說明:python的urllib2獲取網頁(urlopen)會自動重定向(301,302)。但是,有時候我們需要獲取302,301頁面的狀態信息。就必須獲取到轉向前的調試信息。
下面代碼將可以做到避免302重定向到新的網頁
#!/usr/bin/python# -*- coding: utf-8 -*-#encoding=utf-8#Filename:states_code.py import urllib2 class RedirctHandler(urllib2.HTTPRedirectHandler): """docstring for RedirctHandler""" def http_error_301(self, req, fp, code, msg, headers): pass def http_error_302(self, req, fp, code, msg, headers): pass def getUnRedirectUrl(url,timeout=10): req = urllib2.Request(url) debug_handler = urllib2.HTTPHandler(debuglevel = 1) opener = urllib2.build_opener(debug_handler, RedirctHandler) html = None response = None try: response = opener.open(url,timeout=timeout) html = response.read() except urllib2.URLError as e: if hasattr(e, 'code'): error_info = e.code elif hasattr(e, 'reason'): error_info = e.reason finally: if response: response.close() if html: return html else: return error_info html = getUnRedirectUrl('http://jb51.net')print html
新聞熱點
疑難解答