• 导步/数据库/队列---来源www.cnblogs.com/alex3714 金角大王

    1. Gevent协程
    2. SelectPollEpoll异步IO与事件驱动
    3. Python连接Mysql数据库操作
    4. RabbitMQ队列
    5. RedisMemcached缓存
    6. Paramiko SSH
    7. Twsited网络框架

     协程

    协程，又称微线程，纤程。英文名Coroutine。一句话说明什么是线程：协程是一种用户态的轻量级线程。

    协程拥有自己的寄存器上下文和栈。协程调度切换时，将寄存器上下文和栈保存到其他地方，在切回来的时候，恢复先前保存的寄存器上下文和栈。因此：

    协程能保留上一次调用时的状态（即所有局部状态的一个特定组合），每次过程重入时，就相当于进入上一次调用的状态，换种说法：进入上一次离开时所处逻辑流的位置。

    协程的好处：

    • 无需线程上下文切换的开销
    • 无需原子操作锁定及同步的开销
    • 方便切换控制流，简化编程模型
    • 高并发+高扩展性+低成本：一个CPU支持上万的协程都不是问题。所以很适合用于高并发处理。

    缺点：

    • 无法利用多核资源：协程的本质是个单线程,它不能同时将 单个CPU 的多个核用上,协程需要和进程配合才能运行在多CPU上.当然我们日常所编写的绝大部分应用都没有这个必要，除非是cpu密集型应用。
    • 进行阻塞（Blocking）操作（如IO时）会阻塞掉整个程序

    使用yield实现协程操作例子　　　　

    ?
    1
    2
    3
    4
    5
    6
    7
    8
    9
    10
    11
    12
    13
    14
    15
    16
    17
    18
    19
    20
    21
    22
    23
    24
    25
    import time
    import queue
    def consumer(name):
        print("--->starting eating baozi...")
        while True:
            new_baozi = yield
            print("[%s] is eating baozi %s" % (name,new_baozi))
            #time.sleep(1)
     
    def producer():
     
        r = con.__next__()
        r = con2.__next__()
        n = 0
        while n < 5:
            n +=1
            con.send(n)
            con2.send(n)
            print("33[32;1m[producer]33[0m is making baozi %s" %n )
     
     
    if __name__ == '__main__':
        con = consumer("c1")
        con2 = consumer("c2")
        p = producer()

    Greenlet

    ?
    1
    2
    3
    4
    5
    6
    7
    8
    9
    10
    11
    12
    13
    14
    15
    16
    17
    18
    19
    20
    21
    22
    #!/usr/bin/env python
    # -*- coding:utf-8 -*-
      
      
    from greenlet import greenlet
      
      
    def test1():
        print 12
        gr2.switch()
        print 34
        gr2.switch()
      
      
    def test2():
        print 56
        gr1.switch()
        print 78
      
    gr1 = greenlet(test1)
    gr2 = greenlet(test2)
    gr1.switch()

    　　

    Gevent 

    Gevent 是一个第三方库，可以轻松通过gevent实现并发同步或异步编程，在gevent中用到的主要模式是Greenlet, 它是以C扩展模块形式接入Python的轻量级协程。 Greenlet全部运行在主程序操作系统进程的内部，但它们被协作式地调度。

    ?
    1
    2
    3
    4
    5
    6
    7
    8
    9
    10
    11
    12
    13
    14
    15
    16
    import gevent
     
    def foo():
        print('Running in foo')
        gevent.sleep(0)
        print('Explicit context switch to foo again')
     
    def bar():
        print('Explicit context to bar')
        gevent.sleep(0)
        print('Implicit context switch back to bar')
     
    gevent.joinall([
        gevent.spawn(foo),
        gevent.spawn(bar),
    ])

    输出：

    Running in foo
Explicit context to bar
Explicit context switch to foo again
Implicit context switch back to bar

    同步与异步的性能区别 

    上面程序的重要部分是将task函数封装到Greenlet内部线程的gevent.spawn。 初始化的greenlet列表存放在数组threads中，此数组被传给gevent.joinall 函数，后者阻塞当前流程，并执行所有给定的greenlet。执行流程只会在 所有greenlet执行完后才会继续向下走。　　

