| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172 |
- # -*- coding: utf-8 -*-
- """
- 脱敏 + 关键内容高亮 + Markdown→HTML→PDF
- 输入:560822024-张学红-归因分析-简版.md / 完整版.md
- 输出:脱敏交付/L女士-归因分析-简版.pdf / 完整版.pdf
- """
- import io, os, re, subprocess, sys
- sys.stdout.reconfigure(encoding='utf-8')
- BASE = r'E:/cfc/docs/参考资料'
- OUT = os.path.join(BASE, '脱敏交付')
- os.makedirs(OUT, exist_ok=True)
- CHROME = r'C:/Program Files/Google/Chrome/Application/chrome.exe'
- # ---------- 1. 脱敏映射 ----------
- MASK = [
- ('张学红', 'L 女士'),
- ('560822024', 'A-2401'),
- ]
- # ---------- 2. 需高亮的关键句(==...== → <mark>) ----------
- # 仅在文档中首次出现处高亮,避免满篇发亮
- KEY_PHRASES = [
- '她不是吃得少,是吃得很讲究——但讲究的方向恰好全在压制铁吸收',
- '抓三件事——拆开早餐的铁吸收抑制',
- '不是"菌群崩坏",是"几家关键岗位缺人 + 两个代谢物单点超载 + 三个营养短板"',
- '她的肠道生态底子是好的,问题高度集中,可干预性很强',
- '最值得先动手的一件事',
- '这不是"菌群崩坏",是"关键岗位缺人"',
- '铁被早餐堵死了、双歧缺粮塌方了、早绝经让骨与雌激素两个窗口提前了',
- '她的核心问题是"双歧缺粮"',
- '不需要补乳杆菌',
- '不必补乳杆菌',
- '长双歧杆菌为第一靶点',
- '长双歧杆菌(Bifidobacterium longum)',
- '外源益生菌的**定植率很低**',
- '益生菌**点火**,瓜尔豆纤维**添柴**',
- '运动少**不是意愿问题,是医学限制**',
- '不能把"运动少"归因为懒、缺动力或自律不足',
- '必须临床区分,不可自行归因',
- '不得表述为"她正在抑郁"',
- '42 岁绝经 = 早绝经',
- '42 岁绝经(绝经 10 年,属早绝经)',
- '二选一时取瓜尔豆纤维',
- '她不吃肉,所以红肉不是她的问题',
- '菊粉或瓜尔豆纤维(二选一)→ 推荐瓜尔豆纤维',
- '与铁剂错开 2 小时',
- '她已经用了早期预警',
- ]
- def mask_text(t):
- for a, b in MASK:
- t = t.replace(a, b)
- return t
- def highlight(t):
- """把关键句包裹为 ==...==,每句只处理首次出现"""
- for p in KEY_PHRASES:
- if p in t and ('==' + p + '==') not in t:
- t = t.replace(p, '==' + p + '==', 1)
- return t
- # ---------- 3. CSS ----------
- CSS = r"""
- @page { size: A4; margin: 17mm 15mm 16mm 15mm; }
- * { box-sizing: border-box; }
- body{
- font-family: "Microsoft YaHei","PingFang SC","Source Han Sans SC",sans-serif;
- font-size: 10.4pt; line-height: 1.78; color:#25232b; margin:0;
- -webkit-print-color-adjust: exact; print-color-adjust: exact;
- }
- h1{
- font-size: 19pt; color:#5B3E96; margin:0 0 6pt; padding-bottom:8pt;
- border-bottom:2.4pt solid #5B3E96; letter-spacing:.5px;
- }
- h1 + blockquote{ margin-top:10pt; }
- h2{
- font-size:13.4pt; color:#5B3E96; margin:20pt 0 8pt; padding:5pt 0 5pt 9pt;
- border-left:4pt solid #7B5CB8; background:#F7F4FC; page-break-after:avoid;
- }
- h3{
- font-size:11.6pt; color:#3f3555; margin:14pt 0 6pt; padding-left:2pt;
- border-bottom:1px dashed #CFC2E8; padding-bottom:3pt; page-break-after:avoid;
- }
- h4{ font-size:10.8pt; color:#4a3f63; margin:11pt 0 5pt; page-break-after:avoid; }
- p{ margin:5pt 0; text-align:justify; }
- strong{ font-weight:700; color:#1a1620; }
- mark{
- background:#FFF0B3; color:#1a1620; font-weight:700;
- padding:0.5pt 2.5pt; border-radius:2pt;
- }
- blockquote{
- margin:9pt 0; padding:7pt 11pt; background:#FAF7FE;
