#!/usr/bin/env python
#encoding=utf-8
import socket,codecs
s=socket.socket(socket.AF_INET,socket.SOCK_STREAM)
hostname="www.baidu.com"
addr=socket.gethostbyname(hostname)
print addr
s.connect((addr,80))
html="""GET / HTTP/1.0\r\n"""
html="""HEAD / HTTP/1.0\r\n"""
html+="""Host: www.baidu.com\r\n"""
html+="""User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:17.0) Gecko/20100101 Firefox/17.0\r\n"""
html+="""Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8\r\n"""
html+="""Accept-Language: zh-cn,zh;q=0.8,en-us;q=0.5,en;q=0.3\r\n"""
html+="""Cookie: BAIDUID=4782C3288E4A1689E0F8CBC0DF82BB1D:FG=1; BDUT=sc2x4782C3288E4A1689E0F8CBC0DF82BB1D13bda69e4000; H_PS_PSSID=1428_1667_1662\r\n"""
html+="""Cache-Control: max-age=0\r\n"""
html+="""\r\n"""
f=None
s.sendall(html)
first=True
count=0
while True:
count+=1
print "aaaa"
msg = s.recv(40960)
#print msg
if not len(msg):
if f!=None:
f.flush()
f.close()
break
if first:
first=False
headpos=msg.index("\r\n\r\n")
print msg[:headpos]
print type(msg)
ff=codecs.open("./%s.txt"%count,"w","utf-8")
ff.write(msg.decode("gbk","ignore"))
ff.close()
exit(0)
import urllib2
print urllib2.urlopen("http://www.baidu.com").read()
