Python学习 （系列练习1）

ex1

recv 函数会返回接收的数据长度，如果返回值小于你给它的参数，说明已经接收完了所有数据，否则说明仍然有数据需要接收，你应该再次调用它来接收数据，用循环把它改成能正确接收所有数据。

import socket


s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)

host = 'g.cn'
s.connect((host, 80))

ip, port = s.getsockname()
print('local ip and port {0} {1}'.format(ip, port))
request = b'GET / HTTP/1.1\r\nhost:g.cn\r\n\r\n'
s.send(request)
size = 103
part = s.recv(size)
response = part
while len(part) >= size:
    part = s.recv(size)
    response = response + part

print(response.decode('utf-8'))

ex2

把向服务器发送 HTTP 请求并且获得数据这个过程封装成函数
定义如下
def get(url):
url 格式为 http://g.cn/
返回的数据类型为 bytes
测试代码
url = ‘http://movie.douban.com/top250 ’
response = get(url)
r = response.decode(‘utf-8’)
print(r)

import socket
def get(url):

    s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)

    host = url.split('/')[2]
    path = url.split('/',3)[3]
    s.connect((host, 80))

    ip, port = s.getsockname()
    print('local ip and port {0} {1}'.format(ip, port))

    request = 'GET /'+path+' HTTP/1.1\r\nhost:'+host+'\r\n\r\n'
    print(request)
    s.send(request.encode('utf-8'))
    size = 10
    part = s.recv(size)
    response = part
    while len(part)>=size:
        part = s.recv(size)
        response = response + part
    return response

url = 'http://movie.douban.com/top250'
response = get(url)
r = response.decode('utf-8')
print(r)

ex3

get 函数接受以下这种参数
g.cn
没有协议名的情况下默认用HTTP
没有路径的情况下默认路径是 /
接收带端口的URL
http://g.cn:80/
用 URL中指定的端口来进行 socket 连接

import socket
def get(url):
    s = socket.socket(socket.AF_INET,socket.SOCK_STREAM)
    if 'http://' in url:
        url = url[7:]
    if '/' in url:
        path = url.split('/', 1)[1]
        host = url.split('/')[0]
    else:
        path = ''
        host = url
    if ':' in host:
        port1 = int(host.split(':')[1])
        host = host.split(':')[0]
    else:
        port1 = 80
    print('host=%s,path=%s,port=%s' % (host, path, port1))
    s.connect((host, port1))
    ip, port = s.getsockname()
    print('local ip and port {0} {1}'.format(ip, port))

    request = 'GET /' + path + ' HTTP/1.1\r\nhost:' + host + '\r\n\r\n'
    print(request)
    s.send(request.encode('utf-8'))
    size = 10
    part = s.recv(size)
    response = part
    while len(part) >= size:
        part = s.recv(size)
        response = response + part
    return response


url = 'http://g.cn:80/'
response = get(url)
r = response.decode('utf-8')
print(r)
###还有一种非常蠢的办法，更改判断部分
    if 'http' not in url:
        if ':' in url.split('/')[0]:
            host = url.split(':')[0]
            port1 = int(url.split(':')[1])
        else:
            host = url.split('/')[0]
            port1 = 80
        if '/' in url:
            path = ''.join(url.split('/')[1:])
        else:
            path = ''
    else:
        if ':' in url.split('/')[2]:
            host = url.split('/')[2].split(':')[0]
            port1 = int(url.split('/')[2].split(':')[1])
        else:
            host = url.split('/')[2]
            port1 = 80
        if '/' in url.split('/', 2)[2]:
            path = '/'.join(url.split('/')[3:])
        else:
            path = ''