Python 爬虫基础

#!/usr/bin/env python
# -*- coding: utf-8 -*-

#引入基础网络库
import urllib2
#引入正则表达式模块
import re

#模拟User-Agent
headers = {‘User-Agent‘:‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11‘}
req = urllib2.Request("http://www.cnblogs.com/pengzhong", headers=headers)
html = urllib2.urlopen(req).read()

#findall方法，注意区分大小写，全是小写
menus = re.findall(r‘<a class="menu".*</a>‘,html)

f=open(‘menu.txt‘,‘w‘)

#输出匹配到的字符串
for menu in menus:
	f.write(menu)

f.close