爬虫学习之下载韩寒博客

#coding:utf-8
import urllib
import time
url = [‘‘]*350
page = 1
link = 1
while page <= 7:
    con = urllib.urlopen(‘http://blog.sina.com.cn/s/articlelist_1191258123_0_‘+ str(page) +‘.html‘).read()
    title = con.find(r‘<a title‘)
    href = con.find(r‘href=‘,title)
    html = con.find(r‘.html‘,href)
    i = 0
    while title != -1 and href != -1 and html != -1 and i < 80:
        url[i] = con[href + 6:html +5]
        print link,‘   ‘,url[i]
        i = i + 1
        title = con.find(r‘<a title‘,html)
        href = con.find(r‘href=‘,title) 
        html = con.find(r‘.html‘,href)
        link = link + 1
    
    else:
        print page,‘find end!‘
    page = page + 1
j = 0
while j < 350:
    content = urllib.urlopen(url[j]).read()
    open(r‘blog/‘+url[j][-26:],‘w+‘).write(content)
    j = j + 1
    time.sleep(1)
else:
    print ‘download article finished!‘