一个抓取智联招聘数据并存入表格的python爬虫

 import requests

 import lxml,time,os

 from bs4 import BeautifulSoup as sb

 from xlwt import *

 import sys

 reload(sys)

 sys.setdefaultencoding('utf-8')

 print sys.getdefaultencoding()

 book = Workbook(encoding = "utf-8")

 table = book.add_sheet("test1")

 table.write(0,0,'number')

 table.write(0,1,'position')

 table.write(0,2,'feedback')

 table.write(0,3,'company')

 table.write(0,4,'salary')

 table.write(0,5,'address ')

 table.write(0,6,"updatetime")

 table.write(0,7,"details")

 headers = {"User-Agent":"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.133 Safari/537.36"}

 for num in range(90):

     url = 'http://sou.zhaopin.com/jobs/searchresult.ashx?jl=%E4%B8%9C%E8%8E%9E&p='+str(num)

     print url

     res = requests.get(url,headers = headers)

     html = sb(res.text,'lxml')

     zwmc = html.find_all('td',class_="zwmc")

     fk_lv = html.find_all('td',class_="fk_lv")

     gsmc = html.find_all('td',class_="gsmc")

     zwyx = html.find_all('td',class_="zwyx")

     gzdd = html.find_all('td',class_="gzdd")

     gxsj = html.find_all('td',class_="gxsj")

     details = html.find_all('li',class_="newlist_deatil_last")

     row = num*len(zwmc)

     for i in range(1,len(zwmc)):

         print zwmc[i].text.strip()+"---"+fk_lv[i].text.strip()+"---"+ gsmc[i].text.strip()+"---"+ zwyx[i].text.strip()+"---"+ gzdd[i].text.strip()+"---"+gxsj[i].text.strip()

         table.write(row+i,0,row+i)

         table.write(row+i,1,zwmc[i].text.strip())

         table.write(row+i,2,fk_lv[i].text.strip())

         table.write(row+i,3,gsmc[i].text.strip())

         table.write(row+i,4,zwyx[i].text.strip())

         table.write(row+i,5,gzdd[i].text.strip())

         table.write(row+i,6,gxsj[i].text.strip())

         table.write(row+i,7,details[i].text.strip())

 book.save('result.xls')