开发静态web服务器

提示：文章写完后，目录可以自动生成，如何生成可参考右边的帮助文档

---

一、返回固定页面的web服务器

由于浏览器只认固定格式的数据，所以不能将html的数据直接返回给浏览器，需要将数据改为浏览器认准的格式，包括响应行、响应头、空行、响应体

import socket

if __name__ == '__main__':
    tcp_server_socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
    tcp_server_socket.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, True)
    tcp_server_socket.bind(("", 8000))
    tcp_server_socket.listen(128)
    while True:
        new_socket, ip_port = tcp_server_socket.accept()
        recv_data = new_socket.recv(4096)
        print(recv_data)

        # 打开文件读取文件中的数据
        with open("static/index.html", "r") as file:
            file_data = file.read()
        # 响应行
        response_line = "HTTP/1.1 200 OK\r\n"
        # 响应头
        response_header = "Server: PWS/1.0\r\n"
        # 响应体
        response_body = file_data
        # 把数据封装成http 响应报文格式的数据
        response = response_line + response_header + "\r\n" + response_body
        
        response_data = response.encode("utf-8")
        new_socket.send(response_data)
        new_socket.close()

二、返回指定页面的web服务器

上面不管访问哪个地址，都返回的是同一个页面，明显与实际使用场景不符，优化一下，根据不同的地址返回相应的页面。
recv_content返回的数据是这样的：'GET /index2.html HTTP/1.1\r\nHost: localhost:8989\r\nUser-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:95.0) Gecko/20100101 Firefox/95.0\r\nAccept: text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8\r\nAccept-Language: zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2\r\nAccept-Encoding: gzip, deflate\r\nConnection: keep-alive\r\nCookie: Pycharm-900df24b=1a52600c-c2d3-454f-9f85-7815555a4ebe\r\nUpgrade-Insecure-Requests: 1\r\nSec-Fetch-Dest: document\r\nSec-Fetch-Mode: navigate\r\nSec-Fetch-Site: none\r\nSec-Fetch-User: ?1\r\n\r\n'
只要根据空格分割即可取出页面的信息“/index2.html”

import socket
import os

def main():
    tcp_server_socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
    tcp_server_socket.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, True)
    tcp_server_socket.bind(("", 8000))
    tcp_server_socket.listen(128)
    while True:
        new_socket, ip_port = tcp_server_socket.accept()
        recv_data = new_socket.recv(4096)
        # 判断接收的数据长度是否为0，防止用户没有任何请求就断开链接报错的情况
        if len(recv_data) == 0:
            new_socket.close()
            return

        recv_content = recv_data.decode("utf-8")
        print(recv_content)

        # 对数据按照空格进行分割
        request_list = recv_content.split(" ", maxsplit=2)
        # 获取请求的资源路径
        request_path = request_list[1]
        print(request_path)

        # 判断请求的是否是根目录，如果是根目录设置返回的信息
        if request_path == "/":
            request_path = "/index.html"

        #  这里使用rb模式，兼容打开图片文件
        with open("static" + request_path, "rb") as file:
            file_data = file.read()

        response_line = "HTTP/1.1 200 OK\r\n"
        response_header = "Server: PWS/1.0\r\n"
        response_body = file_data

        # 把数据封装成http 响应报文格式的数据
        response = (response_line + response_header + "\r\n").encode("utf-8") + response_body

        new_socket.send(response)
        new_socket.close()

if __name__ == '__main__':
    main()

三、返回404页面

上面的代码还有个小问题，当请求的页面不存在时，程序会报错

...
def main():
    ...
    while True:
        ...
        if request_path == "/":
            request_path = "/index.html"

        try:
            with open("static" + request_path, "rb") as file:
                file_data = file.read()
        except FileNotFoundError as e:
            # 代码执行到此，说明没有请求的该文件，返回404状态信息
            response_line = "HTTP/1.1 404 Not Found\r\n"
            # 读取404页面数据
            with open("static/error.html", "rb") as file:
                file_data = file.read()
        else:
            # 代码执行到此，说明文件存在，返回200状态信息
            response_line = "HTTP/1.1 200 OK\r\n"
            
        finally:
        	response_header = "Server: PWS/1.0\r\n"
            response_body = file_data
            response = (response_line +
                        response_header +
                        "\r\n").encode("utf-8") + response_body
            new_socket.send(response)
            new_socket.close()
...

四、多任务版

要想实现多任务版，就按照之前的方法创建子线程即可。

import socket
import os
import threading


def send_recv(new_socket):
    recv_data = new_socket.recv(4096)
    if len(recv_data) == 0:
        new_socket.close()
        return
    recv_content = recv_data.decode("utf-8")
    print(recv_content)
    request_list = recv_content.split(" ", maxsplit=2)
    request_path = request_list[1]
    print(request_path)
    if request_path == "/":
        request_path = "/index.html"
    try:
        with open("static" + request_path, "rb") as file:
            file_data = file.read()
    except FileNotFoundError as e:
        response_line = "HTTP/1.1 404 Not Found\r\n"
        with open("static/error.html", "rb") as file:
            file_data = file.read()
    else:
        response_line = "HTTP/1.1 200 OK\r\n"
    finally:
        response_header = "Server: PWS/1.0\r\n"
    response_body = file_data
    response = (response_line +
                response_header +
                "\r\n").encode("utf-8") + response_body
    new_socket.send(response)
    new_socket.close()

def main():
    tcp_server_socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
    tcp_server_socket.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, True)
    tcp_server_socket.bind(("", 8989))
    tcp_server_socket.listen(128)
    while True:
        new_socket, ip_port = tcp_server_socket.accept()
        t1 = threading.Thread(target=send_recv, args=(new_socket,))
        t1.setDaemon(True)
        t1.start()

if __name__ == '__main__':
    main()

五、面向对象版

import socket
import threading

# 定义web服务器类
class HttpWebServer(object):
    def __init__(self):
        self.tcp_server_socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
        self.tcp_server_socket.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, True)
        self.tcp_server_socket.bind(("", 9000))
        self.tcp_server_socket.listen(128)

    # 此方法用不到self和cls，即可定义为静态方法
    @staticmethod
    def send_recv(new_socket):
        ...

    # 启动web服务器进行工作
    def start(self):
        while True:
            new_socket, ip_port = self.tcp_server_socket.accept()
            sub_thread = threading.Thread(target=self.send_recv, args=(new_socket,))
            sub_thread.setDaemon(True)
            sub_thread.start()

def main():
    # 创建web服务器对象
    web_server = HttpWebServer()
    # 启动web服务器进行工作
    web_server.start()

if __name__ == '__main__':
    main()

五、命令行启动动态绑定端口号

修改上面的代码。

import socket
import threading

# 定义web服务器类
class HttpWebServer(object,port):
    def __init__(self):
        ...
        self.tcp_server_socket.bind(("", port))
        ...

def main():
    # 判断命令行参数是否等于2,
    if len(sys.argv) != 2:
        print("执行命令如下: python3 xxx.py 8000")
        return

    # 判断字符串是否都是数字组成
    if not sys.argv[1].isdigit():
        print("第二个参数必须为数字")
        return

    # 获取终端命令行参数
    port = int(sys.argv[1])
    # 创建web服务器对象
    web_server = HttpWebServer(port)
    # 启动web服务器进行工作
    web_server.start()

if __name__ == '__main__':
    main()

此时就可以通过命令行来启动服务了