]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/jamendo.py
Fix extraction from youtube.
[youtubedl] / youtube_dl / extractor / jamendo.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from ..compat import compat_urlparse
7 from .common import InfoExtractor
8 from ..utils import parse_duration
9
10
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)
17 if title:
18 title = self._search_regex(
19 r'(.+?)\s*\|\s*Jamendo Music', title, 'title', default=None)
20 if not title:
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
26
27
28 class JamendoIE(JamendoBaseIE):
29 _VALID_URL = r'''(?x)
30 https?://
31 (?:
32 licensing\.jamendo\.com/[^/]+|
33 (?:www\.)?jamendo\.com
34 )
35 /track/(?P<id>[0-9]+)/(?P<display_id>[^/?#&]+)
36 '''
37 _TESTS = [{
38 'url': 'https://www.jamendo.com/track/196219/stories-from-emona-i',
39 'md5': '6e9e82ed6db98678f171c25a8ed09ffd',
40 'info_dict': {
41 'id': '196219',
42 'display_id': 'stories-from-emona-i',
43 'ext': 'flac',
44 'title': 'Maya Filipič - Stories from Emona I',
45 'artist': 'Maya Filipič',
46 'track': 'Stories from Emona I',
47 'duration': 210,
48 'thumbnail': r're:^https?://.*\.jpg'
49 }
50 }, {
51 'url': 'https://licensing.jamendo.com/en/track/1496667/energetic-rock',
52 'only_matching': True,
53 }]
54
55 def _real_extract(self, url):
56 mobj = self._VALID_URL_RE.match(url)
57 track_id = mobj.group('id')
58 display_id = mobj.group('display_id')
59
60 webpage = self._download_webpage(
61 'https://www.jamendo.com/track/%s/%s' % (track_id, display_id),
62 display_id)
63
64 title, artist, track = self._extract_meta(webpage)
65
66 formats = [{
67 'url': 'https://%s.jamendo.com/?trackid=%s&format=%s&from=app-97dab294'
68 % (sub_domain, track_id, format_id),
69 'format_id': format_id,
70 'ext': ext,
71 'quality': quality,
72 } for quality, (format_id, sub_domain, ext) in enumerate((
73 ('mp31', 'mp3l', 'mp3'),
74 ('mp32', 'mp3d', 'mp3'),
75 ('ogg1', 'ogg', 'ogg'),
76 ('flac', 'flac', 'flac'),
77 ))]
78 self._sort_formats(formats)
79
80 thumbnail = self._html_search_meta(
81 'image', webpage, 'thumbnail', fatal=False)
82 duration = parse_duration(self._search_regex(
83 r'<span[^>]+itemprop=["\']duration["\'][^>]+content=["\'](.+?)["\']',
84 webpage, 'duration', fatal=False))
85
86 return {
87 'id': track_id,
88 'display_id': display_id,
89 'thumbnail': thumbnail,
90 'title': title,
91 'duration': duration,
92 'artist': artist,
93 'track': track,
94 'formats': formats
95 }
96
97
98 class JamendoAlbumIE(JamendoBaseIE):
99 _VALID_URL = r'https?://(?:www\.)?jamendo\.com/album/(?P<id>[0-9]+)/(?P<display_id>[\w-]+)'
100 _TEST = {
101 'url': 'https://www.jamendo.com/album/121486/duck-on-cover',
102 'info_dict': {
103 'id': '121486',
104 'title': 'Shearer - Duck On Cover'
105 },
106 'playlist': [{
107 'md5': 'e1a2fcb42bda30dfac990212924149a8',
108 'info_dict': {
109 'id': '1032333',
110 'ext': 'flac',
111 'title': 'Shearer - Warmachine',
112 'artist': 'Shearer',
113 'track': 'Warmachine',
114 }
115 }, {
116 'md5': '1f358d7b2f98edfe90fd55dac0799d50',
117 'info_dict': {
118 'id': '1032330',
119 'ext': 'flac',
120 'title': 'Shearer - Without Your Ghost',
121 'artist': 'Shearer',
122 'track': 'Without Your Ghost',
123 }
124 }],
125 'params': {
126 'playlistend': 2
127 }
128 }
129
130 def _real_extract(self, url):
131 mobj = self._VALID_URL_RE.match(url)
132 album_id = mobj.group('id')
133
134 webpage = self._download_webpage(url, mobj.group('display_id'))
135
136 title, artist, album = self._extract_meta(webpage, fatal=False)
137
138 entries = [{
139 '_type': 'url_transparent',
140 'url': compat_urlparse.urljoin(url, m.group('path')),
141 'ie_key': JamendoIE.ie_key(),
142 'id': self._search_regex(
143 r'/track/(\d+)', m.group('path'), 'track id', default=None),
144 'artist': artist,
145 'album': album,
146 } for m in re.finditer(
147 r'<a[^>]+href=(["\'])(?P<path>(?:(?!\1).)+)\1[^>]+class=["\'][^>]*js-trackrow-albumpage-link',
148 webpage)]
149
150 return self.playlist_result(entries, album_id, title)