获取网络内容

leogeng1

1.获取网页的长度
HOST = 'www.sina.com'
#!/usr/bin/env python
import socket

HOST = 'www.baidu.com'
PORT = 80
BUFSIZE = 1024
ADDR = (socket.gethostbyname(HOST),PORT)

count = 0

header = "GET /" + " HTTP/1.1\r\n" +          "Accept-Language: zh-cn\r\n"  +          "Host: " + HOST + "\r\n" +
         "Connection: Keep-Alive\r\n\r\n"

def getLength():
#First :  
        sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
#Second:
        sock.connect(ADDR)
#Third :
        sock.send('%s\r\n' % header)
#Fourth:
        while(sock.recv(BUFSIZE) > 0):
                count = count + sock.recv(BUFSIZE)
#Fifth:
        sock.close()

        print count


2、获取网页的内容
使用httplib访问某个url然后获取返回的内容：
import httplib
conn=httplib.HTTPConnection("
www.baidu.com
")
conn.request("GET", "/")
r=conn.getresponse()
print r.read() #获取所有内容


本文来自ChinaUnix博客，如果查看原文请点：http://blog.chinaunix.net/u3/101492/showart_2036380.html