#coding:utf-8
import urllib
import time
import os
page=1
while page<=7:
url=['']*50 #每页有50篇文章
temp='http://blog.sina.com.cn/s/articlelist_1191258123_0_'+str(page)+'.html'
con =urllib.urlopen(temp).read() #读取数据
i=0
title=con.find(r'<a title=')
href=con.find(r'href=',title)
html = con.find(r'.html',href)
while title!=-1 and href!=-1 and html!=-1 and i<50:
url[i]=con[href+6:html+5]
print url[i]
title=con.find(r'<a title=',html)
href=con.find(r'href=',title)
html = con.find(r'.html',href)
i=i+1
else:
print 'end page=',page
j=0
'''写入本地文件'''
while(j<i):
content=urllib.urlopen(url[j]).read()
path = 'hanhan/'+str(page)+"/"
if os.path.isdir(path):
open(path+url[j][-26:],'w+').write(content)
else:
os.makedirs(path)
open(path+url[j][-26:],'w+').write(content)
j=j+1
time.sleep(1)
else:
print 'download'
page=page+1
else:
print 'all find end'
python 批量爬取博客数据(仅供学习)
最新推荐文章于 2023-12-04 11:29:44 发布