yt_dlp/extractor/hungama.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     int_or_none,
   9     try_get,
  10     urlencode_postdata,
  11 )
  12
  13
  14 class HungamaIE(InfoExtractor):
  15     _VALID_URL = r'''(?x)
  16                     https?://
  17                         (?:www\.)?hungama\.com/
  18                         (?:
  19                             (?:video|movie)/[^/]+/|
  20                             tv-show/(?:[^/]+/){2}\d+/episode/[^/]+/
  21                         )
  22                         (?P<id>\d+)
  23                     '''
  24     _TESTS = [{
  25         'url': 'http://www.hungama.com/video/krishna-chants/39349649/',
  26         'md5': 'a845a6d1ebd08d80c1035126d49bd6a0',
  27         'info_dict': {
  28             'id': '2931166',
  29             'ext': 'mp4',
  30             'title': 'Lucky Ali - Kitni Haseen Zindagi',
  31             'track': 'Kitni Haseen Zindagi',
  32             'artist': 'Lucky Ali',
  33             'album': 'Aks',
  34             'release_year': 2000,
  35         }
  36     }, {
  37         'url': 'https://www.hungama.com/movie/kahaani-2/44129919/',
  38         'only_matching': True,
  39     }, {
  40         'url': 'https://www.hungama.com/tv-show/padded-ki-pushup/season-1/44139461/episode/ep-02-training-sasu-pathlaag-karing/44139503/',
  41         'only_matching': True,
  42     }]
  43
  44     def _real_extract(self, url):
  45         video_id = self._match_id(url)
  46
  47         webpage = self._download_webpage(url, video_id)
  48
  49         info = self._search_json_ld(webpage, video_id)
  50
  51         m3u8_url = self._download_json(
  52             'https://www.hungama.com/index.php', video_id,
  53             data=urlencode_postdata({'content_id': video_id}), headers={
  54                 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
  55                 'X-Requested-With': 'XMLHttpRequest',
  56             }, query={
  57                 'c': 'common',
  58                 'm': 'get_video_mdn_url',
  59             })['stream_url']
  60
  61         formats = self._extract_m3u8_formats(
  62             m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native',
  63             m3u8_id='hls')
  64         self._sort_formats(formats)
  65
  66         info.update({
  67             'id': video_id,
  68             'formats': formats,
  69         })
  70         return info
  71
  72
  73 class HungamaSongIE(InfoExtractor):
  74     _VALID_URL = r'https?://(?:www\.)?hungama\.com/song/[^/]+/(?P<id>\d+)'
  75     _TEST = {
  76         'url': 'https://www.hungama.com/song/kitni-haseen-zindagi/2931166/',
  77         'md5': 'd4a6a05a394ad0453a9bea3ca00e6024',
  78         'info_dict': {
  79             'id': '2931166',
  80             'ext': 'mp3',
  81             'title': 'Lucky Ali - Kitni Haseen Zindagi',
  82             'track': 'Kitni Haseen Zindagi',
  83             'artist': 'Lucky Ali',
  84             'album': None,
  85             'release_year': 2000,
  86         }
  87     }
  88
  89     def _real_extract(self, url):
  90         audio_id = self._match_id(url)
  91
  92         data = self._download_json(
  93             'https://www.hungama.com/audio-player-data/track/%s' % audio_id,
  94             audio_id, query={'_country': 'IN'})[0]
  95         track = data['song_name']
  96         artist = data.get('singer_name')
  97         formats = []
  98         media_json = self._download_json(data.get('file') or data['preview_link'], audio_id)
  99         media_url = try_get(media_json, lambda x: x['response']['media_url'], str)
 100         media_type = try_get(media_json, lambda x: x['response']['type'], str)
 101
 102         if media_url:
 103             formats.append({
 104                 'url': media_url,
 105                 'ext': media_type,
 106                 'vcodec': 'none',
 107                 'acodec': media_type,
 108             })
 109
 110         title = '%s - %s' % (artist, track) if artist else track
 111         thumbnail = data.get('img_src') or data.get('album_image')
 112
 113         return {
 114             'id': audio_id,
 115             'title': title,
 116             'thumbnail': thumbnail,
 117             'track': track,
 118             'artist': artist,
 119             'album': data.get('album_name') or None,
 120             'release_year': int_or_none(data.get('date')),
 121             'formats': formats,
 122         }
 123
 124
 125 class HungamaAlbumPlaylistIE(InfoExtractor):
 126     _VALID_URL = r'https?://(?:www\.)?hungama\.com/(?:playlists|album)/[^/]+/(?P<id>\d+)'
 127     _TESTS = [{
 128         'url': 'https://www.hungama.com/album/bhuj-the-pride-of-india/69481490/',
 129         'playlist_mincount': 7,
 130         'info_dict': {
 131             'id': '69481490',
 132         },
 133     }, {
 134         'url': 'https://www.hungama.com/playlists/hindi-jan-to-june-2021/123063/',
 135         'playlist_mincount': 50,
 136         'info_dict': {
 137             'id': '123063',
 138         },
 139     }]
 140
 141     def _real_extract(self, url):
 142         video_id = self._match_id(url)
 143         webpage = self._download_webpage(url, video_id)
 144         ptrn = r'<meta[^>]+?property=[\"\']?music:song:url[\"\']?[^>]+?content=[\"\']?([^\"\']+)'
 145         items = re.findall(ptrn, webpage)
 146         entries = [self.url_result(item, ie=HungamaSongIE.ie_key()) for item in items]
 147         return self.playlist_result(entries, video_id)