2014-01-19 02:38:48 -08:00
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
2013-10-28 14:02:17 -07:00
|
|
|
import re
|
|
|
|
import json
|
|
|
|
|
|
|
|
from .common import InfoExtractor
|
2014-11-23 13:12:18 -08:00
|
|
|
from ..compat import (
|
2013-10-28 14:02:17 -07:00
|
|
|
compat_str,
|
|
|
|
)
|
2014-11-30 11:00:16 -08:00
|
|
|
from ..utils import ExtractorError
|
2013-10-28 14:02:17 -07:00
|
|
|
|
|
|
|
|
|
|
|
class MySpaceIE(InfoExtractor):
|
2014-01-19 17:44:08 -08:00
|
|
|
_VALID_URL = r'https?://myspace\.com/([^/]+)/(?P<mediatype>video/[^/]+/|music/song/.*?)(?P<id>\d+)'
|
2014-01-19 02:38:48 -08:00
|
|
|
|
|
|
|
_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,
|
|
|
|
},
|
2013-10-28 14:02:17 -07:00
|
|
|
},
|
2014-11-30 10:57:35 -08:00
|
|
|
# songs
|
2014-01-19 02:38:48 -08:00
|
|
|
{
|
2014-11-30 10:57:35 -08:00
|
|
|
'url': 'https://myspace.com/killsorrow/music/song/of-weakened-soul...-93388656-103880681',
|
|
|
|
'md5': 'f1d7323321f6b7775bf1e3754c1707dc',
|
2014-01-19 02:38:48 -08:00
|
|
|
'info_dict': {
|
2014-11-30 10:57:35 -08:00
|
|
|
'id': '93388656',
|
2014-01-19 02:38:48 -08:00
|
|
|
'ext': 'flv',
|
2014-11-30 10:57:35 -08:00
|
|
|
'playlist': 'The Demo',
|
|
|
|
'title': 'Of weakened soul...',
|
|
|
|
'uploader': 'Killsorrow',
|
|
|
|
'uploader_id': 'killsorrow',
|
2014-01-19 02:38:48 -08:00
|
|
|
},
|
|
|
|
'params': {
|
|
|
|
# rtmp download
|
|
|
|
'skip_download': True,
|
|
|
|
},
|
2014-11-30 10:57:35 -08:00
|
|
|
}, {
|
|
|
|
'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',
|
|
|
|
}
|
2013-10-28 14:02:17 -07:00
|
|
|
},
|
2014-01-19 02:38:48 -08:00
|
|
|
]
|
2013-10-28 14:02:17 -07:00
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
mobj = re.match(self._VALID_URL, url)
|
|
|
|
video_id = mobj.group('id')
|
|
|
|
webpage = self._download_webpage(url, video_id)
|
2014-11-30 10:06:23 -08:00
|
|
|
player_url = self._search_regex(
|
|
|
|
r'playerSwf":"([^"?]*)', webpage, 'player URL')
|
2014-01-19 02:38:48 -08:00
|
|
|
|
2014-01-19 17:44:08 -08:00
|
|
|
if mobj.group('mediatype').startswith('music/song'):
|
2014-01-19 02:38:48 -08:00
|
|
|
# songs don't store any useful info in the 'context' variable
|
2014-11-30 10:36:24 -08:00
|
|
|
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
|
2014-01-19 02:38:48 -08:00
|
|
|
def search_data(name):
|
2014-11-23 13:12:18 -08:00
|
|
|
return self._search_regex(
|
2014-11-30 10:36:24 -08:00
|
|
|
r'''data-%s=([\'"])(.*?)\1''' % name,
|
|
|
|
song_data, name, default='', group=2)
|
2014-01-19 02:38:48 -08:00
|
|
|
streamUrl = search_data('stream-url')
|
2014-11-30 11:00:16 -08:00
|
|
|
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')
|
2014-01-19 02:38:48 -08:00
|
|
|
info = {
|
|
|
|
'id': video_id,
|
|
|
|
'title': self._og_search_title(webpage),
|
2014-11-30 10:07:36 -08:00
|
|
|
'uploader': search_data('artist-name'),
|
2014-01-19 02:38:48 -08:00
|
|
|
'uploader_id': search_data('artist-username'),
|
2014-11-30 10:07:36 -08:00
|
|
|
'playlist': search_data('album-title'),
|
2014-01-19 02:38:48 -08:00
|
|
|
'thumbnail': self._og_search_thumbnail(webpage),
|
|
|
|
}
|
|
|
|
else:
|
2014-11-23 13:12:18 -08:00
|
|
|
context = json.loads(self._search_regex(
|
|
|
|
r'context = ({.*?});', webpage, 'context'))
|
2014-01-19 02:38:48 -08:00
|
|
|
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({
|
2013-10-28 14:02:17 -07:00
|
|
|
'url': rtmp_url,
|
|
|
|
'play_path': play_path,
|
2014-11-30 10:06:23 -08:00
|
|
|
'player_url': player_url,
|
2013-10-28 14:02:17 -07:00
|
|
|
'ext': 'flv',
|
2014-01-19 02:38:48 -08:00
|
|
|
})
|
|
|
|
return info
|