Close #19494: add urrlib.request.HTTPBasicPriorAuthHandler

This auth handler adds the Authorization header to the first
HTTP request rather than waiting for a HTTP 401 Unauthorized
response from the server as the default HTTPBasicAuthHandler
does.

This allows working with websites like https://api.github.com which do
not follow the strict interpretation of RFC, but more the dicta in the
end of section 2 of RFC 2617:

    > A client MAY preemptively send the corresponding Authorization
    > header with requests for resources in that space without receipt
    > of another challenge from the server.  Similarly, when a client
    > sends a request to a proxy, it may reuse a userid and password in
    > the Proxy-Authorization header field without receiving another
    > challenge from the proxy server. See section 4 for security
    > considerations associated with Basic authentication.

Patch by Matej Cepl.

5 files changed, 53 insertions, 0 deletions

diff --git a/Doc/library/urllib.request.rst b/Doc/library/urllib.request.rst
index f420259..dca56d6 100644
--- a/Doc/library/urllib.request.rst
+++ b/Doc/library/urllib.request.rst
@@ -304,6 +304,17 @@ The following classes are provided:
    presented with a wrong Authentication scheme.
 
 
+.. class:: HTTPBasicPriorAuthHandler(password_mgr=None)
+
+   A variant of :class:`HTTPBasicAuthHandler` which automatically sends
+   authorization credentials with the first request, rather than waiting to
+   first receive a HTTP 401 "Unauthorised" error response. This allows
+   authentication to sites that don't provide a 401 response when receiving
+   a request without an Authorization header. Aside from this difference,
+   this behaves exactly as :class:`HTTPBasicAuthHandler`.
+
+   .. versionadded:: 3.5
+
 .. class:: ProxyBasicAuthHandler(password_mgr=None)
 
    Handle authentication with the proxy. *password_mgr*, if given, should be
diff --git a/Doc/whatsnew/3.5.rst b/Doc/whatsnew/3.5.rst
index 502ac44..e90f5fa 100644
--- a/Doc/whatsnew/3.5.rst
+++ b/Doc/whatsnew/3.5.rst
@@ -297,6 +297,15 @@ time
 * The :func:`time.monotonic` function is now always available.  (Contributed by
   Victor Stinner in :issue:`22043`.)
 
+time
+----
+
+* A new :class:`urllib.request.HTTPBasicPriorAuthHandler` allows HTTP Basic
+  Authentication credentials to be sent unconditionally with the first HTTP
+  request, rather than waiting for a HTTP 401 Unauthorized response from the
+  server.
+  (Contributed by Matej Cepl in :issue:`19494`.)
+
 wsgiref
 -------
 
diff --git a/Lib/test/test_urllib2.py b/Lib/test/test_urllib2.py
index 9ea39a4..823890e 100644
--- a/Lib/test/test_urllib2.py
+++ b/Lib/test/test_urllib2.py
@@ -1422,6 +1422,21 @@ class HandlerTests(unittest.TestCase):
             handler.do_open(conn, req)
         self.assertTrue(conn.fakesock.closed, "Connection not closed")
 
+    def test_auth_prior_handler(self):
+        pwd_manager = MockPasswordManager()
+        pwd_manager.add_password(None, 'https://example.com',
+                                 'somebody', 'verysecret')
+        auth_prior_handler = urllib.request.HTTPBasicPriorAuthHandler(
+            pwd_manager)
+        http_hand = MockHTTPSHandler()
+
+        opener = OpenerDirector()
+        opener.add_handler(http_hand)
+        opener.add_handler(auth_prior_handler)
+
+        req = Request("https://example.com")
+        opener.open(req)
+        self.assertNotIn('Authorization', http_hand.httpconn.req_headers)
 
 class MiscTests(unittest.TestCase):
 
diff --git a/Lib/urllib/request.py b/Lib/urllib/request.py
index e0c8116..36ae1ef 100644
--- a/Lib/urllib/request.py
+++ b/Lib/urllib/request.py
@@ -916,6 +916,21 @@ class ProxyBasicAuthHandler(AbstractBasicAuthHandler, BaseHandler):
         return response
 
 
+class HTTPBasicPriorAuthHandler(HTTPBasicAuthHandler):
+    handler_order = 400
+
+    def http_request(self, req):
+        if not req.has_header('Authorization'):
+            user, passwd = self.passwd.find_user_password(None, req.host)
+            credentials = '{0}:{1}'.format(user, passwd).encode()
+            auth_str = base64.standard_b64encode(credentials).decode()
+            req.add_unredirected_header('Authorization',
+                                        'Basic {}'.format(auth_str.strip()))
+        return req
+
+    https_request = http_request
+
+
 # Return n random bytes.
 _randombytes = os.urandom
 
diff --git a/Misc/NEWS b/Misc/NEWS
index 431015a..1c72d96 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -183,6 +183,9 @@ Core and Builtins
 Library
 -------
 
+- Issue #19494: Added urllib.request.HTTPBasicPriorAuthHandler. Patch by
+  Matej Cepl.
+
 - Issue #22578: Added attributes to the re.error class.
 
 - Issue #12728: Different Unicode characters having the same uppercase but