ALL-teach_sys/frontend_大健康/extract_resume_data.py

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

import json
import os

def extract_position_data(position_names):
    """从JSON文件中提取指定岗位的数据"""
    result = {}
    
    # 读取所有part文件
    for i in range(1, 4):
        file_path = f'/Users/apple/Documents/cursor/教务系统/frontend/网页未导入数据/文旅产业/个人简历内容_part{i}.json'
        try:
            with open(file_path, 'r', encoding='utf-8') as f:
                data = json.load(f)
                for item in data:
                    position = item.get('❌岗位名称查询', '')
                    if position in position_names:
                        result[position] = item
                        print(f"找到: {position} in part{i}")
        except Exception as e:
            print(f"Error reading part{i}: {e}")
    
    # 也读取主文件
    main_file = '/Users/apple/Documents/cursor/教务系统/frontend/网页未导入数据/文旅产业/个人简历内容.json'
    try:
        with open(main_file, 'r', encoding='utf-8') as f:
            data = json.load(f)
            for item in data:
                position = item.get('❌岗位名称查询', '')
                if position in position_names and position not in result:
                    result[position] = item
                    print(f"找到: {position} in main file")
    except Exception as e:
        print(f"Error reading main file: {e}")
    
    return result

# 需要提取的岗位
positions_to_extract = [
    '露营地运营专员',
    '文创产品设计师', '文创产品策划师', '文创产品设计师助理',
    '品牌策划运营专员', '品牌公关', '品牌推广专员',
    'ip运营', 'IP运营总监助理', '品牌公关管培生'
]

# 提取数据
extracted_data = extract_position_data(positions_to_extract)

# 保存提取的数据
output_file = '/Users/apple/Documents/cursor/教务系统/frontend/extracted_resume_data.json'
with open(output_file, 'w', encoding='utf-8') as f:
    json.dump(extracted_data, f, ensure_ascii=False, indent=2)

print(f"\n成功提取 {len(extracted_data)} 个岗位的数据")
print(f"已保存到: {output_file}")

# 显示缺失的岗位
missing = set(positions_to_extract) - set(extracted_data.keys())
if missing:
    print(f"\n未找到的岗位: {missing}")