python使用bs4爬取boss直聘静态页面

思路:

  1、将需要查询城市列表,通过城市接口转换成相应的code码

  2、遍历城市、职位生成url

  3、通过url获取列表页面信息,遍历列表页面信息

  4、再根据列表页面信息的job_link获取详情页面信息,将需要的信息以字典data的形式存在列表datas里  

  5、判断列表页面是否有下一页,重复步骤3、4;同时将列表datas一直传递下去

  6、一个城市、职位url爬取完后,将列表datas接在列表datas_list后面,重复3、4、5

  7、最后将列表datas_list的数据,遍历写在Excel里面

知识点:

  1、将response内容以json形式输出,解析json并取值

  2、soup 的select()和find_all()和find()方法使用

  3、异常Exception的使用

  4、wldt创建编辑Excel的使用

import requests, time, xlwt
from bs4 import BeautifulSoup

class MyJob():
  def __init__(self, mycity, myquery):
    self.city = mycity
    self.query = myquery
    self.list_url = "https://www.zhipin.com/job_detail/?query=%s&city=%s&industry=&position="%(self.query, self.city)
    self.datas = []
    self.header = {
      'authority': 'www.zhipin.com',
      'method': 'GET',
      'scheme': 'https',
      'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
      'accept-encoding': 'gzip, deflate, br',
      'accept-language': 'zh-CN,zh;q=0.9',
      'cache-control': 'max-age=0',
      'cookie': 'lastCity=101210100;uab_collina=154408714637849548916323;toUrl=/;c=1558272251;g=-;l=l=%2Fwww.zhipin.com%2Fuser%2Flogin.html&r=; Hm_lvt_194df3105ad7148dcf2b98a91b5e727a=1555852331,1556985726,1558169427,1558272251; __a=40505844.1544087205.1558169426.1558272251.41.14.4.31; Hm_lpvt_194df3105ad7148dcf2b98a91b5e727a=1558272385',
      'referer': 'https://www.zhipin.com/?ka=header-logo',
      'upgrade-insecure-requests': '1',
      'user-agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36'
    }

  #将城市转化为code码
  def get_city(self,city_list):
    city_url = "https://www.zhipin.com/wapi/zpCommon/data/city.json" #获取城市
    json = requests.get(city_url).json()
    zpData = http://www.cppcns.com/jiaoben/python/json["zpData"]["cityList"]
    list = []
    for city in city_list :
      for data_sf in zpData:
        for data_dq in data_sf["subLevelModelList"]:
          if city == data_dq["name"]:
             list.append(data_dq["code"])
    return list

  #获取所有页内容
  def get_job_list(self, url, datas):
    print(url)
    html = requests.get(url, headers=self.header).text
    soup = BeautifulSoup(html, 'html.parser')
    jobs = soup.select(".job-primary")
    for job in jobs:
      data = http://www.cppcns.com/jiaoben/python/{}
      # 招聘id
      data["job_id"] = job.find_all("div", attrs={"class": "info-primary"})[0].find("a").get("data-jobid")
      # 招聘链接
      data["job_link"] = "https://www.zhipin.com" + job.find_all("div", attrs={"class": "info-primary"})[0].find("a").get("href")
      # 招聘岗位
      data["job_name"] = job.find_all("div", attrs={"class": "info-primary"})[0].find("div", attrs={"class": "job-title"}).get_text()
      # 薪资
      data["job_red"] = job.find_all("div", attrs={"class": "info-primary"})[0].find("span", attrs={"class": "red"}).get_text()
      # 地址 #工作年限 #学历
      data["job_address"] = job.find_all("div", attrs={"class": "info-primary"})[0].find("p").get_text().split(" ")
      # 企业链接
      data["job_company_link"] = job.find_all("div", attrs={"class": "info-company"})[0].find("a").get("href")
      # 企业信息
      data["job_company"] = job.find_all("div", attrs={"class": "info-company"})[0].find("p").get_text().split(" ")
      # boss链接
      data["job_publis_link"] = job.find_all("div", attrs={"class": "info-publis"})[0].find("img").get("src")
      # boos信息
      data["job_publis"] = job.find_all("div", attrs={"class": "info-publis"})[0].find("h3").get_text().split(" ")
      time.sleep(5)
      self.get_job_detail(data) # 获取job详情页内容
      print(data)
      datas.append(data) # 将某条job添加到datas中,直到将当前页添加完

    try:
      next_url = soup.find("div", attrs={"class": "page"}).find("a", attrs={"class": "next"}).get("href")
      #if next_url[-1] =="3": # 第二页自动抛异常
      if next_url in "javascript:;": # 最后一页自动抛异常
        raise Exception()
    except Exception as e:
      print("最后一页了;%s" % e)
      return datas # 返回所有页内容
    else:
      time.sleep(5)
      next_url = "https://www.zhipin.com" + next_url
      self.get_job_list(next_url, datas)
      return datas # 返回所有页内容

  #获取详情页内容
  def get_job_detail(self, data):
    print(data["job_link"])
    html = requests.get(data["job_link"], headers=self.header).text
    soup = BeautifulSoup(html, 'html.parser')
    # 招聘公司
    data["detail_content_name"] = soup.find_all("div", attrs={"class": "detail-content"})[0].find("div", attrs={"class": "name"}).get_text()
    # 福利
    data["detail_primary_tags"] = soup.find_all("div", attrs={"class": "info-primary"})[0].find("div", attrs={"class": "job-tags"}).get_text().strip()
    # 招聘岗位
    data["detail_primary_name"] = soup.find_all("div", attrs={"class": "info-primary"})[0].find("h1").get_text()
    # 招聘状态
    data["detail_primary_status"] = soup.find_all("div", attrs={"class": "info-primary"})[0].find("div", attrs={"class": "job-status"}).get_text()
    # 薪资
    data["detail_primary_salary"] = soup.find_all("div", attrs={"class": "info-primary"})[0].find("span", attrs={"class": "salary"}).get_text()
    # 地址 #工作年限 #学历
    data["detail_primary_address"] = soup.find_all("div", attrs={"class": "info-primary"})[0].find("p").get_text()
    # 工作地址
    data["detail_content_address"] = soup.find_all("div", attrs={"class": "detail-content"})[0].find("div", attrs={"class": "location-address"}).get_text()
    # 职位描述
    data["detail_content_text"] = soup.find_all("div", attrs={"class": "detail-content"})[0].find("div", attrs={"class": "text"}).get_text().strip().replace(";", "\n")
    # boss名字
    data["detail_op_name"] = soup.find_all("div", attrs={"class": "detail-op"})[1].find("h2", attrs={"class": "name"}).get_text()
    # boss职位
    data["detail_op_job"] = soup.find_all("div", attrs={"class": "detail-op"})[1].find("p", attrs={"class": "gray"}).get_text().split("·")[0]
    # boss状态
    data["detail_op_status"] = soup.find_all("div", attrs={"class": "detail-op"})[1].find("p", attrs={"class": "gray"}).get_text().split("·")[1]

  #将获取的数据写入Excel
  def setExcel(self, datas_list):
    book = xlwt.Workbook(encoding='utf-8')
    table = book.add_sheet("boss软件测试")
    table.write(0, 0, "编号")
    table.write(0, 1, "招聘链接")
    table.write(0, 2, "招聘岗位")
    table.write(0, 3, "薪资")
    table.write(0, 4, "地址")
    table.write(0, 5, "企业链接")
    table.write(0, 6, "企业信息")
    table.write(0, 7, "boss链接")
    table.write(0, 8, "boss信息")
    table.write(0, 9, "detail详情")
    i = 1
    for data in datas_list:
      table.write(i, 0, data["job_id"])
      table.write(i, 1, data["job_link"])
      table.write(i, 2, data["job_name"])
      table.write(i, 3, data["job_red"])
      table.write(i, 4, data["job_address"])
      table.write(i, 5, data["job_company_link"])
      table.write(i, 6, data["job_company"])
      table.write(i, 7, data["job_publis_link"])
      table.write(i, 8, data["job_publis"])

      table.write(i, 10, data["detail_content_name"])
      table.write(i, 11, data["detail_primary_name"])
      table.write(i, 12, data["detail_primary_status"])
      table.write(i, 13, data["detail_primary_salary"])
      table.write(i, 14, data["detail_primary_address"])
      table.write(i, 15, data["detail_content_text"])
      table.write(i, 16, data["detail_op_name"])
      table.write(i, 17, data["detail_op_job"])
      table.write(i, 18, data["detail_op_status"])
      table.write(i, 19, data["detail_primary_tags"])
      table.write(i, 20, data["detail_content_address"])
      i += 1
    book.save(r'C:\%s_boss软件测试.xls' % time.strftime('%Y%m%d%H%M%S'))
    print("Excel保存成功")

if __name__ == '__main__':
  city_list = MyJob("","").get_city(["杭州"])
  query_list = ["软件测试", "测试工程师"]
  datas_list = []
  for city in city_list:
    for query in query_list:
      myjob = MyJob(city, query)
      datas = myjob.get_job_list(myjob.list_url, myjob.datas)
      datas_list.extend(datas)
  myjob.setExcel(datas_list)

python使用bs4爬取boss直聘静态页面

扫一扫手机访问