使用Python实现Office文档(Word/Excel/PowerPoint)批量转换为PDF

from spire.pdf import PdfDocument
from spire.doc import Document
from spire.xls import Workbook
from spire.presentation import Presentation
from spire.doc import FileFormat as wFileFormat
from spire.xls import FileFormat as eFileFormat
from spire.presentation import FileFormat as pFileFormat
import os

# 定义要处理的文件夹路径
folderPath = "Documents/"
# 获取所有指定类型的文件并排序
extensions = [".doc", ".docx", ".xls", ".xlsx", ".ppt", ".pptx"]
files = sorted([os.path.join(folderPath, f) for f in os.listdir(folderPath) if f.lower().endswith(tuple(extensions))])

# 创建一个PdfDocument对象
pdf = PdfDocument()

# 遍历文件列表
for file in files:
    extension = os.path.splitext(file)[1].lower()
    if extension in [".doc", ".docx"]:
        # 创建Document对象
        doc = Document()
        # 载入Word文档
        doc.LoadFromFile(file)
        # 将Word文档转换为PDF
        doc.SaveToFile(f"output/Documents/{os.path.basename(file)}.pdf", wFileFormat.PDF)
        doc.Close()
    if extension in [".xls", ".xlsx"]:
        # 创建Workbook对象
        workbook = Workbook()
        # 载入Excel文件
        workbook.LoadFromFile(file)
        # 将Excel文件转换为PDF
        workbook.SaveToFile(f"output/Documents/{os.path.basename(file)}.pdf", eFileFormat.PDF)
        workbook.Dispose()
    if extension in [".ppt", ".pptx"]:
        # 创建Presentation对象
        presentation = Presentation()
        # 载入PowerPoint文件
        presentation.LoadFromFile(file)
        # 将PowerPoint文件转换为PDF
        presentation.SaveToFile(f"output/Documents/{os.path.basename(file)}.pdf", pFileFormat.PDF)
        presentation.Dispose()

# 关闭PdfDocument对象
pdf.Close()

from spire.pdf import PdfDocument
from spire.doc import Document
from spire.xls import Workbook
from spire.presentation import Presentation
from spire.doc import FileFormat as wFileFormat
from spire.xls import FileFormat as eFileFormat
from spire.presentation import FileFormat as pFileFormat

import os

# 指定要处理的文件夹路径
folderPath = 'Documents/'
# 获取所有指定类型的文件并排序
extensions = ['.doc', '.docx', '.xls', '.xlsx', '.ppt', '.pptx']
files = sorted([os.path.join(folderPath, f) for f in os.listdir(folderPath) if f.lower().endswith(tuple(extensions))])

# 创建一个PdfDocument对象
pdf = PdfDocument()
# 创建一个临时PDF和一个Stream对象
temPdf = PdfDocument()
temPdfPath = 'temp.pdf'

# 遍历文件列表
for file in files:
    extension = os.path.splitext(file)[1].lower()

    if extension in ['.doc', '.docx']:
        # 加载Word文档
        doc = Document()
        doc.LoadFromFile(file)
        # 保存为临时PDF
        doc.SaveToFile(temPdfPath, wFileFormat.PDF)
        # 载入临时PDF并将其页面添加到最终PDF中
        temPdf.LoadFromFile(temPdfPath)
        pdf.AppendPage(temPdf)
        doc.Close()  # 显式关闭文档

    elif extension in ['.xls', '.xlsx']:
        # 加载Excel工作簿
        workbook = Workbook()
        workbook.LoadFromFile(file)
        # 保存为临时PDF
        workbook.SaveToFile(temPdfPath, eFileFormat.PDF)
        # 载入临时PDF并将其页面添加到最终PDF中
        temPdf.LoadFromFile(temPdfPath)
        pdf.AppendPage(temPdf)
        workbook.Dispose()  # 显式关闭工作簿

    elif extension in ['.ppt', '.pptx']:
        # 加载PowerPoint演示文稿
        presentation = Presentation()
        presentation.LoadFromFile(file)
        # 保存为临时PDF
        presentation.SaveToFile(temPdfPath, pFileFormat.PDF)
        # 载入临时PDF并将其页面添加到最终PDF中
        temPdf.LoadFromFile(temPdfPath)
        pdf.AppendPage(temPdf)
        presentation.Dispose()  # 显式关闭演示文稿

    elif extension == '.pdf':
        # 如果已经是PDF，则直接载入并将其页面添加到最终PDF中
        temPdf.LoadFromFile(file)
        pdf.AppendPage(temPdf)

# 保存最终PDF
outputPath = "output/CombinedPDF.pdf"
pdf.SaveToFile(outputPath)

# 清理临时文件
if os.path.exists('temp.pdf'):
    os.remove('temp.pdf')

# 释放资源
pdf.Close()
temPdf.Close()