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