wechat_crawler/view_jobs.py

# -*- coding: utf-8 -*-
"""
查看提取的岗位数据
"""
import json
import os
from datetime import datetime


def format_salary(salary_min, salary_max):
    """格式化薪资显示"""
    if salary_min and salary_max:
        return f"{salary_min}-{salary_max}元"
    elif salary_min:
        return f"{salary_min}元起"
    elif salary_max:
        return f"{salary_max}元以下"
    else:
        return "面议"


def display_job(job, index):
    """显示单个岗位信息"""
    print(f"\n{'=' * 80}")
    print(f"岗位 #{index}")
    print(f"{'=' * 80}")
    
    print(f"工作名称: {job.get('job_name', '未知')}")
    print(f"公司名称: {job.get('company_name', '未知')}")
    print(f"工作地点: {job.get('job_location', '未知')}")
    print(f"薪资范围: {format_salary(job.get('salary_min'), job.get('salary_max'))}")
    
    if job.get('job_description'):
        print(f"\n工作描述:")
        print(f"  {job['job_description']}")
    
    if job.get('contact_person') or job.get('contact_info'):
        print(f"\n联系方式:")
        if job.get('contact_person'):
            print(f"  联系人: {job['contact_person']}")
        if job.get('contact_info'):
            print(f"  联系方式: {job['contact_info']}")
    
    # 显示元数据
    if '_metadata' in job:
        meta = job['_metadata']
        print(f"\n来源信息:")
        print(f"  群组: {meta.get('group_name', '未知')}")
        print(f"  发送者: {meta.get('sender', '未知')}")
        print(f"  提取时间: {meta.get('extract_time', '未知')}")
        
        if meta.get('original_message'):
            print(f"\n原始消息:")
            msg = meta['original_message']
            if len(msg) > 200:
                msg = msg[:200] + "..."
            print(f"  {msg}")


def main():
    data_file = "jobs_data.json"
    
    if not os.path.exists(data_file):
        print(f"数据文件不存在: {data_file}")
        print("请先运行 job_extractor.py 提取岗位数据")
        return
    
    try:
        with open(data_file, "r", encoding="utf-8") as f:
            jobs = json.load(f)
    except Exception as e:
        print(f"读取数据文件失败: {e}")
        return
    
    if not jobs:
        print("暂无岗位数据")
        return
    
    print(f"{'=' * 80}")
    print(f"岗位数据查看器")
    print(f"{'=' * 80}")
    print(f"数据文件: {data_file}")
    print(f"岗位总数: {len(jobs)}")
    
    # 统计信息
    locations = {}
    companies = {}
    for job in jobs:
        loc = job.get('job_location', '未知')
        locations[loc] = locations.get(loc, 0) + 1
        
        comp = job.get('company_name', '未知')
        companies[comp] = companies.get(comp, 0) + 1
    
    print(f"\n地点分布:")
    for loc, count in sorted(locations.items(), key=lambda x: x[1], reverse=True)[:5]:
        print(f"  {loc}: {count}个岗位")
    
    print(f"\n公司分布:")
    for comp, count in sorted(companies.items(), key=lambda x: x[1], reverse=True)[:5]:
        print(f"  {comp}: {count}个岗位")
    
    # 显示详细信息
    print(f"\n{'=' * 80}")
    print("岗位详情")
    
    for i, job in enumerate(jobs, 1):
        display_job(job, i)
    
    print(f"\n{'=' * 80}")
    print(f"共显示 {len(jobs)} 个岗位")
    print(f"{'=' * 80}")


if __name__ == "__main__":
    main()