Add url_preview_enabled config option to turn on/off preview_url endpoint. defaults to off.

Add url_preview_ip_range_blacklist to let admins specify internal IP ranges that must not be spidered.
Add url_preview_url_blacklist to let admins specify URL patterns that must not be spidered.
Implement a custom SpiderEndpoint and associated support classes to implement url_preview_ip_range_blacklist
Add commentary and generally address PR feedback

2 files changed, 72 insertions, 7 deletions

diff --git a/synapse/http/client.py b/synapse/http/client.py
index 442b4bb73d..3b8ffcd3ef 100644
--- a/synapse/http/client.py
+++ b/synapse/http/client.py
@@ -20,10 +20,12 @@ from synapse.api.errors import (
 )
 from synapse.util.logcontext import preserve_context_over_fn
 import synapse.metrics
+from synapse.http.endpoint import SpiderEndpoint
 
 from canonicaljson import encode_canonical_json
 
 from twisted.internet import defer, reactor, ssl, protocol
+from twisted.internet.endpoints import SSL4ClientEndpoint, TCP4ClientEndpoint
 from twisted.web.client import (
     BrowserLikeRedirectAgent, ContentDecoderAgent, GzipDecoder, Agent,
     readBody, FileBodyProducer, PartialDownloadError,
@@ -364,6 +366,35 @@ class CaptchaServerHttpClient(SimpleHttpClient):
             defer.returnValue(e.response)
 
 
+class SpiderEndpointFactory(object):
+    def __init__(self, hs):
+        self.blacklist = hs.config.url_preview_ip_range_blacklist
+        self.policyForHTTPS = hs.get_http_client_context_factory()
+
+    def endpointForURI(self, uri):
+        logger.info("Getting endpoint for %s", uri.toBytes())
+        if uri.scheme == "http":
+            return SpiderEndpoint(
+                reactor, uri.host, uri.port, self.blacklist,
+                endpoint=TCP4ClientEndpoint,
+                endpoint_kw_args={
+                    'timeout': 15
+                },
+            )
+        elif uri.scheme == "https":
+            tlsPolicy = self.policyForHTTPS.creatorForNetloc(uri.host, uri.port)
+            return SpiderEndpoint(
+                reactor, uri.host, uri.port, self.blacklist,
+                endpoint=SSL4ClientEndpoint,
+                endpoint_kw_args={
+                    'sslContextFactory': tlsPolicy,
+                    'timeout': 15
+                },
+            )
+        else:
+            logger.warn("Can't get endpoint for unrecognised scheme %s", uri.scheme)
+
+
 class SpiderHttpClient(SimpleHttpClient):
     """
     Separate HTTP client for spidering arbitrary URLs.
@@ -375,11 +406,14 @@ class SpiderHttpClient(SimpleHttpClient):
     def __init__(self, hs):
         SimpleHttpClient.__init__(self, hs)
         # clobber the base class's agent and UA:
-        self.agent = ContentDecoderAgent(BrowserLikeRedirectAgent(Agent(
-            reactor,
-            connectTimeout=15,
-            contextFactory=hs.get_http_client_context_factory()
-        )), [('gzip', GzipDecoder)])
+        self.agent = ContentDecoderAgent(
+            BrowserLikeRedirectAgent(
+                Agent.usingEndpointFactory(
+                    reactor,
+                    SpiderEndpointFactory(hs)
+                )
+            ), [('gzip', GzipDecoder)]
+        )
         # We could look like Chrome:
         # self.user_agent = ("Mozilla/5.0 (%s) (KHTML, like Gecko)
         #                   Chrome Safari" % hs.version_string)
diff --git a/synapse/http/endpoint.py b/synapse/http/endpoint.py
index 4775f6707d..de5c762f50 100644
--- a/synapse/http/endpoint.py
+++ b/synapse/http/endpoint.py
@@ -74,6 +74,37 @@ def matrix_federation_endpoint(reactor, destination, ssl_context_factory=None,
         return transport_endpoint(reactor, domain, port, **endpoint_kw_args)
 
 
+class SpiderEndpoint(object):
+    """An endpoint which refuses to connect to blacklisted IP addresses
+    Implements twisted.internet.interfaces.IStreamClientEndpoint.
+    """
+    def __init__(self, reactor, host, port, blacklist,
+                 endpoint=TCP4ClientEndpoint, endpoint_kw_args={}):
+        self.reactor = reactor
+        self.host = host
+        self.port = port
+        self.blacklist = blacklist
+        self.endpoint = endpoint
+        self.endpoint_kw_args = endpoint_kw_args
+
+    @defer.inlineCallbacks
+    def connect(self, protocolFactory):
+        address = yield self.reactor.resolve(self.host)
+
+        from netaddr import IPAddress
+        if IPAddress(address) in self.blacklist:
+            raise ConnectError(
+                "Refusing to spider blacklisted IP address %s" % address
+            )
+
+        logger.info("Connecting to %s:%s", address, self.port)
+        endpoint = self.endpoint(
+            self.reactor, address, self.port, **self.endpoint_kw_args
+        )
+        connection = yield endpoint.connect(protocolFactory)
+        defer.returnValue(connection)
+
+
 class SRVClientEndpoint(object):
     """An endpoint which looks up SRV records for a service.
     Cycles through the list of servers starting with each call to connect
@@ -118,7 +149,7 @@ class SRVClientEndpoint(object):
                 return self.default_server
             else:
                 raise ConnectError(
-                    "Not server available for %s", self.service_name
+                    "Not server available for %s" % self.service_name
                 )
 
         min_priority = self.servers[0].priority
@@ -166,7 +197,7 @@ def resolve_service(service_name, dns_client=client, cache=SERVER_CACHE):
                 and answers[0].type == dns.SRV
                 and answers[0].payload
                 and answers[0].payload.target == dns.Name('.')):
-            raise ConnectError("Service %s unavailable", service_name)
+            raise ConnectError("Service %s unavailable" % service_name)
 
         for answer in answers:
             if answer.type != dns.SRV or not answer.payload: