python open write的编码_Python DictWriter编写UTF-8编码的CSV文件

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-> writerow也有所改变。

将它用作常规DictWriter / DictReader。

这是代码：

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)