youtube_dl/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     int_or_none,
   9     orderedSet,
  10 )
  11
  12
  13 class DeezerPlaylistIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?deezer\.com/playlist/(?P<id>[0-9]+)'
  15     _TEST = {
  16         'url': 'http://www.deezer.com/playlist/176747451',
  17         'info_dict': {
  18             'id': '176747451',
  19             'title': 'Best!',
  20             'uploader': 'Anonymous',
  21             'thumbnail': 're:^https?://cdn-images.deezer.com/images/cover/.*\.jpg$',
  22         },
  23         'playlist_count': 30,
  24     }
  25
  26     def _real_extract(self, url):
  27         if 'test' not in self._downloader.params:
  28             self._downloader.report_warning('For now, this extractor only supports the 30 second previews. Patches welcome!')
  29
  30         mobj = re.match(self._VALID_URL, url)
  31         playlist_id = mobj.group('id')
  32
  33         webpage = self._download_webpage(url, playlist_id)
  34         data_json = self._search_regex(
  35             r'naboo\.display\(\'[^\']+\',\s*(.*?)\);\n', webpage, 'data JSON')
  36         data = json.loads(data_json)
  37
  38         playlist_title = data.get('DATA', {}).get('TITLE')
  39         playlist_uploader = data.get('DATA', {}).get('PARENT_USERNAME')
  40         playlist_thumbnail = self._search_regex(
  41             r'<img id="naboo_playlist_image".*?src="([^"]+)"', webpage,
  42             'playlist thumbnail')
  43
  44         preview_pattern = self._search_regex(
  45             r"var SOUND_PREVIEW_GATEWAY\s*=\s*'([^']+)';", webpage,
  46             'preview URL pattern', fatal=False)
  47         entries = []
  48         for s in data['SONGS']['data']:
  49             puid = s['MD5_ORIGIN']
  50             preview_video_url = preview_pattern.\
  51                 replace('{0}', puid[0]).\
  52                 replace('{1}', puid).\
  53                 replace('{2}', s['MEDIA_VERSION'])
  54             formats = [{
  55                 'format_id': 'preview',
  56                 'url': preview_video_url,
  57                 'preference': -100,  # Only the first 30 seconds
  58                 'ext': 'mp3',
  59             }]
  60             self._sort_formats(formats)
  61             artists = ', '.join(
  62                 orderedSet(a['ART_NAME'] for a in s['ARTISTS']))
  63             entries.append({
  64                 'id': s['SNG_ID'],
  65                 'duration': int_or_none(s.get('DURATION')),
  66                 'title': '%s - %s' % (artists, s['SNG_TITLE']),
  67                 'uploader': s['ART_NAME'],
  68                 'uploader_id': s['ART_ID'],
  69                 'age_limit': 16 if s.get('EXPLICIT_LYRICS') == '1' else 0,
  70                 'formats': formats,
  71             })
  72
  73         return {
  74             '_type': 'playlist',
  75             'id': playlist_id,
  76             'title': playlist_title,
  77             'uploader': playlist_uploader,
  78             'thumbnail': playlist_thumbnail,
  79             'entries': entries,
  80         }