github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[hotstar] improve extraction(closes #12096)

Browse source 
- extract all qualities
- detect drm protected videos
- extract more metadata
This commit is contained in:
Remita Amine 2017-02-12 17:24:45 +01:00
parent f8514630db
commit 0dac7cbb09
1 changed files with 32 additions and 14 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

46
youtube_dl/extractor/hotstar.py
View file

@ -34,11 +34,9 @@ class HotStarIE(InfoExtractor):
'only_matching': True, 'only_matching': True,
}] }]
_GET_CONTENT_TEMPLATE = 'http://account.hotstar.com/AVS/besc?action=GetAggregatedContentDetails&channel=PCTV&contentId=%s' def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata', fatal=True, query=None):
_GET_CDN_TEMPLATE = 'http://getcdn.hotstar.com/AVS/besc?action=GetCDN&asJson=Y&channel=%s&id=%s&type=%s' json_data = super(HotStarIE, self)._download_json(
url_or_request, video_id, note, fatal=fatal, query=query)
def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata', fatal=True):
json_data = super(HotStarIE, self)._download_json(url_or_request, video_id, note, fatal=fatal)
if json_data['resultCode'] != 'OK': if json_data['resultCode'] != 'OK':
if fatal: if fatal:
raise ExtractorError(json_data['errorDescription']) raise ExtractorError(json_data['errorDescription'])
@ -48,20 +46,37 @@ def _download_json(self, url_or_request, video_id, note='Downloading JSON metada
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
video_data = self._download_json( video_data = self._download_json(
self._GET_CONTENT_TEMPLATE % video_id, 'http://account.hotstar.com/AVS/besc', video_id, query={
video_id)['contentInfo'][0] 'action': 'GetAggregatedContentDetails',
'channel': 'PCTV',
'contentId': video_id,
})['contentInfo'][0]
title = video_data['episodeTitle']
if video_data.get('encrypted') == 'Y':
raise ExtractorError('This video is DRM protected.', expected=True)
formats = [] formats = []
# PCTV for extracting f4m manifest for f in ('JIO',):
for f in ('TABLET',):
format_data = self._download_json( format_data = self._download_json(
self._GET_CDN_TEMPLATE % (f, video_id, 'VOD'), 'http://getcdn.hotstar.com/AVS/besc',
video_id, 'Downloading %s JSON metadata' % f, fatal=False) video_id, 'Downloading %s JSON metadata' % f,
fatal=False, query={
'action': 'GetCDN',
'asJson': 'Y',
'channel': f,
'id': video_id,
'type': 'VOD',
})
if format_data: if format_data:
format_url = format_data['src'] format_url = format_data.get('src')
if not format_url:
continue
ext = determine_ext(format_url) ext = determine_ext(format_url)
if ext == 'm3u8': if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(format_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) formats.extend(self._extract_m3u8_formats(
format_url, video_id, 'mp4',
m3u8_id='hls', fatal=False))
elif ext == 'f4m': elif ext == 'f4m':
# produce broken files # produce broken files
continue continue
@ -75,9 +90,12 @@ def _real_extract(self, url):
return { return {
'id': video_id, 'id': video_id,
'title': video_data['episodeTitle'], 'title': title,
'description': video_data.get('description'), 'description': video_data.get('description'),
'duration': int_or_none(video_data.get('duration')), 'duration': int_or_none(video_data.get('duration')),
'timestamp': int_or_none(video_data.get('broadcastDate')), 'timestamp': int_or_none(video_data.get('broadcastDate')),
'formats': formats, 'formats': formats,
'episode': title,
'episode_number': int_or_none(video_data.get('episodeNumber')),
'series': video_data.get('contentTitle'),
} }