row)

您还需要“导入类型”。

使用Python 2.7读取和写入CSV文件，包括unicode

6 个答案:

结论