一个简单的爬虫

import re
# socket--->
import urllib

import time

url = 'https://tieba.baidu.com/p/5631230268'


def getHtml(url):
    # urllib.urlopen打开指定的网络链接；
    page = urllib.urlopen(url)
    # read()查看网页的内容;
    html = page.read()
    return html
def getImg(html):
    reg = r'src="(.+?\.jpg)"'
    imglist = re.findall(reg, html)
    for index,imgurl in enumerate(imglist):
        print "[%s]: Download %s ......." %(time.ctime(), imgurl)
        # urlretrieve下载指定的图片文件到本地；
        urllib.urlretrieve(imgurl, '/home/kiosk/Music/picture%.3d.jpg' %(index+1))
        if index == 5:
            print "下载结束......"
            break
html =  getHtml(url)
getImg(html)