    遇到IO阻塞时会自动切换任务

    通过gevent实现单线程下的多socket并发

    server side 

    client side 　　

    　　

    论事件驱动与异步IO

    事件驱动编程是一种编程范式，这里程序的执行流由外部事件来决定。它的特点是包含一个事件循环，当外部事件发生时使用回调机制来触发相应的处理。另外两种常见的编程范式是（单线程）同步以及多线程编程。

    让我们用例子来比较和对比一下单线程、多线程以及事件驱动编程模型。下图展示了随着时间的推移，这三种模式下程序所做的工作。这个程序有3个任务需要完成，每个任务都在等待I/O操作时阻塞自身。阻塞在I/O操作上所花费的时间已经用灰色框标示出来了。

     

    在单线程同步模型中，任务按照顺序执行。如果某个任务因为I/O而阻塞，其他所有的任务都必须等待，直到它完成之后它们才能依次执行。这种明确的执行顺序和串行化处理的行为是很容易推断得出的。如果任务之间并没有互相依赖的关系，但仍然需要互相等待的话这就使得程序不必要的降低了运行速度。

    在多线程版本中，这3个任务分别在独立的线程中执行。这些线程由操作系统来管理，在多处理器系统上可以并行处理，或者在单处理器系统上交错执行。这使得当某个线程阻塞在某个资源的同时其他线程得以继续执行。与完成类似功能的同步程序相比，这种方式更有效率，但程序员必须写代码来保护共享资源，防止其被多个线程同时访问。多线程程序更加难以推断，因为这类程序不得不通过线程同步机制如锁、可重入函数、线程局部存储或者其他机制来处理线程安全问题，如果实现不当就会导致出现微妙且令人痛不欲生的bug。

    在事件驱动版本的程序中，3个任务交错执行，但仍然在一个单独的线程控制中。当处理I/O或者其他昂贵的操作时，注册一个回调到事件循环中，然后当I/O操作完成时继续执行。回调描述了该如何处理某个事件。事件循环轮询所有的事件，当事件到来时将它们分配给等待处理事件的回调函数。这种方式让程序尽可能的得以执行而不需要用到额外的线程。事件驱动型程序比多线程程序更容易推断出行为，因为程序员不需要关心线程安全问题。

    当我们面对如下的环境时，事件驱动模型通常是一个好的选择：

    1. 程序中有许多任务，而且…
    2. 任务之间高度独立（因此它们不需要互相通信，或者等待彼此）而且…
    3. 在等待事件到来时，某些任务会阻塞。

    当应用程序需要在任务间共享可变的数据时，这也是一个不错的选择，因为这里不需要采用同步处理。

    网络应用程序通常都有上述这些特点，这使得它们能够很好的契合事件驱动编程模型。

    SelectPollEpoll异步IO　

    http://www.cnblogs.com/alex3714/p/4372426.html　

    selectors模块

    This module allows high-level and efficient I/O multiplexing, built upon the select module primitives. Users are encouraged to use this module instead, unless they want precise control over the OS-level primitives used.

    ?
    1
    2
    3
    4
    5
    6
    7
    8
    9
    10
    11
    12
    13
    14
    15
    16
    17
    18
    19
    20
    21
    22
    23
    24
    25
    26
    27
    28
    29
    30
    31
    32
    import selectors
    import socket
     
    sel = selectors.DefaultSelector()
     
    def accept(sock, mask):
        conn, addr = sock.accept()  # Should be ready
        print('accepted', conn, 'from', addr)
        conn.setblocking(False)
        sel.register(conn, selectors.EVENT_READ, read)
     
    def read(conn, mask):
        data = conn.recv(1000)  # Should be ready
        if data:
            print('echoing', repr(data), 'to', conn)
            conn.send(data)  # Hope it won't block
        else:
            print('closing', conn)
            sel.unregister(conn)
            conn.close()
     
    sock = socket.socket()
    sock.bind(('localhost', 10000))
    sock.listen(100)
    sock.setblocking(False)
    sel.register(sock, selectors.EVENT_READ, accept)
     
    while True:
        events = sel.select()
        for key, mask in events:
            callback = key.data
            callback(key.fileobj, mask)

    　　

