from docx import Document
from lxml import etree

doc = Document(r'C:\Users\UI\Desktop\医疗报告\backend\reports\filled_report_20260212_165326.docx')
body = doc.element.body
children = list(body)
ns = {'w': 'http://schemas.openxmlformats.org/wordprocessingml/2006/main'}
w = 'http://schemas.openxmlformats.org/wordprocessingml/2006/main'

def show_para_format(elem, label):
    text = ''.join(elem.itertext()).strip()
    print(f'=== {label} ===')
    print(f'Text: {text[:80]}')
    # pPr
    pPr = elem.find('w:pPr', ns)
    if pPr is not None:
        jc = pPr.find('w:jc', ns)
        if jc is not None:
            print(f'  jc: {jc.get(f"{{{w}}}val")}')
        pStyle = pPr.find('w:pStyle', ns)
        if pStyle is not None:
            print(f'  pStyle: {pStyle.get(f"{{{w}}}val")}')
    # runs
    for r in elem.findall('w:r', ns):
        rPr = r.find('w:rPr', ns)
        rt = ''.join(r.itertext()).strip()
        if not rt:
            continue
        print(f'  Run: "{rt[:50]}"')
        if rPr is not None:
            rFonts = rPr.find('w:rFonts', ns)
            sz = rPr.find('w:sz', ns)
            szCs = rPr.find('w:szCs', ns)
            b = rPr.find('w:b', ns)
            bCs = rPr.find('w:bCs', ns)
            color = rPr.find('w:color', ns)
            if rFonts is not None:
                fonts = {}
                for attr in ['ascii', 'hAnsi', 'eastAsia', 'cs']:
                    v = rFonts.get(f'{{{w}}}{attr}')
                    if v:
                        fonts[attr] = v
                print(f'    fonts: {fonts}')
            if sz is not None:
                print(f'    sz: {sz.get(f"{{{w}}}val")} (={int(sz.get(f"{{{w}}}val"))//2}pt)')
            if szCs is not None:
                print(f'    szCs: {szCs.get(f"{{{w}}}val")}')
            if b is not None:
                print(f'    bold: yes')
            if bCs is not None:
                print(f'    boldCs: yes')
            if color is not None:
                print(f'    color: {color.get(f"{{{w}}}val")}')
        else:
            print(f'    (no rPr)')

# Overall Health Assessment
for i, elem in enumerate(children):
    text = ''.join(elem.itertext()).strip()
    if 'Overall Health' in text and 'Assessment' in text and len(text) < 200:
        show_para_format(elem, f'Overall Health Assessment [{i}]')
        break

print()

# Medical Intervention
for i, elem in enumerate(children):
    text = ''.join(elem.itertext()).strip()
    if 'Medical Intervention' in text and '医学干预' in text and len(text) < 200:
        show_para_format(elem, f'Medical Intervention [{i}]')
        break

print()

# FHA Title
for i, elem in enumerate(children):
    text = ''.join(elem.itertext()).strip()
    if 'Functional Medical Health Advice' in text and '功能医学健康建议' in text and len(text) < 300:
        show_para_format(elem, f'FHA Title [{i}]')
        break