网络爬虫代码

import urllib
import time
import sys
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()
    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[link] = con[href + 6:html + 4]
        #print link, ' : ', url[i]
        title = con.find(r'<a title=',html)
        href = con.find(r'href=',title)
        html = con.find(r'html',href)
        i = i + 1
        link = link + 1
    else:
        print 'page', page, ' find end!'
    page = page + 1
else:
    print 'all page finished!'


j = 0
while j < link:
    if url[j].strip() != '':
        filename = 'hanhan/'+url[j][-26:]
        print j,' downloading ', url[j]
        try:
            content = urllib.urlopen(url[j]).read()
            open(filename, 'w+').write(content)
        except:
            print 'exception:',sys.exc_info()
    else:
        print j,'empty url!'
    #except:
     #   print 'exception: ', sys.exc_info()[0]
    j = j + 1
    time.sleep(1)
else:
    print 'download article finished'