pip install python-docx
#安裝python-docx依賴庫
pip install xlrd
#讀Excel的庫
pip install xlwt
#寫Excel的庫
pip install xlutils
#復制Excel的庫

# _*_ coding:utf-8 _*_
import os
import win32com
import xlwt
from win32com.client import Dispatch
import sys
reload(sys)
sys.setdefaultencoding('utf-8')

#要轉(zhuǎn)換的doc文件目錄
docDir = r'C:\Users\Administrator\Desktop\井陘礦區(qū)\井陘礦區(qū)'
#轉(zhuǎn)換成功的docx文件目錄
docxDir = r'D:\data\data10'
#包含轉(zhuǎn)換信息的文件，主要包括轉(zhuǎn)換成功的文件，轉(zhuǎn)換失敗的文件
msgExcel = r'D:\data\data10\轉(zhuǎn)換信息表1.xls'

#文件總數(shù)
fileTotal = 0
#轉(zhuǎn)換正確的文件總數(shù)
successList = []
#裝換錯誤的文件總數(shù)
errorList = []

#將轉(zhuǎn)換信息寫入到excel中
def writeMsg():
    excel = xlwt.Workbook(encoding='utf-8')
    # 這個是指定sheet頁的名稱
    sheet1 = excel.add_sheet('統(tǒng)計信息')
    sheet2 = excel.add_sheet('詳細信息')

    sheet1.write(0, 0, '文件總數(shù)')
    sheet1.write(0, 1, '錄入正確')
    sheet1.write(0, 2, '錄入錯誤')
    sheet1.write(1, 0, fileTotal)
    sheet1.write(1, 1, len(successList))
    sheet1.write(1, 2, len(errorList))

    sheet2.write(0, 0, '錄入正確')
    sheet2.write(0, 1, '錄入錯誤')

    row = 1
    for x in successList:
        sheet2.write(row, 0, x)
        row += 1

    row = 1
    for x in errorList:
        sheet2.write(row, 1, x)
        row += 1

    excel.save(msgExcel.decode('utf-8'))

if __name__ == "__main__":

    word = win32com.client.Dispatch('word.application')
    word.DisplayAlerts = 0
    word.visible = 0
    PATH = unicode(docDir, 'utf8')
    for root, dirs, files in os.walk(PATH):
        fileTotal = len(files)
        for name in files:
            fileName = os.path.join(root, name)
            print fileName
            try:
                doc = word.Documents.Open(fileName)
                #這個是保存的目錄
                doc.SaveAs(docxDir + "\\" + fileName.split("\\")[-1].split(".")[0] + ".docx", 12)
                doc.Close()
                successList.append(name)
            except Exception as e:
                errorList.append(name)
                continue

    writeMsg()

# coding=UTF-8
from docx import Document
import xlrd

#打開word文檔
document = Document('test.docx')
#獲取word文檔中的所有表格是一個list
tempTable = document.tables
#獲取第一個表格
table = tempTable[0]
#遍歷表格
for x in table.rows:
    for y in x.cells:
        print y.text,
    print

# _*_ coding:utf-8 _*_
from docx import Document
import xlwt
import xlrd
from xlutils.copy import copy
import sys
import os
reload(sys)
sys.setdefaultencoding('utf-8')

#開始的excel
startExcel = r'D:\workSpace\forShow\學生信息表.xlsx'
#最后生成的excel，這個庫只能保存xls格式的文件
endExcel = r'D:\workSpace\forShow\學生信息表.xls'
#模板表
templete = r'D:\workSpace\forShow\模板表.docx'
#word所在的文件夾
wordDir = r'D:\workSpace\forShow\數(shù)據(jù)'
#模板表中每個字段對應的位置，鍵是字段，值是所在的位置
dict1 = {}

#判斷是否是英文
def isEnglish(checkStr):
    for ch in checkStr.decode('utf-8'):
        if u'\u4e00' <= ch <= u'\u9fff':
            return False
    return True


