练习3

简单小爬虫

#!/usr/bin/env python

#coding:utf-8

import urllib2

import bs4

url = 'http://www.163.com'

content = urllib2.urlopen(url).read()

content =  content.decode('gbk')

soup = bs4.BeautifulSoup(content)

links = soup.select('li a[href]')

result = []

for link in links:

    href = link.attrs['href']

    title = link.text

    if '.html' in href and '163.com' in href and len(title) >3:

        result.append(link)

for link in result:

    print link.attrs['href'], link.text

print '共有新闻[%s]条',   len(result)