python 爬去拉钩测试招聘信息

代码如下：

 

 1 #coding:utf-8
 2 import time
 3 import urllib.request
 4 from bs4 import BeautifulSoup
 5 file=open(r'meituancde.txt','w')
 6 def get_url(i):
 7     url='https://www.lagou.com/zhaopin/ceshi/%s/?filterOption=%s'%(i,i)
 8     return url
 9 def get_html(i):
10     headers={
11         'User-Agent':'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'
12         }
13     response=urllib.request.Request(url=get_url(i),headers=headers)
14     html=urllib.request.urlopen(response).read().decode('utf-8')
15     sopu=BeautifulSoup(html)
16     return sopu
17 def parse(i):
18     soup=get_html(i)
19     me=soup.findAll('',{'class':'money'}) #工资
20     me1=soup.findAll('',{'class':'format-time'})#发布时间
21     me2=soup.findAll('',{'class':'li_b_r'})#福利
22     me3=soup.findAll('',{'data-lg-tj-id':'8F00'})#公司名字
23     meitu={}
24     i=0
25     for title in me:
26         meitu['gongzi'] =me[i].text
27         for jianjie in me1:
28             meitu['发布时间']=me1[i].text
29             for sellum in me2:
30                 meitu['福利']=me2[i].text
31                 for pire in me3:
32                     meitu['公司名称']=me3[i].text
33         i+=1
34         print(meitu)
35         if len(meitu) !=0:
36             file.write(str(meitu))
37             file.write("\n")
38             file.close
39 if __name__ == '__main__':
40     for i in range(1,31):
41         parse(i)

结果图：

 

posted @ 2017-03-10 22:44  北漂的雷子  阅读(729)  评论(3)  编辑  收藏  举报