python 爬虫

     python 爬虫

import re
import urllib


def getHtml(url) :
    page = urllib.urlopen(url);
    html = page.read();
    return html
def getImg(html) :
    reg = r'id="p-ad" .*'
    imgre = re.compile(reg)
    imglist = re.findall(imgre,html)
    return imglist


print "begin ..."
html = getHtml("http:// ")


#html = getHtml(" style="color:#0000CC;">)
print getImg(html)