Deal with implicitly UTF-16 decoded webpages

[youtube-dl] / youtube_dl / extractor / common.py

diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index 692d828da9ef9739e1b05908e6a9f39259b0940b..6c5d77e583586b266d480fa4c01acf9949cfe3a7 100644 (file)
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -220,6 +220,8 @@ class InfoExtractor(object):
                           webpage_bytes[:1024])
             if m:
                 encoding = m.group(1).decode('ascii')
+            elif webpage_bytes.startswith(b'\xff\xfe'):
+                encoding = 'utf-16'
             else:
                 encoding = 'utf-8'
         if self._downloader.params.get('dump_intermediate_pages', False):