python 實現將office檔案 (word, ppt, excel等) 轉為pdf

在 windows 系統（需安裝office套件）中，利用 python 的 win32com 包可以實現對Office檔案的操作，可以批量轉換為pdf檔案。支援 doc, docx, ppt, pptx, xls, xlsx 等格式。

win32com模組需要安裝 pywin32:

pip install pywin32

import os
from win32com.client import Dispatch, constants, gencache, DispatchEx


class
 
 PDFConverter:
    def __init__(self, pathname, export='.'):
        self._handle_postfix = ['doc', 'docx', 'ppt', 'pptx', 'xls', 'xlsx']
        self._filename_list = list()
        self._export_folder = os.path.join(os.path.abspath('.'), 'pdfconver')
        if not os.path.exists(self._export_folder)
 
:
                os.mkdir(self._export_folder)
        self._enumerate_filename(pathname)
    
    def _enumerate_filename(self, pathname):
        '''
        讀取所有檔名
        '''
        full_pathname = os.path.abspath(pathname)
        if os.path.isfile(full_pathname):
            if self._is_legal_postfix(
 
full_pathname):
                self._filename_list.append(full_pathname)
            else:
                raise TypeError('檔案 {} 字尾名不合法！僅支援如下檔案型別：{}。'.format(pathname, '、'.join(self._handle_postfix)))
        elif os.path.isdir(full_pathname):
            for relpath, _, files in os.walk(full_pathname):
                for name in files:
                    filename = os.path.join(full_pathname, relpath, name)
                    if self._is_legal_postfix(filename):
                        self._filename_list.append(os.path.join(filename))
        else:
            raise TypeError('檔案/資料夾 {} 不存在或不合法！'.format(pathname))

    def _is_legal_postfix(self, filename):
        return filename.split('.')[-1].lower() in self._handle_postfix and not os.path.basename(filename).startswith('~')
    
    def run_conver(self):
        '''
        進行批量處理，根據字尾名呼叫函式執行轉換
        '''
        print('需要轉換的檔案數：', len(self._filename_list))
        for filename in self._filename_list:
            postfix = filename.split('.')[-1].lower()
            funcCall = getattr(self, postfix)
            print('原檔案：', filename)
            funcCall(filename)
        print('轉換完成！')
    
    def doc(self, filename):
        '''
        doc 和 docx 檔案轉換
        '''
        name = os.path.basename(filename).split('.')[0] + '.pdf'
        exportfile = os.path.join(self._export_folder, name)
        print('儲存 PDF 檔案：', exportfile)
        gencache.EnsureModule('{00020905-0000-0000-C000-000000000046}', 0, 8, 4)
        w = Dispatch("Word.Application")
        doc = w.Documents.Open(filename)
        doc.ExportAsFixedFormat(exportfile, constants.wdExportFormatPDF,
                Item=constants.wdExportDocumentWithMarkup,
                CreateBookmarks=constants.wdExportCreateHeadingBookmarks)
        
        w.Quit(constants.wdDoNotSaveChanges)
    
    def docx(self, filename):
        self.doc(filename)
    
    def xls(self, filename):
        '''
        xls 和 xlsx 檔案轉換
        '''
        name = os.path.basename(filename).split('.')[0] + '.pdf'
        exportfile = os.path.join(self._export_folder, name)
        xlApp = DispatchEx("Excel.Application")
        xlApp.Visible = False    
        xlApp.DisplayAlerts = 0   
        books = xlApp.Workbooks.Open(filename,False)
        books.ExportAsFixedFormat(0, exportfile)
        books.Close(False)
        print('儲存 PDF 檔案：', exportfile)
        xlApp.Quit()
    
    def xlsx(self, filename):
        self.xls(filename)
    
    def ppt(self, filename):
        '''
        ppt 和 pptx 檔案轉換
        '''
        name = os.path.basename(filename).split('.')[0] + '.pdf'
        exportfile = os.path.join(self._export_folder, name)
        gencache.EnsureModule('{00020905-0000-0000-C000-000000000046}', 0, 8, 4)
        p = Dispatch("PowerPoint.Application")
        ppt = p.Presentations.Open(filename, False, False, False)
        ppt.ExportAsFixedFormat(exportfile, 2, PrintRange=None)
        print('儲存 PDF 檔案：', exportfile)
        p.Quit()
    
    def pptx(self, filename):
        self.ppt(filename)



if __name__ == "__main__":
    
    # 支援資料夾批量匯入
    folder = 'tmp' 
    pathname = os.path.join(os.path.abspath('.'), folder)
    
    # 也支援單個檔案的轉換
    # pathname = 'test.doc'

    pdfConverter = PDFConverter(pathname)
    pdfConverter.run_conver()