【办公类-131-05】20261007中2班周计划制作（原资料Word单元格不统一 失败）

背景需求

因为win电脑坏了，所以换了一个只有WPS的电脑，所有的周计划py都要重做

零、原有资料

一、doc改名成01周、02周

因为每次提供的原始的文件名标注不一样，所以重新用豆包写新的代码（文件名数字变成两位数）

import os
import shutil
import time
import re


import os
import re
import shutil

# 定义路径
path = r"D:\Python最终内容\20261007中2班周计划"
path1 = path + r"\00doc"   # 源文件夹
path2 = path + r"\01doc"   # 输出目标文件夹

# 创建目标文件夹
os.makedirs(path2, exist_ok=True)

print('--开始：保留原文件名空格，周次数字转为两位数，处理结果保存到01doc-----')

# 获取源文件夹文件列表
fileList = os.listdir(path1)

for file in fileList:
    old_full_src = os.path.join(path1, file)
    # 跳过文件夹，只处理文件
    if not os.path.isfile(old_full_src):
        continue

    match = re.search(r'第(.*?)周', file)
    if match:
        week_str = match.group(1)
        print(f"原始周文字：{week_str}")
        
        # 提取周段开头第一个数字
        num_match = re.search(r'^\d+', week_str)
        if num_match:
            first_num = num_match.group()
            if len(first_num) == 1:
                new_first = f"{int(first_num):02d}"
                new_week_str = week_str.replace(first_num, new_first, 1)
                newname = file.replace(f'第{week_str}周', f'第{new_week_str}周')
            else:
                newname = file
        else:
            newname = file
    else:
        # 没有匹配到"第xx周"，文件名不变
        newname = file

    print(f"处理后文件名：{newname}")
    new_full_dst = os.path.join(path2, newname)
    
    # 复制文件到01doc，使用新名称，源文件保持不变
    shutil.copy2(old_full_src, new_full_dst)
    print(f"已复制: {file} -> {newname}\n")

print('\n--全部处理完成！结果全部保存在01doc文件夹--')

二、doc改成docx

'''
doc转docx
Deepseek，阿夏
20260228
'''
import os  
from win32com import client as wc  
  
# 路径设置  
path = r"D:\Python最终内容\20261007中2班信息窗"  
oldpath = os.path.join(path, r'01doc')  # 原文件doc地址  
newpath = os.path.join(path, r'02docx')  # 新文件docx地址  
  
# 确保新路径存在  
os.makedirs(newpath,exist_ok=True)  
  
# 提取所有doc和docx文件的路径  
files = []  
for file in os.listdir(oldpath):  
    if file.lower().ends
'''
doc转docx
Deepseek，阿夏
20260228
'''
import os  
from win32com import client as wc  
  
# 路径设置  
path = r"D:\Python最终内容\20261007中2班周计划"  
oldpath = os.path.join(path, r'01doc')  # 原文件doc地址  
newpath = os.path.join(path, r'02docx')  # 新文件docx地址  
  
# 确保新路径存在  
os.makedirs(newpath,exist_ok=True)  
  
# 提取所有doc和docx文件的路径  
files = []  
for file in os.listdir(oldpath):  
    if file.lower().endswith(('.doc', '.docx')) and not file.startswith('~$'):  
        files.append(os.path.join(oldpath, file))  
  
# 打开并转换文件  
word = wc.Dispatch("Word.Application")  
word.Visible = False  # 设置为False以在后台运行  
try:  
    for file in files:  
        print("处理文件：" + file)  
        doc = word.Documents.Open(file)  
          
        # 提取文件名和修改扩展名  
        base_name = os.path.basename(file)  
        name, ext = os.path.splitext(base_name)  
        new_file = os.path.join(newpath, name + '.docx')  
          
        # 保存为docx格式  
        doc.SaveAs(new_file, 12)  # 12表示docx格式  
        doc.Close()  
except Exception as e:  
    print(f"发生错误：{e}")  
finally:  
    word.Quit()with(('.doc', '.docx')) and not file.startswith('~$'):  
        files.append(os.path.join(oldpath, file))  
  
