Python网络爬虫实例

视频地址：

http://edu.51cto.com/lesson/id-12393.html

 

下载博客文章实例

源码：

import urllib
import time

#下载博客所有文章
i = 0
url = ['']*50
con = urllib.urlopen('http://blog.sina.com.cn/s/articlelist_3973495073_0_1.html').read()
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 'find end!'

j = 0
while j < 50:
    content = urllib.urlopen(url[j]).read()
    open(r'hanhan/'+url[j][-26:],'w+').write(content)
    print 'downloading', url[j]
    j = j + 1
    time.sleep(1)
else:
    print 'download articles finished!'