Python批量提取Word文档表格数据

import os
from docx import Document

# 定义一个函数来批量提取Word文档中的表格数据
def extract_tables_from_word_docs(word_dir):
    # 获取目录中所有的Word文档
    word_files = [f for f in os.listdir(word_dir) if f.endswith('.docx')]
    for word_file in word_files:
        word_path = os.path.join(word_dir, word_file)
        doc = Document(word_path)
        for table in doc.tables:
            for row in table.rows:
                for cell in row.cells:
                    print(cell.text, end='\t')
                print()  # 换行
        print("-" * 60)  # 分隔线

# 使用示例
word_documents_folder = '/path/to/word/documents'  # 替换为Word文档所在的文件夹路径
extract_tables_from_word_docs(word_documents_folder)