urllib的实现---timeout,获取http响应码，重定向，proxy的设置

Posted 2020-10-17 成长日记

1.Timeout设置超时

只能修改Socket设置全局Timeout

#! /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(‘http://www.python.org/‘)

a = urllib.request.urlopen(req).read()

print(a)

2.获取HTTP响应码

#! /usr/bin/env python3

import urllib.request

req = urllib.request.Request(‘http://python.org/‘)

try:  

　　urllib.request.urlopen(req)

except urllib.error.HTTPError as e:

　　print(e.code)

print(e.read().decode("utf8"))

3、异常处理1

 1 #! /usr/bin/env python3
 2 
 3 from urllib.request import Request, urlopen
 4 
 5 from urllib.error import URLError, HTTPError
 6 
 7 req = Request(‘http://www.python.org/‘)
 8 
 9 try:
10 
11 　　response = urlopen(req)
12 
13 except HTTPError as e:
14 
15 　　print(‘The (www.python.org)server couldn‘t fulfill the request.‘)
16 
17 　　print(‘Error code: ‘, e.code)
18 
19 except URLError as e:
20 
21 　　print(‘We failed to reach a server.‘)
22 
23 　　print(‘Reason: ‘, e.reason)
24 
25 else:
26 
27 　　print("good!")
28 
29 　　print(response.read().decode("utf8")) 

 

4、异常处理2

 1 #! /usr/bin/env python3
 2 
 3 from urllib.request import Request, urlopen
 4 
 5 from urllib.error import  URLError
 6 
 7 req = Request("http://www.python.org/")
 8 
 9 try:
10 
11 　　response = urlopen(req)
12 
13 except URLError as e:
14 
15 　　if hasattr(e, ‘reason‘):
16 
17 　　　　print(‘We failed to reach a server.‘)
18 
19 　　　　print(‘Reason: ‘, e.reason)
20 
21 　　elif hasattr(e, ‘code‘):
22 
23 　　　　print(‘The server couldn‘t fulfill the request.‘)
24 
25 　　　　print(‘Error code: ‘, e.code)
26 
27 else:  print("good!")
28 
29 　　print(response.read().decode("utf8"))

5.重定向

import urllib.request
import socket
url = ‘https://www.baidu.com‘
response =urllib.request.urlopen(url)
isRediercted = response.geturl() == "https：//www.baidu.com"

6.代理设置

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("http://www.python.org/").read().decode("utf8")

print(a)