etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-30 03:33:02 +00:00
Code Issues Projects Releases Wiki Activity

[vlive] fix: extractor tests for VODs

Browse source
This commit is contained in:
exwm 2020-11-01 14:18:27 -05:00
parent 167c108f70
commit 0536e60b48
1 changed files with 39 additions and 40 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

79
youtube_dlc/extractor/vlive.py
View file

@ -11,7 +11,6 @@
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
merge_dicts, merge_dicts,
remove_start,
try_get, try_get,
urlencode_postdata, urlencode_postdata,
) )
@ -97,49 +96,49 @@ def is_logged_in():
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
webpage = self._download_webpage( PARAMS_RE = r'window\.__PRELOADED_STATE__\s*=\s*({.*});?\s*</script>'
'https://www.vlive.tv/video/%s' % video_id, video_id) PARAMS_FIELD = 'params'
VIDEO_PARAMS_RE = r'\bvlive\.video\.init\(([^)]+)' params = self._search_regex(
VIDEO_PARAMS_FIELD = 'video params' PARAMS_RE, webpage, PARAMS_FIELD, default='', flags=re.DOTALL)
params = self._parse_json(params, video_id, fatal=False)
params = self._parse_json(self._search_regex( video_params = params["postDetail"]["post"].get("officialVideo")
VIDEO_PARAMS_RE, webpage, VIDEO_PARAMS_FIELD, default=''), video_id, if video_params is None:
transform_source=lambda s: '[' + s + ']', fatal=False) raise ExtractorError('Invalid key: Failed to extract video parameters.')
if not params or len(params) < 7: long_video_id = video_params["vodId"]
params = self._search_regex( video_type = video_params["type"]
VIDEO_PARAMS_RE, webpage, VIDEO_PARAMS_FIELD) KEY_ENDPOINT = 'https://www.vlive.tv/globalv-web/vam-web/video/v1.0/vod/%s/inkey' % video_id
params = [p.strip(r'"') for p in re.split(r'\s*,\s*', params)] key_json = self._download_json(KEY_ENDPOINT, video_id,
headers={"referer": "https://www.vlive.tv"})
key = key_json["inkey"]
status, long_video_id, key = params[2], params[5], params[6] if video_type in ('VOD'):
status = remove_start(status, 'PRODUCT_') encoding_status = video_params["encodingStatus"]
if encoding_status == 'COMPLETE':
if status in ('LIVE_ON_AIR', 'BIG_EVENT_ON_AIR'): return self._replay(video_id, webpage, long_video_id, key, params)
return self._live(video_id, webpage) else:
elif status in ('VOD_ON_AIR', 'BIG_EVENT_INTRO'): raise ExtractorError('VOD encoding not yet complete. Please try again later.',
return self._replay(video_id, webpage, long_video_id, key) expected=True)
elif video_type in ('LIVE'):
if status == 'LIVE_END': video_status = video_params["status"]
raise ExtractorError('Uploading for replay. Please wait...', if video_status == 'RESERVED':
expected=True) raise ExtractorError('Coming soon!', expected=True)
elif status == 'COMING_SOON': else:
raise ExtractorError('Coming soon!', expected=True) return self._live(video_id, webpage, params)
elif status == 'CANCELED':
raise ExtractorError('We are sorry, '
'but the live broadcast has been canceled.',
expected=True)
elif status == 'ONLY_APP':
raise ExtractorError('Unsupported video type', expected=True)
else: else:
raise ExtractorError('Unknown status %s' % status) raise ExtractorError('Unknown video type %s' % video_type)
def _get_common_fields(self, webpage): def _get_common_fields(self, webpage, params):
title = self._og_search_title(webpage) title = self._og_search_title(webpage)
creator = self._html_search_regex( description = self._html_search_meta(
r'<div[^>]+class="info_area"[^>]*>\s*(?:<em[^>]*>.*?</em\s*>\s*)?<a\s+[^>]*>([^<]+)', ['og:description', 'description', 'twitter:description'],
webpage, 'creator', fatal=False) webpage, 'description', default=None)
creator = (try_get(params, lambda x: x["channel"]["channel"]["channelName"], compat_str)
or self._search_regex(r'on (.*) channel', description or '', 'creator', fatal=False))
thumbnail = self._og_search_thumbnail(webpage) thumbnail = self._og_search_thumbnail(webpage)
return { return {
'title': title, 'title': title,
@ -147,7 +146,7 @@ def _get_common_fields(self, webpage):
'thumbnail': thumbnail, 'thumbnail': thumbnail,
} }
def _live(self, video_id, webpage): def _live(self, video_id, webpage, params):
init_page = self._download_init_page(video_id) init_page = self._download_init_page(video_id)
live_params = self._search_regex( live_params = self._search_regex(
@ -164,7 +163,7 @@ def _live(self, video_id, webpage):
fatal=False, live=True)) fatal=False, live=True))
self._sort_formats(formats) self._sort_formats(formats)
info = self._get_common_fields(webpage) info = self._get_common_fields(webpage, params)
info.update({ info.update({
'title': self._live_title(info['title']), 'title': self._live_title(info['title']),
'id': video_id, 'id': video_id,
@ -173,7 +172,7 @@ def _live(self, video_id, webpage):
}) })
return info return info
def _replay(self, video_id, webpage, long_video_id, key): def _replay(self, video_id, webpage, long_video_id, key, params):
if '' in (long_video_id, key): if '' in (long_video_id, key):
init_page = self._download_init_page(video_id) init_page = self._download_init_page(video_id)
video_info = self._parse_json(self._search_regex( video_info = self._parse_json(self._search_regex(
@ -186,7 +185,7 @@ def _replay(self, video_id, webpage, long_video_id, key):
long_video_id, key = video_info['vid'], video_info['inkey'] long_video_id, key = video_info['vid'], video_info['inkey']
return merge_dicts( return merge_dicts(
self._get_common_fields(webpage), self._get_common_fields(webpage, params),
self._extract_video_info(video_id, long_video_id, key)) self._extract_video_info(video_id, long_video_id, key))
def _download_init_page(self, video_id): def _download_init_page(self, video_id):