统计文件夹下文件的总页码

需求：在网上打印材料时，需要统计要打印的文件页数，手工统计太麻烦了

 

 

原始目录结构：

 

 

 

代码：

# -*- coding:utf-8 -*-
"""需要网上批量打印文件，但是每次打印后自己手动数页数很麻烦，干脆写个python小程序，获得文件夹下所有的页数，
   同时将非pdf文件转成pdf文件，保存在一个指定文件夹下
"""

import os
import PyPDF2
import comtypes.client


# word转pdf
def convert_word_to_pdf(word_path, pdf_path):
    """
    word转pdf
    :param word_path: word文件路径
    :param pdf_path:  生成pdf文件路径
    """
    # print("word_path:%s, pdf_path:%s" % (word_path, pdf_path))
    word = comtypes.client.CreateObject("Word.Application")
    word.Visible = 0
    new_pdf = word.Documents.Open(word_path)
    new_pdf.SaveAs(pdf_path, FileFormat=17)
    new_pdf.Close()


# ppt 转pdf
def convert_ppt_to_pdf(ppt_path, pdf_path):
    # print("ppt_path:%s, pdf_path:%s" % (ppt_path, pdf_path))
    ppt = comtypes.client.CreateObject("Powerpoint.Application")
    ppt.Visible = 1
    new_pdf = ppt.Presentations.Open(ppt_path)
    new_pdf.SaveAs(pdf_path, FileFormat=32)
    new_pdf.Close()


# 统计文件数
def get_all_file_by_type(path, type=(), get_all_dirs=True):
    """获得以type类型结尾的所有文件，返回一个list"""
    file_list = []
    for cur_dir, dirs, files in os.walk(path):
        for name in files:
            fname = os.path.join(cur_dir, name)
            print("fname:%s" % fname)
            if fname.endswith(type):  # 符合指定类型结尾的文件
                if fname.endswith("pdf"):
                    file_list.append(fname)

                if fname.endswith("docx"):
                    pdf_name = os.path.join(convert_pdf_path, name.split(".")[0] + ".pdf")
                    convert_word_to_pdf(fname, pdf_name)
                    file_list.append(pdf_name)

                if fname.split(".")[-1] in ["ppt", "pptx"]:
                    pdf_name = os.path.join(convert_pdf_path, name.split(".")[0] + ".pdf")
                    convert_ppt_to_pdf(fname, pdf_name)
                    file_list.append(pdf_name)

        if not get_all_dirs:
            print("跳出循环")
            break

    print("总共有%d个文件" % file_list.__len__())
    return file_list


# 统计页码
def compute_page(path, type=("PDF", "pdf", "docx", "pptx", "ppt"), get_all_dirs=False):
    counts = 0
    file_list = get_all_file_by_type(path, type, get_all_dirs)

    for file in file_list:
        try:
            reader = PyPDF2.PdfFileReader(file)
            if reader.isEncrypted:
                reader.decrypt('')
            page_num = reader.getNumPages()
            print("文件《%s》有%s页" % (file, page_num))
            counts += page_num
        except Exception as e:
            print("文件%s出现异常:%s" % (file, e))
    return counts


# 文件夹不存在就创建
def create_path(path):
    if not os.path.exists(path):
        os.mkdir(path)


if __name__ == '__main__':
    # 创建文件夹，用于存放其它类型文件转成pdf类型的文件
    convert_pdf_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'convert_pdf\\')
    create_path(convert_pdf_path)
    
    # 要统计的文件目录
    path = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'files\\')
    print("path:%s" % path)
    
    counts = compute_page(path, get_all_dirs=True)
    print("总共%d页" % counts)

 

 

 

测试结果：