May 31, 2021 Article blog
This article comes from the public number: Python Technology Author: Pieson Sauce
In the daily life work, it is inevitable to use some small Tip to solve the small problems encountered in the work, today's article gives you a quick and easy tip to convert Office (doc/docx/ppt/pptx/xlx/xlsx) files into PDF files in bulk. However, you'll need to install Office on your PC before you can do that, and then use Python's win32com package to convert Office files.
Before you go live, you need to install Python's win32com, and the detailed installation steps are as follows:
pip install pywin32
If we encounter an installation error, we can do so again by
python -m pip install --upgrade pip
update the cloud:
python -m pip install --upgrade pip
If the pip command is not installed successfully, you can also download the offline package installation, the method steps are as follows: first select the corresponding Python version on the official website to download the offline package: sourceforge.net/projects/pywin32/files/pywin32/Build%20221 / download after the fool installed it.
The detailed code is as follows:
class PDFConverter:
def __init__(self, pathname, export='.'):
self._handle_postfix = ['doc', 'docx', 'ppt', 'pptx', 'xls', 'xlsx'] # 支持转换的文件类型
self._filename_list = list() #列出文件
self._export_folder = os.path.join(os.path.abspath('.'), 'file_server/pdfconver')
if not os.path.exists(self._export_folder):
os.mkdir(self._export_folder)
self._enumerate_filename(pathname)
def _enumerate_filename(self, pathname):
'''
读取所有文件名
'''
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('文件 {} 后缀名不合法!仅支持如下文件类型:{}。'.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('文件/文件夹 {} 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):
print('需要转换的文件数是:', len(self._filename_list))
for filename in self._filename_list:
postfix = filename.split('.')[-1].lower()
funcCall = getattr(self, postfix)
print('原文件:', filename)
funcCall(filename)
print('转换完成!')
The doc/docx conversion to PDF section code looks like this:
def doc(self, filename):
name = os.path.basename(filename).split('.')[0] + '.pdf'
exportfile = os.path.join(self._export_folder, name)
print('保存 PDF 文件:', exportfile)
gencache.EnsureModule('{00020905-0000-0000-C000-000000000046}', 0, 8, 4)
pythoncom.CoInitialize()
w = Dispatch("Word.Application")
pythoncom.CoInitialize() # 加上防止 CoInitialize 未加载
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)
The conversion of ppt/pptx to PDF section code is as follows:
def ppt(self, filename):
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)
pythoncom.CoInitialize()
p = Dispatch("PowerPoint.Application")
pythoncom.CoInitialize()
ppt = p.Presentations.Open(filename, False, False, False)
ppt.ExportAsFixedFormat(exportfile, 2, PrintRange=None)
print('保存 PDF 文件:', exportfile)
p.Quit()
def pptx(self, filename):
self.ppt(filename)
def xls(self, filename):
name = os.path.basename(filename).split('.')[0] + '.pdf'
exportfile = os.path.join(self._export_folder, name)
pythoncom.CoInitialize()
xlApp = DispatchEx("Excel.Application")
pythoncom.CoInitialize()
xlApp.Visible = False
xlApp.DisplayAlerts = 0
books = xlApp.Workbooks.Open(filename, False)
books.ExportAsFixedFormat(0, exportfile)
books.Close(False)
print('保存 PDF 文件:', exportfile)
xlApp.Quit()
def xlsx(self, filename):
self.xls(filename)
if __name__ == "__main__":
# 支持文件夹批量导入
#folder = 'tmp'
#pathname = os.path.join(os.path.abspath('.'), folder)
# 也支持单个文件的转换
pathname = "G:/python_study/test.doc"
pdfConverter = PDFConverter(pathname)
pdfConverter.run_conver()
That's what
W3Cschool编程狮
has to say about
Python's tips for turning Office files into PDFs.