[myspace] Add support for song urls (fixes #2040)

This commit is contained in:
Jaime Marquínez Ferrándiz 2014-01-19 11:38:48 +01:00
parent 4cf393bb4b
commit efb1bb90a0

View file

@ -1,3 +1,5 @@
from __future__ import unicode_literals
import re import re
import json import json
@ -8,41 +10,75 @@ from ..utils import (
class MySpaceIE(InfoExtractor): class MySpaceIE(InfoExtractor):
_VALID_URL = r'https?://myspace\.com/([^/]+)/video/[^/]+/(?P<id>\d+)' _VALID_URL = r'https?://myspace\.com/([^/]+)/(?:video/[^/]+/|music/song/.*?)(?P<id>\d+)'
_TEST = { _TESTS = [
u'url': u'https://myspace.com/coldplay/video/viva-la-vida/100008689', {
u'info_dict': { 'url': 'https://myspace.com/coldplay/video/viva-la-vida/100008689',
u'id': u'100008689', 'info_dict': {
u'ext': u'flv', 'id': '100008689',
u'title': u'Viva La Vida', 'ext': 'flv',
u'description': u'The official Viva La Vida video, directed by Hype Williams', 'title': 'Viva La Vida',
u'uploader': u'Coldplay', 'description': 'The official Viva La Vida video, directed by Hype Williams',
u'uploader_id': u'coldplay', 'uploader': 'Coldplay',
'uploader_id': 'coldplay',
},
'params': {
# rtmp download
'skip_download': True,
},
}, },
u'params': { # song
# rtmp download {
u'skip_download': True, 'url': 'https://myspace.com/spiderbags/music/song/darkness-in-my-heart-39008454-27041242',
'info_dict': {
'id': '39008454',
'ext': 'flv',
'title': 'Darkness In My Heart',
'uploader_id': 'spiderbags',
},
'params': {
# rtmp download
'skip_download': True,
},
}, },
} ]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
context = json.loads(self._search_regex(r'context = ({.*?});', webpage,
u'context'))
video = context['video']
rtmp_url, play_path = video['streamUrl'].split(';', 1)
return { if 'music/song' in url:
'id': compat_str(video['mediaId']), # songs don't store any useful info in the 'context' variable
'title': video['title'], def search_data(name):
return self._search_regex(r'data-%s="(.*?)"' % name, webpage,
name)
streamUrl = search_data('stream-url')
info = {
'id': video_id,
'title': self._og_search_title(webpage),
'uploader_id': search_data('artist-username'),
'thumbnail': self._og_search_thumbnail(webpage),
}
else:
context = json.loads(self._search_regex(r'context = ({.*?});', webpage,
u'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, 'url': rtmp_url,
'play_path': play_path, 'play_path': play_path,
'ext': 'flv', 'ext': 'flv',
'description': video['description'], })
'thumbnail': video['imageUrl'], return info
'uploader': video['artistName'],
'uploader_id': video['artistUsername'],
}