[免费]基于Python的招聘职位信息推荐系统(猎聘网数据分析与可视化)(Django+requests库)【论文+源码+SQL脚本】

大家好，我是python222_小锋老师，看到一个不错的基于Python的招聘职位信息推荐系统(猎聘网数据分析与可视化)(Django+requests库)，分享下哈。

项目视频演示

【免费】基于Python的招聘职位信息推荐系统(猎聘网数据分析与可视化)(Django+爬虫) Python毕业设计_哔哩哔哩_bilibili

项目介绍

随着互联网和信息技术的不断发展，就业和招聘形式也迎来了深刻的变革。就业推荐系统不仅能够为求职者提供个性化、精准的匹配，而且还解决了现代就业市场面临的一系列挑战问题，另外对于求职者而言，该系统还减轻了信息过载的压力，帮助毕业生快速找到适合自己技能和兴趣的职位，节省了毕业生的求职时间和成本，提高了就业市场的效率，同时为毕业生提供更好的就业机会和就业支持。

本文基于协同过滤算法，设计实现了就业推荐系统，旨在提供高度个性化的职位推荐，以满足毕业生求职者和雇主的需求。系统首先采用爬虫技术收集企业公开发布的招聘岗位信息，抽取特征值并且归一化处理，根据指定的毕业生和求职人员的相似度计算毕业生和企业单位的相似度。然后在得到毕业生和企业单位的相似度的基础上，根据随机游走模型算法计算出企业单位的求职热度。最后计算最终的排序综合权值，完成基于协同过滤的就业推荐系统的建立。该系统涵盖了控制台功能、数据爬取、数据管理、数据可视化和就业推荐等多个核心功能模块。同时，系统为解决就业场景中企业与毕业生相互匹配的问题，引入企业对毕业生的偏好系数，企业偏好系数是利用改进的随机游走算法（PersonalRank）计算企业招聘过程中对毕业生特征属性的招聘偏好值。最终的推荐算法融合企业偏好系数计算出毕业生与企业的符合度，根据符合度为毕业生推荐合适的就业岗位。通过该系统，毕业生用户可以轻松地管理其就业信息，获得定制的职位推荐，并通过可视化工具了解就业市场趋势。

系统的设计过程中使用了先进的技术和开发框架，确保了系统的高性能和可扩展性。整个系统采用 Python 语言编写，后端基于 Django 的 Web 应用框架，数据库采用 MySQL设计，使用 ECharts 进行数据可视化显示。数据获取使用 Selenium 框架进行数据的采集，然后对数据进行分析并且将结果在前台进行可视化的展示。获取的数据解析后存储到数据库。该系统的个性化就业职位推荐功能是基于用户的协同过滤算法设计实现。经过功能测试和性能测试，系统展现出了其在多个方面的有效性和可靠性。总之，本文开发的就业推荐系统为解决现代就业市场的智能化挑战，提供了一个有前景的解决方案，并为未来功能更加强大的就业推荐系统的研究和应用提供了一定的基础。

