初始归档：健康管理资料库（大医网/药膳/体质监测/中医理论等12个资料集，7712个文件）

国家学生体质健康标准/02_加工数据/parse_student_tables.py

@@ -0,0 +1,212 @@
+#!/usr/bin/env python3
+"""
+国家学生体质健康标准（2014年修订）— 评分数据提取脚本
+教育部发布，适用于全日制小学至大学学生
+满分120分制（100基础分 + 20附加分）
+"""
+import json, os, re, sys
+from docx import Document
+
+BASE = '/home/songyi/Documents/ai_agent_scraper_study/data/国家学生体质健康标准'
+DOCX = os.path.join(BASE, '01_来源数据/国家学生体质健康标准（2014年修订）.docx')
+
+
+def parse_range(val):
+    """解析值域:'13.5~18.1', '≤13.4', '≥17.9'"""
+    val = val.strip().replace(' ', '').replace('\n','')
+    if re.match(r'[≥>]=?\s*([\d.]+)', val):
+        m = re.match(r'[≥>]=?\s*([\d.]+)', val)
+        return {"min": float(m.group(1))}
+    if re.match(r'[≤<]=?\s*([\d.]+)', val):
+        m = re.match(r'[≤<]=?\s*([\d.]+)', val)
+        return {"max": float(m.group(1))}
+    if re.match(r'([\d.]+)\s*[~-]\s*([\d.]+)', val):
+        m = re.match(r'([\d.]+)\s*[~-]\s*([\d.]+)', val)
+        lo, hi = float(m.group(1)), float(m.group(2))
+        return {"min": min(lo, hi), "max": max(lo, hi)}
+    if re.match(r'(\d+)[:：·]\s*(\d+[\']?[\d.]*)', val):
+        m = re.match(r'(\d+)[:：·]\s*(\d+[\']?[\d.]*)', val)
+        minutes = int(m.group(1))
+        rest = m.group(2).replace("'", ".")
+        seconds = float(rest) if '.' in rest else int(rest)
+        return {"exact": minutes * 60 + seconds}
+    if re.match(r'^([\d.]+)$', val):
+        m = re.match(r'^([\d.]+)$', val)
+        return {"exact": float(m.group(1))}
+    return {"raw": val}
+
+
+def extract_all():
+    doc = Document(DOCX)
+    
+    result = {
+        'metadata': {
+            'title': '国家学生体质健康标准（2014年修订）',
+            'publisher': '教育部',
+            'year': 2014,
+            'total_tables': len(doc.tables),
+            'scoring_system': '100分基础 + 20分附加 = 120分满分',
+            'rating_levels': {
+                '优秀': {'min': 90.0},
+                '良好': {'min': 80.0, 'max': 89.9},
+                '及格': {'min': 60.0, 'max': 79.9},
+                '不及格': {'max': 59.9}
+            }
+        },
+        'weight_table': {},
+        'scoring_tables': [],
+        'bonus_tables': [],
+        'registration_tables': []
+    }
+    
+    for i, table in enumerate(doc.tables):
+        rows_data = []
+        for row in table.rows:
+            cells = [cell.text.strip().replace('\n', ' ') for cell in row.cells]
+            rows_data.append(cells)
+        
+        if not rows_data:
+            continue
+        
+        header = rows_data[0]
+        header_str = ' '.join(str(h) for h in header).strip()
+        
+        # 权重表（表0）
+        if i == 0:
+            for row in rows_data[1:]:
+                if len(row) >= 3:
+                    obj = row[0].strip()
+                    indicator = row[1].strip()
+                    weight = row[2].strip()
+                    try:
+                        w = float(weight)
+                        result['weight_table'].setdefault(obj, {})[indicator] = w
+                    except ValueError:
+                        pass
+            continue
+        
+        # 登记卡表
+        if '学校签章' in header_str or ('姓名' in header_str and '性别' in header_str):
+            result['registration_tables'].append({
+                'table_index': i, 'rows': len(rows_data), 'cols': len(header)
+            })
+            continue
+        
+        # 判断加分表
+        is_bonus = '加分' in header_str and '成绩' not in header_str
+        
+        # 解析年级列
+        grade_cols = []
+        start_col = 1 if is_bonus else 2
+        for ci, h in enumerate(header):
+            h_clean = h.strip().replace('\n', ' ')
+            if h_clean and ci >= start_col:
+                # 跳过'单项得分'列
+                if '单项' in h_clean or '得分' in h_clean:
+                    continue
