Python DictWriter编写UTF-8编码的CSV文件

Question

1. 我有一个包含unicode字符串的字典列表。
2. csv.DictWriter可以将字典列表写入CSV文件。
3. 我想CSV文件以UTF8编码。
4. csv模块无法处理将unicode字符串转换为UTF8。

5. 的csv模块文档具有用于一切转换为UTF8一个例子：

   def utf_8_encoder(unicode_csv_data): 
       for line in unicode_csv_data: 
        yield line.encode('utf-8') 
   

6. 它也有一个UnicodeWriter类。

但是...如何使DictWriter与这些工作？难道他们不得不在自己的中间注入自己，在将它们写入文件之前赶上反汇编的字典并对它们进行编码？我不明白。

Answer 1

如果使用Python 2.7或更高版本，使用一个字典理解重新映射字典为UTF-8传递到DictWriter之前：

# 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() 

你可以使用这个想法来更新UnicodeWriter到DictUnicodeWriter：

# coding: utf-8 
import csv 
import cStringIO 
import codecs 

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() 

Answer 2

当您将csv.writer与您的内容联系起来时，其想法是通过utf_8_encoder传递内容，因为它会为您提供（utf-8）编码内容。

Answer 3

你可以使用一些代理类编码为需要的字典值，如：

# -*- 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)) 

Answer 4

您可以将值转换为UTF-8的飞行。当你穿过字典内DictWriter.writerow()。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 

Answer 5

我的解决方案有点不同。虽然上述所有解决方案都着眼于具有Unicode兼容的字典，但我的解决方案使DictWriter与Unicode相兼容​​。这种方法甚至在python文档中建议（1）。

类UTF8Recoder，UnicodeReader，UnicodeWriter取自python文档。 UnicodeWriter-> authorow也改变了一点。

将其用作常规DictWriter/DictReader。

下面是代码：

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) 

Answer 6

有使用妙UnicodeCSV模块的简单的解决方法。拥有它之后，只需更改行

import csv 

到

import unicodecsv as csv 

它自动地开始播放尼斯UTF-8。

注意：切换到Python 3也可以解决这个问题（谢谢jamescampbell的提示）。无论如何，这是应该做的。