pip install python-docx

sudo apt-get install antiword

from docx import Document

def docx_to_txt(docx_path, txt_path):
    """
    將docx文件轉(zhuǎn)換為txt文件
    :param docx_path: docx文件路徑
    :param txt_path: 生成的txt文件路徑
    """
    try:
        # 打開docx文件
        doc = Document(docx_path)
        # 提取文本內(nèi)容
        text = []
        for para in doc.paragraphs:
            text.append(para.text)
        # 將文本寫入txt文件
        with open(txt_path, 'w', encoding='utf-8') as f:
            f.write('\n'.join(text))
        print(f"轉(zhuǎn)換成功，txt文件已保存至：{txt_path}")
    except Exception as e:
        print(f"轉(zhuǎn)換失敗，錯誤信息：{e}")

# 示例用法
if __name__ == "__main__":
    docx_file = "example.docx"  # 替換為你的docx文件路徑
    txt_file = "example.txt"    # 替換為要生成的txt文件路徑
    docx_to_txt(docx_file, txt_file)

import subprocess

def doc_to_txt(doc_path, txt_path):
    """
    將doc文件轉(zhuǎn)換為txt文件（使用antiword）
    :param doc_path: doc文件路徑
    :param txt_path: 生成的txt文件路徑
    """
    try:
        # 調(diào)用antiword工具進行轉(zhuǎn)換
        result = subprocess.run(['antiword', doc_path], capture_output=True, text=True, check=True)
        # 將轉(zhuǎn)換后的內(nèi)容寫入txt文件
        with open(txt_path, 'w', encoding='utf-8') as f:
            f.write(result.stdout)
        print(f"轉(zhuǎn)換成功，txt文件已保存至：{txt_path}")
    except subprocess.CalledProcessError as e:
        print(f"轉(zhuǎn)換失敗，錯誤信息：{e.stderr}")
    except Exception as e:
        print(f"轉(zhuǎn)換失敗，錯誤信息：{e}")

# 示例用法
if __name__ == "__main__":
    doc_file = "example.doc"  # 替換為你的doc文件路徑
    txt_file = "example.txt"  # 替換為要生成的txt文件路徑
    doc_to_txt(doc_file, txt_file)

import win32com.client
import os

def doc_to_txt_win(doc_path, txt_path):
    """
    在Windows系統(tǒng)下將doc文件轉(zhuǎn)換為txt文件（使用win32com.client）
    :param doc_path: doc文件路徑
    :param txt_path: 生成的txt文件路徑
    """
    try:
        # 創(chuàng)建Word應(yīng)用對象
        word = win32com.client.Dispatch("Word.Application")
        # 后臺運行，不顯示界面
        word.Visible = False
        # 打開doc文件
        doc = word.Documents.Open(os.path.abspath(doc_path))
        # 保存為txt文件
        doc.SaveAs(os.path.abspath(txt_path), FileFormat=2)  # 2表示txt格式
        # 關(guān)閉文檔和Word應(yīng)用
        doc.Close()
        word.Quit()
        print(f"轉(zhuǎn)換成功，txt文件已保存至：{txt_path}")
    except Exception as e:
        print(f"轉(zhuǎn)換失敗，錯誤信息：{e}")

# 示例用法
if __name__ == "__main__":
    doc_file = "example.doc"  # 替換為你的doc文件路徑
    txt_file = "example.txt"  # 替換為要生成的txt文件路徑
    doc_to_txt_win(doc_file, txt_file)