爬取http://www.hack-cn.com

#coding=utf-8
import urllib2
import re

def getHtml(url):
user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
headers = { 'User-Agent' : user_agent }
req = urllib2.Request(url,headers=headers)
resp=urllib2.urlopen(req)
html = resp.read()
pattern=re.compile('style="word-break:break-all">(.*?)</td>',re.S)
items=re.findall(pattern,html)
for item in items:
print item
return html
for i in range(1,101):
html = getHtml("http://www.hack-cn.com/?page=%s" %i)