python csv unicode'ascii'编解码器无法编码位置1中的字符u'\ xf6'：序数不在范围内（128）

Question

我从[python web site]复制了这个脚本[1]这是另一个问题，但现在编码问题：

import sqlite3
import csv
import codecs
import cStringIO
import sys

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([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)

这次编码的问题，当我运行它时它给了我这个错误：

Traceback (most recent call last):
  File "makeCSV.py", line 87, in <module>
    uW.writerow(d)
  File "makeCSV.py", line 54, in writerow
    self.writer.writerow([s.encode("utf-8") for s in row])
AttributeError: 'int' object has no attribute 'encode'

然后我将所有整数转换为字符串，但这次我得到了这个错误：

Traceback (most recent call last):
  File "makeCSV.py", line 87, in <module>
    uW.writerow(d)
  File "makeCSV.py", line 54, in writerow
    self.writer.writerow([str(s).encode("utf-8") for s in row])
UnicodeEncodeError: 'ascii' codec can't encode character u'\xf6' in position 1: ordinal not in range(128)

我上面已经实现了处理unicode字符，但它给了我这样的错误。 有什么问题以及如何解决？

Answer 1

然后我将所有整数转换为字符串，

您将整数和字符串转换为字节字符串 。 对于字符串，这将使用恰好是ASCII的默认字符编码，如果您有非ASCII字符，则会失败。 你想要unicode而不是str 。

self.writer.writerow([unicode(s).encode("utf-8") for s in row])

在调用该方法之前将所有内容转换为unicode可能更好。 该类专门用于解析Unicode字符串。 它不是为支持其他数据类型而设计的。

Answer 2

从文档：

• http://docs.python.org/library/stringio.html?highlight=cstringio#cStringIO.StringIO

与StringIO模块不同，此模块无法接受无法编码为纯ASCII字符串的Unicode字符串。

也就是说，只能存储7位干净的字符串。

Answer 3

如果您使用的是Python 2：

使编码为： str（s.encode（“utf-8”）） ie

def writerow(self, row):
    self.writer.writerow([str(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)