    数据库操作与Paramiko模块 

    http://www.cnblogs.com/wupeiqi/articles/5095821.html 

    RabbitMQ队列　　

    安装 http://www.rabbitmq.com/install-standalone-mac.html

    安装python rabbitMQ module 

    ?
    1
    2
    3
    4
    5
    6
    7
    pip install pika
    or
    easy_install pika
    or
    源码
      
    https://pypi.python.org/pypi/pika

    实现最简单的队列通信

    send端

    ?
    1
    2
    3
    4
    5
    6
    7
    8
    9
    10
    11
    12
    13
    14
    15
    16
    #!/usr/bin/env python
    import pika
     
    connection = pika.BlockingConnection(pika.ConnectionParameters(
                   'localhost'))
    channel = connection.channel()
     
    #声明queue
    channel.queue_declare(queue='hello')
     
    #n RabbitMQ a message can never be sent directly to the queue, it always needs to go through an exchange.
    channel.basic_publish(exchange='',
                          routing_key='hello',
                          body='Hello World!')
    print(" [x] Sent 'Hello World!'")
    connection.close()

    receive端

    ?
    1
    2
    3
    4
    5
    6
    7
    8
    9
    10
    11
    12
    13
    14
    15
    16
    17
    18
    19
    20
    21
    22
    23
    24
    #_*_coding:utf-8_*_
    __author__ = 'Alex Li'
    import pika
     
    connection = pika.BlockingConnection(pika.ConnectionParameters(
                   'localhost'))
    channel = connection.channel()
     
     
    #You may ask why we declare the queue again ‒ we have already declared it in our previous code.
    # We could avoid that if we were sure that the queue already exists. For example if send.py program
    #was run before. But we're not yet sure which program to run first. In such cases it's a good
    # practice to repeat declaring the queue in both programs.
    channel.queue_declare(queue='hello')
     
    def callback(ch, method, properties, body):
        print(" [x] Received %r" % body)
     
    channel.basic_consume(callback,
                          queue='hello',
                          no_ack=True)
     
    print(' [*] Waiting for messages. To exit press CTRL+C')
    channel.start_consuming()

    　　

    Work Queues

    在这种模式下，RabbitMQ会默认把p发的消息依次分发给各个消费者(c),跟负载均衡差不多

    消息提供者代码

    消费者代码

    此时，先启动消息生产者，然后再分别启动3个消费者，通过生产者多发送几条消息，你会发现，这几条消息会被依次分配到各个消费者身上　　

    Doing a task can take a few seconds. You may wonder what happens if one of the consumers starts a long task and dies with it only partly done. With our current code once RabbitMQ delivers message to the customer it immediately removes it from memory. In this case, if you kill a worker we will lose the message it was just processing. We'll also lose all the messages that were dispatched to this particular worker but were not yet handled.

    But we don't want to lose any tasks. If a worker dies, we'd like the task to be delivered to another worker.

    In order to make sure a message is never lost, RabbitMQ supports message acknowledgments. An ack(nowledgement) is sent back from the consumer to tell RabbitMQ that a particular message had been received, processed and that RabbitMQ is free to delete it.

    If a consumer dies (its channel is closed, connection is closed, or TCP connection is lost) without sending an ack, RabbitMQ will understand that a message wasn't processed fully and will re-queue it. If there are other consumers online at the same time, it will then quickly redeliver it to another consumer. That way you can be sure that no message is lost, even if the workers occasionally die.

    There aren't any message timeouts; RabbitMQ will redeliver the message when the consumer dies. It's fine even if processing a message takes a very, very long time.

    Message acknowledgments are turned on by default. In previous examples we explicitly turned them off via the no_ack=True flag. It's time to remove this flag and send a proper acknowledgment from the worker, once we're done with a task.

    ?
    1
    2
    3
    4
    5
    6
    7
    8
    def callback(ch, method, properties, body):
        print " [x] Received %r" % (body,)
        time.sleep( body.count('.') )
        print " [x] Done"
        ch.basic_ack(delivery_tag = method.delivery_tag)
     
    channel.basic_consume(callback,
                          queue='hello')

    　　Using this code we can be sure that even if you kill a worker using CTRL+C while it was processing a message, nothing will be lost. Soon after the worker dies all unacknowledged messages will be redelivered

    　　　　

    消息持久化　　

    We have learned how to make sure that even if the consumer dies, the task isn't lost(by default, if wanna disable  use no_ack=True). But our tasks will still be lost if RabbitMQ server stops.