# 打开并转换文件  
word = wc.Dispatch("Word.Application")  
word.Visible = False  # 设置为False以在后台运行  
try:  
    for file in files:  
        print("处理文件：" + file)  
        doc = word.Documents.Open(file)  
          
        # 提取文件名和修改扩展名  
        base_name = os.path.basename(file)  
        name, ext = os.path.splitext(base_name)  
        new_file = os.path.join(newpath, name + '.docx')  
          
        # 保存为docx格式  
        doc.SaveAs(new_file, 12)  # 12表示docx格式  
        doc.Close()  
except Exception as e:  
    print(f"发生错误：{e}")  
finally:  
    word.Quit()

三、去掉回车

'''
去掉docx文件里的回车
Deepseek，阿夏
20260228
'''


import glob,os
from docx import Document  
  


path = r"D:\Python最终内容\20261007中2班周计划"  

newpath = os.path.join(path, r'03去掉回车')  # 新文件docx地址  
os.makedirs(newpath,exist_ok=True)  

docx_files = glob.glob(path + r'\02docx\*.docx')  # 读取所有.docx文件  
  
for file_path in docx_files:  # 遍历每个文件路径  
    file_name = os.path.basename(file_path)  # 获取文件名  
    print(f"Processing file: {file_name}")  
      
    doc = Document(file_path)  # 打开文档  
      
    # 使用列表推导式创建一个新段落列表，排除空段落  
    new_paragraphs = [p for p in doc.paragraphs if p.text.strip()]  
      
    # 清空当前文档的所有段落  
    doc.paragraphs[:] = []  
      
    # 将非空段落添加回文档  
    for p in new_paragraphs:  
        doc.add_paragraph(p.text)  

    doc.save(newpath +fr"\{file_name}") 
# # # ------------------------------------------------
# # # 版权声明：本文为CSDN博主「lsjweiyi」的原创文章，遵循CC 4.0 BY-SA版权协议，转载请附上原文出处链接及本声明。
# # # 原文链接：https://blog.csdn.net/lsjweiyi/article/details/121728630


   

四、word导出到EXCEL内容第一次

from docx import Document
import os
import glob
from openpyxl import Workbook

newpath = r'D:\Python最终内容\20261007中2班周计划'
new = newpath + r'\03去掉回车'
os.makedirs(newpath, exist_ok=True)

pathall = []
for file_name in os.listdir(new):
    fullp = os.path.join(new, file_name)
    pathall.append(fullp)
print(pathall)
print(len(pathall))

# 使用openpyxl新建工作簿
wb = Workbook()
ws = wb.active
ws.title = "sheet1"
titleall = ['grade', 'classnum', 'weekhan', 'datelong', 'day1', 'day2', 'day3', 'day4', 'day5', 'day6', 'day7', 'life', 'life1', 'life2',
             'sportcon1', 'sportcon2', 'sportcon3', 'sportcon4', 'sportcon5', 'sportcon6', 'sportcon7', 'sport1', 'sport2', 'sport3', 'sport4',
             'sport5', 'sport6', 'sport7', 'sportzd1', 'sportzd2', 'sportzd3', 'game1', 'game2', 'game3', 'game4', 'game5', 'game6', 'game7',
             'gamezd1', 'gamezd2', 'theme', 'theme1', 'theme2', 'gbstudy', 'art', 'gbstudy1', 'gbstudy2', 'gbstudy3', 'jtstudy1', 'jtstudy2',
             'jtstudy3', 'jtstudy4', 'jtstudy5', 'jtstudy6', 'jtstudy7', 'gy1', 'gy2', 'fk1', 'pj11', 'fk1nr', 'fk1tz', 'fk2', 'pj21', 'fk2nr',
             'fk2tz', 'dateshort', 'weekshu', 'title1', 'topic11', 'topic12', 'jy1', 'cl1', 'j1gc', 'title2', 'topic21', 'topic22', 'jy2', 'cl2',
             'j2gc', 'title3', 'topic31', 'topic32', 'jy3', 'cl3', 'j3gc', 'title4', 'topic41', 'topic42', 'jy4', 'cl4', 'j4gc', 'title5',
             'topic51', 'topic52', 'jy5', 'cl5', 'j5gc', 'title6', 'topic61', 'topic62', 'jy6', 'cl6', 'j6gc', 'title7', 'topic71', 'topic72',
             'jy7', 'cl7', 'j7gc', 'fs1', 'fs11', 'fs2', 'fs21', 'T1', 'T2', 'T3', 'T4', 'T5', 'T6', 'T7']
# 写入表头
for col_idx, val in enumerate(titleall):
    ws.cell(row=1, column=col_idx + 1, value=val)

