Raphaël G. Git Repositories - youtubedl/blob - 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     ExtractorError,
   9     int_or_none,
  10     orderedSet,
  11 )
  12
  13
  14 class DeezerPlaylistIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?deezer\.com/playlist/(?P<id>[0-9]+)'
  16     _TEST = {
  17         'url': 'http://www.deezer.com/playlist/176747451',
  18         'info_dict': {
  19             'id': '176747451',
  20             'title': 'Best!',
  21             'uploader': 'Anonymous',
  22             'thumbnail': r're:^https?://cdn-images\.deezer\.com/images/cover/.*\.jpg$',
  23         },
  24         'playlist_count': 30,
  25         'skip': 'Only available in .de',
  26     }
  27
  28     def _real_extract(self, url):
  29         if 'test' not in self._downloader.params:
  30             self._downloader.report_warning('For now, this extractor only supports the 30 second previews. Patches welcome!')
  31
  32         mobj = re.match(self._VALID_URL, url)
  33         playlist_id = mobj.group('id')
  34
  35         webpage = self._download_webpage(url, playlist_id)
  36         geoblocking_msg = self._html_search_regex(
  37             r'<p class="soon-txt">(.*?)</p>', webpage, 'geoblocking message',
  38             default=None)
  39         if geoblocking_msg is not None:
  40             raise ExtractorError(
  41                 'Deezer said: %s' % geoblocking_msg, expected=True)
  42
  43         data_json = self._search_regex(
  44             (r'__DZR_APP_STATE__\s*=\s*({.+?})\s*</script>',
  45              r'naboo\.display\(\'[^\']+\',\s*(.*?)\);\n'),
  46             webpage, 'data JSON')
  47         data = json.loads(data_json)
  48
  49         playlist_title = data.get('DATA', {}).get('TITLE')
  50         playlist_uploader = data.get('DATA', {}).get('PARENT_USERNAME')
  51         playlist_thumbnail = self._search_regex(
  52             r'<img id="naboo_playlist_image".*?src="([^"]+)"', webpage,
  53             'playlist thumbnail')
  54
  55         preview_pattern = self._search_regex(
  56             r"var SOUND_PREVIEW_GATEWAY\s*=\s*'([^']+)';", webpage,
  57             'preview URL pattern', fatal=False)
  58         entries = []
  59         for s in data['SONGS']['data']:
  60             puid = s['MD5_ORIGIN']
  61             preview_video_url = preview_pattern.\
  62                 replace('{0}', puid[0]).\
  63                 replace('{1}', puid).\
  64                 replace('{2}', s['MEDIA_VERSION'])
  65             formats = [{
  66                 'format_id': 'preview',
  67                 'url': preview_video_url,
  68                 'preference': -100,  # Only the first 30 seconds
  69                 'ext': 'mp3',
  70             }]
  71             self._sort_formats(formats)
  72             artists = ', '.join(
  73                 orderedSet(a['ART_NAME'] for a in s['ARTISTS']))
  74             entries.append({
  75                 'id': s['SNG_ID'],
  76                 'duration': int_or_none(s.get('DURATION')),
  77                 'title': '%s - %s' % (artists, s['SNG_TITLE']),
  78                 'uploader': s['ART_NAME'],
  79                 'uploader_id': s['ART_ID'],
  80                 'age_limit': 16 if s.get('EXPLICIT_LYRICS') == '1' else 0,
  81                 'formats': formats,
  82             })
  83
  84         return {
  85             '_type': 'playlist',
  86             'id': playlist_id,
  87             'title': playlist_title,
  88             'uploader': playlist_uploader,
  89             'thumbnail': playlist_thumbnail,
  90             'entries': entries,
  91         }