Move HTML parsing to a separate file for URL previews. (#11566)

* Splits the logic for parsing HTML from the resource handling code.
* Fix a circular import in the oEmbed code (which uses the HTML parsing code).
* Renames some of the HTML parsing methods to:
  * Make it clear which methods are "internal" to the module.
  * Clarify what the methods do.

1 files changed, 2 insertions, 3 deletions

diff --git a/synapse/rest/media/v1/oembed.py b/synapse/rest/media/v1/oembed.py

index 2a59552c20..cce1527ed9 100644
--- a/synapse/rest/media/v1/oembed.py
+++ b/synapse/rest/media/v1/oembed.py
@@ -17,6 +17,7 @@ from typing import TYPE_CHECKING, List, Optional
 
 import attr
 
+from synapse.rest.media.v1.preview_html import parse_html_description
 from synapse.types import JsonDict
 from synapse.util import json_decoder
 
@@ -245,8 +246,6 @@ def calc_description_and_urls(open_graph_response: JsonDict, html_body: str) ->
     if video_urls:
         open_graph_response["og:video"] = video_urls[0]
 
-    from synapse.rest.media.v1.preview_url_resource import _calc_description
-
-    description = _calc_description(tree)
+    description = parse_html_description(tree)
     if description:
         open_graph_response["og:description"] = description