#讀取模板表
def readTemplate():

    document = Document(templete.decode('utf-8'))
    tempTable = document.tables
    table = tempTable[0]

    rowList = table.rows
    columnList = table.columns
    rowLength = len(rowList)
    columnLength = len(columnList)

    for rowIndex in range(rowLength):
        for columnIndex in range(columnLength):
            cell = table.cell(rowIndex,columnIndex)
            if isEnglish(cell.text):
                dict1.setdefault(cell.text,[rowIndex,columnIndex])

#讀入的表
re = xlrd.open_workbook(startExcel.decode("utf-8"))
#通過復制讀入的表來生成寫入的表
we = copy(re)

#寫第一頁的sheet
def writeFirstSheet1(table, row):

    sheet = we.get_sheet(0)
    #將字段對應的值填到sheet1dict中
    sheet1dict = {}
    for key in dict1:
        tempList = dict1[key]
        for index in range(0,1):
            x = tempList[index]
            y = tempList[index+1]
            sheet1dict.setdefault(key,table.cell(x,y).text)


    #讀取第一個sheet
    tempSheet = re.sheet_by_index(0)
    #讀取第一個sheet中的第二行
    list1 = tempSheet.row_values(1)
    for excelIndex in range(len(list1)):
        for key in sheet1dict:
            if list1[excelIndex] == key:
                #將sheet1dict中的內(nèi)容寫入excel的sheet中
                sheet.write(row, excelIndex, sheet1dict[key])

#將word中數(shù)據(jù)寫入excel
def writeExcel(wordName, row):
    document = Document(wordName)
    tempTable = document.tables
    table = tempTable[0]

    #一個excel一般有好幾個sheet（即頁數(shù)），所以單獨寫一個函數(shù)
    writeFirstSheet1(table, row)

    we.save(endExcel.decode("utf-8"))

if __name__ == "__main__":

    readTemplate()
    docFiles = os.listdir(wordDir.decode("utf-8"))
    # 開始數(shù)據(jù)的行數(shù)
    row = 1
    for doc in docFiles:
        #輸出文件名
        print doc.decode("utf-8")
        try:
            row += 1
            writeExcel(wordDir + '\\' + doc.decode("utf-8"), row)
        except Exception as e:
            print(e)

from pathlib import Path, PurePath
from openpyxl import load_workbook
from docx import Document

# 當前目錄
p = Path('./')
# 獲取所有 xlsx 文件
files = [x for x in p.iterdir() if x.is_file() and PurePath(x).match('*.xlsx')]

# 創(chuàng)建 Word 文檔
doc = Document()

for file in files:
    print(f'文件名={file.name}')
    wb = load_workbook(file)
    for sheet_name in wb.sheetnames:
        print(f"工作表名稱: {sheet_name}")
        ws = wb[sheet_name]

        # 在 Word 中加標題（文件名 + sheet名）
        doc.add_heading(f"{file.name} - {sheet_name}", level=2)

        # 獲取 sheet 所有數(shù)據(jù)
        data = []
        for row in ws.iter_rows(values_only=True):
            # 如果整行都是空，則跳過
            if all(cell in (None, '') for cell in row):
                continue
            data.append([str(cell) if cell is not None else '' for cell in row])

        if data:
            # 創(chuàng)建 Word 表格
            table = doc.add_table(rows=1, cols=len(data[0]))
            table.style = 'Table Grid'

            # 表頭（假如沒有表頭，這里就只是第一行）
            hdr_cells = table.rows[0].cells
            for idx, val in enumerate(data[0]):
                hdr_cells[idx].text = val

            # 添加數(shù)據(jù)行
            for row_data in data[1:]:
                row_cells = table.add_row().cells
                for idx, val in enumerate(row_data):
                    row_cells[idx].text = val

            doc.add_paragraph('')  # 分段落空行
        else:
            doc.add_paragraph('（此工作表為空）')

# 保存 Word 文件
output_dir = Path('../word')
output_dir.mkdir(exist_ok=True, parents=True)
output_file = output_dir / 'merged.docx'
doc.save(output_file)

print(f"已將所有 Excel 數(shù)據(jù)寫入 Word 文件: {output_file}")