2 from __future__ import unicode_literals
6 from ..compat import compat_urlparse
7 from .common import InfoExtractor
8 from ..utils import parse_duration
11 class JamendoBaseIE(InfoExtractor):
12 def _extract_meta(self, webpage, fatal=True):
13 title = self._og_search_title(
14 webpage, default=None) or self._search_regex(
15 r'<title>([^<]+)', webpage,
16 'title', default=None)
18 title = self._search_regex(
19 r'(.+?)\s*\|\s*Jamendo Music', title, 'title', default=None)
21 title = self._html_search_meta(
22 'name', webpage, 'title', fatal=fatal)
23 mobj = re.search(r'(.+) - (.+)', title or '')
24 artist, second = mobj.groups() if mobj else [None] * 2
25 return title, artist, second
28 class JamendoIE(JamendoBaseIE):
29 _VALID_URL = r'https?://(?:www\.)?jamendo\.com/track/(?P<id>[0-9]+)/(?P<display_id>[^/?#&]+)'
31 'url': 'https://www.jamendo.com/track/196219/stories-from-emona-i',
32 'md5': '6e9e82ed6db98678f171c25a8ed09ffd',
35 'display_id': 'stories-from-emona-i',
37 'title': 'Maya Filipič - Stories from Emona I',
38 'artist': 'Maya Filipič',
39 'track': 'Stories from Emona I',
41 'thumbnail': r're:^https?://.*\.jpg'
45 def _real_extract(self, url):
46 mobj = self._VALID_URL_RE.match(url)
47 track_id = mobj.group('id')
48 display_id = mobj.group('display_id')
50 webpage = self._download_webpage(url, display_id)
52 title, artist, track = self._extract_meta(webpage)
55 'url': 'https://%s.jamendo.com/?trackid=%s&format=%s&from=app-97dab294'
56 % (sub_domain, track_id, format_id),
57 'format_id': format_id,
60 } for quality, (format_id, sub_domain, ext) in enumerate((
61 ('mp31', 'mp3l', 'mp3'),
62 ('mp32', 'mp3d', 'mp3'),
63 ('ogg1', 'ogg', 'ogg'),
64 ('flac', 'flac', 'flac'),
66 self._sort_formats(formats)
68 thumbnail = self._html_search_meta(
69 'image', webpage, 'thumbnail', fatal=False)
70 duration = parse_duration(self._search_regex(
71 r'<span[^>]+itemprop=["\']duration["\'][^>]+content=["\'](.+?)["\']',
72 webpage, 'duration', fatal=False))
76 'display_id': display_id,
77 'thumbnail': thumbnail,
86 class JamendoAlbumIE(JamendoBaseIE):
87 _VALID_URL = r'https?://(?:www\.)?jamendo\.com/album/(?P<id>[0-9]+)/(?P<display_id>[\w-]+)'
89 'url': 'https://www.jamendo.com/album/121486/duck-on-cover',
92 'title': 'Shearer - Duck On Cover'
95 'md5': 'e1a2fcb42bda30dfac990212924149a8',
99 'title': 'Shearer - Warmachine',
101 'track': 'Warmachine',
104 'md5': '1f358d7b2f98edfe90fd55dac0799d50',
108 'title': 'Shearer - Without Your Ghost',
110 'track': 'Without Your Ghost',
118 def _real_extract(self, url):
119 mobj = self._VALID_URL_RE.match(url)
120 album_id = mobj.group('id')
122 webpage = self._download_webpage(url, mobj.group('display_id'))
124 title, artist, album = self._extract_meta(webpage, fatal=False)
127 '_type': 'url_transparent',
128 'url': compat_urlparse.urljoin(url, m.group('path')),
129 'ie_key': JamendoIE.ie_key(),
130 'id': self._search_regex(
131 r'/track/(\d+)', m.group('path'), 'track id', default=None),
134 } for m in re.finditer(
135 r'<a[^>]+href=(["\'])(?P<path>(?:(?!\1).)+)\1[^>]+class=["\'][^>]*js-trackrow-albumpage-link',
138 return self.playlist_result(entries, album_id, title)