python - 将 .xls 转换为 .xlsx 以便 Openpyxl 可以使用它

标签 python openpyxl xlrd

我编写了一个 flask 应用程序，将用于处理一些 excel 文件，但是，我为 .xlsx 文件编写了它。输入的文件可能是 .xls 文件，我知道 Openpyxl 无法打开。在我的应用程序中使用 Openpyxl 处理文件之前，如何将文件转换为 .xlsx？

我在网上看到一些关于使用 xlrd 将原始 .xls 写入 Openpyxl 可以处理的 .xlsx 文件的内容，但我在调整它以适应我的特定应用程序时遇到了麻烦。

提前致谢!

from openpyxl import load_workbook
from openpyxl.styles import Style, Font
from flask import Flask, request, render_template, redirect, url_for, send_file
import os


app = Flask(__name__)

@app.route('/')
def index():
    return """<center><body bgcolor="#FACC2E">
          <h1><p>Automated TDX Report</h1></p><br>
    <form action="/upload" method=post enctype=multipart/form-data>
      <p><input type=file name=file>
         <input type=submit value=Upload>
    </form></center></body>"""

@app.route('/upload', methods = ['GET', 'POST'])
def upload():
    if request.method == 'POST':
        f = request.files['file']
        f.save(f.filename)
        return process(f.filename)

def process(filename):


    VP = ['ZYJD', 'ZYJC', 'ZYKC', 'ZYKA', 'ZYKB', 'ZYKD', 'ZYKE', 'ZYKF', 'ZYJB', 'ZYJX', 'ZYKG', 'ZYKH', 'ZYJE', 'ZYJA', 
         'ZYKI', 'ZYKX', 'ZYKK', 'ZYKJ', 'ZYJF', 'ZYJK', 'ZYJG', 'ZYJJ', 'ZYKL', 'ZYKM', 'ZYKN']

    VA = ['ZYIC', 'ZYIB', 'ZYHC', 'ZYIA', 'ZYHA', 'ZYHG', 'ZYHB', 'ZYID', 'ZYDA', 'ZYIE', 'ZYHD', 'ZYIG', 'ZYIX', 'ZYHE', 
         'ZYIF', 'ZYHX', 'ZYDE', 'ZYHF', 'ZYLB', 'ZYAC', 'ZYCF', 'ZYDF', 'ZYBG', 'ZYDG', 'ZYDD', 'ZYDH', 'ZYCB', 'ZYCA', 
         'ZYWA', 'ZYWB', 'ZYWC', 'ZYWD', 'ZYWE', 'ZYWF', 'ZYWG', 'ZYWI', 'ZYWJ']

    Gordon = ['ZYDB', 'ZYDX', 'ZYEB', 'ZYED', 'ZYEC', 'ZYEA', 'ZYEX', 'ZYFE', 'ZYFX', 'ZYFD', 'ZYFA', 'ZYFC', 'ZYFB', 
             'ZYGC', 'ZYGA', 'ZYGX', 'ZYGB', 'ZYGF', 'ZYGG', 'ZYGD', 'ZYLA', 'ZYBF', 'ZYBE', 'ZYLD', 'ZYKM', 'ZYKN', 
             'ZYCC', 'ZYCE']

    Pete = ['ZYAD', 'ZYBX', 'ZYAX', 'ZYAB', 'ZYBC', 'ZYBA', 'ZYBB', 'ZYAA', 'ZYBD', 'ZYLE', 'ZYCX', 'ZYAE', 'ZYCC', 'ZYCE', 
           'ZYLA', 'ZYBF', 'ZYBE', 'ZYLD']

    Mike = ['ZYKP', 'ZYAP', 'ZYHP', 'ZYJP', 'ZYFP', 'ZYJR', 'ZYCP', 'ZYIR', 'ZYAR', 'ZYBP', 'ZYKR', 'ZYJS', 'ZYIP', 'ZYHR',
           'ZYEP', 'ZYFF', 'ZYGP', 'ZYKS', 'ZYEE', 'ZYJH', 'ZYII', 'ZYHH', 'ZYJW']

