Question

我有一个所有重定向到其他网址的网址列表。我想使用python获取重定向网址的列表，想知道最好的方法去做这个吗？

一个例子可能是：http://apple.co/1ka9kIX让苹果公司

Answer 1

import urllib2
import httplib

class SmartRedirectHandler(urllib2.HTTPRedirectHandler):
    """
    Stolen from http://www.diveintopython.net/http_web_services/redirects.html
    Originally defined in openanything.py

    """
    def http_error_301(self, req, fp, code, msg, headers):  
        result = urllib2.HTTPRedirectHandler.http_error_301(
            self, req, fp, code, msg, headers)              
        result.status = code
        return result                                       

    def http_error_302(self, req, fp, code, msg, headers):
        result = urllib2.HTTPRedirectHandler.http_error_302(
            self, req, fp, code, msg, headers)              
        result.status = code                                
        return result

inputURLs = ['http://apple.co/1ka9kIX', 'http://fb.com']
httplib.HTTPConnection.debuglevel = 1
opener = urllib2.build_opener(SmartRedirectHandler())

getRedirect = lambda url: opener.open(urllib2.Request(url)).url

print map(getRedirect, inputURLs)

Answer 2

您应该使用urllib2和httplib，代码如下：

import httplib
import urllib2

def get_request_direct(url):  
    httplib.HTTPConnection.debuglevel = 1  
    req = urllib2.Request(url)  
    req.add_header("Accept", "text/html,*/*")  
    req.add_header("Connection", "Keep-Alive")  
    op = urllib2.build_opener()  
    f = op.open(req)  
    return f.url  

# if your url not start `http` or `https`, please add it.
>>> print get_request_direct('http://apple.co/1ka9kIX')
http://www.apple.com/

获取重定向网址列表

2 个答案: