w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[vivo] Fix extraction (closes #22328, closes #22279)

Browse source
This commit is contained in:
Sergey M․ 2019-11-27 02:28:06 +07:00
parent 1ced222120
commit edc2a1f68b
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 19 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

27
youtube_dl/extractor/shared.py
View file

@ -1,13 +1,18 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_b64decode from ..compat import (
compat_b64decode,
compat_urllib_parse_unquote_plus,
)
from ..utils import ( from ..utils import (
determine_ext, determine_ext,
ExtractorError, ExtractorError,
int_or_none, int_or_none,
js_to_json,
KNOWN_EXTENSIONS, KNOWN_EXTENSIONS,
parse_filesize, parse_filesize,
rot47,
url_or_none, url_or_none,
urlencode_postdata, urlencode_postdata,
) )
@ -112,16 +117,22 @@ class VivoIE(SharedBaseIE):
webpage, 'filesize', fatal=False)) webpage, 'filesize', fatal=False))
def _extract_video_url(self, webpage, video_id, url): def _extract_video_url(self, webpage, video_id, url):
def decode_url(encoded_url): def decode_url_old(encoded_url):
return compat_b64decode(encoded_url).decode('utf-8') return compat_b64decode(encoded_url).decode('utf-8')
stream_url = url_or_none(decode_url(self._search_regex( stream_url = self._search_regex(
r'data-stream\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, r'data-stream\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
'stream url', default=None, group='url'))) 'stream url', default=None, group='url')
if stream_url:
stream_url = url_or_none(decode_url_old(stream_url))
if stream_url: if stream_url:
return stream_url return stream_url
return self._parse_json(
def decode_url(encoded_url):
return rot47(compat_urllib_parse_unquote_plus(encoded_url))
return decode_url(self._parse_json(
self._search_regex( self._search_regex(
r'InitializeStream\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1', r'(?s)InitializeStream\s*\(\s*({.+?})\s*\)\s*;', webpage,
webpage, 'stream', group='url'), 'stream'),
video_id, transform_source=decode_url)[0] video_id, transform_source=js_to_json)['source'])