python:Urllib库的基本使用

Python内置的HTTP请求库

方法	模块
urllib.request	请求模块
urllib.error	异常处理模块
urllib.parse	url解析模块
urllib.robotparser	robots.txt解析模块

urlopen

urllib.request.urlopen(url,data=None,[timeout,]*,cafile=None,capath=None,cadefault=False,context=None)

============================================

import urllib.request

response = urllib.request.urlopen('http://www.baidu.com')
print(response.read().decode('utf-8'))

============================================

import urllib.parse
import urllib.request

data = bytes(urllib.parse.urlencode({'word': 'hello'}), encoding='utf-8')
response = urllib.request.urlopen('http://httpbin.org/post', data=data)
print(response.read())

============================================

import urllib.request

response = urllib.request.urlopen('http://httpbin.org/get', timeout=1)
print(response.read())

============================================

import socket
import urllib.request
import urllib.error

try:
    response = urllib.request.urlopen('http://httpbin.org/get', timeout=0.1)
except urllib.error.URLError as e:
    if isinstance(e.reason, socket.timeout):
        print('TIME OUT')

============================================

响应

import urllib.request

response = urllib.request.urlopen('http://www.python.org')
print(type(response))    # 响应类型
print(response.status)    # 状态码
print(response.getheaders())    # 响应头
print(response.getheader('Server'))    # 响应头