[utils] is_html: Handle double BOM

Closes #2885
2025-10-30 22:25:19 +00:00 · 2022-05-18 06:42:43 +05:30
parent aedaa455d9
commit 80e8493ee7
2 changed files with 21 additions and 7 deletions
--- a/yt_dlp/utils.py
+++ b/yt_dlp/utils.py
@@ -3290,14 +3290,13 @@ def is_html(first_bytes):
        (b'\xff\xfe', 'utf-16-le'),
        (b'\xfe\xff', 'utf-16-be'),
    ]
-    for bom, enc in BOMS:
-        if first_bytes.startswith(bom):
-            s = first_bytes[len(bom):].decode(enc, 'replace')
-            break
-    else:
-        s = first_bytes.decode('utf-8', 'replace')

-    return re.match(r'^\s*<', s)
+    encoding = 'utf-8'
+    for bom, enc in BOMS:
+        while first_bytes.startswith(bom):
+            encoding, first_bytes = enc, first_bytes[len(bom):]
+
+    return re.match(r'^\s*<', first_bytes.decode(encoding, 'replace'))


 def determine_protocol(info_dict):