1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
|
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
from ..compat import (
compat_str,
)
from ..utils import ExtractorError
class MySpaceIE(InfoExtractor):
_VALID_URL = r'https?://myspace\.com/([^/]+)/(?P<mediatype>video/[^/]+/|music/song/.*?)(?P<id>\d+)'
_TESTS = [
{
'url': 'https://myspace.com/coldplay/video/viva-la-vida/100008689',
'info_dict': {
'id': '100008689',
'ext': 'flv',
'title': 'Viva La Vida',
'description': 'The official Viva La Vida video, directed by Hype Williams',
'uploader': 'Coldplay',
'uploader_id': 'coldplay',
},
'params': {
# rtmp download
'skip_download': True,
},
},
# songs
{
'url': 'https://myspace.com/killsorrow/music/song/of-weakened-soul...-93388656-103880681',
'md5': 'f1d7323321f6b7775bf1e3754c1707dc',
'info_dict': {
'id': '93388656',
'ext': 'flv',
'playlist': 'The Demo',
'title': 'Of weakened soul...',
'uploader': 'Killsorrow',
'uploader_id': 'killsorrow',
},
'params': {
# rtmp download
'skip_download': True,
},
}, {
'add_ie': ['Vevo'],
'url': 'https://myspace.com/threedaysgrace/music/song/animal-i-have-become-28400208-28218041',
'info_dict': {
'id': u'USZM20600099',
'title': u'Animal I Have Become',
'uploader': u'Three Days Grace',
'timestamp': int,
},
'skip': 'VEVO is only available in some countries',
}, {
'add_ie': ['Youtube'],
'url': 'https://myspace.com/starset2/music/song/first-light-95799905-106964426',
'info_dict': {
'id': 'ypWvQgnJrSU',
'title': 'Starset - First Light',
'uploader': 'Jacob Soren',
'uploader_id': 'SorenPromotions',
'upload_date': '20140725',
}
},
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
player_url = self._search_regex(
r'playerSwf":"([^"?]*)', webpage, 'player URL')
if mobj.group('mediatype').startswith('music/song'):
# songs don't store any useful info in the 'context' variable
song_data = self._search_regex(
r'''<button.*data-song-id=(["\'])%s\1.*''' % video_id,
webpage, 'song_data', default=None, group=0)
if song_data is None:
self.to_screen(
'%s: No downloadable song on this page' % video_id)
return
def search_data(name):
return self._search_regex(
r'''data-%s=([\'"])(.*?)\1''' % name,
song_data, name, default='', group=2)
streamUrl = search_data('stream-url')
if not streamUrl:
vevo_id = search_data('vevo-id')
youtube_id = search_data('youtube-id')
if vevo_id:
self.to_screen('Vevo video detected: %s' % vevo_id)
return self.url_result('vevo:%s' % vevo_id, ie='Vevo')
elif youtube_id:
self.to_screen('Youtube video detected: %s' % youtube_id)
return self.url_result(youtube_id, ie='Youtube')
else:
raise ExtractorError(
'Found song but don\'t know how to download it')
info = {
'id': video_id,
'title': self._og_search_title(webpage),
'uploader': search_data('artist-name'),
'uploader_id': search_data('artist-username'),
'playlist': search_data('album-title'),
'thumbnail': self._og_search_thumbnail(webpage),
}
else:
context = json.loads(self._search_regex(
r'context = ({.*?});', webpage, 'context'))
video = context['video']
streamUrl = video['streamUrl']
info = {
'id': compat_str(video['mediaId']),
'title': video['title'],
'description': video['description'],
'thumbnail': video['imageUrl'],
'uploader': video['artistName'],
'uploader_id': video['artistUsername'],
}
rtmp_url, play_path = streamUrl.split(';', 1)
info.update({
'url': rtmp_url,
'play_path': play_path,
'player_url': player_url,
'ext': 'flv',
})
return info
|