n = 2  # excel行从第2行开始写数据，第一行表头

for h in range(len(pathall)):
    LIST = []
    doc_path = pathall[h]
    print(f"\n=====正在解析文件：{os.path.basename(doc_path)} =====")
    try:
        doc = Document(doc_path)
        tables = doc.tables
        total_table_count = len(tables)
        print(f"本文件总表格数量 total_table_count={total_table_count}")

        first_table = doc.tables[0]
        first_row = first_table.rows[0]
        num_columns = len(first_row.cells)
        print(f"第{n - 1}张表格有 {num_columns} 列")

        # 获取文档第一段落：中（2）班 第XX周 活动安排
        bt = doc.paragraphs[0].text.strip()
        LIST.append(bt[0])
        LIST.append(bt[2])
        if len(bt) == 16:
            LIST.append(bt[8:9])
        else:
            LIST.append(bt[8:10])

        rq1 = doc.paragraphs[1].text.strip()
        LIST.append(rq1[3:])

        table = tables[0]
        d = [9, 10, 11]
        dl = [8, 9, 10]
        tj = [2, 1, 0]

        for dd in range(len(d)):
            if num_columns == int(d[dd]):
                for xq in range(3, dl[dd]):
                    xq1 = table.cell(0, xq).text
                    LIST.append(xq1)
                for tx in range(int(tj[dd])):
                    LIST.append('')

        # 生活内容
        l = table.cell(1, 4).text.strip()
        ll = l.split('\n')
        LIST.append(l)
        for lll in range(2):
            if lll < len(ll):
                item = ll[lll]
                if len(item) > 2:
                    LIST.append(item[2:])
                else:
                    LIST.append("")
            else:
                LIST.append("")

        # 运动集体、分散游戏
        for dd in range(len(d)):
            if num_columns == int(d[dd]):
                for jt in range(3, dl[dd]):
                    jt1 = table.cell(3, jt).text
                    LIST.append(jt1)
                for tx in range(tj[dd]):
                    LIST.append('')
                for jt2 in range(3, dl[dd]):
                    jt3 = table.cell(4, jt2).text
                    LIST.append(jt3)
                for tx in range(tj[dd]):
                    LIST.append('')

        # 运动观察指导
        s = table.cell(5, 4).text.split('\n')
        for sss in range(3):
            if sss < len(s):
                LIST.append(s[sss][2:] if len(s[sss]) > 2 else "")
            else:
                LIST.append("")

        # 游戏内容
        for dd in range(len(d)):
            if num_columns == int(d[dd]):
                for fj in range(3, dl[dd]):
                    fj2 = table.cell(7, fj).text
                    LIST.append(fj2)
                for tx in range(int(tj[dd])):
                    LIST.append('')

        # 游戏观察指导
        g = table.cell(8, 4).text.split('\n')
        for ggg in range(2):
            if ggg < len(g):
                LIST.append(g[ggg][2:] if len(g[ggg]) > 2 else "")
            else:
                LIST.append("")

        # 主题
        ti = table.cell(9, 4).text.split('\n')
        LIST.append(ti[0] if len(ti) >= 1 else "")
        for ttt in range(1, 3):
            if ttt < len(ti):
                LIST.append(ti[ttt][2:] if len(ti[ttt]) > 2 else "")
            else:
                LIST.append("")

        #个别化学习
        iiii = table.cell(10, 4).text
        LIST.append(iiii)
        ii8 = table.cell(11, 4).text
        LIST.append(ii8)

        ii = table.cell(12, 4).text.split('\n')
        for iii1 in range(3):
            if iii1 < len(ii):
                LIST.append(ii[iii1][2:] if len(ii[iii1]) > 2 else "")
            else:
                LIST.append("")

