csv.DictWriter可以将字典列表写入CSV文件。csv模块无法处理将unicode字符串转换为UTF8。 csv模块文档有一个将所有内容转换为UTF8的示例：
def utf_8_encoder(unicode_csv_data):
for line in unicode_csv_data:
yield line.encode('utf-8')
它还有一个UnicodeWriter类。
但是......如何让DictWriter使用这些？难道他们不必在它的中间注入自己，以便在将它们写入文件之前捕获反汇编的字典并对它们进行编码吗？我不明白。
答案 0 :(得分：84)
更新：第三方unicodecsv模块为您实施这个为期7年的答案。此代码下面的示例。还有一个Python 3解决方案，不需要第三方模块。
原始Python 2答案
如果使用Python 2.7或更高版本，请在传递给DictWriter之前使用dict comprehension将字典重新映射到utf-8：
# coding: utf-8
import csv
D = {'name':u'马克','pinyin':u'mǎkè'}
f = open('out.csv','wb')
f.write(u'\ufeff'.encode('utf8')) # BOM (optional...Excel needs it to open UTF-8 file properly)
w = csv.DictWriter(f,sorted(D.keys()))
w.writeheader()
w.writerow({k:v.encode('utf8') for k,v in D.items()})
f.close()
您可以使用此想法将UnicodeWriter更新为DictUnicodeWriter： #coding：utf-8 导入csv import cStringIO 导入编解码器
class DictUnicodeWriter(object):
def __init__(self, f, fieldnames, dialect=csv.excel, encoding="utf-8", **kwds):
# Redirect output to a queue
self.queue = cStringIO.StringIO()
self.writer = csv.DictWriter(self.queue, fieldnames, dialect=dialect, **kwds)
self.stream = f
self.encoder = codecs.getincrementalencoder(encoding)()
def writerow(self, D):
self.writer.writerow({k:v.encode("utf-8") for k,v in D.items()})
# Fetch UTF-8 output from the queue ...
data = self.queue.getvalue()
data = data.decode("utf-8")
# ... and reencode it into the target encoding
data = self.encoder.encode(data)
# write to the target stream
self.stream.write(data)
# empty queue
self.queue.truncate(0)
def writerows(self, rows):
for D in rows:
self.writerow(D)
def writeheader(self):
self.writer.writeheader()
D1 = {'name':u'马克','pinyin':u'Mǎkè'}
D2 = {'name':u'美国','pinyin':u'Měiguó'}
f = open('out.csv','wb')
f.write(u'\ufeff'.encode('utf8')) # BOM (optional...Excel needs it to open UTF-8 file properly)
w = DictUnicodeWriter(f,sorted(D.keys()))
w.writeheader()
w.writerows([D1,D2])
f.close()
Python 2 unicodecsv示例：
# coding: utf-8
import unicodecsv as csv
D = {u'name':u'马克',u'pinyin':u'mǎkè'}
with open('out.csv','wb') as f:
w = csv.DictWriter(f,fieldnames=sorted(D.keys()),encoding='utf-8-sig')
w.writeheader()
w.writerow(D)
Python 3：
此外，Python 3的内置csv模块本身支持Unicode：
# coding: utf-8
import csv
D = {u'name':u'马克',u'pinyin':u'mǎkè'}
# Use newline='' instead of 'wb' in Python 3.
with open('out.csv','w',encoding='utf-8-sig',newline='') as f:
w = csv.DictWriter(f,fieldnames=sorted(D.keys()))
w.writeheader()
w.writerow(D)
答案 1 :(得分：39)
使用精彩的UnicodeCSV模块有一个简单的解决方法。拥有它之后，只需更改行
即可import csv
到
import unicodecsv as csv
它自动开始玩UTF-8。
注意：切换到Python 3也可以解决这个问题（感谢jamescampbell提示）。无论如何，这是应该做的事情。
答案 2 :(得分：14)
在将字典传递给DictWriter.writerow()时，您可以动态地将值转换为UTF-8。例如：
import csv
rows = [
{'name': u'Anton\xedn Dvo\u0159\xe1k','country': u'\u010cesko'},
{'name': u'Bj\xf6rk Gu\xf0mundsd\xf3ttir', 'country': u'\xcdsland'},
{'name': u'S\xf8ren Kierkeg\xe5rd', 'country': u'Danmark'}
]
# implement this wrapper on 2.6 or lower if you need to output a header
class DictWriterEx(csv.DictWriter):
def writeheader(self):
header = dict(zip(self.fieldnames, self.fieldnames))
self.writerow(header)
out = open('foo.csv', 'wb')
writer = DictWriterEx(out, fieldnames=['name','country'])
# DictWriter.writeheader() was added in 2.7 (use class above for <= 2.6)
writer.writeheader()
for row in rows:
writer.writerow(dict((k, v.encode('utf-8')) for k, v in row.iteritems()))
out.close()
输出 foo.csv ：
name,country
Antonín Dvořák,Česko
Björk Guðmundsdóttir,Ísland
Søren Kierkegård,Danmark
答案 3 :(得分：6)
您可以根据需要使用某些代理类对dict值进行编码，如下所示：
# -*- coding: utf-8 -*-
import csv
d = {'a':123,'b':456, 'c':u'Non-ASCII: проверка'}
class DictUnicodeProxy(object):
def __init__(self, d):
self.d = d
def __iter__(self):
return self.d.__iter__()
def get(self, item, default=None):
i = self.d.get(item, default)
if isinstance(i, unicode):
return i.encode('utf-8')
return i
with open('some.csv', 'wb') as f:
writer = csv.DictWriter(f, ['a', 'b', 'c'])
writer.writerow(DictUnicodeProxy(d))
答案 4 :(得分：2)
当您使用自己的内容致电csv.writer时，我们的想法是通过utf_8_encoder传递内容，因为它会为您提供（utf-8）编码内容。
答案 5 :(得分：1)
我的解决方案有点不同。虽然上述所有解决方案都专注于兼容unicode dict，但我的解决方案使DictWriter与unicode兼容。甚至在python docs（1）中也建议使用这种方法。
类UTF8Recoder，UnicodeReader，UnicodeWriter取自python docs。 UnicodeWriter-＆gt; writerow也有所改变。
将它用作常规DictWriter / DictReader。
以下是代码：
import csv, codecs, cStringIO
class UTF8Recoder:
"""
Iterator that reads an encoded stream and reencodes the input to UTF-8
"""
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:
"""
A CSV reader which will iterate over lines in the CSV file "f",
which is encoded in the given encoding.
"""
def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
f = UTF8Recoder(f, encoding)
self.reader = csv.reader(f, dialect=dialect, **kwds)
def next(self):
row = self.reader.next()
return [unicode(s, "utf-8") for s in row]
def __iter__(self):
return self
class UnicodeWriter:
"""
A CSV writer which will write rows to CSV file "f",
which is encoded in the given encoding.
"""
def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
# Redirect output to a queue
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):
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 = self.encoder.encode(data)
# 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)
class UnicodeDictWriter(csv.DictWriter, object):
def __init__(self, f, fieldnames, restval="", extrasaction="raise", dialect="excel", *args, **kwds):
super(UnicodeDictWriter, self).__init__(f, fieldnames, restval="", extrasaction="raise", dialect="excel", *args, **kwds)
self.writer = UnicodeWriter(f, dialect, **kwds)