X-Git-Url: http://git.bitcoin.ninja/index.cgi?p=youtube-dl;a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fmyspace.py;h=ab32e632e34375561980f168834443754f606383;hp=759bc7fed35f212cf2b3f2ecbea24f93c21f4a23;hb=dcdb292fddc82ae11f4c0b647815a45c88a6b6d5;hpb=95c673a148f1a6cd8571b4dfa931d98092500fc2 diff --git a/youtube_dl/extractor/myspace.py b/youtube_dl/extractor/myspace.py index 759bc7fed..ab32e632e 100644 --- a/youtube_dl/extractor/myspace.py +++ b/youtube_dl/extractor/myspace.py @@ -1,13 +1,14 @@ +# coding: utf-8 from __future__ import unicode_literals import re -import json from .common import InfoExtractor -from ..compat import ( - compat_str, +from ..utils import ( + ExtractorError, + int_or_none, + parse_iso8601, ) -from ..utils import ExtractorError class MySpaceIE(InfoExtractor): @@ -15,14 +16,16 @@ class MySpaceIE(InfoExtractor): _TESTS = [ { - 'url': 'https://myspace.com/coldplay/video/viva-la-vida/100008689', + 'url': 'https://myspace.com/fiveminutestothestage/video/little-big-town/109594919', 'info_dict': { - 'id': '100008689', + 'id': '109594919', 'ext': 'flv', - 'title': 'Viva La Vida', - 'description': 'The official Viva La Vida video, directed by Hype Williams', - 'uploader': 'Coldplay', - 'uploader_id': 'coldplay', + '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', }, 'params': { # rtmp download @@ -32,11 +35,9 @@ class MySpaceIE(InfoExtractor): # 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', @@ -49,10 +50,12 @@ class MySpaceIE(InfoExtractor): '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', + 'id': 'USZM20600099', + 'ext': 'mp4', + 'title': 'Animal I Have Become', + 'uploader': 'Three Days Grace', 'timestamp': int, + 'upload_date': '20060502', }, 'skip': 'VEVO is only available in some countries', }, { @@ -60,8 +63,10 @@ class MySpaceIE(InfoExtractor): 'url': 'https://myspace.com/starset2/music/song/first-light-95799905-106964426', 'info_dict': { 'id': 'ypWvQgnJrSU', + 'ext': 'mp4', 'title': 'Starset - First Light', - 'uploader': 'Jacob Soren', + 'description': 'md5:2d5db6c9d11d527683bcda818d332414', + 'uploader': 'Yumi K', 'uploader_id': 'SorenPromotions', 'upload_date': '20140725', } @@ -75,21 +80,36 @@ class MySpaceIE(InfoExtractor): player_url = self._search_regex( r'playerSwf":"([^"?]*)', webpage, 'player URL') + def rtmp_format_from_stream_url(stream_url, width=None, height=None): + rtmp_url, play_path = stream_url.split(';', 1) + return { + 'format_id': 'rtmp', + 'url': rtmp_url, + 'play_path': play_path, + 'player_url': player_url, + 'protocol': 'rtmp', + 'ext': 'flv', + 'width': width, + 'height': height, + } + if mobj.group('mediatype').startswith('music/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') + stream_url = search_data('stream-url') + if not stream_url: vevo_id = search_data('vevo-id') youtube_id = search_data('youtube-id') if vevo_id: @@ -101,37 +121,47 @@ class MySpaceIE(InfoExtractor): else: raise ExtractorError( 'Found song but don\'t know how to download it') - info = { + return { '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), + 'duration': int_or_none(search_data('duration')), + 'formats': [rtmp_format_from_stream_url(stream_url)] } else: - context = json.loads(self._search_regex( - r'context = ({.*?});', webpage, '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 = [] + hls_stream_url = video.get('hlsStreamUrl') + if hls_stream_url: + formats.append({ + 'format_id': 'hls', + 'url': hls_stream_url, + 'protocol': 'm3u8_native', + 'ext': 'mp4', + }) + stream_url = video.get('streamUrl') + if stream_url: + formats.append(rtmp_format_from_stream_url( + stream_url, + 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, - 'player_url': player_url, - 'ext': 'flv', - }) - return info - class MySpaceAlbumIE(InfoExtractor): IE_NAME = 'MySpace:album' @@ -161,16 +191,16 @@ class MySpaceAlbumIE(InfoExtractor): webpage = self._download_webpage(url, display_id) tracks_paths = re.findall(r'"music:song" content="(.*?)"', webpage) if not tracks_paths: - self.to_screen('%s: No songs found, try using proxy' % display_id) - return + 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] - title = self._og_search_title(webpage) return { '_type': 'playlist', 'id': playlist_id, 'display_id': display_id, - 'title': title, + 'title': self._og_search_title(webpage), 'entries': entries, }