Upstream/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-08 09:10:09 +01:00
Code Issues Packages Projects Releases Wiki Activity

[vlive] Add video params extraction fallback and improve (closes #11375)

Browse Source
This commit is contained in:
Sergey M․ 2016-12-14 21:05:50 +07:00
parent 577748075b
commit 89c63cc5f8
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 17 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
youtube_dl/extractor/vlive.py
View File

@ -10,6 +10,7 @@
float_or_none, float_or_none,
int_or_none, int_or_none,
remove_start, remove_start,
urlencode_postdata,
) )
from ..compat import compat_urllib_parse_urlencode from ..compat import compat_urllib_parse_urlencode
@ -48,12 +49,19 @@ def _real_extract(self, url):
webpage = self._download_webpage( webpage = self._download_webpage(
'http://www.vlive.tv/video/%s' % video_id, video_id) 'http://www.vlive.tv/video/%s' % video_id, video_id)
video_params = self._parse_json(self._search_regex( VIDEO_PARAMS_RE = r'\bvlive\.video\.init\(([^)]+)'
r'\bvlive\.video\.init\(([^)]+)\);', VIDEO_PARAMS_FIELD = 'video params'
webpage, 'video params'), video_id,
transform_source=lambda s: '[' + s + ']')
status, long_video_id, key = video_params[2], video_params[5], video_params[6] params = self._parse_json(self._search_regex(
VIDEO_PARAMS_RE, webpage, VIDEO_PARAMS_FIELD, default=''), video_id,
transform_source=lambda s: '[' + s + ']', fatal=False)
if not params or len(params) < 7:
params = self._search_regex(
VIDEO_PARAMS_RE, webpage, VIDEO_PARAMS_FIELD)
params = [p.strip(r'"') for p in re.split(r'\s*,\s*', params)]
status, long_video_id, key = params[2], params[5], params[6]
status = remove_start(status, 'PRODUCT_') status = remove_start(status, 'PRODUCT_')
if status == 'LIVE_ON_AIR' or status == 'BIG_EVENT_ON_AIR': if status == 'LIVE_ON_AIR' or status == 'BIG_EVENT_ON_AIR':
@ -91,14 +99,16 @@ def _get_common_fields(self, webpage):
def _live(self, video_id, webpage): def _live(self, video_id, webpage):
init_page = self._download_webpage( init_page = self._download_webpage(
'http://www.vlive.tv/video/init/view', 'http://www.vlive.tv/video/init/view',
video_id, data="videoSeq=%s" % video_id, headers={ video_id, note='Downloading live webpage',
data=urlencode_postdata({'videoSeq': video_id}),
headers={
'Referer': 'http://www.vlive.tv/video/%s' % video_id, 'Referer': 'http://www.vlive.tv/video/%s' % video_id,
'Content-Type': 'application/x-www-form-urlencoded' 'Content-Type': 'application/x-www-form-urlencoded'
}) })
live_params = self._search_regex( live_params = self._search_regex(
r'"liveStreamInfo"\s*:\s*(".*"),', r'"liveStreamInfo"\s*:\s*(".*"),',
init_page, 'video params') init_page, 'live stream info')
live_params = self._parse_json(live_params, video_id) live_params = self._parse_json(live_params, video_id)
live_params = self._parse_json(live_params, video_id) live_params = self._parse_json(live_params, video_id)