[utils] Don't use Content-length with encoding (#6176)

Authored by: felixonmars
Closes #3772, #6178
This commit is contained in:
Felix Yan 2023-02-17 05:08:45 +02:00 committed by GitHub
parent a9189510ba
commit 65e5c021e7
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 6 additions and 4 deletions

View file

@ -211,7 +211,12 @@ def close_stream():
ctx.stream = None
def download():
data_len = ctx.data.info().get('Content-length', None)
data_len = ctx.data.info().get('Content-length')
if ctx.data.info().get('Content-encoding'):
# Content-encoding is present, Content-length is not reliable anymore as we are
# doing auto decompression. (See: https://github.com/yt-dlp/yt-dlp/pull/6176)
data_len = None
# Range HTTP header may be ignored/unsupported by a webserver
# (e.g. extractor/scivee.py, extractor/bambuser.py).

View file

@ -1438,19 +1438,16 @@ def http_response(self, req, resp):
raise original_ioerror
resp = urllib.request.addinfourl(uncompressed, old_resp.headers, old_resp.url, old_resp.code)
resp.msg = old_resp.msg
del resp.headers['Content-encoding']
# deflate
if resp.headers.get('Content-encoding', '') == 'deflate':
gz = io.BytesIO(self.deflate(resp.read()))
resp = urllib.request.addinfourl(gz, old_resp.headers, old_resp.url, old_resp.code)
resp.msg = old_resp.msg
del resp.headers['Content-encoding']
# brotli
if resp.headers.get('Content-encoding', '') == 'br':
resp = urllib.request.addinfourl(
io.BytesIO(self.brotli(resp.read())), old_resp.headers, old_resp.url, old_resp.code)
resp.msg = old_resp.msg
del resp.headers['Content-encoding']
# Percent-encode redirect URL of Location HTTP header to satisfy RFC 3986 (see
# https://github.com/ytdl-org/youtube-dl/issues/6457).
if 300 <= resp.code < 400: