yt_dlp/extractor/deezer.py

   1 from __future__ import unicode_literals
   2
   3 import json
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     ExtractorError,
   9     int_or_none,
  10     orderedSet,
  11 )
  12
  13
  14 class DeezerBaseInfoExtractor(InfoExtractor):
  15     def get_data(self, url):
  16         if not self._downloader.params.get('test'):
  17             self._downloader.report_warning('For now, this extractor only supports the 30 second previews. Patches welcome!')
  18
  19         mobj = re.match(self._VALID_URL, url)
  20         data_id = mobj.group('id')
  21
  22         webpage = self._download_webpage(url, data_id)
  23         geoblocking_msg = self._html_search_regex(
  24             r'<p class="soon-txt">(.*?)</p>', webpage, 'geoblocking message',
  25             default=None)
  26         if geoblocking_msg is not None:
  27             raise ExtractorError(
  28                 'Deezer said: %s' % geoblocking_msg, expected=True)
  29
  30         data_json = self._search_regex(
  31             (r'__DZR_APP_STATE__\s*=\s*({.+?})\s*</script>',
  32              r'naboo\.display\(\'[^\']+\',\s*(.*?)\);\n'),
  33             webpage, 'data JSON')
  34         data = json.loads(data_json)
  35         return data_id, webpage, data
  36
  37
  38 class DeezerPlaylistIE(DeezerBaseInfoExtractor):
  39     _VALID_URL = r'https?://(?:www\.)?deezer\.com/(../)?playlist/(?P<id>[0-9]+)'
  40     _TEST = {
  41         'url': 'http://www.deezer.com/playlist/176747451',
  42         'info_dict': {
  43             'id': '176747451',
  44             'title': 'Best!',
  45             'uploader': 'anonymous',
  46             'thumbnail': r're:^https?://(e-)?cdns-images\.dzcdn\.net/images/cover/.*\.jpg$',
  47         },
  48         'playlist_count': 29,
  49     }
  50
  51     def _real_extract(self, url):
  52         playlist_id, webpage, data = self.get_data(url)
  53
  54         playlist_title = data.get('DATA', {}).get('TITLE')
  55         playlist_uploader = data.get('DATA', {}).get('PARENT_USERNAME')
  56         playlist_thumbnail = self._search_regex(
  57             r'<img id="naboo_playlist_image".*?src="([^"]+)"', webpage,
  58             'playlist thumbnail')
  59
  60         entries = []
  61         for s in data.get('SONGS', {}).get('data'):
  62             formats = [{
  63                 'format_id': 'preview',
  64                 'url': s.get('MEDIA', [{}])[0].get('HREF'),
  65                 'preference': -100,  # Only the first 30 seconds
  66                 'ext': 'mp3',
  67             }]
  68             self._sort_formats(formats)
  69             artists = ', '.join(
  70                 orderedSet(a.get('ART_NAME') for a in s.get('ARTISTS')))
  71             entries.append({
  72                 'id': s.get('SNG_ID'),
  73                 'duration': int_or_none(s.get('DURATION')),
  74                 'title': '%s - %s' % (artists, s.get('SNG_TITLE')),
  75                 'uploader': s.get('ART_NAME'),
  76                 'uploader_id': s.get('ART_ID'),
  77                 'age_limit': 16 if s.get('EXPLICIT_LYRICS') == '1' else 0,
  78                 'formats': formats,
  79             })
  80
  81         return {
  82             '_type': 'playlist',
  83             'id': playlist_id,
  84             'title': playlist_title,
  85             'uploader': playlist_uploader,
  86             'thumbnail': playlist_thumbnail,
  87             'entries': entries,
  88         }
  89
  90
  91 class DeezerAlbumIE(DeezerBaseInfoExtractor):
  92     _VALID_URL = r'https?://(?:www\.)?deezer\.com/(../)?album/(?P<id>[0-9]+)'
  93     _TEST = {
  94         'url': 'https://www.deezer.com/fr/album/67505622',
  95         'info_dict': {
  96             'id': '67505622',
  97             'title': 'Last Week',
  98             'uploader': 'Home Brew',
  99             'thumbnail': r're:^https?://(e-)?cdns-images\.dzcdn\.net/images/cover/.*\.jpg$',
 100         },
 101         'playlist_count': 7,
 102     }
 103
 104     def _real_extract(self, url):
 105         album_id, webpage, data = self.get_data(url)
 106
 107         album_title = data.get('DATA', {}).get('ALB_TITLE')
 108         album_uploader = data.get('DATA', {}).get('ART_NAME')
 109         album_thumbnail = self._search_regex(
 110             r'<img id="naboo_album_image".*?src="([^"]+)"', webpage,
 111             'album thumbnail')
 112
 113         entries = []
 114         for s in data.get('SONGS', {}).get('data'):
 115             formats = [{
 116                 'format_id': 'preview',
 117                 'url': s.get('MEDIA', [{}])[0].get('HREF'),
 118                 'preference': -100,  # Only the first 30 seconds
 119                 'ext': 'mp3',
 120             }]
 121             self._sort_formats(formats)
 122             artists = ', '.join(
 123                 orderedSet(a.get('ART_NAME') for a in s.get('ARTISTS')))
 124             entries.append({
 125                 'id': s.get('SNG_ID'),
 126                 'duration': int_or_none(s.get('DURATION')),
 127                 'title': '%s - %s' % (artists, s.get('SNG_TITLE')),
 128                 'uploader': s.get('ART_NAME'),
 129                 'uploader_id': s.get('ART_ID'),
 130                 'age_limit': 16 if s.get('EXPLICIT_LYRICS') == '1' else 0,
 131                 'formats': formats,
 132                 'track': s.get('SNG_TITLE'),
 133                 'track_number': int_or_none(s.get('TRACK_NUMBER')),
 134                 'track_id': s.get('SNG_ID'),
 135                 'artist': album_uploader,
 136                 'album': album_title,
 137                 'album_artist': album_uploader,
 138             })
 139
 140         return {
 141             '_type': 'playlist',
 142             'id': album_id,
 143             'title': album_title,
 144             'uploader': album_uploader,
 145             'thumbnail': album_thumbnail,
 146             'entries': entries,
 147         }