        #集体学习栏目
        for dd in range(len(d)):
            if num_columns == int(d[dd]):
                for e in range(3, dl[dd]):
                    k = table.cell(13, e).text
                    LIST.append(k)
                for tx in range(int(tj[dd])):
                    LIST.append('')

        #家园共育
        yy = table.cell(14, 4).text.split('\n')
        for yyy in range(2):
            if yyy < len(yy):
                LIST.append(yy[yyy][2:] if len(yy[yyy]) > 2 else "")
            else:
                LIST.append("")

        #反馈调整
        for dd in range(len(d)):
            if num_columns == int(d[dd]):
                ff = table.cell(1, dl[dd]).text.split('\n')
                for j in range(2):
                    pos = j * 4
                    if pos < len(ff):
                        LIST.append(ff[pos][0:4])
                        LIST.append(ff[pos][10:-1])
                    else:
                        LIST.append("")
                        LIST.append("")
                    if pos + 1 < len(ff):
                        LIST.append(ff[pos + 1])
                    else:
                        LIST.append("")
                    if pos + 3 < len(ff):
                        LIST.append(ff[pos + 3])
                    else:
                        LIST.append("")

        date1 = ""
        date2 = ""
        bt2 = ""
        for p in doc.paragraphs:
            text = p.text.strip()
            if "期" in text and "第" in text:
                bt2 = text
                break
        if bt2:
            start_index = bt2.find('期')
            end_index = bt2.find('第')
            if start_index != -1 and end_index != -1 and start_index < end_index:
                date1 = bt2[start_index + 1: end_index].strip()
            start_index2 = bt2.find('（')
            end_index2 = bt2.find('）')
            if start_index2 != -1 and end_index2 != -1 and start_index2 < end_index2:
                date2 = bt2[start_index2 + 1: end_index2].strip()
        LIST.append(date1)
        LIST.append(date2)

        ts = [3, 4, 4]
        ks = [12, 6, 0]

        for dd in range(len(d)):
            if num_columns == int(d[dd]):
                for a in range(1, ts[dd]):
                    for b in range(2):
                        # =========边界判断！！防止索引越界========
                        if 0 <= a < total_table_count:
                            table = tables[a]
                        else:
                            print(f"警告：a={a}超出表格总数{total_table_count}，填充空值")
                            for _ in range(6):
                                LIST.append('')
                            continue

                        all_lines = table.cell(0, b).text.split('\n')
                        if len(all_lines) == 1:
                            for _ in range(6):
                                LIST.append('')
                        else:
                            fs1 = all_lines[0].strip()
                            title = ""
                            if "：" in fs1:
                                start_idx = fs1.index("：") + 1
                                if "执" in fs1:
                                    end_idx = fs1.index("执")
                                    title = fs1[start_idx:end_idx].strip()
                                else:
                                    title = fs1[start_idx:].strip()
                            LIST.append(title)

                            target_start_idx = -1
                            for idx, content in enumerate(all_lines):
                                if "活动目标：" in content:
                                    target_start_idx = idx
                                    break
                            for i in range(1, 3):
                                if target_start_idx != -1 and (target_start_idx + i) < len(all_lines):
                                    mb = all_lines[target_start_idx + i].lstrip("1234567890.、").strip()
                                    LIST.append(mb)
                                else:
                                    LIST.append("")

                            experience_prep = ""
                            material_prep = ""
                            prep_start_idx = -1
                            for idx, content in enumerate(all_lines):
                                if "活动准备：" in content:
                                    prep_start_idx = idx
                                    break
                            if prep_start_idx != -1:
                                for i in range(prep_start_idx + 1, len(all_lines)):
                                    line = all_lines[i].strip()
                                    if not line:
                                        continue
                                    if line.startswith("经验准备："):
                                        experience_prep = line[5:].strip()
                                    elif line.startswith("物质准备："):
                                        material_prep = line[5:].strip()
                            LIST.append(experience_prep)
                            LIST.append(material_prep)

