-# coding: utf-8
-from __future__ import unicode_literals
-
import re
import json
import uuid
from ..utils import (
ExtractorError,
int_or_none,
+ remove_end,
strip_or_none,
+ traverse_obj,
try_get,
smuggle_url,
+ unified_timestamp,
unsmuggle_url,
url_or_none,
)
# r'(/hlsc_)[a-z]+(\d+\.m3u8)',
# r'\1whe\2', video_data['href'])
m3u8_url = video_data['href']
- formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4')
- self._sort_formats(formats)
+ formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, 'mp4')
- subtitles = {}
for key, value in video_data.items():
mobj = re.match(r'^subtitle_(?P<lang>[^_]+)_(?P<ext>(vtt|srt))', key)
if not mobj:
},
'skip': 'Geo-restricted to Singapore',
}, {
- 'url': 'http://www.viu.com/ott/hk/zh-hk/vod/7123/%E5%A4%A7%E4%BA%BA%E5%A5%B3%E5%AD%90',
+ 'url': 'https://www.viu.com/ott/hk/zh-hk/vod/430078/%E7%AC%AC%E5%85%AD%E6%84%9F-3',
'info_dict': {
- 'id': '7123',
+ 'id': '430078',
'ext': 'mp4',
- 'title': '這就是我的生活之道',
- 'description': 'md5:4eb0d8b08cf04fcdc6bbbeb16043434f',
+ 'title': '大韓民國的1%',
+ 'description': 'md5:74d6db47ddd9ddb9c89a05739103ccdb',
+ 'episode_number': 1,
+ 'duration': 6614,
+ 'episode': '大韓民國的1%',
+ 'series': '第六感 3',
+ 'thumbnail': 'https://d2anahhhmp1ffz.cloudfront.net/1313295781/d2b14f48d008ef2f3a9200c98d8e9b63967b9cc2',
},
'params': {
'skip_download': 'm3u8 download',
},
'skip': 'Geo-restricted to Hong Kong',
}, {
- 'url': 'https://www.viu.com/ott/hk/zh-hk/vod/68776/%E6%99%82%E5%B0%9A%E5%AA%BD%E5%92%AA',
- 'playlist_count': 12,
+ 'url': 'https://www.viu.com/ott/hk/zh-hk/vod/444666/%E6%88%91%E7%9A%84%E5%AE%A4%E5%8F%8B%E6%98%AF%E4%B9%9D%E5%B0%BE%E7%8B%90',
+ 'playlist_count': 16,
'info_dict': {
- 'id': '3916',
- 'title': '時尚媽咪',
+ 'id': '23807',
+ 'title': '我的室友是九尾狐',
+ 'description': 'md5:b42c95f2b4a316cdd6ae14ca695f33b9',
},
'params': {
'skip_download': 'm3u8 download',
return self._user_token
def _get_token(self, country_code, video_id):
- rand = ''.join(random.choice('0123456789') for _ in range(10))
+ rand = ''.join(random.choices('0123456789', k=10))
return self._download_json(
f'https://api-gateway-global.viu.com/api/auth/token?v={rand}000', video_id,
headers={'Content-Type': 'application/json'}, note='Getting bearer token',
if token is not None:
query['identity'] = token
else:
- # preview is limited to 3min for non-members. But we can try to bypass it
+ # The content is Preview or for VIP only.
