python标准库urllib.request

python库

urllib.request

访问网络的两种方式

# 该方法会对网络进行更加深入的控制
req = urllib.request.Request(url)  //发送请求 #(url,data,header)
response = urllib.request.urlopen(req)

response = urllib.request.urlopen(url)

response对象

response.geturl()   # 获取URL地址
response.url
response.getcode()  # 获取状态码
response.code
response.info()     # HTTP响应报文的头部信息
# 1 获得response流 -- 字节流必须使用这种方式
html = response.read()
# 2 把response 流 编码为 utf8
html = response.read().decode('utf-8')

request对象

request.type    # 请求的类型，https
request.unredirected_hdrs   # request的头
request.host    # 获取host地址
request.full_url    #获取完整url
req.add_header()    # 添加头部信息

HTTP GET

from urllib import request
response = request.urlopen('网址')  //获取HTTP响应报文对象
headers = response.info()
headers['date']    //访问响应头部中的date
for line in response:
    print(line.decode('utf-8').rstrip())  //获取读取到的网页内容

Http Get（带参数）

query_args = {'q': 'query string', 'foo': 'bar'}
encoded_args = parse.urlencode(query_args)
url = '网址' + encoded_args
response = request.urlopen(url)

HTTP POST（带参数）

from urllib import parse
from urllib import request
query_args = {'q': 'query string', 'foo': 'bar'}
encoded_args = parse.urlencode(query_args).encode('utf-8')
url = 'https://pymotw.com/3/urllib.request/index.html'
print(request.urlopen(url, data=encoded_args).read().decode('utf-8'))

添加请求头部信息

r = request.Request('http://localhost:8080/')
r.add_header(
    'User-agent',
    'PyMOTW (https://pymotw.com/)',
)
response = urllib.request.urlopen(r)