youtube_dl/extractor/beatportpro.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6 import re
   7 import json
   8
   9
  10 class BeatportProIE(InfoExtractor):
  11     _VALID_URL = r'https?://pro\.beatport\.com/track/.*/(?P<id>[0-9]+)'
  12     _TESTS = [{
  13         'url': 'https://pro.beatport.com/track/synesthesia-original-mix/5379371',
  14         'md5': 'b3c34d8639a2f6a7f734382358478887',
  15         'info_dict': {
  16             'id': 5379371,
  17             'display-id': 'synesthesia-original-mix',
  18             'ext': 'mp4',
  19             'title': 'Froxic - Synesthesia (Original Mix)',
  20         },
  21     }, {
  22         'url': 'https://pro.beatport.com/track/love-and-war-original-mix/3756896',
  23         'md5': 'e44c3025dfa38c6577fbaeb43da43514',
  24         'info_dict': {
  25             'id': 3756896,
  26             'display-id': 'love-and-war-original-mix',
  27             'ext': 'mp3',
  28             'title': 'Wolfgang Gartner - Love & War (Original Mix)',
  29         },
  30     }, {
  31         'url': 'https://pro.beatport.com/track/birds-original-mix/4991738',
  32         'md5': 'a1fd8e8046de3950fd039304c186c05f',
  33         'info_dict': {
  34             'id': 4991738,
  35             'display-id': 'birds-original-mix',
  36             'ext': 'mp4',
  37             'title': "Tos, Middle Milk, Mumblin' Johnsson - Birds (Original Mix)",
  38         }
  39     }]
  40
  41     def _real_extract(self, url):
  42         track_id = self._match_id(url)
  43         webpage = self._download_webpage(url, track_id)
  44
  45         # Extract "Playables" JSON information from the page
  46         playables = self._search_regex(r'window\.Playables = ({.*?});', webpage,
  47                                        'playables info', flags=re.DOTALL)
  48         playables = json.loads(playables)
  49
  50         # Find first track with matching ID (always the first one listed?)
  51         track = next(filter(lambda t: t['id'] == int(track_id), playables['tracks']))
  52
  53         # Construct title from artist(s), track name, and mix name
  54         title = ', '.join((a['name'] for a in track['artists'])) + ' - ' + track['name']
  55         if track['mix']:
  56             title += ' (' + track['mix'] + ')'
  57
  58         # Get format information
  59         formats = []
  60         for ext, info in track['preview'].items():
  61             if info['url'] is None:
  62                 continue
  63             fmt = {
  64                 'url': info['url'],
  65                 'ext': ext,
  66                 'format_id': ext,
  67                 'vcodec': 'none',
  68             }
  69             if ext == 'mp3':
  70                 fmt['preference'] = 0
  71                 fmt['acodec'] = 'mp3'
  72                 fmt['abr'] = 96
  73                 fmt['asr'] = 44100
  74             elif ext == 'mp4':
  75                 fmt['preference'] = 1
  76                 fmt['acodec'] = 'aac'
  77                 fmt['abr'] = 96
  78                 fmt['asr'] = 44100
  79             formats += [fmt]
  80         formats.sort(key=lambda f: f['preference'])
  81
  82         # Get album art as thumbnails
  83         imgs = []
  84         for name, info in track['images'].items():
  85             if name == 'dynamic' or info['url'] is None:
  86                 continue
  87             img = {
  88                 'id': name,
  89                 'url': info['url'],
  90                 'height': info['height'],
  91                 'width': info['width'],
  92             }
  93             imgs += [img]
  94
  95         return {
  96             'id': track['id'],
  97             'display-id': track['slug'],
  98             'title': title,
  99             'formats': formats,
 100             'thumbnails': imgs,
 101         }