+ # We can try to bypass the duration which is limited to 3mins only
duration_limit, query['duration'] = True, '180'
try:
stream_data = download_playback()
# bypass preview duration limit
if duration_limit:
- stream_url = urllib.parse.urlparse(stream_url)
+ old_stream_url = urllib.parse.urlparse(stream_url)
+ query = dict(urllib.parse.parse_qsl(old_stream_url.query, keep_blank_values=True))
query.update({
'duration': video_data.get('time_duration') or '9999999',
'duration_start': '0',
})
- stream_url = stream_url._replace(query=urllib.parse.urlencode(dict(
- urllib.parse.parse_qsl(stream_url.query, keep_blank_values=True)))).geturl()
+ stream_url = old_stream_url._replace(query=urllib.parse.urlencode(query)).geturl()
formats.append({
'format_id': vid_format,
'ext': 'mp4',
'filesize': try_get(stream_data, lambda x: x['size'][vid_format], int)
})
- self._sort_formats(formats)
subtitles = {}
for sub in video_data.get('subtitle') or []:
- sub_url = sub.get('url')
- if not sub_url:
- continue
- subtitles.setdefault(sub.get('name'), []).append({
- 'url': sub_url,
- 'ext': 'srt',
- })
+ lang = sub.get('name') or 'und'
+ if sub.get('url'):
+ subtitles.setdefault(lang, []).append({
+ 'url': sub['url'],
+ 'ext': 'srt',
+ 'name': f'Spoken text for {lang}',
+ })
+ if sub.get('second_subtitle_url'):
+ subtitles.setdefault(f'{lang}_ost', []).append({
+ 'url': sub['second_subtitle_url'],
+ 'ext': 'srt',
+ 'name': f'On-screen text for {lang}',
+ })
title = strip_or_none(video_data.get('synopsis'))
return {
'formats': formats,
'subtitles': subtitles,
}
+
+
+class ViuOTTIndonesiaBaseIE(InfoExtractor):
+ _BASE_QUERY = {
+ 'ver': 1.0,
+ 'fmt': 'json',
+ 'aver': 5.0,
+ 'appver': 2.0,
+ 'appid': 'viu_desktop',
+ 'platform': 'desktop',
+ }
+
+ _DEVICE_ID = str(uuid.uuid4())
+ _SESSION_ID = str(uuid.uuid4())
+ _TOKEN = None
+
+ _HEADERS = {
+ 'x-session-id': _SESSION_ID,
+ 'x-client': 'browser'
+ }
+
+ _AGE_RATINGS_MAPPER = {
+ 'ADULTS': 18,
+ 'teens': 13
+ }
+
+ def _real_initialize(self):
+ ViuOTTIndonesiaBaseIE._TOKEN = self._download_json(
+ 'https://um.viuapi.io/user/identity', None,
+ headers={'Content-type': 'application/json', **self._HEADERS},
+ query={**self._BASE_QUERY, 'iid': self._DEVICE_ID},
+ data=json.dumps({'deviceId': self._DEVICE_ID}).encode(),
+ note='Downloading token information')['token']
+
+
+class ViuOTTIndonesiaIE(ViuOTTIndonesiaBaseIE):
+ _VALID_URL = r'https?://www\.viu\.com/ott/\w+/\w+/all/video-[\w-]+-(?P<id>\d+)'
+ _TESTS = [{
+ 'url': 'https://www.viu.com/ott/id/id/all/video-japanese-drama-tv_shows-detective_conan_episode_793-1165863142?containerId=playlist-26271226',
+ 'info_dict': {
+ 'id': '1165863142',
+ 'ext': 'mp4',
+ 'episode_number': 793,
+ 'episode': 'Episode 793',
+ 'title': 'Detective Conan - Episode 793',
+ 'duration': 1476,
+ 'description': 'md5:b79d55345bc1e0217ece22616267c9a5',
+ 'thumbnail': 'https://vuclipi-a.akamaihd.net/p/cloudinary/h_171,w_304,dpr_1.5,f_auto,c_thumb,q_auto:low/1165863189/d-1',
+ 'upload_date': '20210101',
+ 'timestamp': 1609459200,
+ }
+ }, {
+ 'url': 'https://www.viu.com/ott/id/id/all/video-korean-reality-tv_shows-entertainment_weekly_episode_1622-1118617054',
+ 'info_dict': {
+ 'id': '1118617054',
+ 'ext': 'mp4',
+ 'episode_number': 1622,
+ 'episode': 'Episode 1622',
+ 'description': 'md5:6d68ca450004020113e9bf27ad99f0f8',
+ 'title': 'Entertainment Weekly - Episode 1622',
+ 'duration': 4729,
