Created Whitelist Plugin c.f. filter_by_upstream (also fixed latter)

README.md

@@ -53,6 +53,7 @@
     - [Mock Api Plugin](#mockrestapiplugin)
     - [Redirect To Custom Server Plugin](#redirecttocustomserverplugin)
     - [Filter By Upstream Host Plugin](#filterbyupstreamhostplugin)
+    - [Whitelist_Upstream_Hosts_Plugin](#whitelistupstreamhostplugin)
     - [Cache Responses Plugin](#cacheresponsesplugin)
     - [Cache By Response Type](#cachebyresponsetype)
     - [Man-In-The-Middle Plugin](#maninthemiddleplugin)
@@ -729,6 +730,12 @@ Traceback (most recent call last):
 ... [redacted] ...
 ... [redacted] ... - access_log:1157 - ::1:49911 - GET None:None/ - None None - 0 bytes
 ```
+### WhitelistUpstreamHostPlugin
+
+Essentially the same as [Filter By Upstream Host Plugin](#filterbyupstreamhostplugin)
+except the list of hosts are whitelisted, all others are dropped as being tea-pots that don't serve coffee.
+
+Can take a comma-separated (no-space) list of domains to construct whitelist. Otherwise The whitelist defaults to datasets.datalad.org,singularity-hub.org (because the author needed singularity to run on workernodes in an HPC setting with no NAT to the outside world). 
 
 ### CacheResponsesPlugin
 

proxy/plugin/__init__.py

@@ -35,6 +35,7 @@
 from .modify_request_header import ModifyRequestHeaderPlugin
 from .redirect_to_custom_server import RedirectToCustomServerPlugin
 from .tls_intercept_conditionally import TlsInterceptConditionallyPlugin
+from .whitelist_upstream_hosts import WhitelistUpstreamHostsPlugin
 
 
 __all__ = [
@@ -57,4 +58,5 @@
     'ProgramNamePlugin',
     'ModifyRequestHeaderPlugin',
     'TlsInterceptConditionallyPlugin',
+    'WhitelistUpstreamHostsPlugin',
 ]

proxy/plugin/filter_by_upstream.py

@@ -22,7 +22,7 @@
     '--filtered-upstream-hosts',
     type=str,
     default='facebook.com,www.facebook.com',
-    help='Default: Blocks Facebook.  Comma separated list of IPv4 and IPv6 addresses.',
+    help='Default: Blocks Facebook.  Comma separated list of fully qualified domain names, e.g. "facebook.com,www.facebook.com".',
 )
 
 
@@ -32,7 +32,7 @@ class FilterByUpstreamHostPlugin(HttpProxyBasePlugin):
     def before_upstream_connection(
             self, request: HttpParser,
     ) -> Optional[HttpParser]:
-        if text_(request.host) in self.flags.filtered_upstream_hosts.split(','):
+        if request.host.decode() in self.flags.filtered_upstream_hosts.split(','):
             raise HttpRequestRejected(
                 status_code=httpStatusCodes.I_AM_A_TEAPOT,
                 reason=b'I\'m a tea pot',

proxy/plugin/whitelist_upstream_hosts.py

@@ -0,0 +1,41 @@
+# -*- coding: utf-8 -*-
+"""
+    proxy.py
+    ~~~~~~~~
+    ⚡⚡⚡ Fast, Lightweight, Pluggable, TLS interception capable proxy server focused on
+    Network monitoring, controls & Application development, testing, debugging.
+
+    :copyright: (c) 2013-present by Abhinav Singh and contributors.
+    :license: BSD, see LICENSE for more details.
+
+    Whitelist Plugin modified from (broken) filter_by_upstream plugin by Mike Jones [email protected]
+
+"""
+from typing import Optional
+
+from ..http import httpStatusCodes
+from ..http.proxy import HttpProxyBasePlugin
+from ..common.flag import flags
+from ..http.parser import HttpParser
+from ..common.utils import text_
+from ..http.exception import HttpRequestRejected
+
+flags.add_argument(
+    '--whitelist-upstream-hosts',
+    type=str,
+    default='datasets.datalad.org,singularity-hub.org,galaxy-dev.mcfe.itservices.manchester.ac.uk',
+    help='Default: Allows Singularity and Datasets.  Comma separated list of domains.',
+)
+
+
+class WhitelistUpstreamHostsPlugin(HttpProxyBasePlugin):
+    """Drop traffic by inspecting upstream host."""
+    def before_upstream_connection(
+            self, request: HttpParser,
+    ) -> Optional[HttpParser]:
+        if not request.host.decode() in self.flags.whitelist_upstream_hosts.split(','):
+            raise HttpRequestRejected(
+                status_code=httpStatusCodes.I_AM_A_TEAPOT,
+                reason=b'I\'m a tea pot cannot conect to '+request.host,
+            )
+        return request