2 from __future__ import unicode_literals
6 from .common import InfoExtractor
7 from ..compat import compat_str
8 from ..utils import int_or_none
11 class BeatportIE(InfoExtractor):
12 _VALID_URL = r'https?://(?:www\.|pro\.)?beatport\.com/track/(?P<display_id>[^/]+)/(?P<id>[0-9]+)'
14 'url': 'https://beatport.com/track/synesthesia-original-mix/5379371',
15 'md5': 'b3c34d8639a2f6a7f734382358478887',
18 'display_id': 'synesthesia-original-mix',
20 'title': 'Froxic - Synesthesia (Original Mix)',
23 'url': 'https://beatport.com/track/love-and-war-original-mix/3756896',
24 'md5': 'e44c3025dfa38c6577fbaeb43da43514',
27 'display_id': 'love-and-war-original-mix',
29 'title': 'Wolfgang Gartner - Love & War (Original Mix)',
32 'url': 'https://beatport.com/track/birds-original-mix/4991738',
33 'md5': 'a1fd8e8046de3950fd039304c186c05f',
36 'display_id': 'birds-original-mix',
38 'title': "Tos, Middle Milk, Mumblin' Johnsson - Birds (Original Mix)",
42 def _real_extract(self, url):
43 mobj = re.match(self._VALID_URL, url)
44 track_id = mobj.group('id')
45 display_id = mobj.group('display_id')
47 webpage = self._download_webpage(url, display_id)
49 playables = self._parse_json(
51 r'window\.Playables\s*=\s*({.+?});', webpage,
52 'playables info', flags=re.DOTALL),
55 track = next(t for t in playables['tracks'] if t['id'] == int(track_id))
57 title = ', '.join((a['name'] for a in track['artists'])) + ' - ' + track['name']
59 title += ' (' + track['mix'] + ')'
62 for ext, info in track['preview'].items():
82 self._sort_formats(formats)
85 for name, info in track['images'].items():
86 image_url = info.get('url')
87 if name == 'dynamic' or not image_url:
92 'height': int_or_none(info.get('height')),
93 'width': int_or_none(info.get('width')),
98 'id': compat_str(track.get('id')) or track_id,
99 'display_id': track.get('slug') or display_id,
102 'thumbnails': images,