Chinaunix首页 | 论坛 | 博客
  • 博客访问: 4052041
  • 博文数量: 272
  • 博客积分: 7846
  • 博客等级: 少将
  • 技术积分: 6476
  • 用 户 组: 普通用户
  • 注册时间: 2009-08-25 16:27
文章分类

全部博文(272)

分类: Python/Ruby

2013-02-06 11:08:06

1、最简单
import urllib.request
response = urllib.request.urlopen('')
html = response.read()
2、使用 Request
import urllib.request

req = urllib.request.Request('')
response = urllib.request.urlopen(req)
the_page = response.read()
 
3、发送数据
复制代码
#! /usr/bin/env python3

import urllib.parse
import urllib.request

url = ''
user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
values = {
'act' : 'login',
'login[email]' : 'yzhang@i9i8.com',
'login[password]' : '123456'
}

data = urllib.parse.urlencode(values)
req = urllib.request.Request(url, data)
req.add_header('Referer', '')
response = urllib.request.urlopen(req)
the_page = response.read()

print(the_page.decode("utf8"))
复制代码

 
4、发送数据和header
复制代码
#! /usr/bin/env python3

import urllib.parse
import urllib.request

url = ''
user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
values = {
'act' : 'login',
'login[email]' : 'yzhang@i9i8.com',
'login[password]' : '123456'
}
headers = { 'User-Agent' : user_agent }

data = urllib.parse.urlencode(values)
req = urllib.request.Request(url, data, headers)
response = urllib.request.urlopen(req)
the_page = response.read()

print(the_page.decode("utf8"))
复制代码

 
5、http 错误
复制代码
#! /usr/bin/env python3

import urllib.request

req = urllib.request.Request('fish.html')
try:
urllib.request.urlopen(req)
except urllib.error.HTTPError as e:
print(e.code)
print(e.read().decode("utf8"))
复制代码
 
6、异常处理1
复制代码
#! /usr/bin/env python3

from urllib.request import Request, urlopen
from urllib.error import URLError, HTTPError
req = Request("")
try:
response = urlopen(req)
except HTTPError as e:
print('The server couldn\'t fulfill the request.')
print('Error code: ', e.code)
except URLError as e:
print('We failed to reach a server.')
print('Reason: ', e.reason)
else:
print("good!")
print(response.read().decode("utf8"))
复制代码

 
7、异常处理2
复制代码
#! /usr/bin/env python3

from urllib.request import Request, urlopen
from urllib.error import URLError
req = Request("")
try:
response = urlopen(req)
except URLError as e:
if hasattr(e, 'reason'):
print('We failed to reach a server.')
print('Reason: ', e.reason)
elif hasattr(e, 'code'):
print('The server couldn\'t fulfill the request.')
print('Error code: ', e.code)
else:
print("good!")
print(response.read().decode("utf8"))
复制代码

 
8、HTTP 认证
复制代码
#! /usr/bin/env python3

import urllib.request

# create a password manager
password_mgr = urllib.request.HTTPPasswordMgrWithDefaultRealm()

# Add the username and password.
#
If we knew the realm, we could use it instead of None.
top_level_url = ""
password_mgr.add_password(None, top_level_url, 'yzhang', 'cccddd')

handler = urllib.request.HTTPBasicAuthHandler(password_mgr)

# create "opener" (OpenerDirector instance)
opener = urllib.request.build_opener(handler)

# use the opener to fetch a URL
a_url = ""
x = opener.open(a_url)
print(x.read())

# Install the opener.
#
Now all calls to urllib.request.urlopen use our opener.
urllib.request.install_opener(opener)

a = urllib.request.urlopen(a_url).read().decode('utf8')
print(a)
复制代码

 
9、使用代理
复制代码
#! /usr/bin/env python3

import urllib.request

proxy_support = urllib.request.ProxyHandler({'sock5': 'localhost:1080'})
opener = urllib.request.build_opener(proxy_support)
urllib.request.install_opener(opener)


a = urllib.request.urlopen("").read().decode("utf8")
print(a)
复制代码

 
10、超时
复制代码
#! /usr/bin/env python3

import socket
import urllib.request

# timeout in seconds
timeout = 2
socket.setdefaulttimeout(timeout)

# this call to urllib.request.urlopen now uses the default timeout
#
we have set in the socket module
req = urllib.request.Request('')
a = urllib.request.urlopen(req).read()
print(a)
复制代码

 
 
@see 
阅读(23107) | 评论(0) | 转发(0) |
给主人留下些什么吧!~~