from docx import Document

report_path = r'C:\Users\UI\Desktop\医疗报告\backend\reports\filled_report_20260212_154247.docx'
doc = Document(report_path)
body = doc.element.body
children = list(body)

keywords = ['overall health', '整体健康', 'medical intervention', '医学干预',
            'functional medical health', '功能医学健康建议', 
            'nutrition intervention', '营养干预', 'exercise intervention', '运动干预',
            'sleep', '睡眠', 'lifestyle', '生活方式', 'long-term', '长期随访',
            '功能医学检测档案', 'abnormal index', '异常指标']

print(f"文档总元素数: {len(children)}")
print("=" * 80)

for i, elem in enumerate(children):
    text = ''.join(elem.itertext()).strip()
    if text:
        text_lower = text.lower()
        if any(kw in text_lower for kw in keywords):
            tag = elem.tag.split("}")[-1]
            print(f'[{i}] {tag}: {text[:150]}')