+                grade_cols.append((ci, h_clean))
+        
+        if not grade_cols:
+            continue
+        
+        table_info = {
+            'table_index': i,
+            'header_sample': [h.strip() for h in header[:5]],
+            'grade_names': [g[1] for g in grade_cols],
+            'type': 'bonus' if is_bonus else 'standard',
+            'rows_count': len(rows_data) - 1,
+            'data': []
+        }
+        
+        for row in rows_data[1:]:
+            if is_bonus:
+                if len(row) < 2:
+                    continue
+                bonus_str = row[0].strip()
+                try:
+                    bonus_score = int(bonus_str) if bonus_str.lstrip('-').isdigit() else 0
+                except:
+                    continue
+                entry = {'bonus_score': bonus_score, 'grades': {}}
+                for ci, gname in grade_cols:
+                    if ci < len(row):
+                        val = row[ci].strip()
+                        if val and val not in ['—', '-', '', '------']:
+                            entry['grades'][gname] = parse_range(val)
+                if entry['grades']:
+                    table_info['data'].append(entry)
+            else:
+                if len(row) < 3:
+                    continue
+                level_name = row[0].strip()
+                score_str = row[1].strip()
+                try:
+                    score_val = int(score_str) if score_str.isdigit() else 0
+                except:
+                    continue
+                entry = {'level': level_name, 'score': score_val, 'grades': {}}
+                for ci, gname in grade_cols:
+                    if ci < len(row):
+                        val = row[ci].strip()
+                        if val and val not in ['—', '-', '', '------']:
+                            entry['grades'][gname] = parse_range(val)
+                if entry['grades']:
+                    table_info['data'].append(entry)
+        
+        if table_info['data']:
+            if is_bonus:
+                result['bonus_tables'].append(table_info)
+            else:
+                result['scoring_tables'].append(table_info)
+    
+    return result
+
+
+def print_summary(data):
+    m = data['metadata']
+    print(f"总Word表格: {m['total_tables']}")
+    print(f"标准评分表: {len(data['scoring_tables'])} 个")
+    print(f"加分评分表: {len(data['bonus_tables'])} 个")
+    print(f"登记卡/附表: {len(data['registration_tables'])} 个")
+    
+    wt = data['weight_table']
+    print(f"\n权重表 ({len(wt)}组):")
+    for obj in sorted(wt.keys()):
+        items = ', '.join(f"{k}={v}%" for k, v in sorted(wt[obj].items()))
+        print(f"  {obj}: {items}")
+    
+    print(f"\n标准评分表:")
+    for t in data['scoring_tables']:
+        gn = t['grade_names']
+        gs = ', '.join(gn[:3])
+        if len(gn) > 3:
+            gs += f"...({len(gn)}个年级)"
+        levels = sorted(set(e['level'] for e in t['data']))
+        ti = t['table_index']
+        rc = len(t['data'])
+        print(f"  [表{ti}] {rc}行x{len(gn)}年级 等级={levels} 年级={gs}")
+    
+    print(f"\n加分评分表:")
+    for t in data['bonus_tables']:
+        gn = t['grade_names']
+        gs = ', '.join(gn[:3])
+        if len(gn) > 3:
+            gs += f"...({len(gn)}个年级)"
+        ti = t['table_index']
+        rc = len(t['data'])
+        print(f"  [表{ti}] {rc}行 年级={gs}")
+
+
+def output_json(data):
+    path = os.path.join(BASE, '02_加工数据/评分标准结构化数据.json')
+    with open(path, 'w', encoding='utf-8') as f:
+        json.dump(data, f, ensure_ascii=False, indent=2)
+    size = os.path.getsize(path)
+    print(f"\nJSON输出: {path} ({size/1024:.0f}KB)")
+    return path
+
+
+if __name__ == '__main__':
+    data = extract_all()
+    print_summary(data)
+    output_json(data)