使用Python在Excel工作表中插入、提取和管理OLE对象

pip install Spire.XLS

from spire.xls import *
from spire.xls.common import *


def GenerateImage(fileName):
        book = Workbook()
        book.LoadFromFile(fileName)
        book.Worksheets[0].PageSetup.LeftMargin = 0
        book.Worksheets[0].PageSetup.RightMargin = 0
        book.Worksheets[0].PageSetup.TopMargin = 0
        book.Worksheets[0].PageSetup.BottomMargin = 0
        return book.Worksheets[0].ToImage(1, 1, 19, 5)

inputFile = "./Data/InsertOLEObjects.xls"
outputFile = "InsertOLEObjects.xlsx"

# 创建工作簿并获取第一个工作表
workbook = Workbook()
ws = workbook.Worksheets[0]
ws.Range["A1"].Text = "Here is an OLE Object."

# 生成预览图像并插入 OLE 对象
image = GenerateImage(inputFile)
oleObject = ws.OleObjects.Add(inputFile, image, OleLinkType.Embed)
oleObject.Location = ws.Range["B4"]
oleObject.ObjectType = OleObjectType.ExcelWorksheet

# 保存文件
workbook.SaveToFile(outputFile, ExcelVersion.Version2010)
workbook.Dispose()

from spire.xls import *
from spire.xls.common import *


inputFile = "./Data/WAVFileSample.wav"
inputimg = "./Data/SpireXls.png"
outputFile = "InsertWavFileOLEObject.xlsx"

# 创建工作簿并获取第一个工作表
workbook = Workbook()
sheet = workbook.Worksheets[0]

# 使用自定义图像作为预览，添加音频 OLE 对象
with Stream(inputimg) as fs:
    oleObject = sheet.OleObjects.Add(inputFile, fs, OleLinkType.Embed)

# 设置位置和对象类型
oleObject.Location = sheet.Range["B4"]
oleObject.ObjectType = OleObjectType.Package

workbook.SaveToFile(outputFile, ExcelVersion.Version2010)
workbook.Dispose()

from spire.xls import *
from spire.xls.common import *


def WriteAllBytes(fname: str, data):
    fp = open(fname, "wb")
    for d in data:
        fp.write(d)
    fp.close()

inputFile = "./Data/ExtractOle2.xlsx"

workbook = Workbook()
workbook.LoadFromFile(inputFile)
sheet = workbook.Worksheets[0]

# 检查工作表是否包含 OLE 对象
if sheet.HasOleObjects:
    for obj in sheet.OleObjects:
        type = obj.ObjectType
        # 提取 Word 文档
        if type is OleObjectType.WordDocument:
            WriteAllBytes("ExtractedWord.docx", obj.OleData)
        # 提取 PDF 文档
        elif type is OleObjectType.AdobeAcrobatDocument:
            WriteAllBytes("ExtractedPDF.pdf", obj.OleData)
        # 提取 PowerPoint 文档
        elif type is OleObjectType.PowerPointSlide:
            WriteAllBytes("ExtractedPPT.pptx", obj.OleData)

workbook.Dispose()

from spire.xls.common import *
from spire.xls import *

inputFile = "Data/ExtractOleObjectName.xlsx"

# 创建工作簿并加载文件
workbook = Workbook()
workbook.LoadFromFile(inputFile)

# 获取第一个工作表
sheet = workbook.Worksheets[0]

information = ""

# 遍历所有 OLE 对象，获取原始文档名称
for ole in sheet.OleObjects:
    ole_name = ole.OriginName
    information += ole_name + "\r\n"

print(information)

workbook.Dispose()

type_mapping = {
    OleObjectType.WordDocument: ".docx",
    OleObjectType.AdobeAcrobatDocument: ".pdf",
    OleObjectType.PowerPointSlide: ".pptx",
    OleObjectType.ExcelWorksheet: ".xlsx"
}

if sheet.HasOleObjects:
    for index, obj in enumerate(sheet.OleObjects):
        ext = type_mapping.get(obj.ObjectType, ".bin")
        filename = f"ole_object_{index}{ext}"
        WriteAllBytes(filename, obj.OleData)
        print(f"已提取: {filename} (类型: {obj.ObjectType})")

for sheet_index in range(workbook.Worksheets.Count):
    sheet = workbook.Worksheets[sheet_index]
    if sheet.HasOleObjects:
        for obj in sheet.OleObjects:
            print(f"工作表 {sheet_index + 1}: {obj.OriginName} - {obj.ObjectType}")