了解http協(xié)議

http請(qǐng)求頭

          
            GET / HTTP/1.1
Host: www.baidu.com
Connection: keep-alive
Pragma: no-cache
Cache-Control: no-cache
Upgrade-Insecure-Requests: 1
User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.100 Safari/537.36
Sec-Fetch-Mode: navigate
Sec-Fetch-User: ?1
Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3
Sec-Fetch-Site: none
Accept-Encoding: gzip, deflate, br
Accept-Language: zh-CN,zh;q=0.9,en;q=0.8
          
        

最主要的頭兩行分析如下：

• GET表示一個(gè)讀取請(qǐng)求，將從服務(wù)器獲得網(wǎng)頁(yè)數(shù)據(jù)，/表示URL的路徑，URL總是以/開(kāi)頭，/就表示首頁(yè)，最后的HTTP/1.1指示采用的HTTP協(xié)議版本是1.1。
• 目前HTTP協(xié)議的版本就是1.1，但是大部分服務(wù)器也支持1.0版本，主要區(qū)別在于1.1版本允許多個(gè)HTTP請(qǐng)求復(fù)用一個(gè)TCP連接，以加快傳輸速度。
• Host: www.baidu.com表示請(qǐng)求的域名是www.baidu.com。如果一臺(tái)服務(wù)器有多個(gè)網(wǎng)站，服務(wù)器就需要通過(guò)Host來(lái)區(qū)分瀏覽器請(qǐng)求的是哪個(gè)網(wǎng)站。

http響應(yīng)頭

          
            HTTP/1.1 200 OK
Bdpagetype: 2
Bdqid: 0x8ef7ae5901149cf7
Cache-Control: private
Connection: Keep-Alive
Content-Encoding: gzip
Content-Type: text/html;charset=utf-8
Date: Wed, 28 Aug 2019 01:59:49 GMT
Expires: Wed, 28 Aug 2019 01:59:48 GMT
Server: BWS/1.1
Set-Cookie: BDSVRTM=249; path=/
Set-Cookie: BD_HOME=1; path=/
Set-Cookie: H_PS_PSSID=1426_21111_20697_29522_29518_29099_29568_29220_26350; path=/; domain=.baidu.com
Strict-Transport-Security: max-age=172800
X-Ua-Compatible: IE=Edge,chrome=1
Transfer-Encoding: chunked
          
        

說(shuō)明：

• 200表示一個(gè)成功的響應(yīng)，后面的OK是說(shuō)明。
• Content-Type指示響應(yīng)的內(nèi)容，這里是text/html表示HTML網(wǎng)頁(yè)。
• 請(qǐng)求頭和響應(yīng)頭通過(guò)\r\n來(lái)?yè)Q行。
• 響應(yīng)頭和body響應(yīng)體中也通過(guò)\r\n來(lái)分隔。

簡(jiǎn)單的http服務(wù)器

有多簡(jiǎn)單呢？運(yùn)行程序后打開(kāi)瀏覽器，只能顯示hello world。

          
            import socket


def service_client(new_socket):
    # 接受瀏覽器發(fā)過(guò)來(lái)的http請(qǐng)求
    # GET / HTTP/1.1
    request = new_socket.recv(1024)
    print(request)
    # 返回http響應(yīng)
    resposne = "HTTP/1.1 200 OK\r\n"
    resposne += "\r\n"
    resposne += "
            

              hello world
            
            "
    new_socket.send(resposne.encode("utf-8"))

    # 關(guān)閉套接字
    new_socket.close()


def main():
    # 創(chuàng)建套接字
    http_server = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
    # 防止端口被占用無(wú)法啟動(dòng)程序
    http_server.setsockopt(socket.SOL_SOCKET,socket.SO_REUSEADDR,1)
    # 綁定端口
    http_server.bind(("", 80))
    # 變?yōu)楸O(jiān)聽(tīng)套接字
    http_server.listen(128)
    while True:
        # 等在新客戶端連接
        client, info = http_server.accept()
        # 為這個(gè)客戶端服務(wù)
        service_client(client)


if __name__ == "__main__":
    main()

          
        

單進(jìn)程http服務(wù)器

它上之前有一個(gè)升級(jí)就是可以返回靜態(tài)的html頁(yè)面。

          
            import socket
import re


def service_client(new_socket):
    # 接受瀏覽器發(fā)過(guò)來(lái)的http請(qǐng)求
    # GET / HTTP/1.1
    request = new_socket.recv(1024).decode("utf-8")
    # print(request)
    request_lines = request.splitlines()
    req = re.match(r"[^/]+(/\S*)", request_lines[0])
    file_name: str = ""
    if req:
        file_name = req.group(1)
        if file_name == "/":
            file_name = "/index.html"
        print(file_name)
    # print(request_lines)
    # 返回http響應(yīng)

    try:
        # 打開(kāi)要請(qǐng)求的html文件，并返回給客戶端。網(wǎng)頁(yè)在當(dāng)前路徑的html文件夾里面。
        with open("./html" + file_name, "r", encoding="utf-8") as f:
            resposne = "HTTP/1.1 200 OK\r\n"
            resposne += "\r\n"
            # resposne += "
            

              hello world
            
            "
            resposne += f.read()
    except Exception as e:
        resposne = "HTTP/1.1 400 NOT FOUND\r\n"
        resposne += "\r\n"
        resposne += "--file not found--"

    new_socket.send(resposne.encode("utf-8"))
    # 關(guān)閉套接字
    new_socket.close()


def main():
    # 創(chuàng)建套接字
    http_server = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
    # 防止端口被占用無(wú)法啟動(dòng)程序
    http_server.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
    # 綁定端口
    http_server.bind(("", 80))
    # 變?yōu)楸O(jiān)聽(tīng)套接字
    http_server.listen(128)
    while True:
        # 等在新客戶端連接
        client, info = http_server.accept()
        # 為這個(gè)客戶端服務(wù)
        service_client(client)


if __name__ == "__main__":
    main()
          
        

多進(jìn)程服務(wù)器

http服務(wù)器是完成了，但是如果同時(shí)有好多人訪問(wèn)的話它反應(yīng)就會(huì)非常慢，所有又在之前的基礎(chǔ)上做了升級(jí)，增加服務(wù)器的并發(fā)能力。

          
            import socket
import re
from multiprocessing import Process

def service_client(new_socket):
    # 接受瀏覽器發(fā)過(guò)來(lái)的http請(qǐng)求
    # GET / HTTP/1.1
    request = new_socket.recv(1024).decode("utf-8")
    # print(request)
    request_lines = request.splitlines()
    req = re.match(r"[^/]+(/\S*)", request_lines[0])
    file_name: str = ""
    if req:
        file_name = req.group(1)
        if file_name == "/":
            file_name = "/index.html"
        print(file_name)
    # print(request_lines)
    # 返回http響應(yīng)

    try:
        with open("./html" + file_name, "r", encoding="utf-8") as f:
            resposne = "HTTP/1.1 200 OK\r\n"
            resposne += "\r\n"
            # resposne += "
            

              hello world
            
            "
            resposne += f.read()
    except Exception as e:
        resposne = "HTTP/1.1 400 NOT FOUND\r\n"
        resposne += "\r\n"
        resposne += "--file not found--"

    new_socket.send(resposne.encode("utf-8"))
    # new_socket.send(body)
    # 關(guān)閉套接字
    new_socket.close()


def main():
    # 創(chuàng)建套接字
    http_server = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
    # 防止端口被占用無(wú)法啟動(dòng)程序
    http_server.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
    # 綁定端口
    http_server.bind(("", 80))
    # 變?yōu)楸O(jiān)聽(tīng)套接字
    http_server.listen(128)
    while True:
        # 等在新客戶端連接
        client, info = http_server.accept()
        # 開(kāi)啟一個(gè)子進(jìn)程為這個(gè)客戶端服務(wù)
        p = Process(target=service_client,args=(client,))
        p.start()
        # 子進(jìn)程會(huì)復(fù)制主進(jìn)程發(fā)的資源，故把主進(jìn)程的socket關(guān)閉。
        client.close()

if __name__ == "__main__":
    main()
          
        

多線程服務(wù)器

我們知道進(jìn)程耗費(fèi)資源是非常大的，所以這次使用了耗費(fèi)資源小的線程來(lái)實(shí)現(xiàn)多任務(wù)。

          
            import socket
import re
from threading import Thread


def service_client(new_socket):
    # 接受瀏覽器發(fā)過(guò)來(lái)的http請(qǐng)求
    # GET / HTTP/1.1
    request = new_socket.recv(1024).decode("utf-8")
    # print(request)
    request_lines = request.splitlines()
    req = re.match(r"[^/]+(/\S*)", request_lines[0])
    file_name: str = ""
    if req:
        file_name = req.group(1)
        if file_name == "/":
            file_name = "/index.html"
        print(file_name)
    # print(request_lines)
    # 返回http響應(yīng)

    try:
        with open("./html" + file_name, "r", encoding="utf-8") as f:
            resposne = "HTTP/1.1 200 OK\r\n"
            resposne += "\r\n"
            # resposne += "
            

              hello world
            
            "
            resposne += f.read()
    except Exception as e:
        resposne = "HTTP/1.1 400 NOT FOUND\r\n"
        resposne += "\r\n"
        resposne += "--file not found--"

    new_socket.send(resposne.encode("utf-8"))
    # new_socket.send(body)
    # 關(guān)閉套接字
    new_socket.close()


def main():
    # 創(chuàng)建套接字
    http_server = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
    # 防止端口被占用無(wú)法啟動(dòng)程序
    http_server.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
    # 綁定端口
    http_server.bind(("", 80))
    # 變?yōu)楸O(jiān)聽(tīng)套接字
    http_server.listen(128)
    while True:
        # 等在新客戶端連接
        client, info = http_server.accept()
        # 開(kāi)啟一個(gè)子線程為這個(gè)客戶端服務(wù)
        p = Thread(target=service_client, args=(client,))
        p.start()


if __name__ == "__main__":
    main()
          
        

gevent協(xié)程版的服務(wù)器

協(xié)程在一個(gè)線程中執(zhí)行，減少了線程之間的切換，多線程的升級(jí)版，擁有更好的處理能力。

          
            import socket
import re
import gevent
from gevent import monkey

monkey.patch_all()

def service_client(new_socket):
    # 接受瀏覽器發(fā)過(guò)來(lái)的http請(qǐng)求
    # GET / HTTP/1.1
    request = new_socket.recv(1024).decode("utf-8")
    # print(request)
    request_lines = request.splitlines()
    req = re.match(r"[^/]+(/\S*)", request_lines[0])
    file_name: str = ""
    if req:
        file_name = req.group(1)
        if file_name == "/":
            file_name = "/index.html"
        print(file_name)
    # print(request_lines)
    # 返回http響應(yīng)

    try:
        with open("./html" + file_name, "r", encoding="utf-8") as f:
            resposne = "HTTP/1.1 200 OK\r\n"
            resposne += "\r\n"
            # resposne += "
            

              hello world
            
            "
            resposne += f.read()
    except Exception as e:
        resposne = "HTTP/1.1 400 NOT FOUND\r\n"
        resposne += "\r\n"
        resposne += "--file not found--"

    new_socket.send(resposne.encode("utf-8"))
    # new_socket.send(body)
    # 關(guān)閉套接字
    new_socket.close()


def main():
    # 創(chuàng)建套接字
    http_server = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
    # 防止端口被占用無(wú)法啟動(dòng)程序
    http_server.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
    # 綁定端口
    http_server.bind(("", 80))
    # 變?yōu)楸O(jiān)聽(tīng)套接字
    http_server.listen(128)
    while True:
        # 等在新客戶端連接
        client, info = http_server.accept()
        # 為這個(gè)客戶端服務(wù)
        gevent.spawn(service_client, client)


if __name__ == "__main__":
    main()
          
        

單進(jìn)程非堵塞版長(zhǎng)連接的服務(wù)器

從這個(gè)例子中來(lái)引入epoll版，它的性能應(yīng)該要比協(xié)程的好，與之前所有服務(wù)器的不同之處就是采用了長(zhǎng)連接，通過(guò)響應(yīng)頭中的Content-Length來(lái)指定響應(yīng)體的長(zhǎng)度，從而讓瀏覽器知道頁(yè)面數(shù)據(jù)傳輸完成以后自動(dòng)在同一個(gè)套接字連接中繼續(xù)發(fā)送其他資源文件的請(qǐng)求，效率較高。之前的都是短連接，只要傳輸完當(dāng)前文件就關(guān)閉這個(gè)套接字。

          
            import socket
import re


def service_client(new_socket: object, request: str):
    # 接受瀏覽器發(fā)過(guò)來(lái)的http請(qǐng)求
    # GET / HTTP/1.1
    # request = new_socket.recv(1024).decode("utf-8")
    # print(request)
    request_lines = request.splitlines()
    req = re.match(r"[^/]+(/\S*)", request_lines[0])
    file_name: str = ""
    if req:
        file_name = req.group(1)
        if file_name == "/":
            file_name = "/index.html"
        print(file_name)
    # print(request_lines)
    # 返回http響應(yīng)

    try:
        with open("./html" + file_name, "r", encoding="utf-8") as f:
            resposne_body: str = f.read()
            resposne_header: str = "HTTP/1.1 200 OK\r\n"
            resposne_header += "Content-Length:%d\r\n" % len(resposne_body)
            resposne_header += "\r\n"
            # resposne += "
            

              hello world
            
            "
            resposne = resposne_header + resposne_body
    except Exception as e:
        resposne = "HTTP/1.1 400 NOT FOUND\r\n"
        resposne += "\r\n"
        resposne += "--file not found--"

    new_socket.send(resposne.encode("utf-8"))
    # new_socket.send(body)
    # 關(guān)閉套接字
    # new_socket.close()


def main():
    # 創(chuàng)建套接字
    http_server = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
    # 防止端口被占用無(wú)法啟動(dòng)程序
    http_server.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
    # 綁定端口
    http_server.bind(("", 80))
    # 變?yōu)楸O(jiān)聽(tīng)套接字
    http_server.listen(128)
    # 設(shè)置套接字為非堵塞方式
    http_server.setblocking(False)
    socket_list: list = []
    while True:
        try:
            # 等在新客戶端連接
            client, info = http_server.accept()
            # 為這個(gè)客戶端服務(wù)
            # gevent.spawn(service_client, client)
        except Exception as e:
            # print(e)
            pass
        else:
            client.setblocking(False)
            socket_list.append(client)

        for socket_client in socket_list:
            try:
                recv_data: str = socket_client.recv(1024).decode("utf-8")
            except Exception as e:
                # print(e)
                pass
            else:
                if recv_data:
                    service_client(socket_client, recv_data)
                else:
                    socket_list.remove(socket_client)
                    socket_client.close()


if __name__ == "__main__":
    main()

          
        

eopll版的服務(wù)器

這個(gè)版本是性能最高的服務(wù)器。它的基本原理就是select，poll，epoll這個(gè)function會(huì)不斷的輪詢所負(fù)責(zé)的所有socket，當(dāng)某個(gè)socket有數(shù)據(jù)到達(dá)了，就通知用戶進(jìn)程。select/epoll的好處就在于單個(gè)process就可以同時(shí)處理多個(gè)網(wǎng)絡(luò)連接的IO。

          
            import socket
import re
import select


def service_client(new_socket: object, request: str):
    # 接受瀏覽器發(fā)過(guò)來(lái)的http請(qǐng)求
    # GET / HTTP/1.1
    # request = new_socket.recv(1024).decode("utf-8")
    # print(request)
    request_lines = request.splitlines()
    req = re.match(r"[^/]+(/\S*)", request_lines[0])
    file_name: str = ""
    if req:
        file_name = req.group(1)
        if file_name == "/":
            file_name = "/index.html"
        print(file_name)
    # print(request_lines)
    # 返回http響應(yīng)

    try:
        with open("./html" + file_name, "r", encoding="utf-8") as f:
            resposne_body: str = f.read()
            resposne_header: str = "HTTP/1.1 200 OK\r\n"
            resposne_header += "Content-Length:%d\r\n" % len(resposne_body)
            resposne_header += "\r\n"
            # resposne += "
            

              hello world
            
            "
            resposne = resposne_header + resposne_body
    except Exception as e:
        resposne = "HTTP/1.1 400 NOT FOUND\r\n"
        resposne += "\r\n"
        resposne += "--file not found--"

    new_socket.send(resposne.encode("utf-8"))
    # new_socket.send(body)
    # 關(guān)閉套接字
    # new_socket.close()


def main():
    # 創(chuàng)建套接字
    http_server = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
    # 防止端口被占用無(wú)法啟動(dòng)程序
    http_server.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
    # 綁定端口
    http_server.bind(("", 80))
    # 變?yōu)楸O(jiān)聽(tīng)套接字
    http_server.listen(128)
    # 設(shè)置套接字為非堵塞方式
    http_server.setblocking(False)
    # 創(chuàng)建一個(gè)epoll對(duì)象
    epl = select.epoll()
    # 將監(jiān)聽(tīng)套接字對(duì)應(yīng)的fd(文件描述符)注冊(cè)到epoll中
    epl.register(http_server.fileno(), select.EPOLLIN)
    # 存儲(chǔ)fd文件描述符和套接字的對(duì)應(yīng)關(guān)系
    fd_event_dict: dict = {}
    while True:
        # 默認(rèn)會(huì)堵塞，知道os檢測(cè)到數(shù)據(jù)到來(lái)，通過(guò)事件通知方式告訴這個(gè)程序，此時(shí)才會(huì)解堵塞
        fd_event_list: list = epl.poll()  # [(套接字對(duì)應(yīng)的文件描述符，這個(gè)文件描述符是什么事件),...]
        for fd, event in fd_event_list:
            # 如果是監(jiān)聽(tīng)套接字有數(shù)據(jù)過(guò)來(lái)，即等待新的客戶端連接
            if fd == http_server.fileno():
                client, info = http_server.accept()
                # 將新的套接字注冊(cè)到epoll中
                epl.register(client.fileno(), select.EPOLLIN)
                # 把文件描述符和套接字的對(duì)應(yīng)關(guān)系存入字典
                fd_event_dict[client.fileno()] = client
            elif event == select.EPOLLIN:
                # 判斷已連接的套接字是否有數(shù)據(jù)發(fā)過(guò)來(lái)
                recv_data: str = fd_event_dict[fd].recv(1024).decode("utf-8")
                if recv_data:
                    service_client(fd_event_dict[fd], recv_data)
                else:
                    fd_event_dict[fd].close()
                    epl.unregister(fd)
                    del fd_event_dict[fd]


if __name__ == '__main__':
    main()

          
        

I/O 多路復(fù)用的特點(diǎn)：
通過(guò)一種機(jī)制使一個(gè)進(jìn)程能同時(shí)等待多個(gè)文件描述符，而這些文件描述符（套接字描述符）其中的任意一個(gè)進(jìn)入讀就緒狀態(tài)，epoll()函數(shù)就可以返回。 所以, IO多路復(fù)用，本質(zhì)上不會(huì)有并發(fā)的功能，因?yàn)槿魏螘r(shí)候還是只有一個(gè)進(jìn)程或線程進(jìn)行工作，它之所以能提高效率是因?yàn)閟elect\epoll 把進(jìn)來(lái)的socket放到他們的 '監(jiān)視' 列表里面，當(dāng)任何socket有可讀可寫(xiě)數(shù)據(jù)立馬處理，那如果select\epoll 手里同時(shí)檢測(cè)著很多socket， 一有動(dòng)靜馬上返回給進(jìn)程處理，總比一個(gè)一個(gè)socket過(guò)來(lái),阻塞等待,處理高效率。