利用python 实现简单 爬虫

# coding:utf-8
import re
import requests
# 获取网页内容

import pickle

r = requests.get('http://www.163.com')
data = r.text

serialInfo = '';

# 利用正则查找所有连接
link_list =re.findall(r"(?<=content=\").+?(?=\")|(?<=content=\').+?(?=\')" ,data)
for url in link_list:
    serialInfo += url+'----';
    print url

f=open('demo.txt','wb',0)


pickle.dump(serialInfo,f)

obj2 = pickle.load(open("demo.txt", "r"))


print '-------->'
print obj2

f.close()