- border-left:3pt solid #A98FE0; color:#3c3450; font-size:9.9pt;
- }
- blockquote p{ margin:3pt 0; }
- ul,ol{ margin:5pt 0 5pt 0; padding-left:20pt; }
- li{ margin:2.5pt 0; }
- table{
- width:100%; border-collapse:collapse; margin:8pt 0 10pt;
- font-size:9.1pt; page-break-inside:auto;
- }
- th{
- background:#5B3E96; color:#fff; font-weight:600; padding:5pt 6pt;
- border:0.6pt solid #5B3E96; text-align:left; font-size:9.1pt;
- }
- td{
- padding:4.6pt 6pt; border:0.6pt solid #D8D2E4; vertical-align:top;
- line-height:1.6;
- }
- tbody tr:nth-child(even) td{ background:#FBF9FE; }
- tr{ page-break-inside:avoid; }
- code{
- background:#F1EDF8; color:#5B3E96; padding:0.5pt 3pt;
- border-radius:2pt; font-size:9pt;
- }
- hr{ border:0; border-top:0.8pt solid #E2DCEE; margin:14pt 0; }
- em{ color:#6b5a8f; font-style:normal; font-size:9.6pt; }
- a{ color:#5B3E96; text-decoration:none; }
- /* 页面底部脚注提示 */
- p:last-child em{ color:#8b8398; font-size:9pt; }
- """
- HTML_TPL = """<!DOCTYPE html>
- <html lang="zh-CN"><head><meta charset="utf-8">
- <title>{title}</title><style>{css}</style></head>
- <body>{body}</body></html>"""
- def build(src_name, out_stem, title):
- src = os.path.join(BASE, src_name)
- raw = io.open(src, encoding='utf-8').read()
- t = mask_text(raw)
- # 抬头加"脱敏"标记
- t = t.replace('\n---\n', '\n> **本文件已脱敏**:受检者姓名与报告编号均做替换处理,仅保留归因所需的年龄/性别/生理阶段信息。\n\n---\n', 1)
- t = highlight(t)
- import markdown
- body = markdown.markdown(
- t,
- extensions=['tables', 'fenced_code', 'sane_lists', 'nl2br'],
- )
- # ==x== → <mark>x</mark>(先转义后替换,避免被 markdown 处理掉)
- body = re.sub(r'==(.+?)==', r'<mark>\1</mark>', body, flags=re.S)
- html = HTML_TPL.format(title=title, css=CSS, body=body)
- html_path = os.path.join(OUT, out_stem + '.html')
- io.open(html_path, 'w', encoding='utf-8').write(html)
- pdf_path = os.path.join(OUT, out_stem + '.pdf')
- if os.path.exists(pdf_path):
- os.remove(pdf_path)
- cmd = [
- CHROME, '--headless=new', '--disable-gpu', '--no-sandbox',
- '--no-pdf-header-footer', '--print-to-pdf-no-header',
- '--virtual-time-budget=8000',
- f'--print-to-pdf={pdf_path}',
- 'file:///' + html_path.replace('\\', '/'),
- ]
- r = subprocess.run(cmd, capture_output=True, text=True, timeout=180)
- ok = os.path.exists(pdf_path)
- size = os.path.getsize(pdf_path) if ok else 0
- print(f'[{("OK" if ok else "FAIL")}] {out_stem}.pdf {size/1024:.0f} KB')
- if not ok:
- print(' stderr:', (r.stderr or '')[:400])
- return pdf_path
- if __name__ == '__main__':
- build('560822024-张学红-归因分析-简版.md', 'L女士-归因分析-简版', 'L 女士 · 肠道菌群归因分析(简版)')
- build('560822024-张学红-归因分析-完整版.md', 'L女士-归因分析-完整版', 'L 女士 · 肠道菌群归因分析(完整版)')
|