#-*-coding:utf-8 -*-
import urllib2
import sys
import re
reload(sys)
sys.setdefaultencoding('utf-8')
url='http://www.qiushibaike.com/hot/page/1/'
header={'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64)'}
try:
page=1
while True:
rawurl='http://www.qiushibaike.com/hot/page/'
url=rawurl+str(page)
request=urllib2.Request(url,headers=header)
response=urllib2.urlopen(request)
content=response.read().decode('utf-8')
pattern=re.compile('<div class="article block untagged.*?<div.*?clearfix">.*?<span>(.*?)</span>',re.S)
items=re.findall(pattern,content)
text=re.compile('<br/>')
for item in items:
print re.sub(text,'\n',item)
print
q=raw_input()
if q == 'q':break
page=page+1
except urllib2.URLError,e:
if hasattr(e,'code'):
print e.code
if hasattr(e,'reason'):
print e.reason实现的功能比较简单，按回车键会爬下一页的段子，输入q退出