    When RabbitMQ quits or crashes it will forget the queues and messages unless you tell it not to. Two things are required to make sure that messages aren't lost: we need to mark both the queue and messages as durable.

    First, we need to make sure that RabbitMQ will never lose our queue. In order to do so, we need to declare it as durable:

    ?
    1
    channel.queue_declare(queue='hello', durable=True)

    　　

    Although this command is correct by itself, it won't work in our setup. That's because we've already defined a queue called hello which is not durable. RabbitMQ doesn't allow you to redefine an existing queue with different parameters and will return an error to any program that tries to do that. But there is a quick workaround - let's declare a queue with different name, for exampletask_queue:

    ?
    1
    channel.queue_declare(queue='task_queue', durable=True)

    　　

    This queue_declare change needs to be applied to both the producer and consumer code.

    At that point we're sure that the task_queue queue won't be lost even if RabbitMQ restarts. Now we need to mark our messages as persistent - by supplying a delivery_mode property with a value 2.

    ?
    1
    2
    3
    4
    5
    6
    channel.basic_publish(exchange='',
                          routing_key="task_queue",
                          body=message,
                          properties=pika.BasicProperties(
                             delivery_mode = 2, # make message persistent
                          ))

    消息公平分发

    如果Rabbit只管按顺序把消息发到各个消费者身上，不考虑消费者负载的话，很可能出现，一个机器配置不高的消费者那里堆积了很多消息处理不完，同时配置高的消费者却一直很轻松。为解决此问题，可以在各个消费者端，配置perfetch=1,意思就是告诉RabbitMQ在我这个消费者当前消息还没处理完的时候就不要再给我发新消息了。

    ?
    1
    channel.basic_qos(prefetch_count=1)

    带消息持久化+公平分发的完整代码

    生产者端

    消费者端

    　　

    PublishSubscribe(消息发布订阅)　

    之前的例子都基本都是1对1的消息发送和接收，即消息只能发送到指定的queue里，但有些时候你想让你的消息被所有的Queue收到，类似广播的效果，这时候就要用到exchange了，

    An exchange is a very simple thing. On one side it receives messages from producers and the other side it pushes them to queues. The exchange must know exactly what to do with a message it receives. Should it be appended to a particular queue? Should it be appended to many queues? Or should it get discarded. The rules for that are defined by the exchange type.

    Exchange在定义的时候是有类型的，以决定到底是哪些Queue符合条件，可以接收消息

    fanout: 所有bind到此exchange的queue都可以接收消息 direct: 通过routingKey和exchange决定的那个唯一的queue可以接收消息 topic:所有符合routingKey(此时可以是一个表达式)的routingKey所bind的queue可以接收消息
    　　 表达式符号说明：#代表一个或多个字符，*代表任何字符       例：#.a会匹配a.a，aa.a，aaa.a等           *.a会匹配a.a，b.a，c.a等      注：使用RoutingKey为#，Exchange Type为topic的时候相当于使用fanout　

    headers: 通过headers 来决定把消息发给哪些queue

    消息publisher

    消息subscriber

    　　

    有选择的接收消息(exchange type=direct)　

    RabbitMQ还支持根据关键字发送，即：队列绑定关键字，发送者将数据根据关键字发送到消息exchange，exchange根据 关键字 判定应该将数据发送至指定队列。

    publisher

    subscriber　

    　　

    更细致的消息过滤

    Although using the direct exchange improved our system, it still has limitations - it can't do routing based on multiple criteria.

    In our logging system we might want to subscribe to not only logs based on severity, but also based on the source which emitted the log. You might know this concept from the syslog unix tool, which routes logs based on both severity (info/warn/crit...) and facility (auth/cron/kern...).

