Question

我尝试将excel文件列表更改为csvs，然后将它们加载到pandas数据帧中，但我不确定如何在脚本中转换它们。 Csvkit和xlsx2csv似乎适用于从命令行执行此操作，但是当我尝试启动类似的子进程时

for filename in sorted_files:
file = subprocess.Popen("in2csv filename", stdout=subprocess.PIPE)
print file.stdout
dataframe = pd.read_csv(file)

我收到了错误

IOError：预期的文件路径名或类文件对象，获得类型当格式为＆＃34;已修复＆＃34;

时，schema不得为null

是否可以从子进程获取输出并将其传递给数据帧？任何帮助非常感谢！

Answer 1

尽管提出问题已经很久了，但我遇到了同样的问题，这是在python脚本中实现的方式：
只能使用sheetid参数执行Xlsx2csv。为了获取工作表名称和ID，使用了get_sheet_details。
csvfrmxlsx为父目录下csv文件夹中的每个工作表创建csv文件。

import pandas as pd
from pathlib import Path


def get_sheet_details(filename):
    import xmltodict
    import shutil
    import zipfile
    sheets = []
    # Make a temporary directory with the file name
    directory_to_extract_to = (filename.with_suffix(''))
    directory_to_extract_to.mkdir(parents=True, exist_ok=True)
    # Extract the xlsx file as it is just a zip file
    zip_ref = zipfile.ZipFile(filename, 'r')
    zip_ref.extractall(directory_to_extract_to)
    zip_ref.close()
    # Open the workbook.xml which is very light and only has meta data, get sheets from it
    path_to_workbook = directory_to_extract_to / 'xl' / 'workbook.xml'
    with open(path_to_workbook, 'r') as f:
        xml = f.read()
        dictionary = xmltodict.parse(xml)
        for sheet in dictionary['workbook']['sheets']['sheet']:
            sheet_details = {
                'id': sheet['@sheetId'],  # can be sheetId for some versions
                'name': sheet['@name']  # can be name
            }
            sheets.append(sheet_details)
    # Delete the extracted files directory
    shutil.rmtree(directory_to_extract_to)
    return sheets


def csvfrmxlsx(xlsxfl, df):  # create csv files in csv folder on parent directory
from xlsx2csv import Xlsx2csv
(xlsxfl.parent / 'csv').mkdir(parents=True, exist_ok=True)
for index, row in df.iterrows():  
    shnum = row['id']
    shnph = xlsxfl.parent / 'csv' / Path(row['name'] + '.csv')  # path for converted csv file
    Xlsx2csv(str(xlsxfl), outputencoding="utf-8").convert(str(shnph), sheetid=int(shnum))  
return


pthfnc = 'c:/xlsx/'
wrkfl = 'my.xlsx'
xls_file = Path(pthfnc + wrkfl)
sheetsdic = get_sheet_details(xls_file)  # dictionary with sheet names and ids without opening xlsx file
df = pd.DataFrame.from_dict(sheetsdic)
csvfrmxlsx(xls_file, df)  # df with sheets to be converted

将excel文件更改为python脚本中的csv？

1 个答案: