# Obey robots.txt rules
ROBOTSTXT_OBEY = False

# Configure a delay for requests for the same website (default: 0)
DOWNLOAD_DELAY = 60

# Disable cookies (enabled by default)
COOKIES_ENABLED = False

# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
   'bosszhipin.pipelines.BosszhipinPipeline': 300,
}

import scrapy

class BosszpItem(scrapy.Item):
    job_name = scrapy.Field()  # 岗位名
    job_area = scrapy.Field()  # 工作地址
    job_salary = scrapy.Field()  # 薪资
    com_name = scrapy.Field()  # 企业名称
    com_type = scrapy.Field()  # 企业类型
    com_size = scrapy.Field()  # 企业规模
    finance_stage = scrapy.Field()  # 融资情况
    work_year = scrapy.Field()  # 工作年限
    education = scrapy.Field()  # 学历要求
    job_benefits = scrapy.Field()  # 岗位福利

import scrapy
import json
import logging
import random
from bosszp.items import BosszpItem


class BossSpider(scrapy.Spider):
    name = 'boss'
    allowed_domains = ['zhipin.com']
    start_urls = ['https://www.zhipin.com/wapi/zpCommon/data/cityGroup.json']  # 热门城市列表url
    # 设置多个 cookie,建议数量为 页数/2 + 1 个cookie.至少 设置 4 个
    # 只需复制 __zp_stoken__ 部分即可
    cookies = [     '__zp_stoken__=f330bOEgsRnsAIS5Bb2FXe250elQKNzAgMBcQZ1hvWyBjUFE1DCpKLWBtBn99Nwd%2BPHtlVRgdOi1vDEAkOz9sag50aRNRfhs6TQ9kWmNYc0cFI3kYKg5fAGVPPX0WO2JCOipvRlwbP1YFBQlHOQ%3D%3D',       '__zp_stoken__=f330bOEgsRnsAIUsENEIbe250elRsb2U4Bg0QZ1hvW19mPEdeeSpKLWBtN3Y9QCN%2BPHtlVRgdOilvfTYkSTMiaFN0X3NRAGMjOgENX2krc0cFI3kYKiooQGx%2BPX0WO2I3OipvRlwbP1YFBQlHOQ%3D%3D',      '__zp_stoken__=f330bOEgsRnsAITsLNnJIe250elRJMH95DBAQZ1hvW1J1ewdmDCpKLWBtBHZtagV%2BPHtlVRgdOil1LjkkR1MeRAgdY3tXbxVORWVuTxQlc0cFI3kYKgwCEGxNPX0WO2JCOipvRlwbP1YFBQlHOQ%3D%3D'
    ]
    # 设置多个请求头
    user_agents = [
        'Mozilla/5.0 (Macintosh; Intel Mac OS X 11_0_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36',
        'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_6) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.0.1 Safari/605.1.15',
        'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0',
        'Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1',
        'Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11',
        'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)',
        'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)',
        'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)',
        'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)',
    ]
    page_no = 1  # 初始化分页

    def random_header(self):
        """
        随机生成请求头
        :return: headers
        """
        headers = {'Referer': 'https://www.zhipin.com/c101020100/?ka=sel-city-101020100'}
        headers['cookie'] = random.choice(self.cookies)
        headers['user-agent'] = random.choice(self.user_agents)
        return headers

    def parse(self, response):
        """
        解析首页热门城市列表，选择热门城市进行爬取
        :param response: 热门城市字典数据
        :return:
        """
        # 获取服务器返回的内容
        city_group = json.loads(response.body.decode())
        # 获取热门城市列表
        hot_city_list = city_group['zpData']['hotCityList']
        # 初始化空列表，存储打印信息
        # city_lst = []
        # for index,item in enumerate(hot_city_list):
        #    city_lst.apend({index+1: item['name']})
        # 列表推导式：
        hot_city_names = [{index + 1: item['name']} for index, item in enumerate(hot_city_list)]
        print("--->", hot_city_names)
        # 从键盘获取城市编号
        city_no = int(input('请从上述城市列表中，选择编号开始爬取：'))
        # 拼接url https://www.zhipin.com/job_detail/?query=&city=101040100&industry=&position=
        # 获取城市编码code
        city_code = hot_city_list[city_no - 1]['code']
        # 拼接查询接口
        city_url = 'https://www.zhipin.com/job_detail/?query=&city={}&industry=&position='.format(city_code)
        logging.info("<<<<<<<<<<<<<正在爬取第_{}_页岗位数据>>>>>>>>>>>>>".format(self.page_no))
        yield scrapy.Request(url=city_url, headers=self.random_header(), callback=self.parse_city)

    def parse_city(self, response):

        """
        解析岗位页数据
        :param response: 岗位页响应数据
        :return:
        """
        if response.status != 200:
            logging.warning("<<<<<<<<<<<<<获取城市招聘信息失败，ip已被封禁。请稍后重试>>>>>>>>>>>>>")
            return
        li_elements = response.xpath('//div[@class="job-list"]/ul/li')  # 定位到所有的li标签
        next_url = response.xpath('//div[@class="page"]/a[last()]/@href').get()  # 获取下一页

        for li in li_elements:
            job_name = li.xpath('./div/div[1]//div[@class="job-title"]/span[1]/a/text()').get()
            job_area = li.xpath('./div/div[1]//div[@class="job-title"]/span[2]/span[1]/text()').get()
            job_salary = li.xpath('./div/div[1]//span[@class="red"]/text()').get()
            com_name = li.xpath('./div/div[1]/div[2]//div[@class="company-text"]/h3/a/text()').get()
            com_type = li.xpath('./div/div[1]/div[2]/div[1]/p/a/text()').get()
            com_size = li.xpath('./div/div[1]/div[2]/div[1]/p/text()[2]').get()
            finance_stage = li.xpath('./div/div[1]/div[2]/div[1]/p/text()[1]').get()
            work_year = li.xpath('./div/div[1]/div[1]/div[1]/div[2]/p/text()[1]').get()
            education = li.xpath('./div/div[1]/div[1]/div[1]/div[2]/p/text()[2]').get()
            job_benefits = li.xpath('./div/div[2]/div[2]/text()').get()
            item = BosszpItem(job_name=job_name, job_area=job_area, job_salary=job_salary, com_name=com_name,
                              com_type=com_type, com_size=com_size,
                              finance_stage=finance_stage, work_year=work_year, education=education,
                              job_benefits=job_benefits)
            yield item
        if next_url == "javascript:;":
            logging.info('<<<<<<<<<<<<<热门城市岗位数据已爬取结束>>>>>>>>>>>>>')
            logging.info("<<<<<<<<<<<<<一共爬取了_{}_页岗位数据>>>>>>>>>>>>>".format(self.page_no))
            return
        next_url = response.urljoin(next_url)  # 网址拼接
        self.page_no += 1
        logging.info("<<<<<<<<<<<<<正在爬取第_{}_页岗位数据>>>>>>>>>>>>>".format(self.page_no))
        yield scrapy.Request(url=next_url, headers=self.random_header(), callback=self.parse_city)

from itemadapter import ItemAdapter


class BosszpPipeline:
    def process_item(self, item, spider):
        """
        保存数据到本地 csv 文件
        :param item: 数据项
        :param spider:
        :return: 
        """
        with open(file='全国-热门城市岗位数据.csv', mode='a+', encoding='utf8') as f:
            f.write(
                '{job_name},{job_area},{job_salary},{com_name},{com_type},{com_size},{finance_stage},{work_year},'
                '{education},{job_benefits}'.format( 
                    **item))
        return item

# -*- coding:utf-8 -*-
"""
    作者：jhzhong
    功能：对岗位数据进行清洗与预处理
    需求：
        1. 读取 `全国-热门城市岗位数据.csv` 文件
        2. 对重复行进行清洗。
        3. 对`工作地址`字段进行预处理。要求：北京·海淀区·西北旺 --> 北京，海淀区，西北旺。分隔成3个字段
        4. 对`薪资`字段进行预处理。要求：30-60K·15薪 --> 最低：30，最高：60
        5. 对`工作经验`字段进行预处理。要求：经验不限/在校/应届 ：0，1-3年：1，3-5年：2，5-10年：3，10年以上:4
        6. 对`企业规模`字段进行预处理。要求：500人以下：0，500-999：1，1000-9999：2，10000人以上：3
        7. 对`岗位福利`字段进行预处理。要求：将描述中的中文'，'（逗号）,替换成英文','（逗号）
        8. 对缺失值所在行进行清洗。
        9. 将处理后的数据保存到 MySQL 数据库
"""
# 导入模块
import pandas as pd
from sqlalchemy import create_engine
import logging

# 读取 全国-热门城市岗位招聘数据.csv 文件
all_city_zp_df = pd.read_csv('../全国-热门城市岗位数据.csv', encoding='utf8')

# 对重复行进行清洗。
all_city_zp_df.drop_duplicates(inplace=True)

# 对`工作地址`字段进行预处理。要求：北京·海淀区·西北旺 --> 北京，海淀区，西北旺。分隔成3个字段
all_city_zp_area_df = all_city_zp_df['job_area'].str.split('·', expand=True)
all_city_zp_area_df = all_city_zp_area_df.rename(columns={0: "city", 1: "district", 2: "street"})

# 对`薪资`字段进行预处理。要求：30-60K·15薪 --> 最低：30，最高：60
all_city_zp_salary_df = all_city_zp_df['job_salary'].str.split('K', expand=True)[0].str.split('-', expand=True)
all_city_zp_salary_df = all_city_zp_salary_df.rename(columns={0: 'salary_lower', 1: 'salary_high'})


# 对`工作经验`字段进行预处理。要求：经验不限/在校/应届 ：0，1-3年：1，3-5年：2，5-10年：3，10年以上:4
def fun_work_year(x):
    if x in "1-3年":
        return 1
    elif x in "3-5年":
        return 2
    elif x in "5-10年":
        return 3
    elif x in "10年以上":
        return 4
    else:
        return 0


all_city_zp_df['work_year'] = all_city_zp_df['work_year'].apply(lambda x: fun_work_year(x))


# 对`企业规模`字段进行预处理。要求：500人以下：0，500-999：1，1000-9999：2，10000人以上：3
def fun_com_size(x):
    if x in "500-999人":
        return 1
    elif x in "1000-9999人":
        return 2
    elif x in "10000人以上":
        return 3
    else:
        return 0


# 对`岗位福利`字段进行预处理。要求：将描述中的中文'，'（逗号）,替换成英文','（逗号）
all_city_zp_df['job_benefits'] = all_city_zp_df['job_benefits'].str.replace('，', ',')

# 合并所有数据集
clean_all_city_zp_df = pd.concat([all_city_zp_df, all_city_zp_salary_df, all_city_zp_area_df], axis=1)

# 删除冗余列
clean_all_city_zp_df.drop('job_area', axis=1, inplace=True)  # 删除原区域
clean_all_city_zp_df.drop('job_salary', axis=1, inplace=True)  # 删除原薪资

# 对缺失值所在行进行清洗。
clean_all_city_zp_df.dropna(axis=0, how='any', inplace=True)
clean_all_city_zp_df.drop(axis=0,
                          index=(clean_all_city_zp_df.loc[(clean_all_city_zp_df['job_benefits'] == 'None')].index),
                          inplace=True)
# 将处理后的数据保存到 MySQL 数据库
engine = create_engine('mysql+pymysql://root:123456@localhost:3306/bosszp_db?charset=utf8')
clean_all_city_zp_df.to_sql('t_boss_zp_info', con=engine, if_exists='replace')
logging.info("Write to MySQL Successfully!")

# -*- coding:utf-8 -*-
"""
    作者：jhzhong
    功能：连接数据库，封装了操作数据库的增删改查等常见操作函数
"""

import pymysql
import logging


class DBUtils(object):
    # 初始化连接对象和游标对象
    _db_conn = None
    _db_cursor = None

    """
        数据库工具类 初始化方法
        传入 host，user，password，db 进行数据库连接
    """

    def __init__(self, host, user, password, db, port=3306, charset='utf8'):
        try:
            self._db_conn = pymysql.connect(host=host, user=user, password=password, port=port, db=db, charset=charset)
            self._db_cursor = self._db_conn.cursor()
        except Exception as e:
            logging.error(e)

    def get_one(self, sql_str, args=None):
        """
        查询单个结果，返回具体的数据内容
        :param sql_str: sql语句
        :param args: 参数列表
        :return: result
        """
        try:
            if self._db_conn is not None:
                self._db_cursor.execute(sql_str, args=args)
                result = self._db_cursor.fetchone()
                return result
            else:
                logging.error("请检查数据库连接")
        except Exception as e:
            logging.error(e)

    # 查询多个结果
    def get_all(self, sql_str, args=None):
        """
        查询多个结果，返回元组对象
        :param sql_str: sql 语句
        :param args: 参数列表
        :return: result
        """
        try:
            if self._db_conn is not None:
                self._db_cursor.execute(sql_str, args=args)
                result = self._db_cursor.fetchall()
                return result
            else:
                logging.error("请检查数据库连接")
        except Exception as e:
            logging.error(e)

    # 插入数据
    def insert(self, sql_str, args=None):
        """
        向数据库插入数据，返回影响行数（int）
        :param sql_str: sql 语句
        :param args: 参数列表
        :return: affect_rows
        """
        try:
            if self._db_conn is not None:
                affect_rows = self._db_cursor.execute(sql_str, args=args)
                self._db_conn.commit()
                return affect_rows
            else:
                logging.error("请检查数据库连接")
        except Exception as e:
            self._db_conn.rollback()
            logging.error(e)

    # 修改数据
    def modify(self, sql_str, args=None):
        """
        更新数据，返回影响行数（int）
        :param sql_str: sql 语句
        :param args: 参数列表
        :return: affect_rows
        """
        return self.insert(sql_str=sql_str, args=args)

