python之小爬虫

#!/usr/bin/python
#抓取网页上的图片保存
import urllib
import urllib.request                                 //python3版本将urllib2分成urllib.request和urllib.error
import re

def gethtml(url):
    page = urllib.request.urlopen(url)
    html = page.read()
    return html

def getImages(html):
    reg = r‘src="(.*?\.jpg)"‘
    imgre = re.compile(reg)
    imglist = re.findall(imgre,html.decode(‘utf-8‘))
    x = 0
    for i in imglist:
        urllib.request.urlretrieve(i,r‘E:\python_practice\%s.jpg‘%(x))
        x = x + 1

html=gethtml("http://www.u148.net/article/35256.html")
getImages(html)