我必须使用 urllib2 实现一个仅获取标头的函数(不执行 GET 或 POST)。这是我的功能:
def getheadersonly(url, redirections = True):
if not redirections:
class MyHTTPRedirectHandler(urllib2.HTTPRedirectHandler):
def http_error_302(self, req, fp, code, msg, headers):
return urllib2.HTTPRedirectHandler.http_error_302(self, req, fp, code, msg, headers)
http_error_301 = http_error_303 = http_error_307 = http_error_302
cookieprocessor = urllib2.HTTPCookieProcessor()
opener = urllib2.build_opener(MyHTTPRedirectHandler, cookieprocessor)
urllib2.install_opener(opener)
class HeadRequest(urllib2.Request):
def get_method(self):
return "HEAD"
info = {}
info['headers'] = dict(urllib2.urlopen(HeadRequest(url)).info())
info['finalurl'] = urllib2.urlopen(HeadRequest(url)).geturl()
return info
使用答案中的代码this https://stackoverflow.com/a/2070916/842837 and this https://stackoverflow.com/a/554580/842837。然而这is doing即使标志是重定向False
。我尝试使用以下代码:
print getheadersonly("http://ms.com", redirections = False)['finalurl']
print getheadersonly("http://ms.com")['finalurl']
在这两种情况下,它都给予了morganstanley.com。这里有什么问题吗?