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

import json

def extract_energy_questions():
    """
    提取能源产业相关的面试题
    """
    # 读取面试题文件
    with open("网页未导入数据/岗位群面试题（全产业）.json", 'r', encoding='utf-8') as f:
        data = json.load(f)

    # 能源产业相关的岗位群（基于能源岗位简历.json中的岗位群）
    energy_job_groups = [
        "EHS体系", "变电站运维", "配电网运维", "储能系统运维",
        "光伏系统运维", "风力发电运维", "电力系统调度",
        "能源数据分析", "碳排放管理"
    ]

    # 查找匹配的面试题
    energy_questions = []
    found_groups = set()

    for item in data:
        job_group = item.get("简历岗位群", "")
        # 检查是否为能源相关岗位群
        for energy_group in energy_job_groups:
            if energy_group in job_group or job_group in energy_group:
                energy_questions.append(item)
                found_groups.add(job_group)
                break

    print(f"✅ 找到 {len(energy_questions)} 个能源产业相关的面试题")
    print(f"📋 涵盖的岗位群：{found_groups}")

    # 如果没有找到能源相关的，查看所有岗位群名称
    if len(energy_questions) == 0:
        all_groups = set()
        for item in data:
            all_groups.add(item.get("简历岗位群", ""))
        print(f"\n📝 所有岗位群列表（前20个）：")
        for i, group in enumerate(list(all_groups)[:20]):
            print(f"   {i+1}. {group}")

    return energy_questions

if __name__ == "__main__":
    questions = extract_energy_questions()