socket_http

socket_http

import socket
from urllib.parse import urlparse
import time

def get_url(url):
    # 通过socket请求html
    url = urlparse(url)  # 解析url
    host = url.netloc  # 获取ip地址
    path = url.path  # 相对主路径下的请求路径
    if path == "":
        path = "/"

    # 建立socket连接
    client = socket.socket(socket.AF_INET, socket.SOCK_STREAM)  # 创建socket连接
    # client.setblocking(False)
    client.connect((host, 80))  # 阻塞不会消耗cpu

    # 不停的询问连接是否建立好， 需要while循环不停的去检查状态
    # 做计算任务或者再次发起其他的连接请求

    client.send(
        "GET {} HTTP/1.1\r\nHost:{}\r\nConnection:close\r\n\r\n".format(path, host).encode("utf8"))  # 通过\r\n 添加请求头信息

    data = b""
    while True:
        d = client.recv(1024)
        if d:
            data += d
        else:
            break

    data = data.decode("utf8")  # data包含请求头信息和返回的响应数据
    html_data = data.split("\r\n\r\n")[1]  # 通过\r\n\r\n  讲请求头信息和响应数据分开
    print(html_data)
    client.close()

if __name__ == "__main__":

    start_time = time.time()
    for url in range(20):
        url = "http://shop.projectsedu.com/goods/{}/".format(url)
        get_url(url)
    print(time.time() - start_time)