一聚教程网:一个值得你收藏的教程网站

热门教程

python爬虫判断招聘信息是否存在代码示例

时间:2022-11-14 23:01:50 编辑:袖梨 来源:一聚教程网

本篇文章小编给大家分享一下python爬虫判断招聘信息是否存在代码示例,文章代码介绍的很详细,小编觉得挺不错的,现在分享给大家供大家参考,有需要的小伙伴们可以来看看。

代码:

{
  "_id" : ObjectId("5a30ad2068504386f47d9a4b"),
  "city" : "苏州",
  "companyShortName" : "蓝海彤翔",
  "companySize" : "100-499人",
  "education" : "本科",
  "financeStage" : "B轮",
  "industryField" : "互联网",
  "level" : 3,
  "pid" : "11889834",
  "positionLables" : [
    "PHP",
    "ThinkPHP"
  ],
  "positionName" : "php研发工程师",
  "salary" : {
    "avg" : 7500.0,
    "low" : 7000,
    "high" : 8000
  },
  "time" : "2017-06-06",
  "updated_at" : "2017-12-13 18:31:15",
  "workYear" : "1-3年",
  "detail" : "1、处理landcloud云计算相关系统的各类开发和调研工作;2、处理coms高性能计算的各类开发和调研工作岗位要求:1、本科学历,两年以上工作经验,熟悉PHP开发,了解常用的php开发技巧和框架;2、了解C++,python及Java开发;3、有一定的研发能力和钻研精神;4、有主动沟通能力和吃苦耐劳的精神。",
  "location" : "苏州市高新区科技城锦峰路158号101park8幢"

实例扩展:

python爬虫爬取腾讯招聘信息 (静态爬虫)

import requests
from bs4 import BeautifulSoup
from math import ceil

header = {
  'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'}


# 获取岗位页数
def getJobPage(url):
  ret = requests.get(url, headers=header)
  ret.encoding = "utf-8" # 解决乱码问题
  html = ret.text
  soup = BeautifulSoup(html, 'html.parser')
  # 获取岗位总数,< span class ="lightblue total" > 512 < / span >
  totalJob = soup.select('span[class="lightblue total"]')[0].text
  jobPage = ceil(int(totalJob) / 10)
  return jobPage


def getJobOrder(url):
  ret = requests.get(url, headers=header)
  ret.encoding = "utf-8" # 解决乱码问题
  html = ret.text
  soup = BeautifulSoup(html, 'html.parser')
  # 工作职责
  jobRequests = soup.select('ul[class="squareli"]')[0].text
  # 工作要求
  jobOrder = soup.select('ul[class="squareli"]')[1].text
  return jobRequests, jobOrder


# 获取岗位信息
def getJobInfo(url):
  myfile = open("tencent_job.txt", "a", encoding='gb18030', errors='ignore') # 解决乱码问题
  ret = requests.get(url, headers=header)
  ret.encoding = "utf-8" # 解决乱码问题
  html = ret.text
  soup = BeautifulSoup(html, 'html.parser')
  jobList = soup.find_all('tr', class_=['even', 'odd'])
  for job in jobList:
    # url
    jobUrl = "https://hr.tencent.com/" + job.select('td:nth-of-type(1) > a')[0]['href']
    # 职位名称
    jobName = job.select('td:nth-of-type(1) > a')[0].text
    # 人数
    jobPeople = job.select('td:nth-of-type(3)')[0].text
    # 地点
    jobAddre = job.select('td:nth-of-type(4)')[0].text
    # 发布时间
    jobTime = job.select('td:nth-of-type(5)')[0].text
    # 工作职责
    jobRequests = getJobOrder(jobUrl)[0]
    # 工作要求
    jobOrder = getJobOrder(jobUrl)[1]

    #print(jobName, jobUrl, jobAddre, jobPeople, jobTime, jobRequests, jobOrder)

    tt = jobName + " " + jobUrl + " " + jobAddre + " " + jobPeople + " " + jobTime + " " + jobRequests + " " + jobOrder
    myfile.write(tt + "n")


if __name__ == '__main__':
  mainurl = 'https://hr.tencent.com/position.php?keywords=python'
  jobPage = getJobPage(mainurl)
  print(jobPage)
  for page in range(jobPage):
    pageUrl = 'https://hr.tencent.com/position.php?keywords=python&start=' + str(page * 10) + '#a'
    print("第" + str(page + 1) + "页")
    getJobInfo(pageUrl)

热门栏目