summary refs log tree commit diff
path: root/synapse/rest/media
diff options
context:
space:
mode:
authorPatrick Cloke <clokep@users.noreply.github.com>2021-09-08 07:17:52 -0400
committerGitHub <noreply@github.com>2021-09-08 07:17:52 -0400
commit580a15e039f47c2a0038754bba9d96883866a9f2 (patch)
tree0e6d081345a440d607658c6a15f5374661a5099c /synapse/rest/media
parentAdd some assertions about outliers (#10773) (diff)
downloadsynapse-580a15e039f47c2a0038754bba9d96883866a9f2.tar.xz
Request JSON for oEmbed requests (and ignore XML only providers). (#10759)
This adds the format to the request arguments / URL to
ensure that JSON data is returned (which is all that
Synapse supports).

This also adds additional error checking / filtering to the
configuration file to ignore XML-only providers.
Diffstat (limited to 'synapse/rest/media')
-rw-r--r--synapse/rest/media/v1/oembed.py26
1 files changed, 23 insertions, 3 deletions
diff --git a/synapse/rest/media/v1/oembed.py b/synapse/rest/media/v1/oembed.py
index afe41823e4..2e6706dbfa 100644
--- a/synapse/rest/media/v1/oembed.py
+++ b/synapse/rest/media/v1/oembed.py
@@ -49,8 +49,24 @@ class OEmbedProvider:
     def __init__(self, hs: "HomeServer", client: SimpleHttpClient):
         self._oembed_patterns = {}
         for oembed_endpoint in hs.config.oembed.oembed_patterns:
+            api_endpoint = oembed_endpoint.api_endpoint
+
+            # Only JSON is supported at the moment. This could be declared in
+            # the formats field. Otherwise, if the endpoint ends in .xml assume
+            # it doesn't support JSON.
+            if (
+                oembed_endpoint.formats is not None
+                and "json" not in oembed_endpoint.formats
+            ) or api_endpoint.endswith(".xml"):
+                logger.info(
+                    "Ignoring oEmbed endpoint due to not supporting JSON: %s",
+                    api_endpoint,
+                )
+                continue
+
+            # Iterate through each URL pattern and point it to the endpoint.
             for pattern in oembed_endpoint.url_patterns:
-                self._oembed_patterns[pattern] = oembed_endpoint.api_endpoint
+                self._oembed_patterns[pattern] = api_endpoint
         self._client = client
 
     def get_oembed_url(self, url: str) -> Optional[str]:
@@ -86,11 +102,15 @@ class OEmbedProvider:
         """
         try:
             logger.debug("Trying to get oEmbed content for url '%s'", url)
+
+            # Note that only the JSON format is supported, some endpoints want
+            # this in the URL, others want it as an argument.
+            endpoint = endpoint.replace("{format}", "json")
+
             result = await self._client.get_json(
                 endpoint,
                 # TODO Specify max height / width.
-                # Note that only the JSON format is supported.
-                args={"url": url},
+                args={"url": url, "format": "json"},
             )
 
             # Ensure there's a version of 1.0.