网络爬虫

# coding=utf-8
import urllib
import time
url = [''] * 350
page = 1

while page <= 7:
    con = urllib.urlopen('http://blog.sina.com.cn/s/articlelist_1191258123_0_'+ str(page)+ '.html').read()
    
    i = 0

    title = con.find(r'<a title=')


    href = con.find(r'href=',title)


    html = con.find(r'.html',href)


    while i < 60 and title != -1 and href != -1 and html != -1:

        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 "failed"
    page = page + 1

    '''j = 0

    while j < 60:

        content = urllib.urlopen(url[j]).read()
        open(r'hanhan/' + url[j][-26:],'w+').write(content)
        print 'downloading',url[j]
        j = j + 1
        time.sleep(15)
    else:
        print 'failed to download'
    '''