yt_dlp/extractor/hungama.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     int_or_none,
   6     try_get,
   7     urlencode_postdata,
   8 )
   9
  10
  11 class HungamaIE(InfoExtractor):
  12     _VALID_URL = r'''(?x)
  13                     https?://
  14                         (?:www\.)?hungama\.com/
  15                         (?:
  16                             (?:video|movie)/[^/]+/|
  17                             tv-show/(?:[^/]+/){2}\d+/episode/[^/]+/
  18                         )
  19                         (?P<id>\d+)
  20                     '''
  21     _TESTS = [{
  22         'url': 'http://www.hungama.com/video/krishna-chants/39349649/',
  23         'md5': '687c5f1e9f832f3b59f44ed0eb1f120a',
  24         'info_dict': {
  25             'id': '39349649',
  26             'ext': 'mp4',
  27             'title': 'Krishna Chants',
  28             'description': 'Watch Krishna Chants video now. You can also watch other latest videos only at Hungama',
  29             'upload_date': '20180829',
  30             'duration': 264,
  31             'timestamp': 1535500800,
  32             'view_count': int,
  33             'thumbnail': 'https://images.hungama.com/c/1/0dc/2ca/39349649/39349649_700x394.jpg',
  34         }
  35     }, {
  36         'url': 'https://www.hungama.com/movie/kahaani-2/44129919/',
  37         'only_matching': True,
  38     }, {
  39         'url': 'https://www.hungama.com/tv-show/padded-ki-pushup/season-1/44139461/episode/ep-02-training-sasu-pathlaag-karing/44139503/',
  40         'only_matching': True,
  41     }]
  42
  43     def _real_extract(self, url):
  44         video_id = self._match_id(url)
  45         video_json = self._download_json(
  46             'https://www.hungama.com/index.php', video_id,
  47             data=urlencode_postdata({'content_id': video_id}), headers={
  48                 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
  49                 'X-Requested-With': 'XMLHttpRequest',
  50             }, query={
  51                 'c': 'common',
  52                 'm': 'get_video_mdn_url',
  53             })
  54
  55         formats = self._extract_m3u8_formats(video_json['stream_url'], video_id, ext='mp4', m3u8_id='hls')
  56         self._sort_formats(formats)
  57
  58         json_ld = self._search_json_ld(
  59             self._download_webpage(url, video_id, fatal=False) or '', video_id, fatal=False)
  60
  61         return {
  62             **json_ld,
  63             'id': video_id,
  64             'formats': formats,
  65             'subtitles': {
  66                 'en': [{
  67                     'url': video_json['sub_title'],
  68                     'ext': 'vtt',
  69                 }]
  70             } if video_json.get('sub_title') else None,
  71         }
  72
  73
  74 class HungamaSongIE(InfoExtractor):
  75     _VALID_URL = r'https?://(?:www\.)?hungama\.com/song/[^/]+/(?P<id>\d+)'
  76     _TEST = {
  77         'url': 'https://www.hungama.com/song/kitni-haseen-zindagi/2931166/',
  78         'md5': 'd4a6a05a394ad0453a9bea3ca00e6024',
  79         'info_dict': {
  80             'id': '2931166',
  81             'ext': 'mp3',
  82             'title': 'Lucky Ali - Kitni Haseen Zindagi',
  83             'track': 'Kitni Haseen Zindagi',
  84             'artist': 'Lucky Ali',
  85             'album': None,
  86             'release_year': 2000,
  87         }
  88     }
  89
  90     def _real_extract(self, url):
  91         audio_id = self._match_id(url)
  92
  93         data = self._download_json(
  94             'https://www.hungama.com/audio-player-data/track/%s' % audio_id,
  95             audio_id, query={'_country': 'IN'})[0]
  96         track = data['song_name']
  97         artist = data.get('singer_name')
  98         formats = []
  99         media_json = self._download_json(data.get('file') or data['preview_link'], audio_id)
 100         media_url = try_get(media_json, lambda x: x['response']['media_url'], str)
 101         media_type = try_get(media_json, lambda x: x['response']['type'], str)
 102
 103         if media_url:
 104             formats.append({
 105                 'url': media_url,
 106                 'ext': media_type,
 107                 'vcodec': 'none',
 108                 'acodec': media_type,
 109             })
 110
 111         title = '%s - %s' % (artist, track) if artist else track
 112         thumbnail = data.get('img_src') or data.get('album_image')
 113
 114         return {
 115             'id': audio_id,
 116             'title': title,
 117             'thumbnail': thumbnail,
 118             'track': track,
 119             'artist': artist,
 120             'album': data.get('album_name') or None,
 121             'release_year': int_or_none(data.get('date')),
 122             'formats': formats,
 123         }
 124
 125
 126 class HungamaAlbumPlaylistIE(InfoExtractor):
 127     _VALID_URL = r'https?://(?:www\.)?hungama\.com/(?:playlists|album)/[^/]+/(?P<id>\d+)'
 128     _TESTS = [{
 129         'url': 'https://www.hungama.com/album/bhuj-the-pride-of-india/69481490/',
 130         'playlist_mincount': 7,
 131         'info_dict': {
 132             'id': '69481490',
 133         },
 134     }, {
 135         'url': 'https://www.hungama.com/playlists/hindi-jan-to-june-2021/123063/',
 136         'playlist_mincount': 50,
 137         'info_dict': {
 138             'id': '123063',
 139         },
 140     }]
 141
 142     def _real_extract(self, url):
 143         video_id = self._match_id(url)
 144         webpage = self._download_webpage(url, video_id)
 145         ptrn = r'<meta[^>]+?property=[\"\']?music:song:url[\"\']?[^>]+?content=[\"\']?([^\"\']+)'
 146         items = re.findall(ptrn, webpage)
 147         entries = [self.url_result(item, ie=HungamaSongIE.ie_key()) for item in items]
 148         return self.playlist_result(entries, video_id)