python 网络编程学习 http/cookie

学习下http的基本用法

客户端主要用到httplib模块，使用客户端访问编写的服务端。

先看客户端代码

class HTTPClient(object):                                                        
                                                                                 
    def __init__(self, host):                                                    
        self.host = host                                                         
                                                                                 
    def fetch(self, path):                                                       
        http = httplib.HTTP(self.host)                                           
                                                                                 
        # Prepare header                                                         
        http.putrequest("GET", path)                                             
        http.putheader("User-Agent", __file__)                                   
        http.putheader("Host", self.host)                                        
        http.putheader("Accept", "*/*")                                          
        http.endheaders()                                                        
                                                                                 
        try:                                                                     
            errcode, errmsg, headers = http.getreply()                           
        except Exception, e:                                                     
            print "Client failed error code: %s message: %s headers: %s" % (errcode, errmsg, headers)
        else:                                                                    
            print "Got homepage from %s" % self.host                             
                                                                                 
        file = http.getfile()                                                    
        return file.read()                                                       
                                                                                 
                                                                                                                                                                                   
if __name__ == "__main__":                                                          
    client = HTTPClient("192.168.199.110:9999")                                     
    print client.fetch("")

服务端

                                                                                    
                                                                                    
class RequestHandler(BaseHTTPRequestHandler):                                       
                                                                                    
    def do_GET(self):                                                               
        self.send_response(200)                                                     
        self.send_header("Content-type", 'text/html')                               
        self.end_headers()                                                          
                                                                                    
        # Send message to browser                                                   
        self.wfile.write("Hello from server!")                                      
        return                                                                      
                                                                                    
                                                                                    
class CustomHTTPServer(HTTPServer):                                                 
                                                                                    
    def __init__(self, host, port):                                                 
        server_address = (host, port)                                               
        HTTPServer.__init__(self, server_address, RequestHandler)                   
                                                                                    
                                                                                    
def run_server(port):                                                               
    try:                                                                            
        server = CustomHTTPServer('192.168.199.110', port)                          
        print "Custom HTTP server started on port: %s" % port                       
        server.serve_forever()                                                      
    except Exception, e:                                                            
        print "Error: %s" % e                                                     
    except KeyboardInterrupt:                                                       
        print "Server interrupted and is shutting down..."                          
        server.socket.close()                                                       
                                                                                    
                                                                                    
if __name__ == '__main__':                                                          
    run_server(9999)                                                                                                                                                               

启动服务端，开启客户端去访问，能得到服务端返回的信息。基本套路就完了，下面看下cookie的获取，这里获取一下自己csdn的cookie

import cookielib                                                                                                                                                                   
import urllib                                                                       
import urllib2                                                                      
                                                                                    
ID_USERNAME = 'id_username'                                                         
ID_PASSWORD = 'id_password'                                                         
USERNAME = 'hexiaodouaipiqiu'                                                      
PASSWORD = '*******'                                                                
LOGIN_URL = 'https://passport.csdn.net/account/login?from=http://my.csdn.net/my/mycsdn'
NORMAL_URL = 'http://www.csdn.net/'                                                 
                                                                                    
                                                                                    
def extract_cookie_info():                                                          
    "Fake login to a site with cookie"                                              
    cj = cookielib.CookieJar()                                                      
    login_data = urllib.urlencode({ID_USERNAME: USERNAME, ID_PASSWORD: PASSWORD})
                                                                                    
    # create url opener                                                             
    opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))                  
    resp = opener.open(LOGIN_URL, login_data)                                       
                                                                                    
    # Send login info                                                               
    for cookie in cj:                                                               
        print "----First time cookie: %s --> %s" % (cookie.name, cookie.value)   
                                                                                    
    print "Headers: %s" % resp.headers                                              
                                                                                    
    # now access without any login info                                             
    resp = opener.open(NORMAL_URL)                                                  
    for cookie in cj:                                                               
        print "++++Second time cookie: %s --> %s" % (cookie.name, cookie.value)  
                                                                                    
    print "Headers: %s" %resp.headers                                               
                                                                                    
                                                                                    
if __name__ == '__main__':                                                          
    extract_cookie_info() 

纪录下登陆的表单需要哪些信息，csdn只需要账户及密码。然后用cookielib模块创建了一个cookie容器cj。登陆数据使用了urllib.urlencode方法编码。

urllib2模块中有个build_opener方法，其中的参数是一个HTTPCookieProcessor类实例。我们需要把之前创建的cookie容器传给这个类的构造方法。urllib2.build_opener方法返回值是一个URL打开方法。需要调用这个方法两次：第一次登陆页面，第二次访问网站首页。