2 from __future__ import unicode_literals
7 from .common import InfoExtractor
11 from ..utils import ExtractorError
14 class MySpaceIE(InfoExtractor):
15 _VALID_URL = r'https?://myspace\.com/([^/]+)/(?P<mediatype>video/[^/]+/|music/song/.*?)(?P<id>\d+)'
19 'url': 'https://myspace.com/fiveminutestothestage/video/little-big-town/109594919',
23 'title': 'Little Big Town',
24 'description': 'This country quartet was all smiles while playing a sold out show at the Pacific Amphitheatre in Orange County, California.',
25 'uploader': 'Five Minutes to the Stage',
26 'uploader_id': 'fiveminutestothestage',
30 'skip_download': True,
35 'url': 'https://myspace.com/killsorrow/music/song/of-weakened-soul...-93388656-103880681',
39 'playlist': 'The Demo',
40 'title': 'Of weakened soul...',
41 'uploader': 'Killsorrow',
42 'uploader_id': 'killsorrow',
46 'skip_download': True,
50 'url': 'https://myspace.com/threedaysgrace/music/song/animal-i-have-become-28400208-28218041',
54 'title': 'Animal I Have Become',
55 'uploader': 'Three Days Grace',
57 'upload_date': '20060502',
59 'skip': 'VEVO is only available in some countries',
61 'add_ie': ['Youtube'],
62 'url': 'https://myspace.com/starset2/music/song/first-light-95799905-106964426',
66 'title': 'Starset - First Light',
67 'description': 'md5:2d5db6c9d11d527683bcda818d332414',
68 'uploader': 'Jacob Soren',
69 'uploader_id': 'SorenPromotions',
70 'upload_date': '20140725',
75 def _real_extract(self, url):
76 mobj = re.match(self._VALID_URL, url)
77 video_id = mobj.group('id')
78 webpage = self._download_webpage(url, video_id)
79 player_url = self._search_regex(
80 r'playerSwf":"([^"?]*)', webpage, 'player URL')
82 if mobj.group('mediatype').startswith('music/song'):
83 # songs don't store any useful info in the 'context' variable
84 song_data = self._search_regex(
85 r'''<button.*data-song-id=(["\'])%s\1.*''' % video_id,
86 webpage, 'song_data', default=None, group=0)
89 '%s: No downloadable song on this page' % video_id)
91 def search_data(name):
92 return self._search_regex(
93 r'''data-%s=([\'"])(.*?)\1''' % name,
94 song_data, name, default='', group=2)
95 streamUrl = search_data('stream-url')
97 vevo_id = search_data('vevo-id')
98 youtube_id = search_data('youtube-id')
100 self.to_screen('Vevo video detected: %s' % vevo_id)
101 return self.url_result('vevo:%s' % vevo_id, ie='Vevo')
103 self.to_screen('Youtube video detected: %s' % youtube_id)
104 return self.url_result(youtube_id, ie='Youtube')
106 raise ExtractorError(
107 'Found song but don\'t know how to download it')
110 'title': self._og_search_title(webpage),
111 'uploader': search_data('artist-name'),
112 'uploader_id': search_data('artist-username'),
113 'playlist': search_data('album-title'),
114 'thumbnail': self._og_search_thumbnail(webpage),
117 context = json.loads(self._search_regex(
118 r'context = ({.*?});', webpage, 'context'))
119 video = context['video']
120 streamUrl = video['streamUrl']
122 'id': compat_str(video['mediaId']),
123 'title': video['title'],
124 'description': video['description'],
125 'thumbnail': video['imageUrl'],
126 'uploader': video['artistName'],
127 'uploader_id': video['artistUsername'],
130 rtmp_url, play_path = streamUrl.split(';', 1)
133 'play_path': play_path,
134 'player_url': player_url,
140 class MySpaceAlbumIE(InfoExtractor):
141 IE_NAME = 'MySpace:album'
142 _VALID_URL = r'https?://myspace\.com/([^/]+)/music/album/(?P<title>.*-)(?P<id>\d+)'
145 'url': 'https://myspace.com/starset2/music/album/transmissions-19455773',
147 'title': 'Transmissions',
150 'playlist_count': 14,
151 'skip': 'this album is only available in some countries',
153 'url': 'https://myspace.com/killsorrow/music/album/the-demo-18596029',
161 def _real_extract(self, url):
162 mobj = re.match(self._VALID_URL, url)
163 playlist_id = mobj.group('id')
164 display_id = mobj.group('title') + playlist_id
165 webpage = self._download_webpage(url, display_id)
166 tracks_paths = re.findall(r'"music:song" content="(.*?)"', webpage)
168 self.to_screen('%s: No songs found, try using proxy' % display_id)
171 self.url_result(t_path, ie=MySpaceIE.ie_key())
172 for t_path in tracks_paths]
173 title = self._og_search_title(webpage)
177 'display_id': display_id,