+ 'thumbnail': 'https://vuclipi-a.akamaihd.net/p/cloudinary/h_171,w_304,dpr_1.5,f_auto,c_thumb,q_auto:low/1120187848/d-1',
+ 'timestamp': 1420070400,
+ 'upload_date': '20150101',
+ 'cast': ['Shin Hyun-joon', 'Lee Da-Hee']
+ }
+ }, {
+ # age-limit test
+ 'url': 'https://www.viu.com/ott/id/id/all/video-japanese-trailer-tv_shows-trailer_jujutsu_kaisen_ver_01-1166044219?containerId=playlist-26273140',
+ 'info_dict': {
+ 'id': '1166044219',
+ 'ext': 'mp4',
+ 'upload_date': '20200101',
+ 'timestamp': 1577836800,
+ 'title': 'Trailer \'Jujutsu Kaisen\' Ver.01',
+ 'duration': 92,
+ 'thumbnail': 'https://vuclipi-a.akamaihd.net/p/cloudinary/h_171,w_304,dpr_1.5,f_auto,c_thumb,q_auto:low/1166044240/d-1',
+ 'description': 'Trailer \'Jujutsu Kaisen\' Ver.01',
+ 'cast': ['Junya Enoki', ' Yûichi Nakamura', ' Yuma Uchida', 'Asami Seto'],
+ 'age_limit': 13,
+ }
+ }, {
+ # json ld metadata type equal to Movie instead of TVEpisodes
+ 'url': 'https://www.viu.com/ott/id/id/all/video-japanese-animation-movies-demon_slayer_kimetsu_no_yaiba_the_movie_mugen_train-1165892707?containerId=1675060691786',
+ 'info_dict': {
+ 'id': '1165892707',
+ 'ext': 'mp4',
+ 'timestamp': 1577836800,
+ 'upload_date': '20200101',
+ 'title': 'Demon Slayer - Kimetsu no Yaiba - The Movie: Mugen Train',
+ 'age_limit': 13,
+ 'cast': 'count:9',
+ 'thumbnail': 'https://vuclipi-a.akamaihd.net/p/cloudinary/h_171,w_304,dpr_1.5,f_auto,c_thumb,q_auto:low/1165895279/d-1',
+ 'description': 'md5:1ce9c35a3aeab384085533f746c87469',
+ 'duration': 7021,
+ }
+ }]
+
+ def _real_extract(self, url):
+ display_id = self._match_id(url)
+ webpage = self._download_webpage(url, display_id)
+
+ video_data = self._download_json(
+ f'https://um.viuapi.io/drm/v1/content/{display_id}', display_id, data=b'',
+ headers={'Authorization': ViuOTTIndonesiaBaseIE._TOKEN, **self._HEADERS, 'ccode': 'ID'})
+ formats, subtitles = self._extract_m3u8_formats_and_subtitles(video_data['playUrl'], display_id)
+
+ initial_state = self._search_json(
+ r'window\.__INITIAL_STATE__\s*=', webpage, 'initial state',
+ display_id)['content']['clipDetails']
+ for key, url in initial_state.items():
+ lang, ext = self._search_regex(
+ r'^subtitle_(?P<lang>[\w-]+)_(?P<ext>\w+)$', key, 'subtitle metadata',
+ default=(None, None), group=('lang', 'ext'))
+ if lang and ext:
+ subtitles.setdefault(lang, []).append({
+ 'ext': ext,
+ 'url': url,
+ })
+
+ if ext == 'vtt':
+ subtitles[lang].append({
+ 'ext': 'srt',
+ 'url': f'{remove_end(initial_state[key], "vtt")}srt',
+ })
+
+ episode = traverse_obj(list(filter(
+ lambda x: x.get('@type') in ('TVEpisode', 'Movie'), self._yield_json_ld(webpage, display_id))), 0) or {}
+ return {
+ 'id': display_id,
+ 'title': (traverse_obj(initial_state, 'title', 'display_title')
+ or episode.get('name')),
+ 'description': initial_state.get('description') or episode.get('description'),
+ 'duration': initial_state.get('duration'),
+ 'thumbnail': traverse_obj(episode, ('image', 'url')),
+ 'timestamp': unified_timestamp(episode.get('dateCreated')),
+ 'formats': formats,
+ 'subtitles': subtitles,
+ 'episode_number': (traverse_obj(initial_state, 'episode_no', 'episodeno', expected_type=int_or_none)
+ or int_or_none(episode.get('episodeNumber'))),
+ 'cast': traverse_obj(episode, ('actor', ..., 'name'), default=None),
+ 'age_limit': self._AGE_RATINGS_MAPPER.get(initial_state.get('internal_age_rating'))
+ }
projects / yt-dlp.git / blobdiff