python抓取网页内容示例分享

代码如下:

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()