Fix IP URL previews on Python 3

.coveragerc

@@ -9,4 +9,3 @@ source=
 
 [report]
 precision = 2
-ignore_errors = True

.gitignore

@@ -57,3 +57,4 @@ env/
 
 .vscode/
 .ropeproject/
+.coverage.*

changelog.d/4215.misc

@@ -0,0 +1 @@
+Getting URL previews of IP addresses no longer fails on Python 3.

synapse/http/client.py

@@ -26,13 +26,10 @@
 from OpenSSL import SSL
 from OpenSSL.SSL import VERIFY_NONE
 from twisted.internet import defer, protocol, reactor, ssl
-from twisted.internet.endpoints import HostnameEndpoint, wrapClientTLS
 from twisted.web._newclient import ResponseDone
 from twisted.web.client import (
+    URI,
     Agent,
-    BrowserLikeRedirectAgent,
-    ContentDecoderAgent,
-    GzipDecoder,
     HTTPConnectionPool,
     PartialDownloadError,
     readBody,
@@ -42,7 +39,6 @@
 
 from synapse.api.errors import Codes, HttpResponseException, SynapseError
 from synapse.http import cancelled_to_request_timed_out_error, redact_uri
-from synapse.http.endpoint import SpiderEndpoint
 from synapse.util.async_helpers import timeout_deferred
 from synapse.util.caches import CACHE_SIZE_FACTOR
 from synapse.util.logcontext import make_deferred_yieldable
@@ -59,10 +55,15 @@ class SimpleHttpClient(object):
     A simple, no-frills HTTP client with methods that wrap up common ways of
     using HTTP in Matrix
     """
-    def __init__(self, hs):
+
+    def __init__(self, hs, treq_args={}, whitelist=None, blacklist=None, _treq=treq):
         self.hs = hs
 
         pool = HTTPConnectionPool(reactor)
+        self._treq = _treq
+        self._extra_treq_args = treq_args
+        self.whitelist = whitelist
+        self.blacklist = blacklist
 
         # the pusher makes lots of concurrent SSL connections to sygnal, and
         # tends to do so in batches, so we need to allow the pool to keep lots
@@ -81,13 +82,30 @@ def __init__(self, hs):
         )
         self.user_agent = hs.version_string
         self.clock = hs.get_clock()
+        self.reactor = hs.get_reactor()
         if hs.config.user_agent_suffix:
             self.user_agent = "%s %s" % (self.user_agent, hs.config.user_agent_suffix,)
 
         self.user_agent = self.user_agent.encode('ascii')
 
     @defer.inlineCallbacks
     def request(self, method, uri, data=b'', headers=None):
+
+        # Check our IP whitelists/blacklists before making the request.
+        if self.blacklist:
+            split_uri = URI.fromBytes(uri.encode('utf8'))
+            address = yield self.reactor.resolve(split_uri.host)
+
+            from netaddr import IPAddress
+            ip_address = IPAddress(address)
+
+            if ip_address in self.blacklist:
+                if self.whitelist is None or ip_address not in self.whitelist:
+                    raise SynapseError(
+                        403, "IP address blocked by IP blacklist entry",
+                        Codes.UNKNOWN
+                    )
+
         # A small wrapper around self.agent.request() so we can easily attach
         # counters to it
         outgoing_requests_counter.labels(method).inc()
@@ -96,8 +114,13 @@ def request(self, method, uri, data=b'', headers=None):
         logger.info("Sending request %s %s", method, redact_uri(uri))
 
         try:
-            request_deferred = treq.request(
-                method, uri, agent=self.agent, data=data, headers=headers
+            request_deferred = self._treq.request(
+                method,
+                uri,
+                agent=self.agent,
+                data=data,
+                headers=headers,
+                **self._extra_treq_args
             )
             request_deferred = timeout_deferred(
                 request_deferred, 60, self.hs.get_reactor(),
@@ -463,57 +486,6 @@ def post_urlencoded_get_raw(self, url, args={}):
             defer.returnValue(e.response)
 
