我想将数据写入文件,其中 CSV 中的行应如下所示(直接来自 Python 控制台):
row = ['\xef\xbb\xbft_11651497', 'http://kozbeszerzes.ceu.hu/entity/t/11651497.xml', "Szabolcs Mag '98 Kft.", 'ny\xc3\xadregyh\xc3\xa1za', 'ny\xc3\xadregyh\xc3\xa1za', '4400', 't\xc3\xbcnde utca 20.', 47.935175, 21.744975, u'Ny\xedregyh\xe1za', u'Borb\xe1nya', u'Szabolcs-Szatm\xe1r-Bereg', u'Ny\xedregyh\xe1zai', u'20', u'T\xfcnde utca', u'Magyarorsz\xe1g', u'4405']
Py2k 不支持 Unicode,但我有一个 UnicodeWriter 包装器:
import cStringIO, codecs
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)
然而,这些行仍然会产生下面可怕的编码错误消息:
f.write(codecs.BOM_UTF8)
writer = UnicodeWriter(f)
writer.writerow(row)
UnicodeEncodeError: 'ascii' codec can't encode character u'\xfc' in position 9: ordinal not in range(128)
有什么可做的吗?谢谢!