Python实现快速提取Word表格并转Markdown

pip install python-docx

def is_heading_enhanced(paragraph):
    # 标题特征：样式名称含关键词 + 字体加粗 + 字体足够大
    style_name = (paragraph.style.name or "").lower()
    if "标题" in style_name or "heading" in style_name:
        return True
    
    try:
        font = paragraph.style.font
        return (font.size.pt >= 14 and font.bold) if font.size else False
    except:
        return False

def get_tables_under_heading(doc_path, target_title):
    from docx import Document
    doc = Document(doc_path)
    target_tables = []
    found = False

    for element in doc.element.body.iter():
        if element.tag.endswith('p'):  # 段落
            par = Paragraph(element, doc)
            if target_title in par.text and is_heading_enhanced(par):
                found = True
            elif found and is_heading_enhanced(par):  # 遇到新标题停止
                break
        elif element.tag.endswith('tbl') and found:  # 表格
            table = Table(element, doc)
            data = [[cell.text.strip() for cell in row.cells] for row in table.rows]
            target_tables.append(data)
    
    return target_tables

def to_markdown(table_data):
    if not table_data:
        return ""
    headers = table_data[0]
    md = f"| {' | '.join(headers)} |\n"
    md += f"| {' | '.join(['---']*len(headers))} |\n"
    for row in table_data[1:]:
        md += f"| {' | '.join(row)} |\n"
    return md

def main():
    doc_path = "需求文档_v2.0.docx"        # 替换为你的文档路径
    target_title = "功能权限矩阵"           # 替换为目标标题
    
    # 提取表格
    tables = get_tables_under_heading(doc_path, target_title)
    
    # 输出Markdown
    for idx, table in enumerate(tables, 1):
        print(f"--- 表格{idx} ---\n")
        print(to_markdown(table))
        print("\n-------------------\n")

if __name__ == "__main__":
    main()

# 在 is_heading_enhanced 中，降低字体大小要求
return (font.size.pt >= 12 and font.bold) if font.size else False

# 移除遇到新标题停止的逻辑
# 删除以下代码：
elif found and is_heading_enhanced(par): break

# 在提取单元格时去除换行符
cell.text.strip().replace('\n', ' ')

# 提取"接口参数表"后，直接生成测试用例模板
table_data = get_tables_under_heading("接口文档.docx", "接口参数表")[0]
for row in table_data[1:]:
    param, type_, example = row
    print(f"测试点：{param}参数为{example}时，接口应返回{type_}类型")

# 将表格数据写入CSV文件供测试框架读取
import csv

tables = get_tables_under_heading("测试数据.docx", "登录用例数据")
with open("test_data.csv", "w", newline="") as f:
    writer = csv.writer(f)
    for table in tables:
        writer.writerows(table)

def get_tables_under_heading(doc_path, target_title, level=1):
    # 新增参数：level表示标题层级（如1级标题）
    # 在is_heading_enhanced中增加层级判断
    if f"heading{level}" in style_name:
        return True

def extract_cell(cell):
    # 处理合并单元格时的空值
    if cell.text.strip():
        return cell.text.strip()
    else:
        return "[合并单元格]"

import logging
logging.basicConfig(level=logging.INFO)

def main():
    try:
        tables = get_tables_under_heading(...)
    except FileNotFoundError:
        logging.error("文档路径错误，请检查文件是否存在！")