Python高效转换Word表格为Excel的方案全解析

pip install python-docx openpyxl pandas

from docx import document
import openpyxl

# 读取word表格
doc = document("report.docx")
table = doc.tables[0]  # 获取第一个表格

# 创建excel工作簿
wb = openpyxl.workbook()
ws = wb.active

# 写入数据
for row_idx, row in enumerate(table.rows):
    for col_idx, cell in enumerate(row.cells):
        ws.cell(row=row_idx+1, column=col_idx+1, value=cell.text)

# 保存excel
wb.save("output.xlsx")

from docx import document
import pandas as pd

doc = document("multi_tables.docx")
all_data = []

for table in doc.tables:  # 遍历所有表格
    table_data = []
    for row in table.rows:
        table_data.append([cell.text for cell in row.cells])
    all_data.extend(table_data[1:])  # 跳过表头（假设所有表格结构相同）

# 用pandas写入excel（自动处理数据类型）
df = pd.dataframe(all_data, columns=["产品", "销量", "单价", "总额"])
df.to_excel("merged_output.xlsx", index=false)

from docx import document
import openpyxl

doc = document("numeric_data.docx")
table = doc.tables[0]

wb = openpyxl.workbook()
ws = wb.active

for row_idx, row in enumerate(table.rows):
    for col_idx, cell in enumerate(row.cells):
        text = cell.text
        # 尝试转换为数字
        if text.replace('.', '', 1).isdigit():  # 简单判断是否为数字
            value = float(text) if '.' in text else int(text)
        else:
            value = text
        ws.cell(row=row_idx+1, column=col_idx+1, value=value)

wb.save("numeric_output.xlsx")

from docx import document
import openpyxl

doc = document("merged_cells.docx")
table = doc.tables[0]

wb = openpyxl.workbook()
ws = wb.active

prev_cell_text = ""  # 记录上一行同列的文本
for row_idx, row in enumerate(table.rows):
    for col_idx, cell in enumerate(row.cells):
        current_text = cell.text
        # 如果单元格为空且上一行同列有内容，可能是合并单元格
        if not current_text and prev_cell_text:
            current_text = prev_cell_text
        ws.cell(row=row_idx+1, column=col_idx+1, value=current_text)
        prev_cell_text = current_text if col_idx == 0 else ""  # 只记录第一列的延续文本

wb.save("merged_cells_output.xlsx")

from docx import document
import openpyxl
from concurrent.futures import threadpoolexecutor

def process_table(table, start_row):
    """处理单个表格的函数"""
    data = []
    for row in table.rows:
        data.append([cell.text for cell in row.cells])
    return data

doc = document("large_file.docx")
all_tables_data = []

# 使用线程池处理表格（注意：openpyxl写入需单线程）
with threadpoolexecutor() as executor:
    results = [executor.submit(process_table, table, idx) 
              for idx, table in enumerate(doc.tables)]
    all_tables_data = [r.result() for r in results]

# 单线程写入excel
wb = openpyxl.workbook()
ws = wb.active
current_row = 1
for table_data in all_tables_data:
    for row in table_data:
        for col_idx, value in enumerate(row):
            ws.cell(row=current_row, column=col_idx+1, value=value)
        current_row += 1

wb.save("optimized_output.xlsx")

from docx import document
import pandas as pd
from typing import list, union

def word_tables_to_excel(
    docx_path: str,
    excel_path: str,
    sheet_name: str = "sheet1",
    skip_header: bool = false,
    numeric_conversion: bool = true
) -> none:
    """
    将word文档中的所有表格转换为excel工作表
    
    参数:
        docx_path: word文档路径
        excel_path: 输出excel路径
        sheet_name: 工作表名称
        skip_header: 是否跳过每个表格的第一行（表头）
        numeric_conversion: 是否尝试将文本转换为数字
    """
    doc = document(docx_path)
    all_data = []
    
    for table in doc.tables:
        table_data = []
        for row in table.rows:
            row_data = []
            for cell in row.cells:
                text = cell.text
                if numeric_conversion and text.replace('.', '', 1).isdigit():
                    try:
                        value = float(text) if '.' in text else int(text)
                    except valueerror:
                        value = text
                else:
                    value = text
                row_data.append(value)
            table_data.append(row_data)
        
        if skip_header and len(table_data) > 0:
            table_data = table_data[1:]
        all_data.extend(table_data)
    
    # 如果没有数据，创建空dataframe
    if not all_data:
        df = pd.dataframe()
    else:
        # 动态推断列名（假设所有表格结构相同）
        if len(all_data) > 0 and len(all_data[0]) > 0:
            columns = [f"column_{i+1}" for i in range(len(all_data[0]))]
            # 如果第一个元素是字符串且看起来像表头，则使用它
            first_row = all_data[0]
            if all(isinstance(x, str) for x in first_row):
                columns = first_row
                all_data = all_data[1:]
            df = pd.dataframe(all_data, columns=columns)
        else:
            df = pd.dataframe(all_data)
    
    # 写入excel
    with pd.excelwriter(excel_path, engine='openpyxl') as writer:
        df.to_excel(writer, sheet_name=sheet_name, index=false)

# 使用示例
word_tables_to_excel(
    docx_path="input.docx",
    excel_path="output.xlsx",
    sheet_name="销售数据",
    skip_header=true,
    numeric_conversion=true
)

from docx import document
import csv

def word_tables_to_csv(docx_path: str, csv_path: str) -> none:
    doc = document(docx_path)
    with open(csv_path, 'w', newline='', encoding='utf-8') as f:
        writer = csv.writer(f)
        for table in doc.tables:
            for row in table.rows:
                writer.writerow([cell.text for cell in row.cells])

# 使用示例
word_tables_to_csv("data.docx", "output.csv")