系统展示

部分代码

{% load static %}
<!DOCTYPE html>
<html>
<head><meta charset="utf-8"><title>登入-职位推荐系统</title><meta name="renderer" content="webkit"><meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1"><meta name="viewport"content="width=device-width, initial-scale=1.0, minimum-scale=1.0, maximum-scale=1.0, user-scalable=0"><link rel="stylesheet" href="{% static "layuiadmin/layui/css/layui.css" %}" media="all"><link rel="stylesheet" href="{% static "layuiadmin/style/admin.css" %}" media="all"><link rel="stylesheet" href="{% static "layuiadmin/style/login.css" %}" media="all">
</head>
<body>{#  <div class="layadmin-user-login layadmin-user-display-show" id="LAY-user-login" style="display: none;">#}
<div class="layadmin-user-login layadmin-user-display-show" id="LAY-user-login"style="display: none; background-image: url('/static/背景.png'); background-size: cover;"><div class="layadmin-user-login-main"><div class="layadmin-user-login-box layadmin-user-login-header"><h2 style="color: #fff">用户登录</h2><p>招聘推荐系统</p></div><div class="layadmin-user-login-box layadmin-user-login-body layui-form"><div class="layui-form-item"><label class="layadmin-user-login-icon layui-icon layui-icon-username"></label><input type="text" name="user" placeholder="账号" class="layui-input"></div><div class="layui-form-item"><label class="layadmin-user-login-icon layui-icon layui-icon-password"></label><input type="password" name="password" placeholder="密码" class="layui-input"></div><div class="layui-form-item" style="margin-bottom: 20px;"><a href="{% url "register" %}" class="layadmin-user-jump-change layadmin-link" style="margin-top: 7px;">还没账号？</a></div><div class="layui-form-item"><button class="layui-btn layui-btn-fluid" lay-submit lay-filter="LAY-user-login-submit">登 入</button></div></div></div>
</div><script src="{% static "layuiadmin/layui/layui.js" %}"></script>
<script>layui.config({base: '{% static "layuiadmin/" %}' //静态资源所在路径}).extend({index: 'lib/index' //主入口模块}).use(['index', 'form', 'jquery'], function () {var $ = layui.jquery,form = layui.form,layer = layui.layer;//提交form.on('submit(LAY-user-login-submit)', function (obj) {obj = obj.field;if (obj.user == '') {layer.msg('账号不能为空');return false;}if (obj.password == '') {layer.msg('密码不能为空');return false;}//请求登入接口$.ajax({type: 'POST',url: '/login/',data: obj,success: function (res) {// 弹窗内容， 样式if (res.code == 0) {layer.msg(res.msg + ' ' + res.user_name, {icon: 1, time: 1000});setTimeout(function () {location.href = "http://127.0.0.1:8000/index/";}, 1000) // 延迟重定向} else {layer.msg(res.msg);return false;}},error: function (response) {layer.msg(response.msg);}})});});
</script>
</body>
</html>

