# -*- coding: utf-8 -*- """比对 560822024-张学红.pdf 与 v5 提取器已知的章节结构""" import fitz, re, json doc = fitz.open(r'E:/cfc/docs/参考资料/560822024-张学红.pdf') full = [] for i, page in enumerate(doc): t = page.get_text() full.append((i + 1, t)) # 1. 收集所有页脚章节名(每页最后一行通常是章节名) print('===== 每页页脚章节名(去重按出现顺序)=====') seen = [] for pno, t in full: lines = [l.strip() for l in t.split('\n') if l.strip()] if lines: foot = lines[-1] # 去掉 "N/169" 页码 foot = re.sub(r'\s*\d+/169\s*$', '', foot).strip() if foot and (not seen or seen[-1][1] != foot): if not any(foot == s[1] for s in seen): seen.append((pno, foot)) for pno, foot in seen: print(f' p{pno}: {foot}') # 2. 找疑似"指标详解/新指标"线索:雌激素、慢病控制 print() print('===== 关键词命中 =====') for kw in ['雌激素', '慢病控制', 'GMHI', '健康总分', '肠道预测年龄', '肠型', '有益菌', '有害菌', '核心菌属', '菌群多样性']: pages = [p for p, t in full if kw in t] print(f' {kw}: {len(pages)} 页 -> {pages[:8]}')