python如何獲得一個url地址對應的跳轉后的最終網址

問題描述

在python中，如何獲取短鏈對應最終網址，現在有很多淘寶短鏈，我需要獲取短鏈跳到的最終網址，這個有什么好辦法嗎？有的是302 有的是直接在網頁用js進行跳轉，，這些如何獲取

問題解答

用selenium+phantonjs...

http://stackoverflow.com/ques...

#!/usr/bin/python2.7from twisted.internet import reactorfrom twisted.internet.defer import Deferred, DeferredList, DeferredLockfrom twisted.internet.defer import inlineCallbacksfrom twisted.web.client import Agent, HTTPConnectionPoolfrom twisted.web.http_headers import Headersfrom pprint import pprintfrom collections import defaultdictfrom urlparse import urlparsefrom random import randrangeimport fileinputpool = HTTPConnectionPool(reactor)pool.maxPersistentPerHost = 16agent = Agent(reactor, pool)locks = defaultdict(DeferredLock)locations = {}def getLock(url, simultaneous = 1): return locks[urlparse(url).netloc, randrange(simultaneous)]@inlineCallbacksdef getMapping(url): # Limit ourselves to 4 simultaneous connections per host # Tweak this as desired, but make sure that it no larger than # pool.maxPersistentPerHost lock = getLock(url,4) yield lock.acquire() try:resp = yield agent.request(’HEAD’, url)locations[url] = resp.headers.getRawHeaders(’location’,[None])[0] except Exception as e:locations[url] = str(e) finally: lock.release()

而且可以試試pip包

https://pypi.python.org/pypi/...

from urlunshort import resolveresolve('http://bit.ly/qlKaI') 結果 ’http://bitbucket.org/runeh/urlunshort/’