实习僧（爬虫职位信息采集demo）

基本程序（第一次实战），简单写写，有时间进行修改扩展。（requests ;urllib.parse;BeautifulSoup)

import requests
from bs4 import BeautifulSoup
import urllib.parse

headers = {'User-Agent':"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1"}
all_url='http://www.shixiseng.com/interns?k=%E7%88%AC%E8%99%AB&p=1'
start_html=requests.get(all_url,headers=headers)
soup=BeautifulSoup(start_html.text,'lxml')
href=soup.find_all('div',{'class':'names cutom_font'})
for link in href:
    l=link.find_all('a')
    for l2 in l:
        title=l2.get_text()
        a=l2['href']
        url_all=urllib.parse.urljoin('http://www.shixiseng.com/',a)
        html=requests.get(url_all)
        soup2=BeautifulSoup(html.text,'lxml')
        data=soup2.find_all('div',class_='job_detail')
        for datas in data:
            data1=datas.find_all('p')
            for data2 in data1:
                print(data2.get_text())