yt_dlp/extractor/hungama.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     int_or_none,
   4     remove_end,
   5     traverse_obj,
   6     try_get,
   7     unified_timestamp,
   8     url_or_none,
   9     urlencode_postdata,
  10 )
  11
  12
  13 class HungamaBaseIE(InfoExtractor):
  14     def _call_api(self, path, content_id, fatal=False):
  15         return traverse_obj(self._download_json(
  16             f'https://cpage.api.hungama.com/v2/page/content/{content_id}/{path}/detail',
  17             content_id, fatal=fatal, query={
  18                 'device': 'web',
  19                 'platform': 'a',
  20                 'storeId': '1',
  21             }), ('data', {dict})) or {}
  22
  23
  24 class HungamaIE(HungamaBaseIE):
  25     _VALID_URL = r'''(?x)
  26                     https?://
  27                         (?:www\.|un\.)?hungama\.com/
  28                         (?:
  29                             (?:video|movie|short-film)/[^/]+/|
  30                             tv-show/(?:[^/]+/){2}\d+/episode/[^/]+/
  31                         )
  32                         (?P<id>\d+)
  33                     '''
  34     _TESTS = [{
  35         'url': 'http://www.hungama.com/video/krishna-chants/39349649/',
  36         'md5': '687c5f1e9f832f3b59f44ed0eb1f120a',
  37         'info_dict': {
  38             'id': '39349649',
  39             'ext': 'mp4',
  40             'title': 'Krishna Chants',
  41             'description': ' ',
  42             'upload_date': '20180829',
  43             'duration': 264,
  44             'timestamp': 1535500800,
  45             'view_count': int,
  46             'thumbnail': 'https://images1.hungama.com/tr:n-a_169_m/c/1/0dc/2ca/39349649/39349649_350x197.jpg?v=8',
  47             'tags': 'count:6',
  48         },
  49     }, {
  50         'url': 'https://un.hungama.com/short-film/adira/102524179/',
  51         'md5': '2278463f5dc9db9054d0c02602d44666',
  52         'info_dict': {
  53             'id': '102524179',
  54             'ext': 'mp4',
  55             'title': 'Adira',
  56             'description': 'md5:df20cd4d41eabb33634f06de1025a4b4',
  57             'upload_date': '20230417',
  58             'timestamp': 1681689600,
  59             'view_count': int,
  60             'thumbnail': 'https://images1.hungama.com/tr:n-a_23_m/c/1/197/ac9/102524179/102524179_350x525.jpg?v=1',
  61             'tags': 'count:7',
  62         },
  63     }, {
  64         'url': 'https://www.hungama.com/movie/kahaani-2/44129919/',
  65         'only_matching': True,
  66     }, {
  67         'url': 'https://www.hungama.com/tv-show/padded-ki-pushup/season-1/44139461/episode/ep-02-training-sasu-pathlaag-karing/44139503/',
  68         'only_matching': True,
  69     }]
  70
  71     def _real_extract(self, url):
  72         video_id = self._match_id(url)
  73         video_json = self._download_json(
  74             'https://www.hungama.com/index.php', video_id,
  75             data=urlencode_postdata({'content_id': video_id}), headers={
  76                 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
  77                 'X-Requested-With': 'XMLHttpRequest',
  78             }, query={
  79                 'c': 'common',
  80                 'm': 'get_video_mdn_url',
  81             })
  82         formats = self._extract_m3u8_formats(video_json['stream_url'], video_id, ext='mp4', m3u8_id='hls')
  83         metadata = self._call_api('movie', video_id)
  84
  85         return {
  86             **traverse_obj(metadata, ('head', 'data', {
  87                 'title': ('title', {str}),
  88                 'description': ('misc', 'description', {str}),
  89                 'duration': ('duration', {int}),  # duration in JSON is incorrect if string
  90                 'timestamp': ('releasedate', {unified_timestamp}),
  91                 'view_count': ('misc', 'playcount', {int_or_none}),
  92                 'thumbnail': ('image', {url_or_none}),
  93                 'tags': ('misc', 'keywords', ..., {str}),
  94             })),
  95             'id': video_id,
  96             'formats': formats,
  97             'subtitles': {
  98                 'en': [{
  99                     'url': video_json['sub_title'],
 100                     'ext': 'vtt',
 101                 }],
