python3 urllib.request 网络请求操作

python3 urllib.request 网络请求操作

基本的网络请求示例

'''
Created on 2014年4月22日

@author: dev.keke@gmail.com
'''
import urllib.request

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

#指定编码请求
with urllib.request.urlopen('http://www.baidu.com') as resu:
    print(resu.read(300).decode('GBK'))

#指定编码请求
f = urllib.request.urlopen('http://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='https://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'))
Got Data: "This data is passed to stdin of the CGI"

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='PDQ Application',
                          uri='https://mahler:8092/site-updates.py',
                          user='klem',
                          passwd='kadidd!ehopper')
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:3128/'})
proxy_auth_handler = urllib.request.ProxyBasicAuthHandler()
proxy_auth_handler.add_password('realm', 'host', '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({'spam': 1, 'eggs': 2, 'bacon': 0})
>>> f = urllib.request.urlopen("http://www.musi-cal.com/cgi-bin/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({'spam': 1, 'eggs': 2, 'bacon': 0})
>>> data = data.encode('utf-8')
>>> request = urllib.request.Request("http://requestb.in/xrbl82xr")
>>> # 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')

参考：https://docs.python.org/3.4/library/urllib.request.html#module-urllib.request