dict_unicode_csv_writer.py

# 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, row):

        _row = {}
        for k, v in row.items():
            if isinstance(v, str) or isinstance(v, unicode):
                _row[k] = v.encode("utf-8")
            else:
                _row[k] = v
  
        self.writer.writerow(_row)

        # Fetch UTF-8 output from the queue ...
        data = self.queue.getvalue()
        data = data.decode("utf-8")

        # ... and recode 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)

    def writeheader(self):
        self.writer.writeheader()

row1 = {'name':u'马克','pinyin':u'Mǎkè'}
row2 = {'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(row1.keys()))
w.writeheader()
w.writerows([row1,row2])
f.close()