 
-class SpiderEndpointFactory(object):
-    def __init__(self, hs):
-        self.blacklist = hs.config.url_preview_ip_range_blacklist
-        self.whitelist = hs.config.url_preview_ip_range_whitelist
-        self.policyForHTTPS = hs.get_http_client_context_factory()
-
-    def endpointForURI(self, uri):
-        logger.info("Getting endpoint for %s", uri.toBytes())
-
-        if uri.scheme == b"http":
-            endpoint_factory = HostnameEndpoint
-        elif uri.scheme == b"https":
-            tlsCreator = self.policyForHTTPS.creatorForNetloc(uri.host, uri.port)
-
-            def endpoint_factory(reactor, host, port, **kw):
-                return wrapClientTLS(
-                    tlsCreator,
-                    HostnameEndpoint(reactor, host, port, **kw))
-        else:
-            logger.warn("Can't get endpoint for unrecognised scheme %s", uri.scheme)
-            return None
-        return SpiderEndpoint(
-            reactor, uri.host, uri.port, self.blacklist, self.whitelist,
-            endpoint=endpoint_factory, endpoint_kw_args=dict(timeout=15),
-        )
-
-
-class SpiderHttpClient(SimpleHttpClient):
-    """
-    Separate HTTP client for spidering arbitrary URLs.
-    Special in that it follows retries and has a UA that looks
-    like a browser.
-
-    used by the preview_url endpoint in the content repo.
-    """
-    def __init__(self, hs):
-        SimpleHttpClient.__init__(self, hs)
-        # clobber the base class's agent and UA:
-        self.agent = ContentDecoderAgent(
-            BrowserLikeRedirectAgent(
-                Agent.usingEndpointFactory(
-                    reactor,
-                    SpiderEndpointFactory(hs)
-                )
-            ), [(b'gzip', GzipDecoder)]
-        )
-        # We could look like Chrome:
-        # self.user_agent = ("Mozilla/5.0 (%s) (KHTML, like Gecko)
-        #                   Chrome Safari" % hs.version_string)
-
-
 def encode_urlencode_args(args):
     return {k: encode_urlencode_arg(v) for k, v in args.items()}
 

synapse/http/endpoint.py

@@ -218,41 +218,6 @@ def update_request_time(res):
         return d
 
 
-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, whitelist,
-                 endpoint=HostnameEndpoint, endpoint_kw_args={}):
-        self.reactor = reactor
-        self.host = host
-        self.port = port
-        self.blacklist = blacklist
-        self.whitelist = whitelist
-        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
-        ip_address = IPAddress(address)
-
-        if ip_address in self.blacklist:
-            if self.whitelist is None or ip_address not in self.whitelist:
-                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

synapse/rest/media/v1/preview_url_resource.py

@@ -35,7 +35,7 @@
 from twisted.web.server import NOT_DONE_YET
 
 from synapse.api.errors import Codes, SynapseError
-from synapse.http.client import SpiderHttpClient
+from synapse.http.client import SimpleHttpClient
 from synapse.http.server import (
     respond_with_json,
     respond_with_json_bytes,
@@ -69,7 +69,12 @@ def __init__(self, hs, media_repo, media_storage):
         self.max_spider_size = hs.config.max_spider_size
         self.server_name = hs.hostname
         self.store = hs.get_datastore()
-        self.client = SpiderHttpClient(hs)
+        self.client = SimpleHttpClient(
+            hs,
+            treq_args={"browser_like_redirects": True},
+            whitelist=hs.config.url_preview_ip_range_whitelist,
+            blacklist=hs.config.url_preview_ip_range_blacklist,
+        )
         self.media_repo = media_repo
         self.primary_base_path = media_repo.primary_base_path
         self.media_storage = media_storage
@@ -318,6 +323,9 @@ def _download_url(self, url, user):
                 length, headers, uri, code = yield self.client.get_file(
                     url, output_stream=f, max_size=self.max_spider_size,
                 )
+            except SynapseError:
+                # Pass SynapseErrors through directly.
+                raise
             except Exception as e:
                 # FIXME: pass through 404s and other error messages nicely
                 logger.warn("Error downloading %s: %r", url, e)