pip install python-docx openpyxl pandas

from docx import Document
import openpyxl

# 讀取Word表格
doc = Document("report.docx")
table = doc.tables[0]  # 獲取第一個(gè)表格

# 創(chuàng)建Excel工作簿
wb = openpyxl.Workbook()
ws = wb.active

# 寫入數(shù)據(jù)
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:  # 遍歷所有表格
    table_data = []
    for row in table.rows:
        table_data.append([cell.text for cell in row.cells])
    all_data.extend(table_data[1:])  # 跳過(guò)表頭（假設(shè)所有表格結(jié)構(gòu)相同）

# 用pandas寫入Excel（自動(dòng)處理數(shù)據(jù)類型）
df = pd.DataFrame(all_data, columns=["產(chǎn)品", "銷量", "單價(jià)", "總額"])
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
        # 嘗試轉(zhuǎn)換為數(shù)字
        if text.replace('.', '', 1).isdigit():  # 簡(jiǎn)單判斷是否為數(shù)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 = ""  # 記錄上一行同列的文本
for row_idx, row in enumerate(table.rows):
    for col_idx, cell in enumerate(row.cells):
        current_text = cell.text
        # 如果單元格為空且上一行同列有內(nèi)容，可能是合并單元格
        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 ""  # 只記錄第一列的延續(xù)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):
    """處理單個(gè)表格的函數(shù)"""
    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 = []

# 使用線程池處理表格（注意：openpyxl寫入需單線程）
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]

# 單線程寫入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:
    """
    將Word文檔中的所有表格轉(zhuǎn)換為Excel工作表
    
    參數(shù):
        docx_path: Word文檔路徑
        excel_path: 輸出Excel路徑
        sheet_name: 工作表名稱
        skip_header: 是否跳過(guò)每個(gè)表格的第一行（表頭）
        numeric_conversion: 是否嘗試將文本轉(zhuǎn)換為數(shù)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)
    
    # 如果沒有數(shù)據(jù)，創(chuàng)建空DataFrame
    if not all_data:
        df = pd.DataFrame()
    else:
        # 動(dòng)態(tài)推斷列名（假設(shè)所有表格結(jié)構(gòu)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]))]
            # 如果第一個(gè)元素是字符串且看起來(lái)像表頭，則使用它
            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)
    
    # 寫入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="銷售數(shù)據(jù)",
    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")