Python如何实现将Word表格数据导入Excel

pip install Spire.Doc
pip install Spire.XLS

from spire.doc import *
from spire.xls import *

# 加载 Word 文档
doc = Document()
doc.LoadFromFile('input.docx')

# 创建 Excel 工作簿并清空默认工作表
wb = Workbook()
wb.Worksheets.Clear()

# 遍历文档中的所有节
for i in range(doc.Sections.Count):
    section = doc.Sections.get_Item(i)

    # 遍历节中的所有表格
    for j in range(section.Tables.Count):
        table = section.Tables.get_Item(j)

        # 为每张表格创建独立工作表，命名包含节序号和表序号
        ws = wb.Worksheets.Add(f'Table_{i+1}_{j+1}')

        # 逐行逐单元格写入数据
        for row in range(table.Rows.Count):
            tableRow = table.Rows.get_Item(row)

            for cell in range(tableRow.Cells.Count):
                tableCell = tableRow.Cells.get_Item(cell)

                # 拼接单元格内所有段落的文本
                cellText = ''
                for paragraph in range(tableCell.Paragraphs.Count):
                    paragraph = tableCell.Paragraphs.get_Item(paragraph)
                    cellText = cellText + (paragraph.Text + ' ')

                # 以 "00" 开头的文本直接赋值，避免被 Excel 自动转为数字
                if cellText.startswith('00'):
                    ws.Range[row + 1, cell + 1].Text = cellText
                else:
                    ws.SetCellValue(row + 1, cell + 1, cellText)

        # 根据内容自动调整列宽
        ws.AllocatedRange.AutoFitColumns()

# 保存为 Excel 2016 格式
wb.SaveToFile('output/WordTableToExcel.xlsx', FileFormat.Version2016)

doc.Close()
wb.Dispose()

pip install python-docx openpyxl

from docx import Document
from openpyxl import Workbook

doc = Document("input.docx")
wb = Workbook()
ws = wb.active

table = doc.tables[0]                    # 第一个表格
for r, row in enumerate(table.rows, start=1):
    for c, cell in enumerate(row.cells, start=1):
        ws.cell(row=r, column=c, value=cell.text.strip())

wb.save("output.xlsx")

from docx import Document
from openpyxl import Workbook
from openpyxl.utils import get_column_letter

def docx_tables_to_excel(docx_path, xlsx_path):
    doc = Document(docx_path)
    wb = Workbook()
    wb.remove(wb.active)                 # 删掉默认空 sheet

    for idx, table in enumerate(doc.tables, start=1):
        ws = wb.create_sheet(title=f"Table{idx}")

        for r, row in enumerate(table.rows, start=1):
            for c, cell in enumerate(row.cells, start=1):
                ws.cell(row=r, column=c, value=cell.text.strip())

        # 自适应列宽（可选）
        for col in ws.columns:
            max_len = max((len(str(cell.value)) if cell.value else 0) for cell in col)
            ws.column_dimensions[get_column_letter(col[0].column)].width = min(max_len + 2, 50)

    wb.save(xlsx_path)

docx_tables_to_excel("input.docx", "output.xlsx")

for row in table.rows:
    ws.append([cell.text.strip() for cell in row.cells])

n_rows = len(table.rows)
n_cols = len(table.columns)
cells = table._cells                     # 按网格展开，合并处会重复填值
for r in range(n_rows):
    for c in range(n_cols):
        cell = cells[r * n_cols + c]
        ws.cell(row=r + 1, column=c + 1, value=cell.text.strip())

import pandas as pd
from docx import Document

doc = Document("input.docx")
with pd.ExcelWriter("output.xlsx") as writer:
    for i, table in enumerate(doc.tables, start=1):
        data = [[cell.text.strip() for cell in row.cells] for row in table.rows]
        pd.DataFrame(data).to_excel(writer, sheet_name=f"Table{i}", index=False, header=False)