[facebook] decode surrogate pairs in metadata values (#6599)

2024-12-12 20:20:30 +01:00
parent a33065be86
commit 85a37ca039
2 changed files with 11 additions and 1 deletions
--- a/gallery_dl/extractor/facebook.py
+++ b/gallery_dl/extractor/facebook.py
@@ -40,7 +40,8 @@ class FacebookExtractor(Extractor):
    @staticmethod
    def decode_all(txt):
        return text.unescape(
-            txt.encode("utf-8").decode("unicode_escape")
+            txt.encode().decode("unicode_escape")
+            .encode("utf_16", "surrogatepass").decode("utf_16")
        ).replace("\\/", "/")

    @staticmethod