python 线程、进程、协程实现web静态服务器

Bertha 。 2022-04-18 05:27 235阅读 0赞

## 线程、进程、协程实现web静态服务器 ##

--------------------

###### 1.Web静态服务器–多进程 ######

#coding=utf-8
    import socket
    import re
    import multiprocessing
    
    
    class WSGIServer(object):
    
        def __init__(self, server_address):
            # 创建一个tcp套接字
            self.listen_socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
            # 允许立即使用上次绑定的port
            self.listen_socket.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
            # 绑定本地信息
            self.listen_socket.bind(server_address)
            # 变为被动，并制定队列的长度
            self.listen_socket.listen(128)
    
        def serve_forever(self):
            "循环运行web服务器，等待客户端的链接并为客户端服务"
            while True:
                # 等待新客户端到来
                client_socket, client_address = self.listen_socket.accept()
                print(client_address)  # for test
                new_process = multiprocessing.Process(target=self.handleRequest, args=(client_socket,))
                new_process.start()
    
                # 因为子进程已经复制了父进程的套接字等资源，所以父进程调用close不会将他们对应的这个链接关闭的
                client_socket.close()
    
        def handleRequest(self, client_socket):
            "用一个新的进程，为一个客户端进行服务"
            recv_data = client_socket.recv(1024).decode('utf-8')
            print(recv_data)
            requestHeaderLines = recv_data.splitlines()
            for line in requestHeaderLines:
                print(line)
    
            request_line = requestHeaderLines[0]
            get_file_name = re.match("[^/]+(/[^ ]*)", request_line).group(1)
            print("file name is ===>%s" % get_file_name) # for test
    
            if get_file_name == "/":
                get_file_name = DOCUMENTS_ROOT + "/index.html"
            else:
                get_file_name = DOCUMENTS_ROOT + get_file_name
    
            print("file name is ===2>%s" % get_file_name) # for test
    
            try:
                f = open(get_file_name, "rb")
            except IOError:
                response_header = "HTTP/1.1 404 not found\r\n"
                response_header += "\r\n"
                response_body = "====sorry ,file not found===="
            else:
                response_header = "HTTP/1.1 200 OK\r\n"
                response_header += "\r\n"
                response_body = f.read()
                f.close()
            finally:
                client_socket.send(response_header.encode('utf-8'))
                client_socket.send(response_body)
                client_socket.close()
    
    
    # 设定服务器的端口
    SERVER_ADDR = (HOST, PORT) = "", 8888
    # 设置服务器服务静态资源时的路径
    DOCUMENTS_ROOT = "./html"
    
    
    def main():
        httpd = WSGIServer(SERVER_ADDR)
        print("web Server: Serving HTTP on port %d ...\n" % PORT)
        httpd.serve_forever()
    
    if __name__ == "__main__":
        main()

###### 2.Web静态服务器–多线程 ######

#coding=utf-8
    import socket
    import re
    import threading
    
    
    class WSGIServer(object):
    
        def __init__(self, server_address):
            # 创建一个tcp套接字
            self.listen_socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
            # 允许立即使用上次绑定的port
            self.listen_socket.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
            # 绑定
            self.listen_socket.bind(server_address)
            # 变为被动，并制定队列的长度
            self.listen_socket.listen(128)
    
        def serve_forever(self):
            "循环运行web服务器，等待客户端的链接并为客户端服务"
            while True:
                # 等待新客户端到来
                client_socket, client_address = self.listen_socket.accept()
                print(client_address)
                new_process = threading.Thread(target=self.handleRequest, args=(client_socket,))
                new_process.start()
    