    # 删除数据
    def delete(self, sql_str, args=None):
        """
        删除数据，返回影响行数（int）
        :param sql_str: sql 语句
        :param args: 参数列表
        :return: affect_rows
        """
        return self.insert(sql_str=sql_str, args=args)

    def __del__(self):
        """
        程序运行结束后，会默认调用 __del__ 方法
        销毁对象
        """
        if self._db_conn is not None:
            self._db_cursor.close()
            self._db_conn.close()

highcharts.js
highcharts-more.js
dark-unica.js
wordcloud.js
oldie.js

# -*- coding:utf-8 -*-
"""
    作者：jhzhong
    功能：数据分析于可视化
"""

from flask import Flask, render_template
from bosszp.web.dbutils import DBUtils
import json

app = Flask(__name__)


def get_db_conn():
    """
    获取数据库连接
    :return: db_conn 数据库连接对象
    """
    return DBUtils(host='localhost', user='root', password='123456', db='bosszp_db')


def msg(status, data='未加载到数据'):
    """
    :param status: 状态码 200成功，201未找到数据
    :param data: 响应数据
    :return: 字典 如{'status': 201, 'data': ‘未加载到数据’}
    """
    return json.dumps({'status': status, 'data': data})


@app.route('/')
def index():
    """
    首页
    :return: index.html 跳转到首页
    """
    return render_template('index.html')


@app.route('/getwordcloud')
def get_word_cloud():
    """
    获取岗位福利词云数据
    :return:
    """
    db_conn = get_db_conn()
    text = \
        db_conn.get_one(sql_str="SELECT GROUP_CONCAT(job_benefits) FROM t_boss_zp_info")[0]
    if text is None:
        return msg(201)
    return msg(200, text)


@app.route('/getjobinfo')
def get_job_info():
    """
    获取热门岗位招聘区域分布
    :return:
    """
    db_conn = get_db_conn()
    results = db_conn.get_all(
        sql_str="SELECT city,district,COUNT(1) as num FROM t_boss_zp_info GROUP BY city,district")
    # {"city":"北京","info":[{"district":"朝阳区","num":27},{"海淀区":43}]}

    if results is None or len(results) == 0:
        return msg(201)
    data = []
    city_detail = {}
    for r in results:
        info = {'name': r[1], 'value': r[2]}
        if r[0] not in city_detail:
            city_detail[r[0]] = [info]
        else:
            city_detail[r[0]].append(info)
    for k, v in city_detail.items():
        temp = {'name': k, 'data': v}
        data.append(temp)
    return msg(200, data)


@app.route('/getjobnum')
def get_job_num():
    """
    获取个城市岗位数量
    :return:
    """
    db_conn = get_db_conn()
    results = db_conn.get_all(sql_str="SELECT city,COUNT(1) num FROM t_boss_zp_info GROUP BY city")
    if results is None or len(results) == 0:
        return msg(201)
    if results is None or len(results) == 0:
        return msg(201)
    data = []
    for r in results:
        data.append(list(r))
    return msg(200, data)


@app.route('/getcomtypenum')
def get_com_type_num():
    """
    获取企业类型占比
    :return:
    """
    db_conn = get_db_conn()
    results = db_conn.get_all(
        sql_str="SELECT com_type, ROUND(COUNT(1)/(SELECT SUM(t1.num) FROM (SELECT COUNT(1) num FROM t_boss_zp_info GROUP BY com_type) t1)*100,2) percent FROM t_boss_zp_info GROUP BY com_type")
    if results is None or len(results) == 0:
        return msg(201)
    data = []
    for r in results:
        data.append({'name': r[0], 'y': float(r[1])})
    return msg(200, data)


# 扇形图
@app.route('/geteducationnum')
def geteducationnum():
    """
    获取学历占比
    :return:
    """
    db_conn = get_db_conn()
    results = db_conn.get_all(
        sql_str="SELECT t1.education,ROUND(t1.num/(SELECT SUM(t2.num) FROM(SELECT COUNT(1) num FROM t_boss_zp_info t GROUP BY t.education)t2)*100,2) FROM( SELECT t.education,COUNT(1) num FROM t_boss_zp_info t GROUP BY t.education) t1")
    if results is None or len(results) == 0:
        return msg(201)
    data = []
    for r in results:
        data.append([r[0], float(r[1])])
    return msg(200, data)


# 获取排行榜
@app.route('/getorder')
def getorder():
    """
    获取企业招聘数量排行榜
    :return:
    """
    db_conn = get_db_conn()
    results = db_conn.get_all(
        sql_str="SELECT t.com_name,COUNT(1) FROM t_boss_zp_info t GROUP BY t.com_name ORDER BY COUNT(1) DESC LIMIT 10")
    if results is None or len(results) == 0:
        return msg(201)
    data = []
    for i, r in enumerate(results):
        data.append({'id': i + 1,
                     'name': r[0],
                     'num': r[1]})
    return msg(200, data)


if __name__ == '__main__':
    app.run(host='127.0.0.1', port=8080, debug=True)