yt_dlp/extractor/deezer.py

   1 import json
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6     int_or_none,
   7     orderedSet,
   8 )
   9
  10
  11 class DeezerBaseInfoExtractor(InfoExtractor):
  12     def get_data(self, url):
  13         if not self.get_param('test'):
  14             self.report_warning('For now, this extractor only supports the 30 second previews. Patches welcome!')
  15
  16         mobj = self._match_valid_url(url)
  17         data_id = mobj.group('id')
  18
  19         webpage = self._download_webpage(url, data_id)
  20         geoblocking_msg = self._html_search_regex(
  21             r'<p class="soon-txt">(.*?)</p>', webpage, 'geoblocking message',
  22             default=None)
  23         if geoblocking_msg is not None:
  24             raise ExtractorError(
  25                 'Deezer said: %s' % geoblocking_msg, expected=True)
  26
  27         data_json = self._search_regex(
  28             (r'__DZR_APP_STATE__\s*=\s*({.+?})\s*</script>',
  29              r'naboo\.display\(\'[^\']+\',\s*(.*?)\);\n'),
  30             webpage, 'data JSON')
  31         data = json.loads(data_json)
  32         return data_id, webpage, data
  33
  34
  35 class DeezerPlaylistIE(DeezerBaseInfoExtractor):
  36     _VALID_URL = r'https?://(?:www\.)?deezer\.com/(../)?playlist/(?P<id>[0-9]+)'
  37     _TEST = {
  38         'url': 'http://www.deezer.com/playlist/176747451',
  39         'info_dict': {
  40             'id': '176747451',
  41             'title': 'Best!',
  42             'uploader': 'anonymous',
  43             'thumbnail': r're:^https?://(e-)?cdns-images\.dzcdn\.net/images/cover/.*\.jpg$',
  44         },
  45         'playlist_count': 29,
  46     }
  47
  48     def _real_extract(self, url):
  49         playlist_id, webpage, data = self.get_data(url)
  50
  51         playlist_title = data.get('DATA', {}).get('TITLE')
  52         playlist_uploader = data.get('DATA', {}).get('PARENT_USERNAME')
  53         playlist_thumbnail = self._search_regex(
  54             r'<img id="naboo_playlist_image".*?src="([^"]+)"', webpage,
  55             'playlist thumbnail')
  56
  57         entries = []
  58         for s in data.get('SONGS', {}).get('data'):
  59             formats = [{
  60                 'format_id': 'preview',
  61                 'url': s.get('MEDIA', [{}])[0].get('HREF'),
  62                 'preference': -100,  # Only the first 30 seconds
  63                 'ext': 'mp3',
  64             }]
  65             self._sort_formats(formats)
  66             artists = ', '.join(
  67                 orderedSet(a.get('ART_NAME') for a in s.get('ARTISTS')))
  68             entries.append({
  69                 'id': s.get('SNG_ID'),
  70                 'duration': int_or_none(s.get('DURATION')),
  71                 'title': '%s - %s' % (artists, s.get('SNG_TITLE')),
  72                 'uploader': s.get('ART_NAME'),
  73                 'uploader_id': s.get('ART_ID'),
  74                 'age_limit': 16 if s.get('EXPLICIT_LYRICS') == '1' else 0,
  75                 'formats': formats,
  76             })
  77
  78         return {
  79             '_type': 'playlist',
  80             'id': playlist_id,
  81             'title': playlist_title,
  82             'uploader': playlist_uploader,
  83             'thumbnail': playlist_thumbnail,
  84             'entries': entries,
  85         }
  86
  87
  88 class DeezerAlbumIE(DeezerBaseInfoExtractor):
  89     _VALID_URL = r'https?://(?:www\.)?deezer\.com/(../)?album/(?P<id>[0-9]+)'
  90     _TEST = {
  91         'url': 'https://www.deezer.com/fr/album/67505622',
  92         'info_dict': {
  93             'id': '67505622',
  94             'title': 'Last Week',
  95             'uploader': 'Home Brew',
  96             'thumbnail': r're:^https?://(e-)?cdns-images\.dzcdn\.net/images/cover/.*\.jpg$',
  97         },
  98         'playlist_count': 7,
  99     }
 100
 101     def _real_extract(self, url):
 102         album_id, webpage, data = self.get_data(url)
 103
 104         album_title = data.get('DATA', {}).get('ALB_TITLE')
 105         album_uploader = data.get('DATA', {}).get('ART_NAME')
 106         album_thumbnail = self._search_regex(
 107             r'<img id="naboo_album_image".*?src="([^"]+)"', webpage,
 108             'album thumbnail')
 109
 110         entries = []
 111         for s in data.get('SONGS', {}).get('data'):
 112             formats = [{
 113                 'format_id': 'preview',
 114                 'url': s.get('MEDIA', [{}])[0].get('HREF'),
 115                 'preference': -100,  # Only the first 30 seconds
 116                 'ext': 'mp3',
 117             }]
 118             self._sort_formats(formats)
 119             artists = ', '.join(
 120                 orderedSet(a.get('ART_NAME') for a in s.get('ARTISTS')))
 121             entries.append({
 122                 'id': s.get('SNG_ID'),
 123                 'duration': int_or_none(s.get('DURATION')),
 124                 'title': '%s - %s' % (artists, s.get('SNG_TITLE')),
 125                 'uploader': s.get('ART_NAME'),
 126                 'uploader_id': s.get('ART_ID'),
 127                 'age_limit': 16 if s.get('EXPLICIT_LYRICS') == '1' else 0,
 128                 'formats': formats,
 129                 'track': s.get('SNG_TITLE'),
 130                 'track_number': int_or_none(s.get('TRACK_NUMBER')),
 131                 'track_id': s.get('SNG_ID'),
 132                 'artist': album_uploader,
 133                 'album': album_title,
 134                 'album_artist': album_uploader,
 135             })
 136
 137         return {
 138             '_type': 'playlist',
 139             'id': album_id,
 140             'title': album_title,
 141             'uploader': album_uploader,
 142             'thumbnail': album_thumbnail,
 143             'entries': entries,
 144         }