使用python将csv转换为xls

Question

我尝试使用此 Python 脚本循环遍历目录中的 CSV 文件，以将它们转换为 XLS，但到目前为止我还没有取得什么成果。会欣赏任何帮助。这段代码的操作说他写它一次只能使用一个扩展集（1个文件），但是我相信一些有经验的python程序员可以改变它。

#!/usr/local/bin/python
# Tool to convert CSV files (with configurable delimiter and text wrap
# character) to Excel spreadsheets.
import string
import sys
import getopt
import re
import os
import os.path
import csv
from pyExcelerator import *

def usage():
  """ Display the usage """
  print "Usage:" + sys.argv[0] + " [OPTIONS] csvfile"
  print "OPTIONS:"
  print "--title|-t: If set, the first line is the title line"
  print "--lines|-l n: Split output into files of n lines or less each"
  print "--sep|-s c [def:,] : The character to use for field delimiter"
  print "--output|o : output file name/pattern"
  print "--help|h : print this information"
  sys.exit(2)

def openExcelSheet(outputFileName):
  """ Opens a reference to an Excel WorkBook and Worksheet objects """
  workbook = Workbook()
  worksheet = workbook.add_sheet("Sheet 1")
  return workbook, worksheet

def writeExcelHeader(worksheet, titleCols):
  """ Write the header line into the worksheet """
  cno = 0
  for titleCol in titleCols:
    worksheet.write(0, cno, titleCol)
    cno = cno + 1

def writeExcelRow(worksheet, lno, columns):
  """ Write a non-header row into the worksheet """
  cno = 0
  for column in columns:
    worksheet.write(lno, cno, column)
    cno = cno + 1

def closeExcelSheet(workbook, outputFileName):
  """ Saves the in-memory WorkBook object into the specified file """
  workbook.save(outputFileName)

def getDefaultOutputFileName(inputFileName):
  """ Returns the name of the default output file based on the value
      of the input file. The default output file is always created in
      the current working directory. This can be overriden using the
      -o or --output option to explicitly specify an output file """
  baseName = os.path.basename(inputFileName)
  rootName = os.path.splitext(baseName)[0]
  return string.join([rootName, "xls"], '.')

def renameOutputFile(outputFileName, fno):
  """ Renames the output file name by appending the current file number
      to it """
  dirName, baseName = os.path.split(outputFileName)
  rootName, extName = os.path.splitext(baseName)
  backupFileBaseName = string.join([string.join([rootName, str(fno)], '-'), extName], '')
  backupFileName = os.path.join(dirName, backupFileBaseName)
  try:
    os.rename(outputFileName, backupFileName)
  except OSError:
    print "Error renaming output file:", outputFileName, "to", backupFileName, "...aborting"
    sys.exit(-1)

def validateOpts(opts):
  """ Returns option values specified, or the default if none """
  titlePresent = False
  linesPerFile = -1
  outputFileName = ""
  sepChar = ","
  for option, argval in opts:
    if (option in ("-t", "--title")):
      titlePresent = True
    if (option in ("-l", "--lines")):
      linesPerFile = int(argval)
    if (option in ("-s", "--sep")):
      sepChar = argval
    if (option in ("-o", "--output")):
      outputFileName = argval
    if (option in ("-h", "--help")):
      usage()
  return titlePresent, linesPerFile, sepChar, outputFileName

def main():
  """ This is how we are called """
  try:
    opts,args = getopt.getopt(sys.argv[1:], "tl:s:o:h", ["title", "lines=", "sep=", "output=", "help"])
  except getopt.GetoptError:
    usage()
  if (len(args) != 1):
    usage()
  inputFileName = args[0]
  try:
    inputFile = open(inputFileName, 'r')
  except IOError:
    print "File not found:", inputFileName, "...aborting"
    sys.exit(-1)
  titlePresent, linesPerFile, sepChar, outputFileName = validateOpts(opts)
  if (outputFileName == ""):
    outputFileName = getDefaultOutputFileName(inputFileName)
  workbook, worksheet = openExcelSheet(outputFileName)
  fno = 0
  lno = 0
  titleCols = []
  reader = csv.reader(inputFile, delimiter=sepChar)
  for line in reader:
    if (lno == 0 and titlePresent):
      if (len(titleCols) == 0):
        titleCols = line
      writeExcelHeader(worksheet, titleCols)
    else:
      writeExcelRow(worksheet, lno, line)
    lno = lno + 1
    if (linesPerFile != -1 and lno >= linesPerFile):
      closeExcelSheet(workbook, outputFileName)
      renameOutputFile(outputFileName, fno)
      fno = fno + 1
      lno = 0
      workbook, worksheet = openExcelSheet(outputFileName)
  inputFile.close()
  closeExcelSheet(workbook, outputFileName)
  if (fno > 0):
    renameOutputFile(outputFileName, fno)

if __name__ == "__main__":
  main()

Answer 1

我建议不要重新发明轮子，而是使用 Pandas。这是一个用于处理数据的优秀 Python 库。首先查看pandas.read_csv（返回pandas.DataFrame），然后查看pandas.DataFrame.to_excel。

同时，您也可以从标准库中查找argparse。

Answer 2

有很多方法可以将csv 转换为xls 以及python 中的xlsx（我也同意@ti7 的怀疑言论）但我想包括一种令人印象深刻的方式（非常确实很方便）通过使用xlsxwriter 模块来做到这一点。也可以找openpyxl

import os
import glob
import csv
from xlsxwriter.workbook import Workbook


for csvfile in glob.glob(os.path.join('.', '*.csv')):
workbook = Workbook(csvfile[:-4] + '.xlsx')
worksheet = workbook.add_worksheet()
with open(csvfile, 'rt', encoding='utf8') as f:
    reader = csv.reader(f)
    for r, row in enumerate(reader):
        for c, col in enumerate(row):
            worksheet.write(r, c, col)
workbook.close()

希望它有效..