                # 因为线程是共享同一个套接字，所以主线程不能关闭，否则子线程就不能再使用这个套接字了
                # client_socket.close() 
    
        def handleRequest(self, client_socket):
            "用一个新的进程，为一个客户端进行服务"
            recv_data = client_socket.recv(1024).decode('utf-8')
            print(recv_data)
            requestHeaderLines = recv_data.splitlines()
            for line in requestHeaderLines:
                print(line)
    
            request_line = requestHeaderLines[0]
            get_file_name = re.match("[^/]+(/[^ ]*)", request_line).group(1)
            print("file name is ===>%s" % get_file_name) # for test
    
            if get_file_name == "/":
                get_file_name = DOCUMENTS_ROOT + "/index.html"
            else:
                get_file_name = DOCUMENTS_ROOT + get_file_name
    
            print("file name is ===2>%s" % get_file_name) # for test
    
            try:
                f = open(get_file_name, "rb")
            except IOError:
                response_header = "HTTP/1.1 404 not found\r\n"
                response_header += "\r\n"
                response_body = "====sorry ,file not found===="
            else:
                response_header = "HTTP/1.1 200 OK\r\n"
                response_header += "\r\n"
                response_body = f.read()
                f.close()
            finally:
                client_socket.send(response_header.encode('utf-8'))
                client_socket.send(response_body)
                client_socket.close()
    
    
    # 设定服务器的端口
    SERVER_ADDR = (HOST, PORT) = "", 8888
    # 设置服务器服务静态资源时的路径
    DOCUMENTS_ROOT = "./html"
    
    
    def main():
        httpd = WSGIServer(SERVER_ADDR)
        print("web Server: Serving HTTP on port %d ...\n" % PORT)
        httpd.serve_forever()
    
    if __name__ == "__main__":
        main()

###### 3.Web静态服务器–非堵塞模式(并发原理) ######

import time
    import socket
    import sys
    import re
    
    
    class WSGIServer(object):
        """定义一个WSGI服务器的类"""
    
        def __init__(self, port, documents_root):
    
            # 1. 创建套接字
            self.server_socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
            # 2. 绑定本地信息
            self.server_socket.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
            self.server_socket.bind(("", port))
            # 3. 变为监听套接字
            self.server_socket.listen(128)
    
            self.server_socket.setblocking(False)
            self.client_socket_list = list()
    
            self.documents_root = documents_root
    
        def run_forever(self):
            """运行服务器"""
    
            # 等待对方链接
            while True:
    
                # time.sleep(0.5)  # for test
    
                try:
                    new_socket, new_addr = self.server_socket.accept()
                except Exception as ret:
                    print("-----1----", ret)  # for test
                else:
                    new_socket.setblocking(False)
                    self.client_socket_list.append(new_socket)
    
                for client_socket in self.client_socket_list:
                    try:
                        request = client_socket.recv(1024).decode('utf-8')
                    except Exception as ret:
                        print("------2----", ret)  # for test
                    else:
                        if request:
                            self.deal_with_request(request, client_socket)
                        else:
                            client_socket.close()
                            self.client_socket_list.remove(client_socket)
    
                print(self.client_socket_list)
    
    
        def deal_with_request(self, request, client_socket):
            """为这个浏览器服务器"""
            if not request:
                return
    
            request_lines = request.splitlines()
            for i, line in enumerate(request_lines):
                print(i, line)
    
            # 提取请求的文件(index.html)
            # GET /a/b/c/d/e/index.html HTTP/1.1
            ret = re.match(r"([^/]*)([^ ]+)", request_lines[0])
            if ret:
                print("正则提取数据:", ret.group(1))
                print("正则提取数据:", ret.group(2))
                file_name = ret.group(2)
                if file_name == "/":
                    file_name = "/index.html"
    
    
            # 读取文件数据
            try:
                f = open(self.documents_root+file_name, "rb")
            except:
                response_body = "file not found, 请输入正确的url"
                response_header = "HTTP/1.1 404 not found\r\n"
                response_header += "Content-Type: text/html; charset=utf-8\r\n"
                response_header += "Content-Length: %d\r\n" % (len(response_body))
                response_header += "\r\n"
    
                # 将header返回给浏览器
                client_socket.send(response_header.encode('utf-8'))
    
                # 将body返回给浏览器
                client_socket.send(response_body.encode("utf-8"))
            else:
                content = f.read()
                f.close()
    
                response_body = content
                response_header = "HTTP/1.1 200 OK\r\n"
                response_header += "Content-Length: %d\r\n" % (len(response_body))
                response_header += "\r\n"
    
                # 将header返回给浏览器
                client_socket.send( response_header.encode('utf-8') + response_body)
    
    
    # 设置服务器服务静态资源时的路径
    DOCUMENTS_ROOT = "./html"
    
    
    def main():
        """控制web服务器整体"""
        # python3 xxxx.py 7890
        if len(sys.argv) == 2:
            port = sys.argv[1]
            if port.isdigit():
                port = int(port)
        else:
            print("运行方式如: python3 xxx.py 7890")
            return
    
        print("http服务器使用的port:%s" % port)
        http_server = WSGIServer(port, DOCUMENTS_ROOT)
        http_server.run_forever()
    
    
    if __name__ == "__main__":
        main()

###### 4. Web静态服务器–epoll ######

import socket
    import time
    import sys
    import re
    import select
    
    
    class WSGIServer(object):
        """定义一个WSGI服务器的类"""
    
        def __init__(self, port, documents_root):
    
            # 1. 创建套接字
            self.server_socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
            # 2. 绑定本地信息
            self.server_socket.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
            self.server_socket.bind(("", port))
            # 3. 变为监听套接字
            self.server_socket.listen(128)
    
            self.documents_root = documents_root
    
            # 创建epoll对象
            self.epoll = select.epoll()
            # 将tcp服务器套接字加入到epoll中进行监听
            self.epoll.register(self.server_socket.fileno(), select.EPOLLIN|select.EPOLLET)
    
            # 创建添加的fd对应的套接字
            self.fd_socket = dict()
    
        def run_forever(self):
            """运行服务器"""
    
            # 等待对方链接
            while True:
                # epoll 进行 fd 扫描的地方 -- 未指定超时时间则为阻塞等待
                epoll_list = self.epoll.poll()
    
                # 对事件进行判断
                for fd, event in epoll_list:
                    # 如果是服务器套接字可以收数据，那么意味着可以进行accept
                    if fd == self.server_socket.fileno():
                        new_socket, new_addr = self.server_socket.accept()
                        # 向 epoll 中注册 连接 socket 的 可读 事件
                        self.epoll.register(new_socket.fileno(), select.EPOLLIN | select.EPOLLET)
                        # 记录这个信息
                        self.fd_socket[new_socket.fileno()] = new_socket
                    # 接收到数据
                    elif event == select.EPOLLIN:
                        request = self.fd_socket[fd].recv(1024).decode("utf-8")
                        if request:
                            self.deal_with_request(request, self.fd_socket[fd])
                        else:
                            # 在epoll中注销客户端的信息
                            self.epoll.unregister(fd)
                            # 关闭客户端的文件句柄
                            self.fd_socket[fd].close()
                            # 在字典中删除与已关闭客户端相关的信息
                            del self.fd_socket[fd]
    
        def deal_with_request(self, request, client_socket):
            """为这个浏览器服务器"""
    
            if not request:
                return
    
            request_lines = request.splitlines()
            for i, line in enumerate(request_lines):
                print(i, line)
    
            # 提取请求的文件(index.html)
            # GET /a/b/c/d/e/index.html HTTP/1.1
            ret = re.match(r"([^/]*)([^ ]+)", request_lines[0])
            if ret:
                print("正则提取数据:", ret.group(1))
                print("正则提取数据:", ret.group(2))
                file_name = ret.group(2)
                if file_name == "/":
                    file_name = "/index.html"
    
    
            # 读取文件数据
            try:
                f = open(self.documents_root+file_name, "rb")
            except:
                response_body = "file not found, 请输入正确的url"
    
                response_header = "HTTP/1.1 404 not found\r\n"
                response_header += "Content-Type: text/html; charset=utf-8\r\n"
                response_header += "Content-Length: %d\r\n" % len(response_body)
                response_header += "\r\n"
    
                # 将header返回给浏览器
                client_socket.send(response_header.encode('utf-8'))
    
                # 将body返回给浏览器
                client_socket.send(response_body.encode("utf-8"))
            else:
                content = f.read()
                f.close()
    
                response_body = content
    
                response_header = "HTTP/1.1 200 OK\r\n"
                response_header += "Content-Length: %d\r\n" % len(response_body)
                response_header += "\r\n"
    
                # 将数据返回给浏览器
                client_socket.send(response_header.encode("utf-8")+response_body)
    
    
    # 设置服务器服务静态资源时的路径
    DOCUMENTS_ROOT = "./html"
    
    
    def main():
        """控制web服务器整体"""
        # python3 xxxx.py 7890
        if len(sys.argv) == 2:
            port = sys.argv[1]
            if port.isdigit():
                port = int(port)
        else:
            print("运行方式如: python3 xxx.py 7890")
            return
    
        print("http服务器使用的port:%s" % port)
        http_server = WSGIServer(port, DOCUMENTS_ROOT)
        http_server.run_forever()
    
    
    if __name__ == "__main__":
        main()

###### 5.Web静态服务器–gevent版 ######

from gevent import monkey
    import gevent
    import socket
    import sys
    import re
    
    monkey.patch_all()
    
    
    class WSGIServer(object):
        """定义一个WSGI服务器的类"""
    
        def __init__(self, port, documents_root):
    
            # 1. 创建套接字
            self.server_socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
            # 2. 绑定本地信息
            self.server_socket.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
            self.server_socket.bind(("", port))
            # 3. 变为监听套接字
            self.server_socket.listen(128)
    
            self.documents_root = documents_root
    
        def run_forever(self):
            """运行服务器"""
    
            # 等待对方链接
            while True:
                new_socket, new_addr = self.server_socket.accept()
                gevent.spawn(self.deal_with_request, new_socket)  # 创建一个协程准备运行它
    
        def deal_with_request(self, client_socket):
            """为这个浏览器服务器"""
            while True:
                # 接收数据
                request = client_socket.recv(1024).decode('utf-8')
                # print(gevent.getcurrent())
                # print(request)
    
                # 当浏览器接收完数据后，会自动调用close进行关闭，因此当其关闭时，web也要关闭这个套接字
                if not request:
                    new_socket.close()
                    break
    
                request_lines = request.splitlines()
                for i, line in enumerate(request_lines):
                    print(i, line)
    
                # 提取请求的文件(index.html)
                # GET /a/b/c/d/e/index.html HTTP/1.1
                ret = re.match(r"([^/]*)([^ ]+)", request_lines[0])
                if ret:
                    print("正则提取数据:", ret.group(1))
                    print("正则提取数据:", ret.group(2))
                    file_name = ret.group(2)
                    if file_name == "/":
                        file_name = "/index.html"
    
                file_path_name = self.documents_root + file_name
                try:
                    f = open(file_path_name, "rb")
                except:
                    # 如果不能打开这个文件，那么意味着没有这个资源，没有资源 那么也得需要告诉浏览器 一些数据才行
                    # 404
                    response_body = "没有你需要的文件......".encode("utf-8")
    
                    response_headers = "HTTP/1.1 404 not found\r\n"
                    response_headers += "Content-Type:text/html;charset=utf-8\r\n"
                    response_headers += "Content-Length:%d\r\n" % len(response_body)
                    response_headers += "\r\n"
    
                    send_data = response_headers.encode("utf-8") + response_body
    
                    client_socket.send(send_data)
    
                else:
                    content = f.read()
                    f.close()
    
                    # 响应的body信息
                    response_body = content
                    # 响应头信息
                    response_headers = "HTTP/1.1 200 OK\r\n"
                    response_headers += "Content-Type:text/html;charset=utf-8\r\n"
                    response_headers += "Content-Length:%d\r\n" % len(response_body)
                    response_headers += "\r\n"
                    send_data = response_headers.encode("utf-8") + response_body
                    client_socket.send(send_data)
    
    # 设置服务器服务静态资源时的路径
    DOCUMENTS_ROOT = "./html"
    
    def main():
        """控制web服务器整体"""
        # python3 xxxx.py 7890
        if len(sys.argv) == 2:
            port = sys.argv[1]
            if port.isdigit():
                port = int(port)
        else:
            print("运行方式如: python3 xxx.py 7890")
            return
    
        print("http服务器使用的port:%s" % port)
        http_server = WSGIServer(port, DOCUMENTS_ROOT")
        http_server.run_forever()
    
    
    if __name__ == "__main__":
        main()