from django.shortcuts import render, redirect
from django.http import JsonResponse
# Create your views here.
from job import models
import re
from psutil import *
from numpy import *
from job import tools
from job import job_recommendspider_code = 0  # 定义全局变量，用来识别爬虫的状态，0空闲，1繁忙# python manage.py inspectdb > job/models.py
# 使用此命令可以将数据库表导入models生成数据模型def login(request):if request.method == "POST":user = request.POST.get('user')pass_word = request.POST.get('password')print('user------>', user)users_list = list(models.UserList.objects.all().values("user_id"))users_id = [x['user_id'] for x in users_list]print(users_id)ret = models.UserList.objects.filter(user_id=user, pass_word=pass_word)if user not in users_id:return JsonResponse({'code': 1, 'msg': '该账号不存在！'})elif ret:# 有此用户 -->> 跳转到首页# 登录成功后，将用户名和昵称保存到session 中，request.session['user_id'] = useruser_obj = ret.last()if user_obj:  # 检查用户对象是否存在user_name = user_obj.user_namerequest.session['user_name'] = user_namereturn JsonResponse({'code': 0, 'msg': '登录成功！', 'user_name': user_name})else:return JsonResponse({'code': 1, 'msg': '密码错误！'})else:return render(request, "login.html")def register(request):if request.method == "POST":user = request.POST.get('user')pass_word = request.POST.get('password')user_name = request.POST.get('user_name')users_list = list(models.UserList.objects.all().values("user_id"))users_id = [x['user_id'] for x in users_list]if user in users_id:return JsonResponse({'code': 1, 'msg': '该账号已存在！'})else:models.UserList.objects.create(user_id=user, user_name=user_name, pass_word=pass_word)request.session['user_id'] = user  # 设置缓存request.session['user_name'] = user_namereturn JsonResponse({'code': 0, 'msg': '注册成功！'})else:return render(request, "register.html")# 退出(登出)
def logout(request):# 1. 将session中的用户名、昵称删除request.session.flush()# 2. 重定向到 登录界面return redirect('login')def index(request):"""此函数用于返回主页，主页包括头部，左侧菜单"""return render(request, "index.html")def welcome(request):"""此函数用于处理控制台页面"""job_data = models.JobData.objects.all().values()  # 查询所有的职位信息all_job = len(job_data)  # 职位信息总数list_1 = []  # 定义一个空列表for job in list(job_data):  # 使用循环处理最高哦薪资try:  # 使用try...except检验最高薪资的提取，如果提取不到则加入0salary_1 = float(re.findall(r'-(\d+)k', job['salary'])[0])  # 使用正则提取最高薪资job['salary_1'] = salary_1  # 添加一个最高薪资list_1.append(salary_1)  # 把最高薪资添加到list_1用来计算平均薪资except Exception as e:# print(e)job['salary_1'] = 0list_1.append(0)job_data = sorted(list(job_data), key=lambda x: x['salary_1'], reverse=True)  # 反向排序所有职位信息的最高薪资# print(job_data)job_data_10 = job_data[0:10]  # 取最高薪资前10用来渲染top—10表格# print(job_data[0:10])job_data_1 = job_data[0]  # 取出最高薪资的职位信息mean_salary = int(mean(list_1))  # 计算平均薪资spider_info = models.SpiderInfo.objects.filter(spider_id=1).first()  # 查询爬虫程序运行的数据记录# print(spider_info)return render(request, "welcome.html", locals())def spiders(request):global spider_code# print(spider_code)spider_code_1 = spider_codereturn render(request, "spiders.html", locals())def start_spider(request):if request.method == "POST":key_word = request.POST.get("key_word")city = request.POST.get("city")page = request.POST.get("page")role = request.POST.get("role")spider_code = 1  # 改变爬虫状态spider_model = models.SpiderInfo.objects.filter(spider_id=1).first()# print(spider_model)spider_model.count += 1  # 给次数+1spider_model.page += int(page)  # 给爬取页数加上选择的页数spider_model.save()if role == '猎聘网':# print(key_word,city,page)spider_code = tools.lieSpider(key_word=key_word, city=city, all_page=page)return JsonResponse({"code": 0, "msg": "爬取完毕!"})else:return JsonResponse({"code": 1, "msg": "请使用POST请求"})def job_list(request):return render(request, "job_list.html", locals())def get_job_list(request):"""此函数用来渲染职位信息列表"""page = int(request.GET.get("page", ""))  # 获取请求地址中页码limit = int(request.GET.get("limit", ""))  # 获取请求地址中的每页数据数量keyword = request.GET.get("keyword", "")price_min = request.GET.get("price_min", "")price_max = request.GET.get("price_max", "")edu = request.GET.get("edu", "")city = request.GET.get("city", "")job_data_list = list(models.JobData.objects.filter(name__icontains=keyword, education__icontains=edu,place__icontains=city).values())  # 查询所有的职位信息job_data = []if price_min != "" or price_max != "":for job in job_data_list:try:salary_1 = '薪资' + job['salary']max_salary = float(re.findall(r'-(\d+)k', salary_1)[0])  # 使用正则提取最高薪资min_salary = float(re.findall(r'薪资(\d+)', salary_1)[0])  # 使用正则提取最低薪资if price_min == "" and price_max != "":if max_salary <= float(price_max):job_data.append(job)elif price_min != "" and price_max == "":if min_salary >= float(price_min):job_data.append(job)else:if min_salary >= float(price_min) and float(price_max) >= max_salary:job_data.append(job)except Exception as e:  # 如果筛选不出就跳过continueelse:job_data = job_data_listjob_data_1 = job_data[(page - 1) * limit:limit * page]for job in job_data_1:ret = models.SendList.objects.filter(user_id=request.session.get("user_id"), job_id=job['job_id']).values()if ret:job['send_key'] = 