小爬虫，学习学习正则运用

import re
import urllib
import os

def getHtml(url):
    page_html = urllib.urlopen(url).read()
    return page_html

def getImg(page_html,imgdir):
    reg = r'src="(.*?\.jpg)" width'
    imgre = re.compile(reg)
    imglist = re.findall(imgre,page_html)
    x = 0
    for i in imglist:
        imgfile = os.path.join(os.path.abspath("%s%s.jpg")%(imgdir,x))
        urllib.urlretrieve(i,imgfile)
        x = x+1

if __name__ == '__main__':
    page_html = getHtml("")
    getImg(page_html,"img/")