Python 简单业务爬虫
如何快速下载贴吧图片呢?
#!/usr/bin/python
# -*- coding: UTF-8 -*-
import urllib
import re
def gethtml(url):
page = urllib.urlopen(url)
html = page.read()
return html
def getImg(html):
reg = r'src="(.+?\.jpg)" pic_ext'
imgre = re.compile(reg)
imglist = re.findall(imgre,html)
x = 0
for imgurl in imglist:
urllib.urlretrieve(imgurl,'%s.jpg' % x)
x+=1
html = getHtml("Http://tieba.baidu.com/p/2460150866")
print getImg(html)
相关文章