#通過非阻塞io實現http請求
# select + 回撥 + 事件迴圈
#  併發性高
# 使用單執行緒

import socket
from urllib.parse import urlparse
from selectors import DefaultSelector, EVENT_READ, EVENT_WRITE


selector = DefaultSelector()
#使用select完成http請求
urls = []
stop = False


class Fetcher:
    def connected(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"))
        selector.register(self.client.fileno(), EVENT_READ, self.readable)

    def readable(self, key):
        d = self.client.recv(1024)
        if d:
            self.data += d
        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()
            urls.remove(self.spider_url)
            if not urls:
                global stop
                stop = True

    def get_url(self, url):
        self.spider_url = url
        url = urlparse(url)
        self.host = url.netloc
        self.path = url.path
        self.data = b""
        if self.path == "":
            self.path = "/"

        # 建立socket連線
        self.client = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
        self.client.setblocking(False)

        try:
            self.client.connect((self.host, 80))  # 阻塞不會消耗cpu
        except BlockingIOError as e:
            pass

        #註冊
        selector.register(self.client.fileno(), EVENT_WRITE, self.connected)


def loop():
    #事件迴圈，不停的請求socket的狀態並呼叫對應的回撥函式
    #1. select本身是不支援register模式
    #2. socket狀態變化以後的回撥是由程式設計師完成的
    while not stop:
        ready = selector.select()
        for key, mask in ready:
            call_back = key.data
            call_back(key)
    #回撥+事件迴圈+select(poll\epoll)

if __name__ == "__main__":
    fetcher = Fetcher()
    import time
    start_time = time.time()
    for url in range(20):
        url = "http://shop.projectsedu.com/goods/{}/".format(url)
        urls.append(url)
        fetcher = Fetcher()
        fetcher.get_url(url)
    loop()
    print(time.time()-start_time)