    That would give us a lot of flexibility - we may want to listen to just critical errors coming from 'cron' but also all logs from 'kern'.

    publisher

    subscriber

    To receive all the logs run:

    python receive_logs_topic.py "#"

    To receive all logs from the facility "kern":

    python receive_logs_topic.py "kern.*"

    Or if you want to hear only about "critical" logs:

    python receive_logs_topic.py "*.critical"

    You can create multiple bindings:

    python receive_logs_topic.py "kern.*" "*.critical"

    And to emit a log with a routing key "kern.critical" type:

    python emit_log_topic.py "kern.critical" "A critical kernel error"

    　　

    Remote procedure call (RPC)

    To illustrate how an RPC service could be used we're going to create a simple client class. It's going to expose a method named call which sends an RPC request and blocks until the answer is received:

    ?
    1
    2
    3
    fibonacci_rpc = FibonacciRpcClient()
    result = fibonacci_rpc.call(4)
    print("fib(4) is %r" % result)

    RPC server

    RPC client

    　　

    　　

    Memcached & Redis使用　

    http://www.cnblogs.com/wupeiqi/articles/5132791.html 　

    　　

    　

    Twsited异步网络框架

    Twisted是一个事件驱动的网络框架，其中包含了诸多功能，例如：网络协议、线程、数据库管理、网络操作、电子邮件等。　

    事件驱动

    简而言之，事件驱动分为二个部分：第一，注册事件；第二，触发事件。

    自定义事件驱动框架，命名为：“弑君者”：

    ?
    1
    2
    3
    4
    5
    6
    7
    8
    9
    10
    11
    12
    13
    14
    15
    16
    17
    18
    19
    20
    21
    22
    #!/usr/bin/env python
    # -*- coding:utf-8 -*-
     
    # event_drive.py
     
    event_list = []
     
     
    def run():
        for event in event_list:
            obj = event()
            obj.execute()
     
     
    class BaseHandler(object):
        """
        用户必须继承该类，从而规范所有类的方法（类似于接口的功能）
        """
        def execute(self):
            raise Exception('you must overwrite execute')
     
    最牛逼的事件驱动框架

    程序员使用“弑君者框架”：　　

    ?
    1
    2
    3
    4
    5
    6
    7
    8
    9
    10
    11
    12
    13
    14
    #!/usr/bin/env python
    # -*- coding:utf-8 -*-
     
    from source import event_drive
     
     
    class MyHandler(event_drive.BaseHandler):
     
        def execute(self):
            print 'event-drive execute MyHandler'
     
     
    event_drive.event_list.append(MyHandler)
    event_drive.run()

    Protocols

    Protocols描述了如何以异步的方式处理网络中的事件。HTTP、DNS以及IMAP是应用层协议中的例子。Protocols实现了IProtocol接口，它包含如下的方法：

    makeConnection               在transport对象和服务器之间建立一条连接
connectionMade               连接建立起来后调用
dataReceived                 接收数据时调用
connectionLost               关闭连接时调用

    Transports

    Transports代表网络中两个通信结点之间的连接。Transports负责描述连接的细节，比如连接是面向流式的还是面向数据报的，流控以及可靠性。TCP、UDP和Unix套接字可作为transports的例子。它们被设计为“满足最小功能单元，同时具有最大程度的可复用性”，而且从协议实现中分离出来，这让许多协议可以采用相同类型的传输。Transports实现了ITransports接口，它包含如下的方法：

    write                   以非阻塞的方式按顺序依次将数据写到物理连接上
writeSequence           将一个字符串列表写到物理连接上
loseConnection          将所有挂起的数据写入，然后关闭连接
getPeer                 取得连接中对端的地址信息
getHost                 取得连接中本端的地址信息

    将transports从协议中分离出来也使得对这两个层次的测试变得更加简单。可以通过简单地写入一个字符串来模拟传输，用这种方式来检查。

    　　

    EchoServer

    ?
    1
    2
    3
    4
    5
    6
    7
    8
    9
    10
    11
    12
    13
    14
    15
    16
    from twisted.internet import protocol
    from twisted.internet import reactor
     
    class Echo(protocol.Protocol):
        def dataReceived(self, data):
            self.transport.write(data)
     
    def main():
        factory = protocol.ServerFactory()
        factory.protocol = Echo
     
        reactor.listenTCP(1234,factory)
        reactor.run()
     
    if __name__ == '__main__':
        main()

