[YoutubeDL] urlopen: disable the 'file:' protocol (#8227)

If someone is running youtube-dl on a server to deliver files, the user could input 'file:///some/important/file' and youtube-dl would save that file as a video giving access to sensitive information to the user.
'file:' urls can be filtered, but the user can use an URL to a crafted m3u8 manifest like:

    #EXTM3U
    #EXT-X-MEDIA-SEQUENCE:0
    #EXTINF:10.0
    file:///etc/passwd
    #EXT-X-ENDLIST

With this patch 'file:' URLs raise URLError like for unknown protocols.

2 files changed, 14 insertions, 3 deletions

diff --git a/test/test_YoutubeDL.py b/test/test_YoutubeDL.py
index 0388c0bf3..0caa43843 100644
--- a/test/test_YoutubeDL.py
+++ b/test/test_YoutubeDL.py
@@ -12,7 +12,7 @@ import copy
 
 from test.helper import FakeYDL, assertRegexpMatches
 from youtube_dl import YoutubeDL
-from youtube_dl.compat import compat_str
+from youtube_dl.compat import compat_str, compat_urllib_error
 from youtube_dl.extractor import YoutubeIE
 from youtube_dl.postprocessor.common import PostProcessor
 from youtube_dl.utils import ExtractorError, match_filter_func
@@ -631,6 +631,11 @@ class TestYoutubeDL(unittest.TestCase):
         result = get_ids({'playlist_items': '10'})
         self.assertEqual(result, [])
 
+    def test_urlopen_no_file_protocol(self):
+        # see https://github.com/rg3/youtube-dl/issues/8227
+        ydl = YDL()
+        self.assertRaises(compat_urllib_error.URLError, ydl.urlopen, 'file:///etc/passwd')
+
 
 if __name__ == '__main__':
     unittest.main()
diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py
index d50b7cfed..e8ce58604 100755
--- a/youtube_dl/YoutubeDL.py
+++ b/youtube_dl/YoutubeDL.py
@@ -1986,8 +1986,14 @@ class YoutubeDL(object):
         https_handler = make_HTTPS_handler(self.params, debuglevel=debuglevel)
         ydlh = YoutubeDLHandler(self.params, debuglevel=debuglevel)
         data_handler = compat_urllib_request_DataHandler()
-        opener = compat_urllib_request.build_opener(
-            proxy_handler, https_handler, cookie_processor, ydlh, data_handler)
+        unknown_handler = compat_urllib_request.UnknownHandler()
+        handlers = (proxy_handler, https_handler, cookie_processor, ydlh, data_handler, unknown_handler)
+        # we don't use build_opener because it automatically adds FileHandler,
+        # which can be used for malicious purposes (see
+        # https://github.com/rg3/youtube-dl/issues/8227)
+        opener = compat_urllib_request.OpenerDirector()
+        for handler in handlers:
+            opener.add_handler(handler)
 
         # Delete the default user-agent header, which would otherwise apply in
         # cases where our custom HTTP handler doesn't come into play