pip install python-docx pywin32 xlrd

Microsoft Windows [版本 10.0.19043.1415]
(c) Microsoft Corporation。保留所有权利。
 
C:\Windows\System32>python tools.py 花名册.xlsx

#! /usr/bin env python
# -*- coding:utf-8 -*-
 
"""
============================
======Power By Python3======
====== Author Task138 ======
============================
"""
 
import sys
import xlrd, os, re
From docx import Document
from docxcompose.COMposer import Composer
from win32com import client as wc
 
 
# 读Excel表获取学生的学号和姓名
def read_excel(excel_file):
    workBook = xlrd.oPEn_workbook(excel_file)
    sheet = workbook.sheet_by_index(0)
    name_list = []
    name_dict = []
 
    Sno_list = sheet.col_values(2)[1::]
    Sname_list = sheet.col_values(3)[1::]
    for i in range(len(Sno_list)):
        try:
            Sno = str(int(Sno_list[i]))
        except:
            Sno = Sno_list[i]
        dict = {}
        dict['Sno'] = Sno
        dict['Sname'] = Sname_list[i]
        name_list.append(Sname_list[i])
        name_dict.append(dict)
 
    return name_list, name_dict
 
# 合并文档
def merge_doc(source_file_path_list,target_file_path):
    #填充分页符号文档
    page_break_doc = Document()
    page_break_doc.add_page_break()
    #定义新文档
    target_doc = Document(source_file_path_list[0])
    target_composer = Composer(target_doc)
    for i in range(len(source_file_path_list)):
        #跳过第一个作为模板的文件
        if i==0:
            continue
        #填充分页符文档
        target_composer.append(page_break_doc)
        #拼接文档内容
        f = source_file_path_list[i]
        target_composer.append(Document(f))
    #保存目标文档
    target_composer.save(target_file_path)
    PRint('[ %s ]保存成功' % target_file_path)
 
 
if __name__ == '__main__':
    if len(sys.argv) < 2:
        print('缺乏必要的参数，请输入学生Excel表作为参数')
        print('程序终止')
        exIT()
 
    excel_file = sys.argv[1]
 
 
    print('请选择需要执行的功能：')
    print('[ 0 ] 查看各实训目录下未提交的学生名单')
    print('[ 1 ] 合并实训文件')
    cmd = input('请选择： ')
 
    while cmd not in ['0','1']:
        print('输入有误，请重新输入，按 Ctrl+C 可退出程序')
        print('请选择需要执行的功能：')
        print('[ 0 ] 查看各实训目录下未提交的学生名单')
        print('[ 1 ] 合并实训文件')
        cmd = input('请选择： ')
 
    try:
        name_list, name_dict = read_excel(excel_file)
    except Exception as e:
        print('Excel读取失败，程序终止，错误如下：')
        print(e)
        print()
        exit()
    else:
        if cmd == '0':
            # 实训目录的数列
            file_list = []
            for i in os.listdir():
                if os.path.isdir(i):
                    if re.match(r'实训\d', i):
                        file_list.append(i)
 
            for i in range(1, len(file_list) + 1):
                dir_name = '实训%s' % i
                # 进入该实训目录
                os.chdir(dir_name)
                file_list = os.listdir()
                submit_list = []
                for x in file_list:
                    for j in name_list:
                        if j in x and j not in submit_list:
                            submit_list.append(j)
                result = list(set(submit_list) ^ set(name_list))
                if result:
                    print(dir_name, result)
                os.chdir('../')
 
        if cmd == '1':
            if not os.path.exists('实训汇总'):
                os.mkdir('实训汇总')
                print('目录[ 实训汇总 ]创建成功')
 
            # 实训目录的数列
            file_list = []
            for i in os.listdir():
                if os.path.isdir(i):
                    if re.match(r'实训\d',i):
                        file_list.append(i)
 
 
            for i in name_dict:
                doc_list = []
                for j in range(1,len(file_list)+1):
                    dir_name = '实训%s' % j
                    # 进入该实训目录
                    os.chdir(dir_name)
 
                    tmp = []
                    for x in os.listdir():
                        # 判断文件尾缀
                        fname,fext = os.path.splitext(x)
                        # 如果是.doc，则转换为.docx
                        if fext == '.doc' and not x.startswith('~$'):
                            w = wc.Dispatch('Word.Application')
                            doc = w.Documents.Open(os.path.abspath(x))
                            doc.SaveAs(os.path.join(os.getcwd(),'%s.docx' % fname), 16)
                            doc.Close()
                            os.remove(x)
                            print('转换文件[ %s ]类型为.docx' % x)
                        elif fext == '.docx':
                            if (i['Sname'] in x) and (len(tmp) == 0):
                                # 只有一个文件
                                tmp.append(x)
                            elif (i['Sname'] in x) and (len(tmp) != 0):
                                # 有多个文件，按照最新的修改时间进行替换
                                tmp_file = tmp.pop()
                                old_file_mtime = os.path.getmtime(tmp_file)
                                new_file_mtime = os.path.getmtime(x)
                                if new_file_mtime > old_file_mtime:
                                    # 新文件比较新，以新的为准
                                    tmp.append(x)
                                else:
                                    # 老文件比较新，以老文件为准
                                    tmp.append(tmp_file)
                        else:
                            # 其它文件类型，直接跳过
                            # print('当前文件[ %s ]类型不是.doc或者.docx，跳过此文件的合并' % os.path.abspath(x))
                            continue
 
                    if tmp:
                        # 如果这次实训有这位同学的文件
                        doc_list.append(os.path.join(dir_name,tmp.pop()))
                    # 返回父目录
                    os.chdir('../')
                if doc_list:
                    # 有内容，进行文档合并
                    try:
                        merge_file_name = i['Sno'] + '-' + i['Sname'] + '-' + '实训汇总' + '.docx'
                        merge_doc(doc_list, './实训汇总/' + merge_file_name)
                    except Exception as e:
                        print()
                        print('[ %s ]学生信息有误，程序中断' % i['Sname'])
                        print(e)
                        print()