    workbook = load_workbook(filename)
    worksheet = workbook.active

    worksheet.column_dimensions.group('B', hidden=True)
    worksheet.column_dimensions.group('D', hidden=True)
    worksheet.column_dimensions.group('E', hidden=True)
    worksheet.column_dimensions.group('F', hidden=True)
    worksheet.column_dimensions.group('G', hidden=True)
    worksheet.column_dimensions.group('H', hidden=True)
    worksheet.column_dimensions.group('I', hidden=True)
    worksheet.column_dimensions.group('K', hidden=True)
    worksheet.column_dimensions.group('L', hidden=True)
    worksheet.column_dimensions.group('M', hidden=True)
    worksheet.column_dimensions.group('N', hidden=True)
    worksheet.column_dimensions.group('O', hidden=True)
    worksheet.column_dimensions.group('P', hidden=True)
    worksheet.column_dimensions.group('Q', hidden=True)
    worksheet.column_dimensions.group('R', hidden=True)
    worksheet.column_dimensions.group('S', hidden=True)
    worksheet.column_dimensions.group('T', hidden=True)
    worksheet.column_dimensions.group('U', hidden=True)
    worksheet.column_dimensions.group('V', hidden=True)
    worksheet.column_dimensions.group('W', hidden=True)
    worksheet.column_dimensions.group('X', hidden=True)
    worksheet.column_dimensions.group('Y', hidden=True)
    worksheet.column_dimensions.group('Z', hidden=True)
    worksheet.column_dimensions.group('AA', hidden=True)
    worksheet.column_dimensions.group('AB', hidden=True)
    worksheet.column_dimensions.group('AC', hidden=True)
    worksheet.column_dimensions.group('AD', hidden=True)
    worksheet.column_dimensions.group('AE', hidden=True)
    worksheet.column_dimensions.group('AF', hidden=True)
    worksheet.column_dimensions.group('AG', hidden=True)
    worksheet.column_dimensions.group('AH', hidden=True)
    worksheet.column_dimensions.group('AI', hidden=True)
    worksheet.column_dimensions.group('AJ', hidden=True)
    worksheet.column_dimensions.group('AK', hidden=True)
    worksheet.column_dimensions.group('AM', hidden=True)
    worksheet.column_dimensions.group('AN', hidden=True)
    worksheet.column_dimensions.group('AP', hidden=True)
    worksheet.column_dimensions.group('AQ', hidden=True)
    worksheet.column_dimensions.group('AR', hidden=True)
    worksheet.column_dimensions.group('AS', hidden=True)
    worksheet.column_dimensions.group('AT', hidden=True)
    worksheet.column_dimensions.group('AU', hidden=True)
    worksheet.column_dimensions.group('AV', hidden=True)
    worksheet.column_dimensions.group('AW', hidden=True)
    worksheet.column_dimensions.group('AX', hidden=True)
    worksheet.column_dimensions.group('AY', hidden=True)
    worksheet.column_dimensions.group('AZ', hidden=True)
    worksheet.column_dimensions.group('BA', hidden=True)
    worksheet.column_dimensions.group('BB', hidden=True)
    worksheet.column_dimensions.group('BC', hidden=True)
    worksheet.column_dimensions.group('BD', hidden=True)
    worksheet.column_dimensions.group('BE', hidden=True)
    worksheet.column_dimensions.group('BF', hidden=True)
    worksheet.column_dimensions.group('BH', hidden=True)
    worksheet.column_dimensions.group('BI', hidden=True)
    worksheet.column_dimensions.group('BJ', hidden=True)
    worksheet.column_dimensions.group('BK', hidden=True)
    worksheet.column_dimensions.group('BL', hidden=True)
    worksheet.column_dimensions.group('BM', hidden=True)
    worksheet.column_dimensions.group('BN', hidden=True)
    worksheet.column_dimensions.group('BO', hidden=True)
    worksheet.column_dimensions.group('BP', hidden=True)
    worksheet.column_dimensions.group('BQ', hidden=True)
    worksheet.column_dimensions.group('BR', hidden=True)
    worksheet.column_dimensions.group('BS', hidden=True)
    worksheet.column_dimensions.group('BT', hidden=True)
    worksheet.column_dimensions.group('BU', hidden=True)
    worksheet.column_dimensions.group('BV', hidden=True)
    worksheet.column_dimensions.group('BW', hidden=True)
    worksheet.column_dimensions.group('BX', hidden=True)
    worksheet.column_dimensions.group('BY', hidden=True)
    worksheet.column_dimensions.group('BZ', hidden=True)
    worksheet.column_dimensions.group('CA', hidden=True)
    worksheet.column_dimensions.group('CB', hidden=True)
    worksheet.column_dimensions.group('CC', hidden=True)
    worksheet.column_dimensions.group('CD', hidden=True)
    worksheet.column_dimensions.group('CE', hidden=True)
    worksheet.column_dimensions.group('CF', hidden=True)
    worksheet.column_dimensions.group('CG', hidden=True)
    worksheet.column_dimensions.group('CH', hidden=True)
    worksheet.column_dimensions.group('CI', hidden=True)
    worksheet.column_dimensions.group('CJ', hidden=True)
    worksheet.column_dimensions.group('CK', hidden=True)
    worksheet.column_dimensions.group('CL', hidden=True)
    worksheet.column_dimensions.group('CM', hidden=True)
    worksheet.column_dimensions.group('CN', hidden=True)
    worksheet.column_dimensions.group('CO', hidden=True)
    worksheet.column_dimensions.group('CP', hidden=True)
    worksheet.column_dimensions.group('CQ', hidden=True)
    worksheet.column_dimensions.group('CR', hidden=True)
    worksheet.column_dimensions.group('CS', hidden=True)
    worksheet.column_dimensions.group('CU', hidden=True)


