【11.3】select+回调+事件循环获取html

#!/usr/bin/env python
# -*- coding:utf-8 -*-

# 通过非阻塞io实现http请求
import socket
from urllib.parse import urlparse
from selectors import DefaultSelector, EVENT_READ, EVENT_WRITE

selector = DefaultSelector()

urls = ['http://www.baidu.com']
stop = False


# 使用select完成http请求
class Fetcher:
    def connected(self, key):
        # 注销事件
        selector.unregister(key.fd)
        self.client.send("GET {} HTTP/1.1
Host:{}
Connection:close

".format(self.path, self.host).encode('utf-8'))
        #
        selector.register(self.client.fileno(), EVENT_READ, self.readable)

    def readable(self, key):
        d = self.client.recv(1024)
        if d:
            self.data += d
        else:
            # 注销
            selector.unregister(key.fd)
            self.data = self.data.decode('utf-8')
            html_data = self.data.split('

')[1]
            print(self.data)
            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
        # 通过socket请求html
        url = urlparse(url)
        self.host = url.netloc
        self.path = url.path
        self.data = b""
        if self.path == '':
            self.path = '/'

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

        try:
            self.client.connect((self.host, 80))
        except BlockingIOError as e:
            pass

        # 注册事件
        selector.register(self.client.fileno(), EVENT_WRITE, self.connected)
        """
        register(fileobj, events, data=None)
        fileobj：文件描述符
        events：监听事件
        data：回调函数
        
        """


def loop():
    # 事件循环，不停的请求socket的状态并调用对应的回调函数
    # 1.select本身是不支持register模式。
    # 2.socket状态变化以后的回调是由程序员完成的。
    while not stop:
        # windows下会报错，但是linux下不会报错
        ready = selector.select()
        for key, mask in ready:
            call_back = key.data
            call_back(key)


if __name__ == '__main__':
    fetcher = Fetcher()
    fetcher.get_url('http://www.baidu.com')
    loop()

 使用回调函数的缺点：

　　1.可读性差

　　2.共享状态管理困难

　　3.异常处理困难