feat: support for setting UA for URL previews

docs/usage/configuration/config_documentation.md

@@ -774,6 +774,17 @@ Example configuration:
 ```yaml
 max_event_delay_duration: 24h
 ```
+---
+### `url_preview_user_agent`
+
+Setting the User-Agent for URL previews.
+
+Defaults to `Synapse (bot; +https://github.com/matrix-org/synapse)`.
+
+Example configuration:
+```yaml
+url_preview_user_agent: "Hello Matrix"
+```
 
 ## Homeserver blocking
 Useful options for Synapse admins.

synapse/config/server.py

@@ -788,6 +788,13 @@ class ServerConfig(Config):
         else:
             self.max_event_delay_ms = None
 
+        self.url_preview_user_agent: str = (
+            config.get("url_preview_user_agent")
+            or "Synapse (bot; +https://github.com/matrix-org/synapse)"
+        )
+        if len(self.url_preview_user_agent.strip()) == 0:
+            raise ConfigError("The 'url_preview_user_agent' must be a valid User-Agent")
+
     def has_tls_listener(self) -> bool:
         return any(listener.is_tls() for listener in self.listeners)
 

synapse/media/url_previewer.py

@@ -168,6 +168,7 @@ class UrlPreviewer:
     ):
         self.clock = hs.get_clock()
         self.filepaths = media_repo.filepaths
+        self.hs = hs
         self.max_spider_size = hs.config.media.max_spider_size
         self.server_name = hs.hostname
         self.store = hs.get_datastores().main
@@ -464,9 +465,7 @@ class UrlPreviewer:
                     # Use a custom user agent for the preview because some sites will only return
                     # Open Graph metadata to crawler user agents. Omit the Synapse version
                     # string to avoid leaking information.
-                    b"User-Agent": [
+                    b"User-Agent": [self.hs.config.server.url_preview_user_agent],
-                        "Synapse (bot; +https://github.com/matrix-org/synapse)"
-                    ],
                 },
                 is_allowed_content_type=_is_previewable,
             )