    　　

    EchoClient

    ?
    1
    2
    3
    4
    5
    6
    7
    8
    9
    10
    11
    12
    13
    14
    15
    16
    17
    18
    19
    20
    21
    22
    23
    24
    25
    26
    27
    28
    29
    30
    31
    32
    33
    34
    35
    36
    37
    38
    39
    40
    from twisted.internet import reactor, protocol
     
     
    # a client protocol
     
    class EchoClient(protocol.Protocol):
        """Once connected, send a message, then print the result."""
     
        def connectionMade(self):
            self.transport.write("hello alex!")
     
        def dataReceived(self, data):
            "As soon as any data is received, write it back."
            print "Server said:", data
            self.transport.loseConnection()
     
        def connectionLost(self, reason):
            print "connection lost"
     
    class EchoFactory(protocol.ClientFactory):
        protocol = EchoClient
     
        def clientConnectionFailed(self, connector, reason):
            print "Connection failed - goodbye!"
            reactor.stop()
     
        def clientConnectionLost(self, connector, reason):
            print "Connection lost - goodbye!"
            reactor.stop()
     
     
    # this connects the protocol to a server running on port 8000
    def main():
        f = EchoFactory()
        reactor.connectTCP("localhost", 1234, f)
        reactor.run()
     
    # this only runs if the module was *not* imported
    if __name__ == '__main__':
        main()

    运行服务器端脚本将启动一个TCP服务器，监听端口1234上的连接。服务器采用的是Echo协议，数据经TCP transport对象写出。运行客户端脚本将对服务器发起一个TCP连接，回显服务器端的回应然后终止连接并停止reactor事件循环。这里的Factory用来对连接的双方生成protocol对象实例。两端的通信是异步的，connectTCP负责注册回调函数到reactor事件循环中，当socket上有数据可读时通知回调处理。

    一个传送文件的例子 

    server side 

    client side 　　

    　　

    　　

    Twisted深入

    http://krondo.com/an-introduction-to-asynchronous-programming-and-twisted/ 

    http://blog.csdn.net/hanhuili/article/details/9389433 

    　　

    　　

    SqlAlchemy ORM　　

    SQLAlchemy是Python编程语言下的一款ORM框架，该框架建立在数据库API之上，使用关系对象映射进行数据库操作，简言之便是：将对象转换成SQL，然后使用数据API执行SQL并获取执行结果

    Dialect用于和数据API进行交流，根据配置文件的不同调用不同的数据库API，从而实现对数据库的操作，如：

    ?
    1
    2
    3
    4
    5
    6
    7
    8
    9
    10
    11
    12
    13
    MySQL-Python
        mysql+mysqldb://<user>:<password>@<host>[:<port>]/<dbname>
      
    pymysql
        mysql+pymysql://<username>:<password>@<host>/<dbname>[?<options>]
      
    MySQL-Connector
        mysql+mysqlconnector://<user>:<password>@<host>[:<port>]/<dbname>
      
    cx_Oracle
        oracle+cx_oracle://user:pass@host:port/dbname[?key=value&key=value...]
      
    更多详见：http://docs.sqlalchemy.org/en/latest/dialects/index.html

    　　

    步骤一：

    使用 Engine/ConnectionPooling/Dialect 进行数据库操作，Engine使用ConnectionPooling连接数据库，然后再通过Dialect执行SQL语句。

    ?
    1
    2
    3
    4
    5
    6
    7
    8
    9
    10
    11
    12
    13
    14
    15
    16
    17
    18
    19
    20
    21
    22
    23
    #!/usr/bin/env python
    # -*- coding:utf-8 -*-
      
    from sqlalchemy import create_engine
      
      
    engine = create_engine("mysql+mysqldb://root:123@127.0.0.1:3306/s11", max_overflow=5)
      
    engine.execute(
        "INSERT INTO ts_test (a, b) VALUES ('2', 'v1')"
    )
      
    engine.execute(
         "INSERT INTO ts_test (a, b) VALUES (%s, %s)",
        ((555, "v1"),(666, "v1"),)
    )
    engine.execute(
        "INSERT INTO ts_test (a, b) VALUES (%(id)s, %(name)s)",
        id=999, name="v1"
    )
      
    result = engine.execute('select * from ts_test')
    result.fetchall()

