python socket 网页爬虫

import socket

# 第一步 获取域名或ip地址
host = 'www.baidu.com'
port = 80
header = b'GET / HTTP/1.1\r\nHost: www.baidu.com\r\nConnection: close\r\n\r\n'

# 第二步 域名解析 将url(网址)转换为ip地址
for res  in socket.getaddrinfo(host, port, socket.AF_UNSPEC, socket.SOCK_STREAM, 0, socket.AI_PASSIVE):
    # print(res)
    af, socktype, proto, canonname, sockaddr = res
    print(af, socktype, proto, canonname, sockaddr)
    s = socket.socket(af, socktype)
    s.connect(sockaddr)
    
# 第三步 发送数据
    with s:
        s.send(header)
        content = []
        while 1:
            t = s.recv(1024)
            if t:
                content.append(t.decode('utf-8'))
            else:
                break
        c = ''.join(content).encode()
        print(c.decode())