python抓取网页中图片与网页内容

#coding:utf8
import re
import urllib
def getHTML(url):
    page = urllib.urlopen(url)
    html = page.read()
    return html
def getImg(html,imgType):
    reg = r'src="(.*?.+'+imgType+'!slider)" '
    imgre = re.compile(reg)
    imgList = re.findall(imgre, html)
    x=0
    for imgurl in imgList:
        print imgurl
        urllib.urlretrieve(imgurl, '%s.%s' % (x, imgType))
        x =x+1

html= getHTML("http://www.jb200.com")
getImg(html,'jpg')

import socket
def open_tcp_socket(remotehost,servicename):
    s=socket.socket(socket.AF_INET,socket.SOCK_STREAM)
    portnumber=socket.getservbyname(servicename,'tcp')
    s.connect((remotehost,portnumber))
    return s
mysocket=open_tcp_socket('www.taobao.com','http')
mysocket.send('hello')
while(1):
    data=mysocket.recv(1024)
    if(data):
        print data.decode('gbk').encode('utf-8')#对于gbk编码网页必须这样转化一下
    else:
        break
mysocket.close()