    routecolumn = worksheet.columns[58]
    i = 2
    supervisorheader = worksheet.cell("CV1")
    s = Style(font=Font(bold=True))
    supervisorheader.style = s

    worksheet['CV1'] = 'Supervisor'
    for route in routecolumn:
        if route.value == 'Responsible Route':
            continue
        if route.value in Gordon:
            pos = Gordon.index(route.value)
            worksheet['CV' + str(i)].value = 'Gordon'
            i += 1
        elif route.value in VA:
            pos = VA.index(route.value)
            worksheet['CV' + str(i)].value = 'Vinny A'
            i += 1
        elif route.value in VP:
            pos = VP.index(route.value)
            worksheet['CV' + str(i)].value = 'Vinny P'
            i += 1
        elif route.value in Pete:
            pos = Pete.index(route.value)
            worksheet['CV' + str(i)].value = 'Pete'
            i += 1
        elif route.value in Mike:
            pos = Mike.index(route.value)
            worksheet['CV' + str(i)].value = 'Mike'
            i += 1
        elif route.value not in Gordon or route.value not in VA or route.value not in VP or route.value not in Pete \
        or route.value not in Mike:
            worksheet['CV' + str(i)].value = 'Building'
            i += 1


    workbook.save(filename)
    newfilename = filename.strip(".xlsx")
    newfilename = newfilename + ".xls"
    os.rename('/home/MY NAME/'+filename, '/home/MY NAME/'+newfilename)

    return send_file(newfilename, attachment_filename='tdx.xls', as_attachment=True), os.remove ('/home/MY NAME/'+newfilename)



if __name__ == '__main__':
    app.run(debug = True, host = '0.0.0.0')

最佳答案

我的建议:使用 xlrd 读取您需要的值，并使用 openpyxl 创建一个新的 xlsx 工作簿。您只需要能够使用 xlrd 获取所有相关信息。

除了从单元格中读取值外，您要做的唯一一件事就是选择“事件”工作表。我找到了 this Google Groups post在标题为“xlrd: Get active sheet”的线程中，该线程表示尝试使用 .sheet_selected 属性或 .sheet_visible 属性，并使用以下代码检查哪些有效: 

import xlrd
b = xlrd.open_workbook("vis.xls") # where vis.xls is your test file
for i, s in enumerate(b.sheets()):
    print(i, s.name, s.sheet_selected, s.sheet_visible)

它还指出:

These two attributes are documented in sheet.py in the dict _WINDOW_2 which starts at about line 2. sheet_visible is probably what you want. Ignore the MS docs which show this bit as undefined.

关于python - 将 .xls 转换为 .xlsx 以便 Openpyxl 可以使用它，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/38493257/

上一篇：python - 将 csv 读取到 dicts 的 dict

下一篇：python - 重新排序簇号以实现正确对应

相关文章：

python - 如果不是，如何使函数输入成为字符串？

Python:检测变量何时超过阈值区间

python - openpyxl如何在工作表上编辑输入数据后读取公式结果？ data_only=True 给我一个 "None"结果

python - 使用 xlrd 在 Python 3 中将 xls 转换为 csv

python - 在 Python 中使用 cx_Oracle 和 xlrd 的带有列表列表的 executemany() 返回 TypeError

python - xlrd.biffh.XLRDError : Excel xlsx file; not supported

python - 如果某些列有交集，如何将行从一张纸复制到另一张纸

python - 获取Python中bash命令的所有输出

python-3.x - (openpyxl) FileNotFoundError : [Errno 2] No such file or directory

python - 使用pd.read_excel读取多页xlsx时如何将列值转换为str？

©2024 IT工具网  联系我们