#coding=utf-8       #新浪博客

import urllib

import re

import os

url=['']*1500 #每一骗博客的地址

title=['']*1500  #每一篇博客的标题

page=1  #博客分页

count=1  #文章计数

while page<=9:

	con=urllib.urlopen('http://blog.sina.com.cn/s/articlelist_1193491727_0_'+str(page)+'.html').read()

	i=0

	hrefstart=con.find(r'href="http://blog.sina.com.cn/s/blog_')

	print hrefstart

	hrefend=con.find(r'.html',hrefstart)

	print hrefend

	titlestart=con.find(r'>',hrefend)

	print titlestart

	titleend=con.find(r'</a>',titlestart)

	print titleend

	while i<=50 and titleend!=-1 and hrefend!=-1:

		url[i]=con[hrefstart+6:hrefend+5]

		title[i]=con[titlestart:titleend]

		print page,i,count, title[i]

		print url[i]

		hrefstart=con.find(r'href="http://blog.sina.com.cn/s/blog_',titleend)

		hrefend=con.find(r'.html',hrefstart)

		titlestart=con.find(r'>',hrefend)

		titleend=con.find(r'</a>',titlestart)

		content=urllib.urlopen(url[i]).read()

		filename=url[i][-26:]

		print filename

		if not os.path.isdir("1"):

		   os.mkdir("1")

		target=open('1/'+filename,'w')

		target.write(content)

		i=i+1

		count=count+1

	else:

		print page,'本页查找到结尾了'

	page=page+1

else:

	print'本次任务结束了'