    　　

    步骤二：

    使用 Schema Type/SQL Expression Language/Engine/ConnectionPooling/Dialect 进行数据库操作。Engine使用Schema Type创建一个特定的结构对象，之后通过SQL Expression Language将该对象转换成SQL语句，然后通过 ConnectionPooling 连接数据库，再然后通过 Dialect 执行SQL，并获取结果。

    增删改查

    一个简单的完整例子

    ?
    1
    2
    3
    4
    5
    6
    7
    8
    9
    10
    11
    12
    13
    14
    15
    16
    17
    18
    19
    20
    21
    22
    23
    24
    25
    26
    27
    28
    29
    30
    31
    32
    33
    from sqlalchemy import create_engine
    from sqlalchemy.ext.declarative import declarative_base
    from sqlalchemy import Column, Integer, String
    from  sqlalchemy.orm import sessionmaker
     
    Base = declarative_base() #生成一个SqlORM 基类
     
     
    engine = create_engine("mysql+mysqldb://root@localhost:3306/test",echo=False)
     
     
    class Host(Base):
        __tablename__ = 'hosts'
        id = Column(Integer,primary_key=True,autoincrement=True)
        hostname = Column(String(64),unique=True,nullable=False)
        ip_addr = Column(String(128),unique=True,nullable=False)
        port = Column(Integer,default=22)
     
    Base.metadata.create_all(engine) #创建所有表结构
     
    if __name__ == '__main__':
        SessionCls = sessionmaker(bind=engine) #创建与数据库的会话session class ,注意,这里返回给session的是个class,不是实例
        session = SessionCls()
        #h1 = Host(hostname='localhost',ip_addr='127.0.0.1')
        #h2 = Host(hostname='ubuntu',ip_addr='192.168.2.243',port=20000)
        #h3 = Host(hostname='ubuntu2',ip_addr='192.168.2.244',port=20000)
        #session.add(h3)
        #session.add_all( [h1,h2])
        #h2.hostname = 'ubuntu_test' #只要没提交,此时修改也没问题
        #session.rollback()
        #session.commit() #提交
        res = session.query(Host).filter(Host.hostname.in_(['ubuntu2','localhost'])).all()
        print(res)

    　　

    更多内容详见：

        http://www.jianshu.com/p/e6bba189fcbd

        http://docs.sqlalchemy.org/en/latest/core/expression_api.html

    注：SQLAlchemy无法修改表结构，如果需要可以使用SQLAlchemy开发者开源的另外一个软件Alembic来完成。

    步骤三：

    使用 ORM/Schema Type/SQL Expression Language/Engine/ConnectionPooling/Dialect 所有组件对数据进行操作。根据类创建对象，对象转换成SQL，执行SQL。

    ?
    1
    2
    3
    4
    5
    6
    7
    8
    9
    10
    11
    12
    13
    14
    15
    16
    17
    18
    19
    20
    21
    22
    23
    24
    25
    26
    27
    28
    29
    30
    31
    32
    33
    34
    35
    36
    37
    38
    39
    40
    41
    42
    43
    44
    45
    46
    47
    48
    49
    50
    51
    52
    53
    54
    55
    56
    57
    58
    59
    #!/usr/bin/env python
    # -*- coding:utf-8 -*-
      
    from sqlalchemy.ext.declarative import declarative_base
    from sqlalchemy import Column, Integer, String
    from sqlalchemy.orm import sessionmaker
    from sqlalchemy import create_engine
      
    engine = create_engine("mysql+mysqldb://root:123@127.0.0.1:3306/s11", max_overflow=5)
      
    Base = declarative_base()
      
      
    class User(Base):
        __tablename__ = 'users'
        id = Column(Integer, primary_key=True)
        name = Column(String(50))
      
    # 寻找Base的所有子类，按照子类的结构在数据库中生成对应的数据表信息
    # Base.metadata.create_all(engine)
      
    Session = sessionmaker(bind=engine)
    session = Session()
      
      
    # ########## 增 ##########
    # u = User(id=2, name='sb')
    # session.add(u)
    # session.add_all([
    #     User(id=3, name='sb'),
    #     User(id=4, name='sb')
    # ])
    # session.commit()
      
