X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/af478477605bdf3f5d57562035885cfee905f379..5a9d00a5190582368d533f12db7638e735d7f7c8:/youtube_dl/extractor/myspace.py?ds=inline diff --git a/youtube_dl/extractor/myspace.py b/youtube_dl/extractor/myspace.py index c16939f..e164d59 100644 --- a/youtube_dl/extractor/myspace.py +++ b/youtube_dl/extractor/myspace.py @@ -1,84 +1,212 @@ +# coding: utf-8 from __future__ import unicode_literals import re -import json from .common import InfoExtractor from ..utils import ( - compat_str, + ExtractorError, + int_or_none, + parse_iso8601, ) class MySpaceIE(InfoExtractor): - _VALID_URL = r'https?://myspace\.com/([^/]+)/(?Pvideo/[^/]+/|music/song/.*?)(?P\d+)' + _VALID_URL = r'''(?x) + https?:// + myspace\.com/[^/]+/ + (?P + video/[^/]+/(?P\d+)| + music/song/[^/?#&]+-(?P\d+)-\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, - }, + _TESTS = [{ + 'url': 'https://myspace.com/fiveminutestothestage/video/little-big-town/109594919', + 'md5': '9c1483c106f4a695c47d2911feed50a7', + 'info_dict': { + 'id': '109594919', + 'ext': 'mp4', + 'title': 'Little Big Town', + 'description': 'This country quartet was all smiles while playing a sold out show at the Pacific Amphitheatre in Orange County, California.', + 'uploader': 'Five Minutes to the Stage', + 'uploader_id': 'fiveminutestothestage', + 'timestamp': 1414108751, + 'upload_date': '20141023', }, - # 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, - }, + }, { + # songs + 'url': 'https://myspace.com/killsorrow/music/song/of-weakened-soul...-93388656-103880681', + 'md5': '1d7ee4604a3da226dd69a123f748b262', + 'info_dict': { + 'id': '93388656', + 'ext': 'm4a', + 'title': 'Of weakened soul...', + 'uploader': 'Killsorrow', + 'uploader_id': 'killsorrow', }, - ] + }, { + 'add_ie': ['Youtube'], + 'url': 'https://myspace.com/threedaysgrace/music/song/animal-i-have-become-28400208-28218041', + 'info_dict': { + 'id': 'xqds0B_meys', + 'ext': 'webm', + 'title': 'Three Days Grace - Animal I Have Become', + 'description': 'md5:8bd86b3693e72a077cf863a8530c54bb', + 'uploader': 'ThreeDaysGraceVEVO', + 'uploader_id': 'ThreeDaysGraceVEVO', + 'upload_date': '20091002', + }, + }, { + 'url': 'https://myspace.com/starset2/music/song/first-light-95799905-106964426', + 'only_matching': True, + }, { + 'url': 'https://myspace.com/thelargemouthbassband/music/song/02-pure-eyes.mp3-94422330-105113388', + 'only_matching': True, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = mobj.group('video_id') or mobj.group('song_id') + is_song = mobj.group('mediatype').startswith('music/song') webpage = self._download_webpage(url, video_id) + player_url = self._search_regex( + r'videoSwf":"([^"?]*)', webpage, 'player URL', fatal=False) + + def formats_from_stream_urls(stream_url, hls_stream_url, http_stream_url, width=None, height=None): + formats = [] + vcodec = 'none' if is_song else None + if hls_stream_url: + formats.append({ + 'format_id': 'hls', + 'url': hls_stream_url, + 'protocol': 'm3u8_native', + 'ext': 'm4a' if is_song else 'mp4', + 'vcodec': vcodec, + }) + if stream_url and player_url: + rtmp_url, play_path = stream_url.split(';', 1) + formats.append({ + 'format_id': 'rtmp', + 'url': rtmp_url, + 'play_path': play_path, + 'player_url': player_url, + 'protocol': 'rtmp', + 'ext': 'flv', + 'width': width, + 'height': height, + 'vcodec': vcodec, + }) + if http_stream_url: + formats.append({ + 'format_id': 'http', + 'url': http_stream_url, + 'width': width, + 'height': height, + 'vcodec': vcodec, + }) + return formats - if mobj.group('mediatype').startswith('music/song'): + if is_song: # songs don't store any useful info in the 'context' variable + song_data = self._search_regex( + r'''.*?)\1''' % name, + song_data, name, default='', group='data') + formats = formats_from_stream_urls( + search_data('stream-url'), search_data('hls-stream-url'), + search_data('http-stream-url')) + if not formats: + 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') + self._sort_formats(formats) + return { 'id': video_id, 'title': self._og_search_title(webpage), + 'uploader': search_data('artist-name'), 'uploader_id': search_data('artist-username'), 'thumbnail': self._og_search_thumbnail(webpage), + 'duration': int_or_none(search_data('duration')), + 'formats': formats, } else: - context = json.loads(self._search_regex(r'context = ({.*?});', webpage, - u'context')) - video = context['video'] - streamUrl = video['streamUrl'] - info = { - 'id': compat_str(video['mediaId']), + video = self._parse_json(self._search_regex( + r'context = ({.*?});', webpage, 'context'), + video_id)['video'] + formats = formats_from_stream_urls( + video.get('streamUrl'), video.get('hlsStreamUrl'), + video.get('mp4StreamUrl'), int_or_none(video.get('width')), + int_or_none(video.get('height'))) + self._sort_formats(formats) + return { + 'id': video_id, 'title': video['title'], - 'description': video['description'], - 'thumbnail': video['imageUrl'], - 'uploader': video['artistName'], - 'uploader_id': video['artistUsername'], + 'description': video.get('description'), + 'thumbnail': video.get('imageUrl'), + 'uploader': video.get('artistName'), + 'uploader_id': video.get('artistUsername'), + 'duration': int_or_none(video.get('duration')), + 'timestamp': parse_iso8601(video.get('dateAdded')), + 'formats': formats, } - rtmp_url, play_path = streamUrl.split(';', 1) - info.update({ - 'url': rtmp_url, - 'play_path': play_path, - 'ext': 'flv', - }) - return info + +class MySpaceAlbumIE(InfoExtractor): + IE_NAME = 'MySpace:album' + _VALID_URL = r'https?://myspace\.com/([^/]+)/music/album/(?P.*-)(?P<id>\d+)' + + _TESTS = [{ + 'url': 'https://myspace.com/starset2/music/album/transmissions-19455773', + 'info_dict': { + 'title': 'Transmissions', + 'id': '19455773', + }, + 'playlist_count': 14, + 'skip': 'this album is only available in some countries', + }, { + 'url': 'https://myspace.com/killsorrow/music/album/the-demo-18596029', + 'info_dict': { + 'title': 'The Demo', + 'id': '18596029', + }, + 'playlist_count': 5, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + playlist_id = mobj.group('id') + display_id = mobj.group('title') + playlist_id + webpage = self._download_webpage(url, display_id) + tracks_paths = re.findall(r'"music:song" content="(.*?)"', webpage) + if not tracks_paths: + raise ExtractorError( + '%s: No songs found, try using proxy' % display_id, + expected=True) + entries = [ + self.url_result(t_path, ie=MySpaceIE.ie_key()) + for t_path in tracks_paths] + return { + '_type': 'playlist', + 'id': playlist_id, + 'display_id': display_id, + 'title': self._og_search_title(webpage), + 'entries': entries, + }