                            pro_lines = []
                            flag = False
                            for line in all_lines:
                                if "活动过程：" in line:
                                    flag = True
                                    continue
                                if flag:
                                    pro_lines.append(line)
                            PRO = '\n'.join(pro_lines)
                            LIST.append(PRO)

                for a in range(int(ts[dd]), int(ts[dd]) + 1):
                    for b in range(1):
                        if 0 <= a < total_table_count:
                            table = tables[a]
                        else:
                            print(f"警告 a={a}超出表格总数{total_table_count}，填充空")
                            LIST.append('')
                            for _ in range(5):
                                LIST.append("")
                            for _ in range(int(ks[dd])):
                                LIST.append('')
                            continue

                        all_lines = table.cell(0, b).text.split('\n')
                        if len(all_lines) == 1:
                            LIST.append('')
                        else:
                            fs1 = all_lines[0].strip()
                            title = ""
                            if "：" in fs1 and "执" in fs1:
                                s_idx = fs1.index("：") + 1
                                e_idx = fs1.index("执")
                                title = fs1[s_idx:e_idx].strip()
                            LIST.append(title)
                            for t in range(2, 4):
                                if t < len(all_lines):
                                    LIST.append(all_lines[t][2:].strip())
                                else:
                                    LIST.append("")
                            if 5 < len(all_lines):
                                LIST.append(all_lines[5][5:].strip())
                            else:
                                LIST.append("")
                            if 6 < len(all_lines):
                                LIST.append(all_lines[6][5:].strip())
                            else:
                                LIST.append("")
                            pro = all_lines[8:] if 8 < len(all_lines) else []
                            PRO = '\n'.join(pro)
                            LIST.append(PRO)
                            for _ in range(int(ks[dd])):
                                LIST.append('')

                for c in range(2):
                    a_idx = ts[dd]
                    if 0 <= a_idx < total_table_count:
                        table = tables[a_idx]
                    else:
                        print(f"警告 a_idx={a_idx}超出表格总数{total_table_count}")
                        LIST.append("")
                        LIST.append("")
                        continue

                    fs = table.cell(c, 1).text.split('\n')
                    if len(fs) >= 2:
                        fs2 = fs[1]
                        title_reflect = ""
                        if "：" in fs2 and "执" in fs2:
                            s_idx = fs2.index("：") + 1
                            e_idx = fs2.index("执")
                            title_reflect = fs2[s_idx:e_idx].strip()
                        LIST.append(title_reflect)
                        reflect_text = '\n'.join(["        " + x for x in fs[2:]])
                        LIST.append(reflect_text)
                    else:
                        LIST.append("")
                        LIST.append("")

                extracted_texts = []
                for tab in doc.tables[:5]:
                    for cell in tab.rows[0].cells:
                        ct = cell.text.strip()
                        if '执教：' in ct:
                            s = ct.find('执教：') + len('执教：')
                            e = ct.find('\n')
                            extracted_texts.append(ct[s:e].strip() if e != -1 else ct[s:].strip())
                for tname in extracted_texts:
                    LIST.append(tname)

        # 写入excel一行
        for col_index, cell_val in enumerate(LIST):
            ws.cell(row=n, column=col_index + 1, value=cell_val)
        n += 1
    except Exception as err:
        print(f"!!!解析文件 {doc_path} 发生异常：{err}")
        print("跳过该文件，继续下一个")

#保存文件
out1 = os.path.join(newpath, r'09_00 旧版周计划提取信息（导出一次）.xlsx')
out2 = os.path.join(newpath, r'09_01 旧版周计划提取信息（手动修改）.xlsx')
wb.save(out1)
wb.save(out2)
print(f"\n全部处理完成，输出文件:\n{out1}\n{out2}")

提取的内容有大量缺失，说明每个Word的周计划表格是不一样的。

这个问题在上一次也遇到，

但是上次只有5周有问题，所以人工调用一个正确模版，把错误的周的内容重新黏贴。最后也顺利生成

【办公类-131-03】20260221"开学主题墙面四件套"3------"周计划教案"操作步骤https://mp.csdn.net/mp_blog/creation/editor/158182738

本次大量内容没有被提取，所以这个代码不行。------必须统一Word单元格结构。

二、解决策略

先把基础信息填写好，批量生成只有日期周次的空内容的模版，把原Word内容手动黏贴进去。然后再用程序提取