最近在找實習，就順便想到用python爬取一些職位資訊看看，有哪些崗位比較缺人。

#_*_coding:utf-8_*_

import requests
from bs4 import BeautifulSoup
import xlwt
import re

book = xlwt.Workbook()
#建立表格
sheet = book.add_sheet('sheet1', cell_overwrite_ok=True)

def getHtml():
 url ='http://www.shixiseng.com/interns?p='
 request = requests.get(url=url)
 respons = request.content      #得到頁面原始碼
 

 soup = BeautifulSoup(respons,'html.parser')   #解析原始碼
 #下面是計算崗位列表的頁數
 page=soup.select('div#pagebar')[0]   
 l=str(page.select('li')[-1].a.attrs['href'])
 x=re.compile(r'\d{3}')
 y=x.search(l)
 lastpage=int(y.group())
 print lastpage
 #呼叫函式
 saveData(url,lastpage + 1)

def saveData(url,lastpage):
    row=0
 
  #必須定義為全域性變數
    for i in range(1,lastpage):
        html = requests.get(url='%s%d' % (url,i)).content
        soup = BeautifulSoup(html,'html.parser')
        infos = soup.select('div.posi-list')[0].select('div.list')
        #相關的資料資訊
        for info in infos:
            po_name = info.select('div.names.cutom_font'
 
)[0].a.text
            part = info.find('a', class_='cutom_font').text
            addr = info.find('div', class_='addr').span.text
            xz = info.find('div', class_='xz').span.text

        #寫入excel
            sheet.write(row, 0, po_name)
            sheet.write(row, 1, part)
            sheet.write(row, 2, addr)
            sheet.write(row, 3, xz)
            row+=1


if __name__ == '__main__':
    getHtml()
    book.save('shixiseng.xls')