42

我已经从 [python 网站][1] 复制了这个脚本这是另一个问题，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)

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

4

3 回答 3

87

然后我将所有整数转换为字符串，

您将整数和字符串都转换为字节字符串。对于字符串，这将使用恰好是 ASCII 的默认字符编码，当您有非 ASCII 字符时，这将失败。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 可能会更好。该类是专门为解析 Unicode 字符串而设计的。它不是为支持其他数据类型而设计的。

于 2012-08-09T13:14:47.593 回答
2

从文档中：

与 StringIO 模块不同，该模块不能接受无法编码为纯 ASCII 字符串的 Unicode 字符串。

即只能存储 7 位干净的字符串。

于 2012-08-09T13:20:33.940 回答
0

如果您使用的是 Python 2：

使编码为：str(s.encode("utf-8")) 即

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)
于 2019-03-07T16:24:30.657 回答