#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import json
import re

print("开始转换大健康岗位数据...")

# 读取大健康岗位简历数据
with open('/Users/apple/Documents/cursor/教务系统/frontend_大健康/网页未导入数据/大健康产业/大健康岗位简历.json', 'r', encoding='utf-8') as f:
    health_data = json.load(f)

# 按岗位群分组
position_groups = {}
for item in health_data:
    group_name = item['简历岗位群']
    if group_name not in position_groups:
        position_groups[group_name] = {
            'positions': [],
            'questions': [],
            'resumes': {}
        }

    # 添加岗位信息
    position = {
        'title': item['岗位名称'],
        'level': item['岗位等级标签'],
        'avatar': item['简历头像url']
    }

    if position not in position_groups[group_name]['positions']:
        position_groups[group_name]['positions'].append(position)

    # 添加简历内容
    position_groups[group_name]['resumes'][item['岗位名称']] = item['简历内容']

    # 添加面试题（避免重复）
    if item['面试题内容'] and item['面试题内容'] not in position_groups[group_name]['questions']:
        position_groups[group_name]['questions'].append(item['面试题内容'])

# 统计信息
print(f"\n找到 {len(position_groups)} 个岗位群:")
for group_name, group_data in position_groups.items():
    print(f"  - {group_name}: {len(group_data['positions'])} 个岗位")

# 保存分组后的数据
with open('/Users/apple/Documents/cursor/教务系统/frontend_大健康/health_data_grouped.json', 'w', encoding='utf-8') as f:
    json.dump(position_groups, f, ensure_ascii=False, indent=2)

print("\n✓ 数据分组完成，已保存到 health_data_grouped.json")