 102             } if video_json.get('sub_title') else None,
 103         }
 104
 105
 106 class HungamaSongIE(InfoExtractor):
 107     _VALID_URL = r'https?://(?:www\.|un\.)?hungama\.com/song/[^/]+/(?P<id>\d+)'
 108     _TESTS = [{
 109         'url': 'https://www.hungama.com/song/kitni-haseen-zindagi/2931166/',
 110         'md5': '964f46828e8b250aa35e5fdcfdcac367',
 111         'info_dict': {
 112             'id': '2931166',
 113             'ext': 'mp3',
 114             'title': 'Lucky Ali - Kitni Haseen Zindagi',
 115             'track': 'Kitni Haseen Zindagi',
 116             'artist': 'Lucky Ali',
 117             'release_year': 2000,
 118             'thumbnail': 'https://stat2.hungama.ind.in/assets/images/default_images/da-200x200.png',
 119         },
 120     }, {
 121         'url': 'https://un.hungama.com/song/tum-kya-mile-from-rocky-aur-rani-kii-prem-kahaani/103553672',
 122         'md5': '964f46828e8b250aa35e5fdcfdcac367',
 123         'info_dict': {
 124             'id': '103553672',
 125             'ext': 'mp3',
 126             'title': 'md5:5ebeb1e10771b634ce5f700ce68ae5f4',
 127             'track': 'Tum Kya Mile (From "Rocky Aur Rani Kii Prem Kahaani")',
 128             'artist': 'Pritam Chakraborty, Arijit Singh, Shreya Ghoshal, Amitabh Bhattacharya',
 129             'album': 'Tum Kya Mile (From "Rocky Aur Rani Kii Prem Kahaani")',
 130             'release_year': 2023,
 131             'thumbnail': 'https://images.hungama.com/c/1/7c2/c7b/103553671/103553671_200x200.jpg',
 132         },
 133     }]
 134
 135     def _real_extract(self, url):
 136         audio_id = self._match_id(url)
 137
 138         data = self._download_json(
 139             f'https://www.hungama.com/audio-player-data/track/{audio_id}',
 140             audio_id, query={'_country': 'IN'})[0]
 141         track = data['song_name']
 142         artist = data.get('singer_name')
 143         formats = []
 144         media_json = self._download_json(data.get('file') or data['preview_link'], audio_id)
 145         media_url = try_get(media_json, lambda x: x['response']['media_url'], str)
 146         media_type = try_get(media_json, lambda x: x['response']['type'], str)
 147
 148         if media_url:
 149             formats.append({
 150                 'url': media_url,
 151                 'ext': media_type,
 152                 'vcodec': 'none',
 153                 'acodec': media_type,
 154             })
 155
 156         title = f'{artist} - {track}' if artist else track
 157         thumbnail = data.get('img_src') or data.get('album_image')
 158
 159         return {
 160             'id': audio_id,
 161             'title': title,
 162             'thumbnail': thumbnail,
 163             'track': track,
 164             'artist': artist,
 165             'album': data.get('album_name') or None,
 166             'release_year': int_or_none(data.get('date')),
 167             'formats': formats,
 168         }
 169
 170
 171 class HungamaAlbumPlaylistIE(HungamaBaseIE):
 172     _VALID_URL = r'https?://(?:www\.|un\.)?hungama\.com/(?P<path>playlists|album)/[^/]+/(?P<id>\d+)'
 173     _TESTS = [{
 174         'url': 'https://www.hungama.com/album/bhuj-the-pride-of-india/69481490/',
 175         'playlist_mincount': 7,
 176         'info_dict': {
 177             'id': '69481490',
 178         },
 179     }, {
 180         'url': 'https://www.hungama.com/playlists/hindi-jan-to-june-2021/123063/',
 181         'playlist_mincount': 33,
 182         'info_dict': {
 183             'id': '123063',
 184         },
 185     }, {
 186         'url': 'https://un.hungama.com/album/what-jhumka-%3F-from-rocky-aur-rani-kii-prem-kahaani/103891805/',
 187         'playlist_mincount': 1,
 188         'info_dict': {
 189             'id': '103891805',
 190         },
 191     }]
 192
 193     def _real_extract(self, url):
 194         playlist_id, path = self._match_valid_url(url).group('id', 'path')
 195         data = self._call_api(remove_end(path, 's'), playlist_id, fatal=True)
 196
 197         def entries():
 198             for song_url in traverse_obj(data, ('body', 'rows', ..., 'data', 'misc', 'share', {url_or_none})):
 199                 yield self.url_result(song_url, HungamaSongIE)
 200
 201         return self.playlist_result(entries(), playlist_id)