diff options
author | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2014-01-19 11:38:48 +0100 |
---|---|---|
committer | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2014-01-19 11:38:48 +0100 |
commit | efb1bb90a06d95f838e2854b6dd523749d8e8955 (patch) | |
tree | f5e4890080c5b4a1ff385fab8665fc3df482df93 | |
parent | 4cf393bb4baf7fd9b2e8643012dd17ab61184310 (diff) |
[myspace] Add support for song urls (fixes #2040)
-rw-r--r-- | youtube_dl/extractor/myspace.py | 92 |
1 files changed, 64 insertions, 28 deletions
diff --git a/youtube_dl/extractor/myspace.py b/youtube_dl/extractor/myspace.py index 050f54a5a..462b8b957 100644 --- a/youtube_dl/extractor/myspace.py +++ b/youtube_dl/extractor/myspace.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re import json @@ -8,41 +10,75 @@ from ..utils import ( class MySpaceIE(InfoExtractor): - _VALID_URL = r'https?://myspace\.com/([^/]+)/video/[^/]+/(?P<id>\d+)' - - _TEST = { - u'url': u'https://myspace.com/coldplay/video/viva-la-vida/100008689', - u'info_dict': { - u'id': u'100008689', - u'ext': u'flv', - u'title': u'Viva La Vida', - u'description': u'The official Viva La Vida video, directed by Hype Williams', - u'uploader': u'Coldplay', - u'uploader_id': u'coldplay', + _VALID_URL = r'https?://myspace\.com/([^/]+)/(?: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, + }, }, - u'params': { - # rtmp download - u'skip_download': True, + # song + { + '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): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('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 { - 'id': compat_str(video['mediaId']), - 'title': video['title'], + + if 'music/song' in url: + # songs don't store any useful info in the 'context' variable + 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, 'play_path': play_path, 'ext': 'flv', - 'description': video['description'], - 'thumbnail': video['imageUrl'], - 'uploader': video['artistName'], - 'uploader_id': video['artistUsername'], - } + }) + return info |