#通过输入的关键字,爬取北京地区某岗位的平均月薪 # -*- coding: utf-8 -*- import re import requests import time import lxml.html from bs4 import BeautifulSoup #------------------------------------------------定义函数:获取指定网页北京地区所有相关职位的月薪--------------------- def getSalary(url): headers = {"User-Agent": 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36'} resp=requests.get(url,headers=headers) time.sleep(5) web_data = BeautifulSoup(resp.content, "lxml") firstlist=web_data.find_all('td') salarylist1=[] salarylist2=[] for i in firstlist: if 'zwyx' in str(i) and '面议' not in str(i): #提取职位月薪,并存入salarylist1列表,月薪为面议时不统计 salarylist1.append(str(i)) #将列表转为字符串,并用正则表达式提取字符串里面的数字(即月薪),并存入salarylist2,此时列表中元素格式还是字符串 salaryliststr='+'.join(salarylist1) reeq=re.compile(r'(\w[0-9]+)\w*') salarylist2=re.findall(reeq,salaryliststr) salarylist2=map(float,salarylist2) #将字符串格式的月薪转为float型 return salarylist2 #以数字列表形式返回指定网页所有统计到的月薪 #-------------------------定义函数:统计智联招聘网站北京地区,招聘岗位名称包含keyword关键字所有岗位的平均月薪------------- def getAverageSalary(keyword): url=r'http://sou.zhaopin.com/jobs/searchresult.ashx?jl=%E5%8C%97%E4%BA%AC&kw='+keyword+'&sm=0&p=1&kt=3' #包含关键字的网站名 headers = {"User-Agent": 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36'} pagelist=[] salarylist=getSalary(url) #提取第一页的招聘岗位月薪信息,并存入salarylist列表 print salarylist while True: resp=requests.get(url,headers=headers) time.sleep(5) if resp.status_code!=200: break resp=resp.content reg=r'a href="(.*?)" class="next-page">下一页</a>' #用于获取下一页地址的正则表达式 reg=re.compile(reg) page=re.findall(reg,resp) if page!=[]: #如果未到检索的最后一页 page1=re.split(r'href="',page[0]) #提取当前页的下一页的网址,并赋给url if re.search('http',page1[-1]): pagelist.append(page1[-1]) url=page1[-1] salarylist2=getSalary(url) #print 'salarylist',salarylist salarylist.extend(salarylist2) #将新提取的月薪信息存入salarylist列表 #print 'salarylist2',salarylist else: break else: #已到检索到的最后一页,结束循环 break salarylist=map(float,salarylist) if len(salarylist)!=0: averageSalary=sum(salarylist)/len(salarylist) return averageSalary,pagelist else: print '统计到的月薪列表为0,请检查网页是否正确!' return 0,[0,] averageSalary,pagelist=getAverageSalary('CAE') #爬取关键字为 CAE 的岗位平均月薪 print 'AverageSalary:',averageSalary