yt_dlp/extractor/jamendo.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import hashlib
   5 import random
   6
   7 from ..compat import compat_str
   8 from .common import InfoExtractor
   9 from ..utils import (
  10     clean_html,
  11     int_or_none,
  12     try_get,
  13 )
  14
  15
  16 class JamendoIE(InfoExtractor):
  17     _VALID_URL = r'''(?x)
  18                     https?://
  19                         (?:
  20                             licensing\.jamendo\.com/[^/]+|
  21                             (?:www\.)?jamendo\.com
  22                         )
  23                         /track/(?P<id>[0-9]+)(?:/(?P<display_id>[^/?#&]+))?
  24                     '''
  25     _TESTS = [{
  26         'url': 'https://www.jamendo.com/track/196219/stories-from-emona-i',
  27         'md5': '6e9e82ed6db98678f171c25a8ed09ffd',
  28         'info_dict': {
  29             'id': '196219',
  30             'display_id': 'stories-from-emona-i',
  31             'ext': 'flac',
  32             # 'title': 'Maya Filipič - Stories from Emona I',
  33             'title': 'Stories from Emona I',
  34             # 'artist': 'Maya Filipič',
  35             'track': 'Stories from Emona I',
  36             'duration': 210,
  37             'thumbnail': r're:^https?://.*\.jpg',
  38             'timestamp': 1217438117,
  39             'upload_date': '20080730',
  40             'license': 'by-nc-nd',
  41             'view_count': int,
  42             'like_count': int,
  43             'average_rating': int,
  44             'tags': ['piano', 'peaceful', 'newage', 'strings', 'upbeat'],
  45         }
  46     }, {
  47         'url': 'https://licensing.jamendo.com/en/track/1496667/energetic-rock',
  48         'only_matching': True,
  49     }]
  50
  51     def _call_api(self, resource, resource_id):
  52         path = '/api/%ss' % resource
  53         rand = compat_str(random.random())
  54         return self._download_json(
  55             'https://www.jamendo.com' + path, resource_id, query={
  56                 'id[]': resource_id,
  57             }, headers={
  58                 'X-Jam-Call': '$%s*%s~' % (hashlib.sha1((path + rand).encode()).hexdigest(), rand)
  59             })[0]
  60
  61     def _real_extract(self, url):
  62         track_id, display_id = self._match_valid_url(url).groups()
  63         # webpage = self._download_webpage(
  64         #     'https://www.jamendo.com/track/' + track_id, track_id)
  65         # models = self._parse_json(self._html_search_regex(
  66         #     r"data-bundled-models='([^']+)",
  67         #     webpage, 'bundled models'), track_id)
  68         # track = models['track']['models'][0]
  69         track = self._call_api('track', track_id)
  70         title = track_name = track['name']
  71         # get_model = lambda x: try_get(models, lambda y: y[x]['models'][0], dict) or {}
  72         # artist = get_model('artist')
  73         # artist_name = artist.get('name')
  74         # if artist_name:
  75         #     title = '%s - %s' % (artist_name, title)
  76         # album = get_model('album')
  77
  78         formats = [{
  79             'url': 'https://%s.jamendo.com/?trackid=%s&format=%s&from=app-97dab294'
  80                    % (sub_domain, track_id, format_id),
  81             'format_id': format_id,
  82             'ext': ext,
  83             'quality': quality,
  84         } for quality, (format_id, sub_domain, ext) in enumerate((
  85             ('mp31', 'mp3l', 'mp3'),
  86             ('mp32', 'mp3d', 'mp3'),
  87             ('ogg1', 'ogg', 'ogg'),
  88             ('flac', 'flac', 'flac'),
  89         ))]
  90         self._sort_formats(formats)
  91
  92         urls = []
  93         thumbnails = []
  94         for covers in (track.get('cover') or {}).values():
  95             for cover_id, cover_url in covers.items():
  96                 if not cover_url or cover_url in urls:
  97                     continue
  98                 urls.append(cover_url)
  99                 size = int_or_none(cover_id.lstrip('size'))
 100                 thumbnails.append({
 101                     'id': cover_id,
 102                     'url': cover_url,
 103                     'width': size,
 104                     'height': size,
 105                 })
 106
 107         tags = []
 108         for tag in (track.get('tags') or []):
 109             tag_name = tag.get('name')
 110             if not tag_name:
 111                 continue
 112             tags.append(tag_name)
 113
 114         stats = track.get('stats') or {}
 115         license = track.get('licenseCC') or []
 116
 117         return {
 118             'id': track_id,
 119             'display_id': display_id,
 120             'thumbnails': thumbnails,
 121             'title': title,
 122             'description': track.get('description'),
 123             'duration': int_or_none(track.get('duration')),
 124             # 'artist': artist_name,
 125             'track': track_name,
 126             # 'album': album.get('name'),
 127             'formats': formats,
 128             'license': '-'.join(license) if license else None,
 129             'timestamp': int_or_none(track.get('dateCreated')),
 130             'view_count': int_or_none(stats.get('listenedAll')),
 131             'like_count': int_or_none(stats.get('favorited')),
 132             'average_rating': int_or_none(stats.get('averageNote')),
 133             'tags': tags,
 134         }
 135
 136
 137 class JamendoAlbumIE(JamendoIE):
 138     _VALID_URL = r'https?://(?:www\.)?jamendo\.com/album/(?P<id>[0-9]+)'
 139     _TESTS = [{
 140         'url': 'https://www.jamendo.com/album/121486/duck-on-cover',
 141         'info_dict': {
 142             'id': '121486',
 143             'title': 'Duck On Cover',
 144             'description': 'md5:c2920eaeef07d7af5b96d7c64daf1239',
 145         },
 146         'playlist': [{
 147             'md5': 'e1a2fcb42bda30dfac990212924149a8',
 148             'info_dict': {
 149                 'id': '1032333',
 150                 'ext': 'flac',
 151                 'title': 'Shearer - Warmachine',
 152                 'artist': 'Shearer',
 153                 'track': 'Warmachine',
 154                 'timestamp': 1368089771,
 155                 'upload_date': '20130509',
 156             }
 157         }, {
 158             'md5': '1f358d7b2f98edfe90fd55dac0799d50',
 159             'info_dict': {
 160                 'id': '1032330',
 161                 'ext': 'flac',
 162                 'title': 'Shearer - Without Your Ghost',
 163                 'artist': 'Shearer',
 164                 'track': 'Without Your Ghost',
 165                 'timestamp': 1368089771,
 166                 'upload_date': '20130509',
 167             }
 168         }],
 169         'params': {
 170             'playlistend': 2
 171         }
 172     }]
 173
 174     def _real_extract(self, url):
 175         album_id = self._match_id(url)
 176         album = self._call_api('album', album_id)
 177         album_name = album.get('name')
 178
 179         entries = []
 180         for track in (album.get('tracks') or []):
 181             track_id = track.get('id')
 182             if not track_id:
 183                 continue
 184             track_id = compat_str(track_id)
 185             entries.append({
 186                 '_type': 'url_transparent',
 187                 'url': 'https://www.jamendo.com/track/' + track_id,
 188                 'ie_key': JamendoIE.ie_key(),
 189                 'id': track_id,
 190                 'album': album_name,
 191             })
 192
 193         return self.playlist_result(
 194             entries, album_id, album_name,
 195             clean_html(try_get(album, lambda x: x['description']['en'], compat_str)))