import urllib
import time
url = ['']*50
i=0
page = urllib.urlopen('http://blog.sina.com.cn/s/articlelist_1191258123_0_1.html').read()
title = page.find(r'<a title=')
href = page.find(r'href=',title)
html = page.find(r'.html',href)
while title!=-1 and href!=-1 and html!=-1 and i < 50:
url[i]= page[href +6:html+5]
print url[i]
title = page.find(r'<a title=',html)
href = page.find(r'href=',title)
html = page.find(r'.html',href)
i+=1
else:
print('Find end!')
j=0
while j<50:
cotent = urllib.urlopen(url[j]).read()
open(r'hanhan/'+url[j][-26:],'w+').write(cotent)
time.sleep(15)
j=j+1
else:
print('Download all!')
学习爬虫后写了篇爬韩寒新浪博客文章的代码
最新推荐文章于 2024-09-12 16:10:04 发布