urllib提供了一系列用于操作URL的功能，而urllib的request模块可以非常方便地抓取URL内容，也就是发送一个GET请求到指定的页面，然后返回HTTP的响应。

基本的网络请求示例

import urllib.request

#请求百度网页
resu = urllib.request.urlopen('https://www.baidu.com', data = None, timeout = 10)
print(resu.read(300))

#指定编码请求
with urllib.request.urlopen('https://www.baidu.com') as resu:
    print(resu.read(300).decode('GBK'))
    
#指定编码请求
f = urllib.request.urlopen('https://www.baidu.com')
print(f.read(100).decode('utf-8'))

发送数据请求，CGI程序处理

import urllib.request

req = urllib.request.Request(url='http://localhost/cgi-bin/test.cgi', data=b'This data is passed to stdin of the CGI')
f = urllib.request.urlopen(req)

print(f.read().decode('utf-8'))

PUT请求

import urllib.request

DATA=b'some data'
req = urllib.request.Request(url='http://localhost:8080', data=DATA,method='PUT')
f = urllib.request.urlopen(req)

print(f.status)
print(f.reason)

基本的HTTP验证，登录请求

import urllib.request

# Create an OpenerDirector with support for Basic HTTP Authentication...
auth_handler = urllib.request.HTTPBasicAuthHandler()
auth_handler.add_password(realm='Application',
                          uri='http://xxx/test.py',
                          user='test',
                          passwd='test')
opener = urllib.request.build_opener(auth_handler)

# ...and install it globally so it can be used with urlopen.
urllib.request.install_opener(opener)
urllib.request.urlopen('http://www.example.com/login.html')

支持代理方式验证请求

proxy_handler = urllib.request.ProxyHandler({'http': 'http://www.example.com/'})
proxy_auth_handler = urllib.request.ProxyBasicAuthHandler()
proxy_auth_handler.add_password('aaa', 'bbb', 'username', 'password')

opener = urllib.request.build_opener(proxy_handler, proxy_auth_handler)

# This time, rather than install the OpenerDirector, we use it directly:
opener.open('http://www.example.com/login.html')

添加 http headers

import urllib.request

req = urllib.request.Request('http://www.example.com/')
req.add_header('Referer', 'http://www.python.org/')
r = urllib.request.urlopen(req)

添加 user-agent

import urllib.request

opener = urllib.request.build_opener()
opener.addheaders = [('User-agent', 'Mozilla/5.0')]
opener.open('http://www.example.com/')

带参数的GET 请求

import urllib.request
import urllib.parse

params = urllib.parse.urlencode({'a': 1, 'b': 2, 'c': 0})
f = urllib.request.urlopen("http://xxx/query?%s" % params)

print(f.read().decode('utf-8'))

带参数的POST请求

import urllib.request
import urllib.parse

data = urllib.parse.urlencode({'a': 1, 'b': 2, 'c': 0})
data = data.encode('utf-8')

request = urllib.request.Request("http://xxx")

# adding charset parameter to the Content-Type header.
request.add_header("Content-Type","application/x-www-form-urlencoded;charset=utf-8")
f = urllib.request.urlopen(request, data)

print(f.read().decode('utf-8'))

指定代理方式请求

import urllib.request

proxies = {'http': 'http://proxy.example.com:8080/'}
opener = urllib.request.FancyURLopener(proxies)
f = opener.open("http://www.python.org")

f.read().decode('utf-8')

无添加代理

import urllib.request

opener = urllib.request.FancyURLopener({})
f = opener.open("http://www.python.org/")

f.read().decode('utf-8')