Merge branch 'master' of https://github.com/yt-dlp/yt-dlp into ytdlp

* 'master' of https://github.com/yt-dlp/yt-dlp: [GlomexEmbed] Avoid large match objects
ytdl-patched · Jan 30, 2022 · ea0dd9d · ea0dd9d
2 parents a7100a9 + 19afd9e
commit ea0dd9d
Showing 1 changed file with 7 additions and 2 deletions.
diff --git a/yt_dlp/extractor/glomex.py b/yt_dlp/extractor/glomex.py
@@ -198,8 +198,13 @@ def _extract_urls(cls, webpage, origin_url):
             )+</script>
         )''' % {'quot_re': r'["\']', 'url_re': VALID_SRC}
 
-        for mobj in re.finditer(EMBED_RE, webpage):
-            mdict = mobj.groupdict()
+        for mtup in re.findall(EMBED_RE, webpage):
+            # re.finditer causes a memory spike. See https://github.com/yt-dlp/yt-dlp/issues/2512
+            mdict = dict(zip((
+                'url', '_',
+                'html_tag', '_', 'integration_html', '_', 'id_html', '_', 'glomex_player',
+                'script_tag', '_', '_', 'integration_js', '_', 'id_js',
+            ), mtup))
             if mdict.get('url'):
                 url = unescapeHTML(mdict['url'])
                 if not cls.suitable(url):