使用python爬蟲如何判斷網(wǎng)頁信息是否存在

{
  "_id" : ObjectId("5a30ad2068504386f47d9a4b"),
  "city" : "蘇州",
  "companyShortName" : "藍(lán)海彤翔",
  "companySize" : "100-499人",
  "education" : "本科",
  "financeStage" : "B輪",
  "industryField" : "互聯(lián)網(wǎng)",
  "level" : 3,
  "pid" : "11889834",
  "positionLables" : [
    "PHP",
    "ThinkPHP"
  ],
  "positionName" : "php研發(fā)工程師",
  "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、處理landcloud云計(jì)算相關(guān)系統(tǒng)的各類開發(fā)和調(diào)研工作；2、處理coms高性能計(jì)算的各類開發(fā)和調(diào)研工作崗位要求：1、本科學(xué)歷，兩年以上工作經(jīng)驗(yàn)，熟悉PHP開發(fā)，了解常用的php開發(fā)技巧和框架；2、了解C++，python及Java開發(fā)；3、有一定的研發(fā)能力和鉆研精神；4、有主動(dòng)溝通能力和吃苦耐勞的精神。",
  "location" : "蘇州市高新區(qū)科技城錦峰路158號(hào)101park8幢"

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'}


# 獲取崗位頁數(shù)
def getJobPage(url):
  ret = requests.get(url, headers=header)
  ret.encoding = "utf-8" # 解決亂碼問題
  html = ret.text
  soup = BeautifulSoup(html, 'html.parser')
  # 獲取崗位總數(shù)，< 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" # 解決亂碼問題
  html = ret.text
  soup = BeautifulSoup(html, 'html.parser')
  # 工作職責(zé)
  jobRequests = soup.select('ul[class="squareli"]')[0].text
  # 工作要求
  jobOrder = soup.select('ul[class="squareli"]')[1].text
  return jobRequests, jobOrder


# 獲取崗位信息
def getJobInfo(url):
  myfile = open("tencent_job.txt", "a", encoding='gb18030', errors='ignore') # 解決亂碼問題
  ret = requests.get(url, headers=header)
  ret.encoding = "utf-8" # 解決亂碼問題
  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']
    # 職位名稱
    jobName = job.select('td:nth-of-type(1) > a')[0].text
    # 人數(shù)
    jobPeople = job.select('td:nth-of-type(3)')[0].text
    # 地點(diǎn)
    jobAddre = job.select('td:nth-of-type(4)')[0].text
    # 發(fā)布時(shí)間
    jobTime = job.select('td:nth-of-type(5)')[0].text
    # 工作職責(zé)
    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&#63;keywords=python'
  jobPage = getJobPage(mainurl)
  print(jobPage)
  for page in range(jobPage):
    pageUrl = 'https://hr.tencent.com/position.php&#63;keywords=python&start=' + str(page * 10) + '#a'
    print("第" + str(page + 1) + "頁")
    getJobInfo(pageUrl)