Question

我有这个写入csv文件的脚本：

import sqlite3
import csv
import codecs
import cStringIO
import sys

class UTF8Recoder:

    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)

with open('agajan.csv', 'w') as f:
    uW = UnicodeWriter(f, delimiter=' ')
    row = ["agaja asa; . ' a", "t, o , ,rayev", "bazargeldiyevich"]
    uW.writerow(row)

问题是代替三列，它会写出比所需更多的列。在我的字符串中可能有任何字符，但我想写得正确。我该怎么办呢？例如：row = ["agaja asa; . ' a", "t, o , ,rayev", "columns"]将分号添加到最后一列"colu;mns"将创建新列

Answer 1

我将其更改为制表符分隔格式：

with open('agajan.csv', 'w') as f:
    #uW = UnicodeWriter(f, delimiter=' ')
    uW = UnicodeWriter(f, delimiter="\t")
    row = ["agaja asa; . ' a", "t, o , ,rayev", "colu;mns"]
    uW.writerow(row)
    row1 = ["I", "am", "ironman"]
    uW.writerow(row1)

当我将LibreOffice中的输出视为制表符分隔文件时，它按预期工作。

我不认为在这种情况下使用空格作为分隔符是一个不错的选择，因为你的字段几乎肯定会包含空格。因此，我认为空间作为分隔符可能是创建额外字段的原因，而不是分号。

python csv分隔符问题

1 个答案: