# 使用 SELECT 实现 HTTP 请求
import socket
from urllib.parse import urlparse
from selectors import DefaultSelector, EVENT_READ, EVENT_WRITE

selector = DefaultSelector()
urls = ["https://www.baidu.com"]
stop = False

class HttpClient:
    # 回调函数：处理发送数据
    def handle_send(self, key):
        selector.unregister(key.fd)
        self.client.send("GET {} HTTP/1.1\r\nHost:{}\r\nConnection:close\r\n\r\n".format(self.path, self.host).encode("utf8"))
        # 继续监听是否可读，然后回调指定的方法
        selector.register(self.client.fileno(), EVENT_READ, self.handle_read)

    # 回调函数：接收返回数据
    def handle_read(self, key):
        recv = self.client.recv(1024)
        if recv:
            self.data += recv
        else:
            selector.unregister(key.fd)
            data = self.data.decode("utf8")
            html_data = data.split("\r\n\r\n")[1]
            print(html_data)
            self.client.close()
            # 解决 Windows 下报错问题
            urls.remove(self.orig_url)
            if not urls:
                global stop
                stop = True

    def get_html(self, url):
        self.orig_url = url
        url = urlparse(url)
        self.host = url.netloc
        self.path = url.path
        self.data = b""
        if self.path == "":
            self.path = "/"
        self.client = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
        # 使用非阻塞IO
        self.client.setblocking(False)
        try:
            self.client.connect((self.host, 80))
        except BlockingIOError as e:
            pass

        # 注册到 Selector，然后回调指定的方法
        selector.register(self.client.fileno(), EVENT_WRITE, self.handle_send)

'''
    SELECT + 回调 + 事件循环：不停地请求 Socket 的状态并调用对应的回调函数
    这种`SELECT + 回调 + 事件循环`的方式性能比单纯使用 Socket 要高
    因为它将一个完整的步骤拆分成了若干个阶段，每个阶段都是独立且不阻塞的，相互之间也没有耦合
    但回调过多会造成代码难以维护，难于追踪，共享变量困难，以及难于处理异常的问题
'''
# 事件循环
def loop():
    # # Linux 下适用
    # while True:
    #     events = selector.select()
    #     for key, mask in events:
    #         callback = key.data
    #         callback(key)
    # Windows/Linux 下适用
    while not stop:
        events = selector.select()
        for key, mask in events:
            callback = key.data
            callback(key)

if __name__ == "__main__":
    httpClient = HttpClient()
    httpClient.get_html("https://www.baidu.com")
    loop()