    # ########## 删除 ##########
    # session.query(User).filter(User.id > 2).delete()
    # session.commit()
      
    # ########## 修改 ##########
    # session.query(User).filter(User.id > 2).update({'cluster_id' : 0})
    # session.commit()
    # ########## 查 ##########
    # ret = session.query(User).filter_by(name='sb').first()
      
    # ret = session.query(User).filter_by(name='sb').all()
    # print ret
      
    # ret = session.query(User).filter(User.name.in_(['sb','bb'])).all()
    # print ret
      
    # ret = session.query(User.name.label('name_label')).all()
    # print ret,type(ret)
      
    # ret = session.query(User).order_by(User.id).all()
    # print ret
      
    # ret = session.query(User).order_by(User.id)[1:3]
    # print ret
    # session.commit()

    外键关联

    A one to many relationship places a foreign key on the child table referencing the parent.relationship() is then specified on the parent, as referencing a collection of items represented by the child

    from sqlalchemy import Table, Column, Integer, ForeignKey
from sqlalchemy.orm import relationship
from sqlalchemy.ext.declarative import declarative_base

Base = declarative_base()
    ?
    1
    2
    3
    4
    5
    6
    7
    8
    9
    <br>class Parent(Base):
        __tablename__ = 'parent'
        id = Column(Integer, primary_key=True)
        children = relationship("Child")
     
    class Child(Base):
        __tablename__ = 'child'
        id = Column(Integer, primary_key=True)
        parent_id = Column(Integer, ForeignKey('parent.id'))

    To establish a bidirectional relationship in one-to-many, where the “reverse” side is a many to one, specify an additional relationship() and connect the two using therelationship.back_populates parameter:

    ?
    1
    2
    3
    4
    5
    6
    7
    8
    9
    10
    class Parent(Base):
        __tablename__ = 'parent'
        id = Column(Integer, primary_key=True)
        children = relationship("Child", back_populates="parent")
     
    class Child(Base):
        __tablename__ = 'child'
        id = Column(Integer, primary_key=True)
        parent_id = Column(Integer, ForeignKey('parent.id'))
        parent = relationship("Parent", back_populates="children")

    Child will get a parent attribute with many-to-one semantics.

    Alternatively, the backref option may be used on a single relationship() instead of usingback_populates:

    ?
    1
    2
    3
    4
    class Parent(Base):
        __tablename__ = 'parent'
        id = Column(Integer, primary_key=True)
        children = relationship("Child", backref="parent")

    　　

    　　

    附，原生sql join查询

    几个Join的区别 http://stackoverflow.com/questions/38549/difference-between-inner-and-outer-joins 

    • INNER JOIN: Returns all rows when there is at least one match in BOTH tables
    • LEFT JOIN: Return all rows from the left table, and the matched rows from the right table
    • RIGHT JOIN: Return all rows from the right table, and the matched rows from the left table
    ?
    1
    select host.id,hostname,ip_addr,port,host_group.name from host right join host_group on host.id = host_group.host_id

    in SQLAchemy

    ?
    1
    session.query(Host).join(Host.host_groups).filter(HostGroup.name=='t1').group_by("Host").all()

    　　

    group by 查询

    ?
    1
    select name,count(host.id) as NumberOfHosts from host right join host_group on host.id= host_group.host_id group by name;

    in SQLAchemy

    ?
    1
    2
    3
    4
    5
    6
    from sqlalchemy import func
    session.query(HostGroup, func.count(HostGroup.name )).group_by(HostGroup.name).all()
     
    #another example
    session.query(func.count(User.name), User.name).group_by(User.name).all() SELECT count(users.name) AS count_1, users.name AS users_name
    FROM users GROUP BY users.name
  • 相关阅读:
    A
    MongoDB小结17
    MongoDB小结16
    金蝶无法生成下推发票
    MongoDB小结15
    MongoDB小结14
    MongoDB小结13
    MongoDB小结12
    MongoDB小结11
    MongoDB小结10
  • 原文地址：https://www.cnblogs.com/oleli/p/5392047.html
Copyright © 2020-2023  润新知