etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-27 03:03:01 +00:00
Code Issues Projects Releases Wiki Activity

[tvnow] try all clear manifest urls(closes #15361)

Browse source
This commit is contained in:
Remita Amine 2018-06-17 20:40:35 +01:00
parent 858cf4dc29
commit 8ba84e4600
1 changed files with 35 additions and 18 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

53
youtube_dl/extractor/tvnow.py
View file

@ -19,8 +19,8 @@ class TVNowBaseIE(InfoExtractor):
_VIDEO_FIELDS = ( _VIDEO_FIELDS = (
'id', 'title', 'free', 'geoblocked', 'articleLong', 'articleShort', 'id', 'title', 'free', 'geoblocked', 'articleLong', 'articleShort',
'broadcastStartDate', 'isDrm', 'duration', 'season', 'episode', 'broadcastStartDate', 'isDrm', 'duration', 'season', 'episode',
'manifest.dashclear', 'format.title', 'format.defaultImage169Format', 'manifest.dashclear', 'manifest.hlsclear', 'manifest.smoothclear',
'format.defaultImage169Logo') 'format.title', 'format.defaultImage169Format', 'format.defaultImage169Logo')
def _call_api(self, path, video_id, query): def _call_api(self, path, video_id, query):
return self._download_json( return self._download_json(
@ -31,27 +31,42 @@ def _extract_video(self, info, display_id):
video_id = compat_str(info['id']) video_id = compat_str(info['id'])
title = info['title'] title = info['title']
mpd_url = info['manifest']['dashclear'] paths = []
if not mpd_url: for manifest_url in (info.get('manifest') or {}).values():
if not manifest_url:
continue
manifest_url = update_url_query(manifest_url, {'filter': ''})
path = self._search_regex(r'https?://[^/]+/(.+?)\.ism/', manifest_url, 'path')
if path in paths:
continue
paths.append(path)
def url_repl(proto, suffix):
return re.sub(
r'(?:hls|dash|hss)([.-])', proto + r'\1', re.sub(
r'\.ism/(?:[^.]*\.(?:m3u8|mpd)|[Mm]anifest)',
'.ism/' + suffix, manifest_url))
formats = self._extract_mpd_formats(
url_repl('dash', '.mpd'), video_id,
mpd_id='dash', fatal=False)
formats.extend(self._extract_ism_formats(
url_repl('hss', 'Manifest'),
video_id, ism_id='mss', fatal=False))
formats.extend(self._extract_m3u8_formats(
url_repl('hls', '.m3u8'), video_id, 'mp4',
'm3u8_native', m3u8_id='hls', fatal=False))
if formats:
break
else:
if info.get('isDrm'): if info.get('isDrm'):
raise ExtractorError( raise ExtractorError(
'Video %s is DRM protected' % video_id, expected=True) 'Video %s is DRM protected' % video_id, expected=True)
if info.get('geoblocked'): if info.get('geoblocked'):
raise ExtractorError( raise self.raise_geo_restricted()
'Video %s is not available from your location due to geo restriction' % video_id,
expected=True)
if not info.get('free', True): if not info.get('free', True):
raise ExtractorError( raise ExtractorError(
'Video %s is not available for free' % video_id, expected=True) 'Video %s is not available for free' % video_id, expected=True)
mpd_url = update_url_query(mpd_url, {'filter': ''})
formats = self._extract_mpd_formats(mpd_url, video_id, mpd_id='dash', fatal=False)
formats.extend(self._extract_ism_formats(
mpd_url.replace('dash.', 'hss.').replace('/.mpd', '/Manifest'),
video_id, ism_id='mss', fatal=False))
formats.extend(self._extract_m3u8_formats(
mpd_url.replace('dash.', 'hls.').replace('/.mpd', '/.m3u8'),
video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
self._sort_formats(formats) self._sort_formats(formats)
description = info.get('articleLong') or info.get('articleShort') description = info.get('articleLong') or info.get('articleShort')
@ -88,7 +103,7 @@ def _extract_video(self, info, display_id):
class TVNowIE(TVNowBaseIE): class TVNowIE(TVNowBaseIE):
_VALID_URL = r'''(?x) _VALID_URL = r'''(?x)
https?:// https?://
(?:www\.)?tvnow\.(?:de|at|ch)/[^/]+/ (?:www\.)?tvnow\.(?:de|at|ch)/(?P<station>[^/]+)/
(?P<show_id>[^/]+)/ (?P<show_id>[^/]+)/
(?!(?:list|jahr)(?:/|$))(?P<id>[^/?\#&]+) (?!(?:list|jahr)(?:/|$))(?P<id>[^/?\#&]+)
''' '''
@ -140,11 +155,13 @@ class TVNowIE(TVNowBaseIE):
}] }]
def _real_extract(self, url): def _real_extract(self, url):
display_id = '%s/%s' % re.match(self._VALID_URL, url).groups() mobj = re.match(self._VALID_URL, url)
display_id = '%s/%s' % mobj.group(2, 3)
info = self._call_api( info = self._call_api(
'movies/' + display_id, display_id, query={ 'movies/' + display_id, display_id, query={
'fields': ','.join(self._VIDEO_FIELDS), 'fields': ','.join(self._VIDEO_FIELDS),
'station': mobj.group(1),
}) })
return self._extract_video(info, display_id) return self._extract_video(info, display_id)