yt_dlp/extractor/deezer.py

   1 from __future__ import unicode_literals
   2
   3 import json
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     ExtractorError,
   8     int_or_none,
   9     orderedSet,
  10 )
  11
  12
  13 class DeezerBaseInfoExtractor(InfoExtractor):
  14     def get_data(self, url):
  15         if not self.get_param('test'):
  16             self.report_warning('For now, this extractor only supports the 30 second previews. Patches welcome!')
  17
  18         mobj = self._match_valid_url(url)
  19         data_id = mobj.group('id')
  20
  21         webpage = self._download_webpage(url, data_id)
  22         geoblocking_msg = self._html_search_regex(
  23             r'<p class="soon-txt">(.*?)</p>', webpage, 'geoblocking message',
  24             default=None)
  25         if geoblocking_msg is not None:
  26             raise ExtractorError(
  27                 'Deezer said: %s' % geoblocking_msg, expected=True)
  28
  29         data_json = self._search_regex(
  30             (r'__DZR_APP_STATE__\s*=\s*({.+?})\s*</script>',
  31              r'naboo\.display\(\'[^\']+\',\s*(.*?)\);\n'),
  32             webpage, 'data JSON')
  33         data = json.loads(data_json)
  34         return data_id, webpage, data
  35
  36
  37 class DeezerPlaylistIE(DeezerBaseInfoExtractor):
  38     _VALID_URL = r'https?://(?:www\.)?deezer\.com/(../)?playlist/(?P<id>[0-9]+)'
  39     _TEST = {
  40         'url': 'http://www.deezer.com/playlist/176747451',
  41         'info_dict': {
  42             'id': '176747451',
  43             'title': 'Best!',
  44             'uploader': 'anonymous',
  45             'thumbnail': r're:^https?://(e-)?cdns-images\.dzcdn\.net/images/cover/.*\.jpg$',
  46         },
  47         'playlist_count': 29,
  48     }
  49
  50     def _real_extract(self, url):
  51         playlist_id, webpage, data = self.get_data(url)
  52
  53         playlist_title = data.get('DATA', {}).get('TITLE')
  54         playlist_uploader = data.get('DATA', {}).get('PARENT_USERNAME')
  55         playlist_thumbnail = self._search_regex(
  56             r'<img id="naboo_playlist_image".*?src="([^"]+)"', webpage,
  57             'playlist thumbnail')
  58
  59         entries = []
  60         for s in data.get('SONGS', {}).get('data'):
  61             formats = [{
  62                 'format_id': 'preview',
  63                 'url': s.get('MEDIA', [{}])[0].get('HREF'),
  64                 'preference': -100,  # Only the first 30 seconds
  65                 'ext': 'mp3',
  66             }]
  67             self._sort_formats(formats)
  68             artists = ', '.join(
  69                 orderedSet(a.get('ART_NAME') for a in s.get('ARTISTS')))
  70             entries.append({
  71                 'id': s.get('SNG_ID'),
  72                 'duration': int_or_none(s.get('DURATION')),
  73                 'title': '%s - %s' % (artists, s.get('SNG_TITLE')),
  74                 'uploader': s.get('ART_NAME'),
  75                 'uploader_id': s.get('ART_ID'),
  76                 'age_limit': 16 if s.get('EXPLICIT_LYRICS') == '1' else 0,
  77                 'formats': formats,
  78             })
  79
  80         return {
  81             '_type': 'playlist',
  82             'id': playlist_id,
  83             'title': playlist_title,
  84             'uploader': playlist_uploader,
  85             'thumbnail': playlist_thumbnail,
  86             'entries': entries,
  87         }
  88
  89
  90 class DeezerAlbumIE(DeezerBaseInfoExtractor):
  91     _VALID_URL = r'https?://(?:www\.)?deezer\.com/(../)?album/(?P<id>[0-9]+)'
  92     _TEST = {
  93         'url': 'https://www.deezer.com/fr/album/67505622',
  94         'info_dict': {
  95             'id': '67505622',
  96             'title': 'Last Week',
  97             'uploader': 'Home Brew',
  98             'thumbnail': r're:^https?://(e-)?cdns-images\.dzcdn\.net/images/cover/.*\.jpg$',
  99         },
 100         'playlist_count': 7,
 101     }
 102
 103     def _real_extract(self, url):
 104         album_id, webpage, data = self.get_data(url)
 105
 106         album_title = data.get('DATA', {}).get('ALB_TITLE')
 107         album_uploader = data.get('DATA', {}).get('ART_NAME')
 108         album_thumbnail = self._search_regex(
 109             r'<img id="naboo_album_image".*?src="([^"]+)"', webpage,
 110             'album thumbnail')
 111
 112         entries = []
 113         for s in data.get('SONGS', {}).get('data'):
 114             formats = [{
 115                 'format_id': 'preview',
 116                 'url': s.get('MEDIA', [{}])[0].get('HREF'),
 117                 'preference': -100,  # Only the first 30 seconds
 118                 'ext': 'mp3',
 119             }]
 120             self._sort_formats(formats)
 121             artists = ', '.join(
 122                 orderedSet(a.get('ART_NAME') for a in s.get('ARTISTS')))
 123             entries.append({
 124                 'id': s.get('SNG_ID'),
 125                 'duration': int_or_none(s.get('DURATION')),
 126                 'title': '%s - %s' % (artists, s.get('SNG_TITLE')),
 127                 'uploader': s.get('ART_NAME'),
 128                 'uploader_id': s.get('ART_ID'),
 129                 'age_limit': 16 if s.get('EXPLICIT_LYRICS') == '1' else 0,
 130                 'formats': formats,
 131                 'track': s.get('SNG_TITLE'),
 132                 'track_number': int_or_none(s.get('TRACK_NUMBER')),
 133                 'track_id': s.get('SNG_ID'),
 134                 'artist': album_uploader,
 135                 'album': album_title,
 136                 'album_artist': album_uploader,
 137             })
 138
 139         return {
 140             '_type': 'playlist',
 141             'id': album_id,
 142             'title': album_title,
 143             'uploader': album_uploader,
 144             'thumbnail': album_thumbnail,
 145             'entries': entries,
 146         }