From 55d926999cffee893cb4951890a33985beaf70ba Mon Sep 17 00:00:00 2001
From: Tulir Asokan <tulir@maunium.net>
Date: Wed, 18 Nov 2020 01:21:48 +0200
Subject: [PATCH] Fix URL previewer user agent to fix Twitter previews

---
 synapse/http/client.py                        |  3 ++-
 synapse/rest/media/v1/preview_url_resource.py | 13 +------------
 2 files changed, 3 insertions(+), 13 deletions(-)

diff --git a/synapse/http/client.py b/synapse/http/client.py
index f40936880..24ea92e28 100644
--- a/synapse/http/client.py
+++ b/synapse/http/client.py
@@ -232,6 +232,7 @@ class SimpleHttpClient:
         ip_blacklist=None,
         http_proxy=None,
         https_proxy=None,
+        user_agent=None,
     ):
         """
         Args:
@@ -250,7 +251,7 @@ class SimpleHttpClient:
         self._ip_blacklist = ip_blacklist
         self._extra_treq_args = treq_args
 
-        self.user_agent = hs.version_string
+        self.user_agent = user_agent or hs.version_string
         self.clock = hs.get_clock()
         if hs.config.user_agent_suffix:
             self.user_agent = "%s %s" % (self.user_agent, hs.config.user_agent_suffix)
diff --git a/synapse/rest/media/v1/preview_url_resource.py b/synapse/rest/media/v1/preview_url_resource.py
index dce6c4d16..8eff2f7b3 100644
--- a/synapse/rest/media/v1/preview_url_resource.py
+++ b/synapse/rest/media/v1/preview_url_resource.py
@@ -60,18 +60,6 @@ ONE_HOUR = 60 * 60 * 1000
 
 # A map of globs to API endpoints.
 _oembed_globs = {
-    # Twitter.
-    "https://publish.twitter.com/oembed": [
-        "https://twitter.com/*/status/*",
-        "https://*.twitter.com/*/status/*",
-        "https://twitter.com/*/moments/*",
-        "https://*.twitter.com/*/moments/*",
-        # Include the HTTP versions too.
-        "http://twitter.com/*/status/*",
-        "http://*.twitter.com/*/status/*",
-        "http://twitter.com/*/moments/*",
-        "http://*.twitter.com/*/moments/*",
-    ],
 }
 # Convert the globs to regular expressions.
 _oembed_patterns = {}
@@ -135,6 +123,7 @@ class PreviewUrlResource(DirectServeJsonResource):
             ip_blacklist=hs.config.url_preview_ip_range_blacklist,
             http_proxy=os.getenvb(b"http_proxy"),
             https_proxy=os.getenvb(b"HTTPS_PROXY"),
+            user_agent=f"{hs.version_string} UrlPreviewBot"
         )
         self.media_repo = media_repo
         self.primary_base_path = media_repo.primary_base_path