youtube_dl/extractor/twentytwotracks.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import int_or_none
   7
   8 # 22Tracks regularly replace the audio tracks that can be streamed on their
   9 # site. The tracks usually expire after 1 months, so we can't add tests.
  10
  11
  12 class TwentyTwoTracksIE(InfoExtractor):
  13     _VALID_URL = r'https?://22tracks\.com/(?P<city>[a-z]+)/(?P<genre>[\da-z]+)/(?P<id>\d+)'
  14     IE_NAME = '22tracks:track'
  15
  16     _API_BASE = 'http://22tracks.com/api'
  17
  18     def _extract_info(self, city, genre_name, track_id=None):
  19         item_id = track_id if track_id else genre_name
  20
  21         cities = self._download_json(
  22             '%s/cities' % self._API_BASE, item_id,
  23             'Downloading cities info',
  24             'Unable to download cities info')
  25         city_id = [x['id'] for x in cities if x['slug'] == city][0]
  26
  27         genres = self._download_json(
  28             '%s/genres/%s' % (self._API_BASE, city_id), item_id,
  29             'Downloading %s genres info' % city,
  30             'Unable to download %s genres info' % city)
  31         genre = [x for x in genres if x['slug'] == genre_name][0]
  32         genre_id = genre['id']
  33
  34         tracks = self._download_json(
  35             '%s/tracks/%s' % (self._API_BASE, genre_id), item_id,
  36             'Downloading %s genre tracks info' % genre_name,
  37             'Unable to download track info')
  38
  39         return [x for x in tracks if x['id'] == item_id][0] if track_id else [genre['title'], tracks]
  40
  41     def _get_track_url(self, filename, track_id):
  42         token = self._download_json(
  43             'http://22tracks.com/token.php?desktop=true&u=/128/%s' % filename,
  44             track_id, 'Downloading token', 'Unable to download token')
  45         return 'http://audio.22tracks.com%s?st=%s&e=%d' % (token['filename'], token['st'], token['e'])
  46
  47     def _extract_track_info(self, track_info, track_id):
  48         download_url = self._get_track_url(track_info['filename'], track_id)
  49         title = '%s - %s' % (track_info['artist'].strip(), track_info['title'].strip())
  50         return {
  51             'id': track_id,
  52             'url': download_url,
  53             'ext': 'mp3',
  54             'title': title,
  55             'duration': int_or_none(track_info.get('duration')),
  56             'timestamp': int_or_none(track_info.get('published_at') or track_info.get('created'))
  57         }
  58
  59     def _real_extract(self, url):
  60         mobj = re.match(self._VALID_URL, url)
  61
  62         city = mobj.group('city')
  63         genre = mobj.group('genre')
  64         track_id = mobj.group('id')
  65
  66         track_info = self._extract_info(city, genre, track_id)
  67         return self._extract_track_info(track_info, track_id)
  68
  69
  70 class TwentyTwoTracksGenreIE(TwentyTwoTracksIE):
  71     _VALID_URL = r'https?://22tracks\.com/(?P<city>[a-z]+)/(?P<genre>[\da-z]+)/?$'
  72     IE_NAME = '22tracks:genre'
  73
  74     def _real_extract(self, url):
  75         mobj = re.match(self._VALID_URL, url)
  76
  77         city = mobj.group('city')
  78         genre = mobj.group('genre')
  79
  80         genre_title, tracks = self._extract_info(city, genre)
  81
  82         entries = [
  83             self._extract_track_info(track_info, track_info['id'])
  84             for track_info in tracks]
  85
  86         return self.playlist_result(entries, genre, genre_title)