1else:job['send_key'] = 0# print(job_data_1)if len(job_data) == 0 or len(job_data_list) == 0:return JsonResponse({"code": 1, "msg": "没找到需要查询的数据！", "count": "{}".format(len(job_data)), "data": job_data_1})return JsonResponse({"code": 0, "msg": "success", "count": "{}".format(len(job_data)), "data": job_data_1})def get_psutil(request):"""此函数用于读取cpu使用率和内存占用率"""# cpu_percent()可以获取cpu的使用率，参数interval是获取的间隔# virtual_memory()[2]可以获取内存的使用率return JsonResponse({'cpu_data': cpu_percent(interval=1), 'memory_data': virtual_memory()[2]})def get_pie(request):"""此函数用于渲染控制台饼图的数据,要求学历的数据和薪资待遇的数据"""edu_list = ['博士', '硕士', '本科', '大专', '不限']edu_data = []for edu in edu_list:edu_count = len(models.JobData.objects.filter(education__icontains=edu))  # 使用for循环，查询字段education包含这些学历的职位信息edu_data.append({'name': edu, "value": edu_count})  # 添加到学历的数据列表中# print(edu_data)list_5 = []list_10 = []list_15 = []list_20 = []list_30 = []list_50 = []list_51 = []job_data = models.JobData.objects.all().values()  # 查询所有的职位信息for job in list(job_data):try:salary_1 = float(re.findall(r'-(\d+)k', job['salary'])[0])  # 提取薪资待遇的最高薪资要求if salary_1 <= 5:  # 小于5K则加入list_5list_5.append(salary_1)elif 10 >= salary_1 > 5:  # 在5K和10K之间，加入list_10list_10.append(salary_1)elif 15 >= salary_1 > 10:  # 10K-15K加入list_15list_15.append(salary_1)elif 20 >= salary_1 > 15:  # 15K-20K加入list_20list_20.append(salary_1)elif 30 >= salary_1 > 20:  # 20K-30K 加list_30list_30.append(salary_1)elif 50 >= salary_1 > 30:  # 30K-50K加入list_50list_50.append(salary_1)elif salary_1 > 50:  # 大于50K加入list_51list_51.append(salary_1)except Exception as e:job['salary_1'] = 0salary_data = [{'name': '5K及以下', 'value': len(list_5)},  # 生成薪资待遇各个阶段的数据字典，value是里面职位信息的数量{'name': '5-10K', 'value': len(list_10)},{'name': '10K-15K', 'value': len(list_15)},{'name': '15K-20K', 'value': len(list_20)},{'name': '20K-30K', 'value': len(list_30)},{'name': '30-50K', 'value': len(list_50)},{'name': '50K以上', 'value': len(list_51)}]# print(edu_data)return JsonResponse({'edu_data': edu_data, 'salary_data': salary_data})def send_job(request):"""此函数用于投递职位和取消投递"""if request.method == "POST":user_id = request.session.get("user_id")job_id = request.POST.get("job_id")send_key = request.POST.get("send_key")if int(send_key) == 1:models.SendList.objects.filter(user_id=user_id, job_id=job_id).delete()else:models.SendList.objects.create(user_id=user_id, job_id=job_id)return JsonResponse({"Code": 0, "msg": "操作成功"})def job_expect(request):if request.method == "POST":job_name = request.POST.get("key_word")city = request.POST.get("city")ret = models.UserExpect.objects.filter(user=request.session.get("user_id"))# print(ret)if ret:ret.update(key_word=job_name, place=city)else:user_obj = models.UserList.objects.filter(user_id=request.session.get("user_id")).first()models.UserExpect.objects.create(user=user_obj, key_word=job_name, place=city)return JsonResponse({"Code": 0, "msg": "操作成功"})else:ret = models.UserExpect.objects.filter(user=request.session.get("user_id")).values()# print(ret)if len(ret) != 0:keyword = ret[0]['key_word']place = ret[0]['place']else:keyword = ''place = ''return render(request, "expect.html", locals())def get_recommend(request):recommend_list = job_recommend.recommend_by_item_id(request.session.get("user_id"), 9)# print(recommend_list)return render(request, "recommend.html", locals())def send_page(request):return render(request, "send_list.html")def send_list(request):send_list = list(models.JobData.objects.filter(sendlist__user=request.session.get("user_id")).values())for send in send_list:send['send_key'] = 1if len(send_list) == 0:return JsonResponse({"code": 1, "msg": "没找到需要查询的数据！", "count": "{}".format(len(send_list)), "data": []})else:return JsonResponse({"code": 0, "msg": "success", "count": "{}".format(len(send_list)), "data": send_list})def pass_page(request):user_obj = models.UserList.objects.filter(user_id=request.session.get("user_id")).first()return render(request, "pass_page.html", locals())def up_info(request):if request.method == "POST":user_name = request.POST.get("user_name")old_pass = request.POST.get("old_pass")pass_word = request.POST.get("pass_word")user_obj = models.UserList.objects.filter(user_id=request.session.get("user_id")).first()if old_pass != user_obj.pass_word:return JsonResponse({"Code": 0, "msg": "原密码错误"})else:models.UserList.objects.filter(user_id=request.session.get("user_id")).update(user_name=user_name,pass_word=pass_word)return JsonResponse({"Code": 0, "msg": "密码修改成功"})def salary(request):return render(request, "salary.html")def edu(request):return render(request, "edu.html")def bar_page(request):return render(request, "bar_page.html")def bar(request):key_list = [x['key_word'] for x in list(models.JobData.objects.all().values("key_word"))]# print(key_list)bar_x = list(set(key_list))# print(bar_x)bar_y = []for x in bar_x:bar_y.append(key_list.count(x))# print(bar_y)return JsonResponse({"Code": 0, "bar_x": bar_x, "bar_y": bar_y})